Papers

Back

GFPose: Learning 3D Human Pose Prior With Gradient Fields

Hai Ci,

Mingdong Wu,

Wentao Zhu,

Xiaoxuan Ma,

Hao Dong,

Fangwei Zhong,

Yizhou Wang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Ci_2023_CVPR, author = {Ci, Hai and Wu, Mingdong and Zhu, Wentao and Ma, Xiaoxuan and Dong, Hao and Zhong, Fangwei and Wang, Yizhou}, title = {GFPose: Learning 3D Human Pose Prior With Gradient Fields}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4800-4810} }

CXTrack: Improving 3D Point Cloud Tracking With Contextual Information

Tian-Xing Xu,

Yuan-Chen Guo,

Yu-Kun Lai,

Song-Hai Zhang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Xu_2023_CVPR, author = {Xu, Tian-Xing and Guo, Yuan-Chen and Lai, Yu-Kun and Zhang, Song-Hai}, title = {CXTrack: Improving 3D Point Cloud Tracking With Contextual Information}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1084-1093} }

Deep Frequency Filtering for Domain Generalization

Shiqi Lin,

Zhizheng Zhang,

Zhipeng Huang,

Yan Lu,

Cuiling Lan,

Peng Chu,

Quanzeng You,

Jiang Wang,

Zicheng Liu,

Amey Parulkar,

Viraj Navkal,

Zhibo Chen

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Lin_2023_CVPR, author = {Lin, Shiqi and Zhang, Zhizheng and Huang, Zhipeng and Lu, Yan and Lan, Cuiling and Chu, Peng and You, Quanzeng and Wang, Jiang and Liu, Zicheng and Parulkar, Amey and Navkal, Viraj and Chen, Zhibo}, title = {Deep Frequency Filtering for Domain Generalization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11797-11807} }

Frame Flexible Network

Yitian Zhang,

Yue Bai,

Chang Liu,

Huan Wang,

Sheng Li,

Yun Fu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Zhang_2023_CVPR, author = {Zhang, Yitian and Bai, Yue and Liu, Chang and Wang, Huan and Li, Sheng and Fu, Yun}, title = {Frame Flexible Network}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10504-10513} }

Unsupervised Cumulative Domain Adaptation for Foggy Scene Optical Flow

Hanyu Zhou,

Yi Chang,

Wending Yan,

Luxin Yan

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Zhou_2023_CVPR, author = {Zhou, Hanyu and Chang, Yi and Yan, Wending and Yan, Luxin}, title = {Unsupervised Cumulative Domain Adaptation for Foggy Scene Optical Flow}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9569-9578} }

NoisyTwins: Class-Consistent and Diverse Image Generation Through StyleGANs

Harsh Rangwani,

Lavish Bansal,

Kartik Sharma,

Tejan Karmali,

Varun Jampani,

R. Venkatesh Babu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Rangwani_2023_CVPR, author = {Rangwani, Harsh and Bansal, Lavish and Sharma, Kartik and Karmali, Tejan and Jampani, Varun and Babu, R. Venkatesh}, title = {NoisyTwins: Class-Consistent and Diverse Image Generation Through StyleGANs}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5987-5996} }

DisCoScene: Spatially Disentangled Generative Radiance Fields for Controllable 3D-Aware Scene Synthesis

Yinghao Xu,

Menglei Chai,

Zifan Shi,

Sida Peng,

Ivan Skorokhodov,

Aliaksandr Siarohin,

Ceyuan Yang,

Yujun Shen,

Hsin-Ying Lee,

Bolei Zhou,

Sergey Tulyakov

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Xu_2023_CVPR, author = {Xu, Yinghao and Chai, Menglei and Shi, Zifan and Peng, Sida and Skorokhodov, Ivan and Siarohin, Aliaksandr and Yang, Ceyuan and Shen, Yujun and Lee, Hsin-Ying and Zhou, Bolei and Tulyakov, Sergey}, title = {DisCoScene: Spatially Disentangled Generative Radiance Fields for Controllable 3D-Aware Scene Synthesis}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4402-4412} }

Revisiting Self-Similarity: Structural Embedding for Image Retrieval

Seongwon Lee,

Suhyeon Lee,

Hongje Seong,

Euntai Kim

[pdf] [supp]

[bibtex]

@InProceedings{Lee_2023_CVPR, author = {Lee, Seongwon and Lee, Suhyeon and Seong, Hongje and Kim, Euntai}, title = {Revisiting Self-Similarity: Structural Embedding for Image Retrieval}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {23412-23421} }

Minimizing the Accumulated Trajectory Error To Improve Dataset Distillation

Jiawei Du,

Yidi Jiang,

Vincent Y. F. Tan,

Joey Tianyi Zhou,

Haizhou Li

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Du_2023_CVPR, author = {Du, Jiawei and Jiang, Yidi and Tan, Vincent Y. F. and Zhou, Joey Tianyi and Li, Haizhou}, title = {Minimizing the Accumulated Trajectory Error To Improve Dataset Distillation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3749-3758} }

Decoupling-and-Aggregating for Image Exposure Correction

Yang Wang,

Long Peng,

Liang Li,

Yang Cao,

Zheng-Jun Zha

[pdf]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Yang and Peng, Long and Li, Liang and Cao, Yang and Zha, Zheng-Jun}, title = {Decoupling-and-Aggregating for Image Exposure Correction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {18115-18124} }

Implicit Occupancy Flow Fields for Perception and Prediction in Self-Driving

Ben Agro,

Quinlan Sykora,

Sergio Casas,

Raquel Urtasun

[pdf] [supp]

[bibtex]

@InProceedings{Agro_2023_CVPR, author = {Agro, Ben and Sykora, Quinlan and Casas, Sergio and Urtasun, Raquel}, title = {Implicit Occupancy Flow Fields for Perception and Prediction in Self-Driving}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1379-1388} }

CCuantuMM: Cycle-Consistent Quantum-Hybrid Matching of Multiple Shapes

Harshil Bhatia,

Edith Tretschk,

Zorah Lähner,

Marcel Seelbach Benkner,

Michael Moeller,

Christian Theobalt,

Vladislav Golyanik

[pdf] [supp]

[bibtex]

@InProceedings{Bhatia_2023_CVPR, author = {Bhatia, Harshil and Tretschk, Edith and L\"ahner, Zorah and Benkner, Marcel Seelbach and Moeller, Michael and Theobalt, Christian and Golyanik, Vladislav}, title = {CCuantuMM: Cycle-Consistent Quantum-Hybrid Matching of Multiple Shapes}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1296-1305} }

TrojViT: Trojan Insertion in Vision Transformers

Mengxin Zheng,

Qian Lou,

Lei Jiang

[pdf] [arXiv]

[bibtex]

@InProceedings{Zheng_2023_CVPR, author = {Zheng, Mengxin and Lou, Qian and Jiang, Lei}, title = {TrojViT: Trojan Insertion in Vision Transformers}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4025-4034} }

MarS3D: A Plug-and-Play Motion-Aware Model for Semantic Segmentation on Multi-Scan 3D Point Clouds

Jiahui Liu,

Chirui Chang,

Jianhui Liu,

Xiaoyang Wu,

Lan Ma,

Xiaojuan Qi

[pdf] [supp]

[bibtex]

@InProceedings{Liu_2023_CVPR, author = {Liu, Jiahui and Chang, Chirui and Liu, Jianhui and Wu, Xiaoyang and Ma, Lan and Qi, Xiaojuan}, title = {MarS3D: A Plug-and-Play Motion-Aware Model for Semantic Segmentation on Multi-Scan 3D Point Clouds}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9372-9381} }

An Image Quality Assessment Dataset for Portraits

Nicolas Chahine,

Stefania Calarasanu,

Davide Garcia-Civiero,

Théo Cayla,

Sira Ferradans,

Jean Ponce

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Chahine_2023_CVPR, author = {Chahine, Nicolas and Calarasanu, Stefania and Garcia-Civiero, Davide and Cayla, Th\'eo and Ferradans, Sira and Ponce, Jean}, title = {An Image Quality Assessment Dataset for Portraits}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9968-9978} }

MSeg3D: Multi-Modal 3D Semantic Segmentation for Autonomous Driving

Jiale Li,

Hang Dai,

Hao Han,

Yong Ding

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Li_2023_CVPR, author = {Li, Jiale and Dai, Hang and Han, Hao and Ding, Yong}, title = {MSeg3D: Multi-Modal 3D Semantic Segmentation for Autonomous Driving}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {21694-21704} }

Robust Outlier Rejection for 3D Registration With Variational Bayes

Haobo Jiang,

Zheng Dang,

Zhen Wei,

Jin Xie,

Jian Yang,

Mathieu Salzmann

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Jiang_2023_CVPR, author = {Jiang, Haobo and Dang, Zheng and Wei, Zhen and Xie, Jin and Yang, Jian and Salzmann, Mathieu}, title = {Robust Outlier Rejection for 3D Registration With Variational Bayes}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1148-1157} }

Dynamically Instance-Guided Adaptation: A Backward-Free Approach for Test-Time Domain Adaptive Semantic Segmentation

Wei Wang,

Zhun Zhong,

Weijie Wang,

Xi Chen,

Charles Ling,

Boyu Wang,

Nicu Sebe

[pdf] [supp]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Wei and Zhong, Zhun and Wang, Weijie and Chen, Xi and Ling, Charles and Wang, Boyu and Sebe, Nicu}, title = {Dynamically Instance-Guided Adaptation: A Backward-Free Approach for Test-Time Domain Adaptive Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {24090-24099} }

Painting 3D Nature in 2D: View Synthesis of Natural Scenes From a Single Semantic Mask

Shangzhan Zhang,

Sida Peng,

Tianrun Chen,

Linzhan Mou,

Haotong Lin,

Kaicheng Yu,

Yiyi Liao,

Xiaowei Zhou

[pdf] [arXiv]

[bibtex]

@InProceedings{Zhang_2023_CVPR, author = {Zhang, Shangzhan and Peng, Sida and Chen, Tianrun and Mou, Linzhan and Lin, Haotong and Yu, Kaicheng and Liao, Yiyi and Zhou, Xiaowei}, title = {Painting 3D Nature in 2D: View Synthesis of Natural Scenes From a Single Semantic Mask}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8518-8528} }

LANIT: Language-Driven Image-to-Image Translation for Unlabeled Data

Jihye Park,

Sunwoo Kim,

Soohyun Kim,

Seokju Cho,

Jaejun Yoo,

Youngjung Uh,

Seungryong Kim

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Park_2023_CVPR, author = {Park, Jihye and Kim, Sunwoo and Kim, Soohyun and Cho, Seokju and Yoo, Jaejun and Uh, Youngjung and Kim, Seungryong}, title = {LANIT: Language-Driven Image-to-Image Translation for Unlabeled Data}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {23401-23411} }

MoLo: Motion-Augmented Long-Short Contrastive Learning for Few-Shot Action Recognition

Xiang Wang,

Shiwei Zhang,

Zhiwu Qing,

Changxin Gao,

Yingya Zhang,

Deli Zhao,

Nong Sang

[pdf] [arXiv]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Xiang and Zhang, Shiwei and Qing, Zhiwu and Gao, Changxin and Zhang, Yingya and Zhao, Deli and Sang, Nong}, title = {MoLo: Motion-Augmented Long-Short Contrastive Learning for Few-Shot Action Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {18011-18021} }

Fast Point Cloud Generation With Straight Flows

Lemeng Wu,

Dilin Wang,

Chengyue Gong,

Xingchao Liu,

Yunyang Xiong,

Rakesh Ranjan,

Raghuraman Krishnamoorthi,

Vikas Chandra,

Qiang Liu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Wu_2023_CVPR, author = {Wu, Lemeng and Wang, Dilin and Gong, Chengyue and Liu, Xingchao and Xiong, Yunyang and Ranjan, Rakesh and Krishnamoorthi, Raghuraman and Chandra, Vikas and Liu, Qiang}, title = {Fast Point Cloud Generation With Straight Flows}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9445-9454} }

Text-Guided Unsupervised Latent Transformation for Multi-Attribute Image Manipulation

Xiwen Wei,

Zhen Xu,

Cheng Liu,

Si Wu,

Zhiwen Yu,

Hau San Wong

[pdf]

[bibtex]

@InProceedings{Wei_2023_CVPR, author = {Wei, Xiwen and Xu, Zhen and Liu, Cheng and Wu, Si and Yu, Zhiwen and Wong, Hau San}, title = {Text-Guided Unsupervised Latent Transformation for Multi-Attribute Image Manipulation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {19285-19294} }

Achieving a Better Stability-Plasticity Trade-Off via Auxiliary Networks in Continual Learning

Sanghwan Kim,

Lorenzo Noci,

Antonio Orvieto,

Thomas Hofmann

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Kim_2023_CVPR, author = {Kim, Sanghwan and Noci, Lorenzo and Orvieto, Antonio and Hofmann, Thomas}, title = {Achieving a Better Stability-Plasticity Trade-Off via Auxiliary Networks in Continual Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11930-11939} }

Power Bundle Adjustment for Large-Scale 3D Reconstruction

Simon Weber,

Nikolaus Demmel,

Tin Chon Chan,

Daniel Cremers

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Weber_2023_CVPR, author = {Weber, Simon and Demmel, Nikolaus and Chan, Tin Chon and Cremers, Daniel}, title = {Power Bundle Adjustment for Large-Scale 3D Reconstruction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {281-289} }

Picture That Sketch: Photorealistic Image Generation From Abstract Sketches

Subhadeep Koley,

Ayan Kumar Bhunia,

Aneeshan Sain,

Pinaki Nath Chowdhury,

Tao Xiang,

Yi-Zhe Song

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Koley_2023_CVPR, author = {Koley, Subhadeep and Bhunia, Ayan Kumar and Sain, Aneeshan and Chowdhury, Pinaki Nath and Xiang, Tao and Song, Yi-Zhe}, title = {Picture That Sketch: Photorealistic Image Generation From Abstract Sketches}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6850-6861} }

Contrastive Semi-Supervised Learning for Underwater Image Restoration via Reliable Bank

Shirui Huang,

Keyan Wang,

Huan Liu,

Jun Chen,

Yunsong Li

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Huang_2023_CVPR, author = {Huang, Shirui and Wang, Keyan and Liu, Huan and Chen, Jun and Li, Yunsong}, title = {Contrastive Semi-Supervised Learning for Underwater Image Restoration via Reliable Bank}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {18145-18155} }

Video Event Restoration Based on Keyframes for Video Anomaly Detection

Zhiwei Yang,

Jing Liu,

Zhaoyang Wu,

Peng Wu,

Xiaotao Liu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Yang_2023_CVPR, author = {Yang, Zhiwei and Liu, Jing and Wu, Zhaoyang and Wu, Peng and Liu, Xiaotao}, title = {Video Event Restoration Based on Keyframes for Video Anomaly Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14592-14601} }

EcoTTA: Memory-Efficient Continual Test-Time Adaptation via Self-Distilled Regularization

Junha Song,

Jungsoo Lee,

In So Kweon,

Sungha Choi

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Song_2023_CVPR, author = {Song, Junha and Lee, Jungsoo and Kweon, In So and Choi, Sungha}, title = {EcoTTA: Memory-Efficient Continual Test-Time Adaptation via Self-Distilled Regularization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11920-11929} }

3D-Aware Object Goal Navigation via Simultaneous Exploration and Identification

Jiazhao Zhang,

Liu Dai,

Fanpeng Meng,

Qingnan Fan,

Xuelin Chen,

Kai Xu,

He Wang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Zhang_2023_CVPR, author = {Zhang, Jiazhao and Dai, Liu and Meng, Fanpeng and Fan, Qingnan and Chen, Xuelin and Xu, Kai and Wang, He}, title = {3D-Aware Object Goal Navigation via Simultaneous Exploration and Identification}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6672-6682} }

Tri-Perspective View for Vision-Based 3D Semantic Occupancy Prediction

Yuanhui Huang,

Wenzhao Zheng,

Yunpeng Zhang,

Jie Zhou,

Jiwen Lu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Huang_2023_CVPR, author = {Huang, Yuanhui and Zheng, Wenzhao and Zhang, Yunpeng and Zhou, Jie and Lu, Jiwen}, title = {Tri-Perspective View for Vision-Based 3D Semantic Occupancy Prediction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9223-9232} }

Castling-ViT: Compressing Self-Attention via Switching Towards Linear-Angular Attention at Vision Transformer Inference

Haoran You,

Yunyang Xiong,

Xiaoliang Dai,

Bichen Wu,

Peizhao Zhang,

Haoqi Fan,

Peter Vajda,

Yingyan (Celine) Lin

[pdf] [supp]

[bibtex]

@InProceedings{You_2023_CVPR, author = {You, Haoran and Xiong, Yunyang and Dai, Xiaoliang and Wu, Bichen and Zhang, Peizhao and Fan, Haoqi and Vajda, Peter and Lin, Yingyan (Celine)}, title = {Castling-ViT: Compressing Self-Attention via Switching Towards Linear-Angular Attention at Vision Transformer Inference}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14431-14442} }

Shape, Pose, and Appearance From a Single Image via Bootstrapped Radiance Field Inversion

Dario Pavllo,

David Joseph Tan,

Marie-Julie Rakotosaona,

Federico Tombari

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Pavllo_2023_CVPR, author = {Pavllo, Dario and Tan, David Joseph and Rakotosaona, Marie-Julie and Tombari, Federico}, title = {Shape, Pose, and Appearance From a Single Image via Bootstrapped Radiance Field Inversion}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4391-4401} }

Unlearnable Clusters: Towards Label-Agnostic Unlearnable Examples

Jiaming Zhang,

Xingjun Ma,

Qi Yi,

Jitao Sang,

Yu-Gang Jiang,

Yaowei Wang,

Changsheng Xu

[pdf] [arXiv]

[bibtex]

@InProceedings{Zhang_2023_CVPR, author = {Zhang, Jiaming and Ma, Xingjun and Yi, Qi and Sang, Jitao and Jiang, Yu-Gang and Wang, Yaowei and Xu, Changsheng}, title = {Unlearnable Clusters: Towards Label-Agnostic Unlearnable Examples}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3984-3993} }

Rethinking Federated Learning With Domain Shift: A Prototype View

Wenke Huang,

Mang Ye,

Zekun Shi,

He Li,

Bo Du

[pdf]

[bibtex]

@InProceedings{Huang_2023_CVPR, author = {Huang, Wenke and Ye, Mang and Shi, Zekun and Li, He and Du, Bo}, title = {Rethinking Federated Learning With Domain Shift: A Prototype View}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16312-16322} }

NoPe-NeRF: Optimising Neural Radiance Field With No Pose Prior

Wenjing Bian,

Zirui Wang,

Kejie Li,

Jia-Wang Bian,

Victor Adrian Prisacariu

[pdf] [supp]

[bibtex]

@InProceedings{Bian_2023_CVPR, author = {Bian, Wenjing and Wang, Zirui and Li, Kejie and Bian, Jia-Wang and Prisacariu, Victor Adrian}, title = {NoPe-NeRF: Optimising Neural Radiance Field With No Pose Prior}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4160-4169} }

HGFormer: Hierarchical Grouping Transformer for Domain Generalized Semantic Segmentation

Jian Ding,

Nan Xue,

Gui-Song Xia,

Bernt Schiele,

Dengxin Dai

[pdf] [arXiv]

[bibtex]

@InProceedings{Ding_2023_CVPR, author = {Ding, Jian and Xue, Nan and Xia, Gui-Song and Schiele, Bernt and Dai, Dengxin}, title = {HGFormer: Hierarchical Grouping Transformer for Domain Generalized Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15413-15423} }

Distilling Vision-Language Pre-Training To Collaborate With Weakly-Supervised Temporal Action Localization

Chen Ju,

Kunhao Zheng,

Jinxiang Liu,

Peisen Zhao,

Ya Zhang,

Jianlong Chang,

Qi Tian,

Yanfeng Wang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Ju_2023_CVPR, author = {Ju, Chen and Zheng, Kunhao and Liu, Jinxiang and Zhao, Peisen and Zhang, Ya and Chang, Jianlong and Tian, Qi and Wang, Yanfeng}, title = {Distilling Vision-Language Pre-Training To Collaborate With Weakly-Supervised Temporal Action Localization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14751-14762} }

Augmentation Matters: A Simple-Yet-Effective Approach to Semi-Supervised Semantic Segmentation

Zhen Zhao,

Lihe Yang,

Sifan Long,

Jimin Pi,

Luping Zhou,

Jingdong Wang

[pdf] [arXiv]

[bibtex]

@InProceedings{Zhao_2023_CVPR, author = {Zhao, Zhen and Yang, Lihe and Long, Sifan and Pi, Jimin and Zhou, Luping and Wang, Jingdong}, title = {Augmentation Matters: A Simple-Yet-Effective Approach to Semi-Supervised Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11350-11359} }

SIEDOB: Semantic Image Editing by Disentangling Object and Background

Wuyang Luo,

Su Yang,

Xinjian Zhang,

Weishan Zhang

[pdf] [arXiv]

[bibtex]

@InProceedings{Luo_2023_CVPR, author = {Luo, Wuyang and Yang, Su and Zhang, Xinjian and Zhang, Weishan}, title = {SIEDOB: Semantic Image Editing by Disentangling Object and Background}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1868-1878} }

Multiclass Confidence and Localization Calibration for Object Detection

Bimsara Pathiraja,

Malitha Gunawardhana,

Muhammad Haris Khan

[pdf] [supp]

[bibtex]

@InProceedings{Pathiraja_2023_CVPR, author = {Pathiraja, Bimsara and Gunawardhana, Malitha and Khan, Muhammad Haris}, title = {Multiclass Confidence and Localization Calibration for Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {19734-19743} }

Query-Dependent Video Representation for Moment Retrieval and Highlight Detection

WonJun Moon,

Sangeek Hyun,

SangUk Park,

Dongchan Park,

Jae-Pil Heo

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Moon_2023_CVPR, author = {Moon, WonJun and Hyun, Sangeek and Park, SangUk and Park, Dongchan and Heo, Jae-Pil}, title = {Query-Dependent Video Representation for Moment Retrieval and Highlight Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {23023-23033} }

Robust 3D Shape Classification via Non-Local Graph Attention Network

Shengwei Qin,

Zhong Li,

Ligang Liu

[pdf] [supp]

[bibtex]

@InProceedings{Qin_2023_CVPR, author = {Qin, Shengwei and Li, Zhong and Liu, Ligang}, title = {Robust 3D Shape Classification via Non-Local Graph Attention Network}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5374-5383} }

Boosting Verified Training for Robust Image Classifications via Abstraction

Zhaodi Zhang,

Zhiyi Xue,

Yang Chen,

Si Liu,

Yueling Zhang,

Jing Liu,

Min Zhang

[pdf] [arXiv]

[bibtex]

@InProceedings{Zhang_2023_CVPR, author = {Zhang, Zhaodi and Xue, Zhiyi and Chen, Yang and Liu, Si and Zhang, Yueling and Liu, Jing and Zhang, Min}, title = {Boosting Verified Training for Robust Image Classifications via Abstraction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16251-16260} }

Exploring Structured Semantic Prior for Multi Label Recognition With Incomplete Labels

Zixuan Ding,

Ao Wang,

Hui Chen,

Qiang Zhang,

Pengzhang Liu,

Yongjun Bao,

Weipeng Yan,

Jungong Han

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Ding_2023_CVPR, author = {Ding, Zixuan and Wang, Ao and Chen, Hui and Zhang, Qiang and Liu, Pengzhang and Bao, Yongjun and Yan, Weipeng and Han, Jungong}, title = {Exploring Structured Semantic Prior for Multi Label Recognition With Incomplete Labels}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3398-3407} }

Instance-Specific and Model-Adaptive Supervision for Semi-Supervised Semantic Segmentation

Zhen Zhao,

Sifan Long,

Jimin Pi,

Jingdong Wang,

Luping Zhou

[pdf] [arXiv]

[bibtex]

@InProceedings{Zhao_2023_CVPR, author = {Zhao, Zhen and Long, Sifan and Pi, Jimin and Wang, Jingdong and Zhou, Luping}, title = {Instance-Specific and Model-Adaptive Supervision for Semi-Supervised Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {23705-23714} }

3D Shape Reconstruction of Semi-Transparent Worms

Thomas P. Ilett,

Omer Yuval,

Thomas Ranner,

Netta Cohen,

David C. Hogg

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Ilett_2023_CVPR, author = {Ilett, Thomas P. and Yuval, Omer and Ranner, Thomas and Cohen, Netta and Hogg, David C.}, title = {3D Shape Reconstruction of Semi-Transparent Worms}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12565-12575} }

Mapping Degeneration Meets Label Evolution: Learning Infrared Small Target Detection With Single Point Supervision

Xinyi Ying,

Li Liu,

Yingqian Wang,

Ruojing Li,

Nuo Chen,

Zaiping Lin,

Weidong Sheng,

Shilin Zhou

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Ying_2023_CVPR, author = {Ying, Xinyi and Liu, Li and Wang, Yingqian and Li, Ruojing and Chen, Nuo and Lin, Zaiping and Sheng, Weidong and Zhou, Shilin}, title = {Mapping Degeneration Meets Label Evolution: Learning Infrared Small Target Detection With Single Point Supervision}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15528-15538} }

Swept-Angle Synthetic Wavelength Interferometry

Alankar Kotwal,

Anat Levin,

Ioannis Gkioulekas

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Kotwal_2023_CVPR, author = {Kotwal, Alankar and Levin, Anat and Gkioulekas, Ioannis}, title = {Swept-Angle Synthetic Wavelength Interferometry}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8233-8243} }

Delving Into Shape-Aware Zero-Shot Semantic Segmentation

Xinyu Liu,

Beiwen Tian,

Zhen Wang,

Rui Wang,

Kehua Sheng,

Bo Zhang,

Hao Zhao,

Guyue Zhou

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Liu_2023_CVPR, author = {Liu, Xinyu and Tian, Beiwen and Wang, Zhen and Wang, Rui and Sheng, Kehua and Zhang, Bo and Zhao, Hao and Zhou, Guyue}, title = {Delving Into Shape-Aware Zero-Shot Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2999-3009} }

Post-Training Quantization on Diffusion Models

Yuzhang Shang,

Zhihang Yuan,

Bin Xie,

Bingzhe Wu,

Yan Yan

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Shang_2023_CVPR, author = {Shang, Yuzhang and Yuan, Zhihang and Xie, Bin and Wu, Bingzhe and Yan, Yan}, title = {Post-Training Quantization on Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1972-1981} }

Adaptive Global Decay Process for Event Cameras

Urbano Miguel Nunes,

Ryad Benosman,

Sio-Hoi Ieng

[pdf] [supp]

[bibtex]

@InProceedings{Nunes_2023_CVPR, author = {Nunes, Urbano Miguel and Benosman, Ryad and Ieng, Sio-Hoi}, title = {Adaptive Global Decay Process for Event Cameras}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9771-9780} }

Multi-Space Neural Radiance Fields

Ze-Xin Yin,

Jiaxiong Qiu,

Ming-Ming Cheng,

Bo Ren

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Yin_2023_CVPR, author = {Yin, Ze-Xin and Qiu, Jiaxiong and Cheng, Ming-Ming and Ren, Bo}, title = {Multi-Space Neural Radiance Fields}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12407-12416} }

Leveraging Inter-Rater Agreement for Classification in the Presence of Noisy Labels

Maria Sofia Bucarelli,

Lucas Cassano,

Federico Siciliano,

Amin Mantrach,

Fabrizio Silvestri

[pdf] [supp]

[bibtex]

@InProceedings{Bucarelli_2023_CVPR, author = {Bucarelli, Maria Sofia and Cassano, Lucas and Siciliano, Federico and Mantrach, Amin and Silvestri, Fabrizio}, title = {Leveraging Inter-Rater Agreement for Classification in the Presence of Noisy Labels}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3439-3448} }

Bitstream-Corrupted JPEG Images Are Restorable: Two-Stage Compensation and Alignment Framework for Image Restoration

Wenyang Liu,

Yi Wang,

Kim-Hui Yap,

Lap-Pui Chau

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Liu_2023_CVPR, author = {Liu, Wenyang and Wang, Yi and Yap, Kim-Hui and Chau, Lap-Pui}, title = {Bitstream-Corrupted JPEG Images Are Restorable: Two-Stage Compensation and Alignment Framework for Image Restoration}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9979-9988} }

Analyzing Physical Impacts Using Transient Surface Wave Imaging

Tianyuan Zhang,

Mark Sheinin,

Dorian Chan,

Mark Rau,

Matthew O’Toole,

Srinivasa G. Narasimhan

[pdf] [supp]

[bibtex]

@InProceedings{Zhang_2023_CVPR, author = {Zhang, Tianyuan and Sheinin, Mark and Chan, Dorian and Rau, Mark and O{\textquoteright}Toole, Matthew and Narasimhan, Srinivasa G.}, title = {Analyzing Physical Impacts Using Transient Surface Wave Imaging}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4339-4348} }

X-Pruner: eXplainable Pruning for Vision Transformers

Lu Yu,

Wei Xiang

[pdf]

[bibtex]

@InProceedings{Yu_2023_CVPR, author = {Yu, Lu and Xiang, Wei}, title = {X-Pruner: eXplainable Pruning for Vision Transformers}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {24355-24363} }

Hard Sample Matters a Lot in Zero-Shot Quantization

Huantong Li,

Xiangmiao Wu,

Fanbing Lv,

Daihai Liao,

Thomas H. Li,

Yonggang Zhang,

Bo Han,

Mingkui Tan

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Li_2023_CVPR, author = {Li, Huantong and Wu, Xiangmiao and Lv, Fanbing and Liao, Daihai and Li, Thomas H. and Zhang, Yonggang and Han, Bo and Tan, Mingkui}, title = {Hard Sample Matters a Lot in Zero-Shot Quantization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {24417-24426} }

Meta Compositional Referring Expression Segmentation

Li Xu,

Mark He Huang,

Xindi Shang,

Zehuan Yuan,

Ying Sun,

Jun Liu

[pdf] [arXiv]

[bibtex]

@InProceedings{Xu_2023_CVPR, author = {Xu, Li and Huang, Mark He and Shang, Xindi and Yuan, Zehuan and Sun, Ying and Liu, Jun}, title = {Meta Compositional Referring Expression Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {19478-19487} }

Histopathology Whole Slide Image Analysis With Heterogeneous Graph Representation Learning

Tsai Hor Chan,

Fernando Julio Cendra,

Lan Ma,

Guosheng Yin,

Lequan Yu

[pdf] [supp]

[bibtex]

@InProceedings{Chan_2023_CVPR, author = {Chan, Tsai Hor and Cendra, Fernando Julio and Ma, Lan and Yin, Guosheng and Yu, Lequan}, title = {Histopathology Whole Slide Image Analysis With Heterogeneous Graph Representation Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15661-15670} }

ScanDMM: A Deep Markov Model of Scanpath Prediction for 360deg Images

Xiangjie Sui,

Yuming Fang,

Hanwei Zhu,

Shiqi Wang,

Zhou Wang

[pdf]

[bibtex]

@InProceedings{Sui_2023_CVPR, author = {Sui, Xiangjie and Fang, Yuming and Zhu, Hanwei and Wang, Shiqi and Wang, Zhou}, title = {ScanDMM: A Deep Markov Model of Scanpath Prediction for 360deg Images}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6989-6999} }

Towards All-in-One Pre-Training via Maximizing Multi-Modal Mutual Information

Weijie Su,

Xizhou Zhu,

Chenxin Tao,

Lewei Lu,

Bin Li,

Gao Huang,

Yu Qiao,

Xiaogang Wang,

Jie Zhou,

Jifeng Dai

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Su_2023_CVPR, author = {Su, Weijie and Zhu, Xizhou and Tao, Chenxin and Lu, Lewei and Li, Bin and Huang, Gao and Qiao, Yu and Wang, Xiaogang and Zhou, Jie and Dai, Jifeng}, title = {Towards All-in-One Pre-Training via Maximizing Multi-Modal Mutual Information}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15888-15899} }

Aligning Bag of Regions for Open-Vocabulary Object Detection

Size Wu,

Wenwei Zhang,

Sheng Jin,

Wentao Liu,

Chen Change Loy

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Wu_2023_CVPR, author = {Wu, Size and Zhang, Wenwei and Jin, Sheng and Liu, Wentao and Loy, Chen Change}, title = {Aligning Bag of Regions for Open-Vocabulary Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15254-15264} }

Two-View Geometry Scoring Without Correspondences

Axel Barroso-Laguna,

Eric Brachmann,

Victor Adrian Prisacariu,

Gabriel J. Brostow,

Daniyar Turmukhambetov

[pdf] [supp]

[bibtex]

@InProceedings{Barroso-Laguna_2023_CVPR, author = {Barroso-Laguna, Axel and Brachmann, Eric and Prisacariu, Victor Adrian and Brostow, Gabriel J. and Turmukhambetov, Daniyar}, title = {Two-View Geometry Scoring Without Correspondences}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8979-8989} }

Annealing-Based Label-Transfer Learning for Open World Object Detection

Yuqing Ma,

Hainan Li,

Zhange Zhang,

Jinyang Guo,

Shanghang Zhang,

Ruihao Gong,

Xianglong Liu

[pdf] [supp]

[bibtex]

@InProceedings{Ma_2023_CVPR, author = {Ma, Yuqing and Li, Hainan and Zhang, Zhange and Guo, Jinyang and Zhang, Shanghang and Gong, Ruihao and Liu, Xianglong}, title = {Annealing-Based Label-Transfer Learning for Open World Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11454-11463} }

Continual Semantic Segmentation With Automatic Memory Sample Selection

Lanyun Zhu,

Tianrun Chen,

Jianxiong Yin,

Simon See,

Jun Liu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Zhu_2023_CVPR, author = {Zhu, Lanyun and Chen, Tianrun and Yin, Jianxiong and See, Simon and Liu, Jun}, title = {Continual Semantic Segmentation With Automatic Memory Sample Selection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3082-3092} }

Meta-Tuning Loss Functions and Data Augmentation for Few-Shot Object Detection

Berkan Demirel,

Orhun Buğra Baran,

Ramazan Gokberk Cinbis

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Demirel_2023_CVPR, author = {Demirel, Berkan and Baran, Orhun Bu\u{g}ra and Cinbis, Ramazan Gokberk}, title = {Meta-Tuning Loss Functions and Data Augmentation for Few-Shot Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7339-7349} }

A Light Weight Model for Active Speaker Detection

Junhua Liao,

Haihan Duan,

Kanghui Feng,

Wanbing Zhao,

Yanbing Yang,

Liangyin Chen

[pdf] [arXiv]

[bibtex]

@InProceedings{Liao_2023_CVPR, author = {Liao, Junhua and Duan, Haihan and Feng, Kanghui and Zhao, Wanbing and Yang, Yanbing and Chen, Liangyin}, title = {A Light Weight Model for Active Speaker Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {22932-22941} }

Self-Supervised Video Forensics by Audio-Visual Anomaly Detection

Chao Feng,

Ziyang Chen,

Andrew Owens

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Feng_2023_CVPR, author = {Feng, Chao and Chen, Ziyang and Owens, Andrew}, title = {Self-Supervised Video Forensics by Audio-Visual Anomaly Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10491-10503} }

CLIP2Scene: Towards Label-Efficient 3D Scene Understanding by CLIP

Runnan Chen,

Youquan Liu,

Lingdong Kong,

Xinge Zhu,

Yuexin Ma,

Yikang Li,

Yuenan Hou,

Yu Qiao,

Wenping Wang

[pdf] [arXiv]

[bibtex]

@InProceedings{Chen_2023_CVPR, author = {Chen, Runnan and Liu, Youquan and Kong, Lingdong and Zhu, Xinge and Ma, Yuexin and Li, Yikang and Hou, Yuenan and Qiao, Yu and Wang, Wenping}, title = {CLIP2Scene: Towards Label-Efficient 3D Scene Understanding by CLIP}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7020-7030} }

GCFAgg: Global and Cross-View Feature Aggregation for Multi-View Clustering

Weiqing Yan,

Yuanyang Zhang,

Chenlei Lv,

Chang Tang,

Guanghui Yue,

Liang Liao,

Weisi Lin

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Yan_2023_CVPR, author = {Yan, Weiqing and Zhang, Yuanyang and Lv, Chenlei and Tang, Chang and Yue, Guanghui and Liao, Liang and Lin, Weisi}, title = {GCFAgg: Global and Cross-View Feature Aggregation for Multi-View Clustering}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {19863-19872} }

Class Balanced Adaptive Pseudo Labeling for Federated Semi-Supervised Learning

Ming Li,

Qingli Li,

Yan Wang

[pdf] [supp]

[bibtex]

@InProceedings{Li_2023_CVPR, author = {Li, Ming and Li, Qingli and Wang, Yan}, title = {Class Balanced Adaptive Pseudo Labeling for Federated Semi-Supervised Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16292-16301} }

Rethinking Out-of-Distribution (OOD) Detection: Masked Image Modeling Is All You Need

Jingyao Li,

Pengguang Chen,

Zexin He,

Shaozuo Yu,

Shu Liu,

Jiaya Jia

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Li_2023_CVPR, author = {Li, Jingyao and Chen, Pengguang and He, Zexin and Yu, Shaozuo and Liu, Shu and Jia, Jiaya}, title = {Rethinking Out-of-Distribution (OOD) Detection: Masked Image Modeling Is All You Need}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11578-11589} }

DeGPR: Deep Guided Posterior Regularization for Multi-Class Cell Detection and Counting

Aayush Kumar Tyagi,

Chirag Mohapatra,

Prasenjit Das,

Govind Makharia,

Lalita Mehra,

Prathosh AP,

Mausam

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Tyagi_2023_CVPR, author = {Tyagi, Aayush Kumar and Mohapatra, Chirag and Das, Prasenjit and Makharia, Govind and Mehra, Lalita and AP, Prathosh and Mausam}, title = {DeGPR: Deep Guided Posterior Regularization for Multi-Class Cell Detection and Counting}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {23913-23923} }

Masked Scene Contrast: A Scalable Framework for Unsupervised 3D Representation Learning

Xiaoyang Wu,

Xin Wen,

Xihui Liu,

Hengshuang Zhao

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Wu_2023_CVPR, author = {Wu, Xiaoyang and Wen, Xin and Liu, Xihui and Zhao, Hengshuang}, title = {Masked Scene Contrast: A Scalable Framework for Unsupervised 3D Representation Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9415-9424} }

Multi Domain Learning for Motion Magnification

Jasdeep Singh,

Subrahmanyam Murala,

G. Sankara Raju Kosuru

[pdf] [supp]

[bibtex]

@InProceedings{Singh_2023_CVPR, author = {Singh, Jasdeep and Murala, Subrahmanyam and Kosuru, G. Sankara Raju}, title = {Multi Domain Learning for Motion Magnification}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13914-13923} }

LOGO: A Long-Form Video Dataset for Group Action Quality Assessment

Shiyi Zhang,

Wenxun Dai,

Sujia Wang,

Xiangwei Shen,

Jiwen Lu,

Jie Zhou,

Yansong Tang

[pdf] [supp]

[bibtex]

@InProceedings{Zhang_2023_CVPR, author = {Zhang, Shiyi and Dai, Wenxun and Wang, Sujia and Shen, Xiangwei and Lu, Jiwen and Zhou, Jie and Tang, Yansong}, title = {LOGO: A Long-Form Video Dataset for Group Action Quality Assessment}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2405-2414} }

A Simple Baseline for Video Restoration With Grouped Spatial-Temporal Shift

Dasong Li,

Xiaoyu Shi,

Yi Zhang,

Ka Chun Cheung,

Simon See,

Xiaogang Wang,

Hongwei Qin,

Hongsheng Li

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Li_2023_CVPR, author = {Li, Dasong and Shi, Xiaoyu and Zhang, Yi and Cheung, Ka Chun and See, Simon and Wang, Xiaogang and Qin, Hongwei and Li, Hongsheng}, title = {A Simple Baseline for Video Restoration With Grouped Spatial-Temporal Shift}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9822-9832} }

UniSim: A Neural Closed-Loop Sensor Simulator

Ze Yang,

Yun Chen,

Jingkang Wang,

Sivabalan Manivasagam,

Wei-Chiu Ma,

Anqi Joyce Yang,

Raquel Urtasun

[pdf]

[bibtex]

@InProceedings{Yang_2023_CVPR, author = {Yang, Ze and Chen, Yun and Wang, Jingkang and Manivasagam, Sivabalan and Ma, Wei-Chiu and Yang, Anqi Joyce and Urtasun, Raquel}, title = {UniSim: A Neural Closed-Loop Sensor Simulator}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1389-1399} }

itKD: Interchange Transfer-Based Knowledge Distillation for 3D Object Detection

Hyeon Cho,

Junyong Choi,

Geonwoo Baek,

Wonjun Hwang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Cho_2023_CVPR, author = {Cho, Hyeon and Choi, Junyong and Baek, Geonwoo and Hwang, Wonjun}, title = {itKD: Interchange Transfer-Based Knowledge Distillation for 3D Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13540-13549} }

SliceMatch: Geometry-Guided Aggregation for Cross-View Pose Estimation

Ted Lentsch,

Zimin Xia,

Holger Caesar,

Julian F. P. Kooij

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Lentsch_2023_CVPR, author = {Lentsch, Ted and Xia, Zimin and Caesar, Holger and Kooij, Julian F. P.}, title = {SliceMatch: Geometry-Guided Aggregation for Cross-View Pose Estimation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {17225-17234} }

2PCNet: Two-Phase Consistency Training for Day-to-Night Unsupervised Domain Adaptive Object Detection

Mikhail Kennerley,

Jian-Gang Wang,

Bharadwaj Veeravalli,

Robby T. Tan

[pdf] [arXiv]

[bibtex]

@InProceedings{Kennerley_2023_CVPR, author = {Kennerley, Mikhail and Wang, Jian-Gang and Veeravalli, Bharadwaj and Tan, Robby T.}, title = {2PCNet: Two-Phase Consistency Training for Day-to-Night Unsupervised Domain Adaptive Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11484-11493} }

Prefix Conditioning Unifies Language and Label Supervision

Kuniaki Saito,

Kihyuk Sohn,

Xiang Zhang,

Chun-Liang Li,

Chen-Yu Lee,

Kate Saenko,

Tomas Pfister

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Saito_2023_CVPR, author = {Saito, Kuniaki and Sohn, Kihyuk and Zhang, Xiang and Li, Chun-Liang and Lee, Chen-Yu and Saenko, Kate and Pfister, Tomas}, title = {Prefix Conditioning Unifies Language and Label Supervision}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2861-2870} }

Panoptic Lifting for 3D Scene Understanding With Neural Fields

Yawar Siddiqui,

Lorenzo Porzi,

Samuel Rota Bulò,

Norman Müller,

Matthias Nießner,

Angela Dai,

Peter Kontschieder

[pdf] [supp]

[bibtex]

@InProceedings{Siddiqui_2023_CVPR, author = {Siddiqui, Yawar and Porzi, Lorenzo and Bul\`o, Samuel Rota and M\"uller, Norman and Nie{\ss}ner, Matthias and Dai, Angela and Kontschieder, Peter}, title = {Panoptic Lifting for 3D Scene Understanding With Neural Fields}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9043-9052} }

WeatherStream: Light Transport Automation of Single Image Deweathering

Howard Zhang,

Yunhao Ba,

Ethan Yang,

Varan Mehra,

Blake Gella,

Akira Suzuki,

Arnold Pfahnl,

Chethan Chinder Chandrappa,

Alex Wong,

Achuta Kadambi

[pdf] [supp]

[bibtex]

@InProceedings{Zhang_2023_CVPR, author = {Zhang, Howard and Ba, Yunhao and Yang, Ethan and Mehra, Varan and Gella, Blake and Suzuki, Akira and Pfahnl, Arnold and Chandrappa, Chethan Chinder and Wong, Alex and Kadambi, Achuta}, title = {WeatherStream: Light Transport Automation of Single Image Deweathering}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13499-13509} }

Learning To Detect Mirrors From Videos via Dual Correspondences

Jiaying Lin,

Xin Tan,

Rynson W.H. Lau

[pdf] [supp]

[bibtex]

@InProceedings{Lin_2023_CVPR, author = {Lin, Jiaying and Tan, Xin and Lau, Rynson W.H.}, title = {Learning To Detect Mirrors From Videos via Dual Correspondences}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9109-9118} }

Single View Scene Scale Estimation Using Scale Field

Byeong-Uk Lee,

Jianming Zhang,

Yannick Hold-Geoffroy,

In So Kweon

[pdf] [supp]

[bibtex]

@InProceedings{Lee_2023_CVPR, author = {Lee, Byeong-Uk and Zhang, Jianming and Hold-Geoffroy, Yannick and Kweon, In So}, title = {Single View Scene Scale Estimation Using Scale Field}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {21435-21444} }

Learning Semantic-Aware Disentangled Representation for Flexible 3D Human Body Editing

Xiaokun Sun,

Qiao Feng,

Xiongzheng Li,

Jinsong Zhang,

Yu-Kun Lai,

Jingyu Yang,

Kun Li

[pdf] [supp]

[bibtex]

@InProceedings{Sun_2023_CVPR, author = {Sun, Xiaokun and Feng, Qiao and Li, Xiongzheng and Zhang, Jinsong and Lai, Yu-Kun and Yang, Jingyu and Li, Kun}, title = {Learning Semantic-Aware Disentangled Representation for Flexible 3D Human Body Editing}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16985-16994} }

Generating Features With Increased Crop-Related Diversity for Few-Shot Object Detection

Jingyi Xu,

Hieu Le,

Dimitris Samaras

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Xu_2023_CVPR, author = {Xu, Jingyi and Le, Hieu and Samaras, Dimitris}, title = {Generating Features With Increased Crop-Related Diversity for Few-Shot Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {19713-19722} }

Towards Scalable Neural Representation for Diverse Videos

Bo He,

Xitong Yang,

Hanyu Wang,

Zuxuan Wu,

Hao Chen,

Shuaiyi Huang,

Yixuan Ren,

Ser-Nam Lim,

Abhinav Shrivastava

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{He_2023_CVPR, author = {He, Bo and Yang, Xitong and Wang, Hanyu and Wu, Zuxuan and Chen, Hao and Huang, Shuaiyi and Ren, Yixuan and Lim, Ser-Nam and Shrivastava, Abhinav}, title = {Towards Scalable Neural Representation for Diverse Videos}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6132-6142} }

The Devil Is in the Points: Weakly Semi-Supervised Instance Segmentation via Point-Guided Mask Representation

Beomyoung Kim,

Joonhyun Jeong,

Dongyoon Han,

Sung Ju Hwang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Kim_2023_CVPR, author = {Kim, Beomyoung and Jeong, Joonhyun and Han, Dongyoon and Hwang, Sung Ju}, title = {The Devil Is in the Points: Weakly Semi-Supervised Instance Segmentation via Point-Guided Mask Representation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11360-11370} }

Towards Compositional Adversarial Robustness: Generalizing Adversarial Training to Composite Semantic Perturbations

Lei Hsiung,

Yun-Yun Tsai,

Pin-Yu Chen,

Tsung-Yi Ho

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Hsiung_2023_CVPR, author = {Hsiung, Lei and Tsai, Yun-Yun and Chen, Pin-Yu and Ho, Tsung-Yi}, title = {Towards Compositional Adversarial Robustness: Generalizing Adversarial Training to Composite Semantic Perturbations}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {24658-24667} }

Language-Guided Audio-Visual Source Separation via Trimodal Consistency

Reuben Tan,

Arijit Ray,

Andrea Burns,

Bryan A. Plummer,

Justin Salamon,

Oriol Nieto,

Bryan Russell,

Kate Saenko

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Tan_2023_CVPR, author = {Tan, Reuben and Ray, Arijit and Burns, Andrea and Plummer, Bryan A. and Salamon, Justin and Nieto, Oriol and Russell, Bryan and Saenko, Kate}, title = {Language-Guided Audio-Visual Source Separation via Trimodal Consistency}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10575-10584} }

CVT-SLR: Contrastive Visual-Textual Transformation for Sign Language Recognition With Variational Alignment

Jiangbin Zheng,

Yile Wang,

Cheng Tan,

Siyuan Li,

Ge Wang,

Jun Xia,

Yidong Chen,

Stan Z. Li

[pdf]

[bibtex]

@InProceedings{Zheng_2023_CVPR, author = {Zheng, Jiangbin and Wang, Yile and Tan, Cheng and Li, Siyuan and Wang, Ge and Xia, Jun and Chen, Yidong and Li, Stan Z.}, title = {CVT-SLR: Contrastive Visual-Textual Transformation for Sign Language Recognition With Variational Alignment}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {23141-23150} }

DynaMask: Dynamic Mask Selection for Instance Segmentation

Ruihuang Li,

Chenhang He,

Shuai Li,

Yabin Zhang,

Lei Zhang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Li_2023_CVPR, author = {Li, Ruihuang and He, Chenhang and Li, Shuai and Zhang, Yabin and Zhang, Lei}, title = {DynaMask: Dynamic Mask Selection for Instance Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11279-11288} }

Paint by Example: Exemplar-Based Image Editing With Diffusion Models

Binxin Yang,

Shuyang Gu,

Bo Zhang,

Ting Zhang,

Xuejin Chen,

Xiaoyan Sun,

Dong Chen,

Fang Wen

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Yang_2023_CVPR, author = {Yang, Binxin and Gu, Shuyang and Zhang, Bo and Zhang, Ting and Chen, Xuejin and Sun, Xiaoyan and Chen, Dong and Wen, Fang}, title = {Paint by Example: Exemplar-Based Image Editing With Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {18381-18391} }

Ego-Body Pose Estimation via Ego-Head Pose Estimation

Jiaman Li,

Karen Liu,

Jiajun Wu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Li_2023_CVPR, author = {Li, Jiaman and Liu, Karen and Wu, Jiajun}, title = {Ego-Body Pose Estimation via Ego-Head Pose Estimation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {17142-17151} }

SAP-DETR: Bridging the Gap Between Salient Points and Queries-Based Transformer Detector for Fast Model Convergency

Yang Liu,

Yao Zhang,

Yixin Wang,

Yang Zhang,

Jiang Tian,

Zhongchao Shi,

Jianping Fan,

Zhiqiang He

[pdf] [supp]

[bibtex]

@InProceedings{Liu_2023_CVPR, author = {Liu, Yang and Zhang, Yao and Wang, Yixin and Zhang, Yang and Tian, Jiang and Shi, Zhongchao and Fan, Jianping and He, Zhiqiang}, title = {SAP-DETR: Bridging the Gap Between Salient Points and Queries-Based Transformer Detector for Fast Model Convergency}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15539-15547} }

GD-MAE: Generative Decoder for MAE Pre-Training on LiDAR Point Clouds

Honghui Yang,

Tong He,

Jiaheng Liu,

Hua Chen,

Boxi Wu,

Binbin Lin,

Xiaofei He,

Wanli Ouyang

[pdf] [supp]

[bibtex]

@InProceedings{Yang_2023_CVPR, author = {Yang, Honghui and He, Tong and Liu, Jiaheng and Chen, Hua and Wu, Boxi and Lin, Binbin and He, Xiaofei and Ouyang, Wanli}, title = {GD-MAE: Generative Decoder for MAE Pre-Training on LiDAR Point Clouds}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9403-9414} }

Towards Robust Tampered Text Detection in Document Image: New Dataset and New Solution

Chenfan Qu,

Chongyu Liu,

Yuliang Liu,

Xinhong Chen,

Dezhi Peng,

Fengjun Guo,

Lianwen Jin

[pdf] [supp]

[bibtex]

@InProceedings{Qu_2023_CVPR, author = {Qu, Chenfan and Liu, Chongyu and Liu, Yuliang and Chen, Xinhong and Peng, Dezhi and Guo, Fengjun and Jin, Lianwen}, title = {Towards Robust Tampered Text Detection in Document Image: New Dataset and New Solution}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5937-5946} }

Learning Rotation-Equivariant Features for Visual Correspondence

Jongmin Lee,

Byungjin Kim,

Seungwook Kim,

Minsu Cho

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Lee_2023_CVPR, author = {Lee, Jongmin and Kim, Byungjin and Kim, Seungwook and Cho, Minsu}, title = {Learning Rotation-Equivariant Features for Visual Correspondence}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {21887-21897} }

DexArt: Benchmarking Generalizable Dexterous Manipulation With Articulated Objects

Chen Bao,

Helin Xu,

Yuzhe Qin,

Xiaolong Wang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Bao_2023_CVPR, author = {Bao, Chen and Xu, Helin and Qin, Yuzhe and Wang, Xiaolong}, title = {DexArt: Benchmarking Generalizable Dexterous Manipulation With Articulated Objects}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {21190-21200} }

DeSTSeg: Segmentation Guided Denoising Student-Teacher for Anomaly Detection

Xuan Zhang,

Shiyu Li,

Xi Li,

Ping Huang,

Jiulong Shan,

Ting Chen

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Zhang_2023_CVPR, author = {Zhang, Xuan and Li, Shiyu and Li, Xi and Huang, Ping and Shan, Jiulong and Chen, Ting}, title = {DeSTSeg: Segmentation Guided Denoising Student-Teacher for Anomaly Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3914-3923} }

Neural Rate Estimator and Unsupervised Learning for Efficient Distributed Image Analytics in Split-DNN Models

Nilesh Ahuja,

Parual Datta,

Bhavya Kanzariya,

V. Srinivasa Somayazulu,

Omesh Tickoo

[pdf] [supp]

[bibtex]

@InProceedings{Ahuja_2023_CVPR, author = {Ahuja, Nilesh and Datta, Parual and Kanzariya, Bhavya and Somayazulu, V. Srinivasa and Tickoo, Omesh}, title = {Neural Rate Estimator and Unsupervised Learning for Efficient Distributed Image Analytics in Split-DNN Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2022-2030} }

Object Pop-Up: Can We Infer 3D Objects and Their Poses From Human Interactions Alone?

Ilya A. Petrov,

Riccardo Marin,

Julian Chibane,

Gerard Pons-Moll

[pdf]

[bibtex]

@InProceedings{Petrov_2023_CVPR, author = {Petrov, Ilya A. and Marin, Riccardo and Chibane, Julian and Pons-Moll, Gerard}, title = {Object Pop-Up: Can We Infer 3D Objects and Their Poses From Human Interactions Alone?}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4726-4736} }

VoP: Text-Video Co-Operative Prompt Tuning for Cross-Modal Retrieval

Siteng Huang,

Biao Gong,

Yulin Pan,

Jianwen Jiang,

Yiliang Lv,

Yuyuan Li,

Donglin Wang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Huang_2023_CVPR, author = {Huang, Siteng and Gong, Biao and Pan, Yulin and Jiang, Jianwen and Lv, Yiliang and Li, Yuyuan and Wang, Donglin}, title = {VoP: Text-Video Co-Operative Prompt Tuning for Cross-Modal Retrieval}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6565-6574} }

Exploiting Unlabelled Photos for Stronger Fine-Grained SBIR

Aneeshan Sain,

Ayan Kumar Bhunia,

Subhadeep Koley,

Pinaki Nath Chowdhury,

Soumitri Chattopadhyay,

Tao Xiang,

Yi-Zhe Song

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Sain_2023_CVPR, author = {Sain, Aneeshan and Bhunia, Ayan Kumar and Koley, Subhadeep and Chowdhury, Pinaki Nath and Chattopadhyay, Soumitri and Xiang, Tao and Song, Yi-Zhe}, title = {Exploiting Unlabelled Photos for Stronger Fine-Grained SBIR}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6873-6883} }

You Do Not Need Additional Priors or Regularizers in Retinex-Based Low-Light Image Enhancement

Huiyuan Fu,

Wenkai Zheng,

Xiangyu Meng,

Xin Wang,

Chuanming Wang,

Huadong Ma

[pdf]

[bibtex]

@InProceedings{Fu_2023_CVPR, author = {Fu, Huiyuan and Zheng, Wenkai and Meng, Xiangyu and Wang, Xin and Wang, Chuanming and Ma, Huadong}, title = {You Do Not Need Additional Priors or Regularizers in Retinex-Based Low-Light Image Enhancement}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {18125-18134} }

PIP-Net: Patch-Based Intuitive Prototypes for Interpretable Image Classification

Meike Nauta,

Jörg Schlötterer,

Maurice van Keulen,

Christin Seifert

[pdf] [supp]

[bibtex]

@InProceedings{Nauta_2023_CVPR, author = {Nauta, Meike and Schl\"otterer, J\"org and van Keulen, Maurice and Seifert, Christin}, title = {PIP-Net: Patch-Based Intuitive Prototypes for Interpretable Image Classification}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2744-2753} }

SCADE: NeRFs from Space Carving With Ambiguity-Aware Depth Estimates

Mikaela Angelina Uy,

Ricardo Martin-Brualla,

Leonidas Guibas,

Ke Li

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Uy_2023_CVPR, author = {Uy, Mikaela Angelina and Martin-Brualla, Ricardo and Guibas, Leonidas and Li, Ke}, title = {SCADE: NeRFs from Space Carving With Ambiguity-Aware Depth Estimates}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16518-16527} }

Re-Thinking Model Inversion Attacks Against Deep Neural Networks

Ngoc-Bao Nguyen,

Keshigeyan Chandrasegaran,

Milad Abdollahzadeh,

Ngai-Man Cheung

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Nguyen_2023_CVPR, author = {Nguyen, Ngoc-Bao and Chandrasegaran, Keshigeyan and Abdollahzadeh, Milad and Cheung, Ngai-Man}, title = {Re-Thinking Model Inversion Attacks Against Deep Neural Networks}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16384-16393} }

1% VS 100%: Parameter-Efficient Low Rank Adapter for Dense Predictions

Dongshuo Yin,

Yiran Yang,

Zhechao Wang,

Hongfeng Yu,

Kaiwen Wei,

Xian Sun

[pdf]

[bibtex]

@InProceedings{Yin_2023_CVPR, author = {Yin, Dongshuo and Yang, Yiran and Wang, Zhechao and Yu, Hongfeng and Wei, Kaiwen and Sun, Xian}, title = {1\% VS 100\%: Parameter-Efficient Low Rank Adapter for Dense Predictions}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {20116-20126} }

ResFormer: Scaling ViTs With Multi-Resolution Training

Rui Tian,

Zuxuan Wu,

Qi Dai,

Han Hu,

Yu Qiao,

Yu-Gang Jiang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Tian_2023_CVPR, author = {Tian, Rui and Wu, Zuxuan and Dai, Qi and Hu, Han and Qiao, Yu and Jiang, Yu-Gang}, title = {ResFormer: Scaling ViTs With Multi-Resolution Training}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {22721-22731} }

You Need Multiple Exiting: Dynamic Early Exiting for Accelerating Unified Vision Language Model

Shengkun Tang,

Yaqing Wang,

Zhenglun Kong,

Tianchi Zhang,

Yao Li,

Caiwen Ding,

Yanzhi Wang,

Yi Liang,

Dongkuan Xu

[pdf] [arXiv]

[bibtex]

@InProceedings{Tang_2023_CVPR, author = {Tang, Shengkun and Wang, Yaqing and Kong, Zhenglun and Zhang, Tianchi and Li, Yao and Ding, Caiwen and Wang, Yanzhi and Liang, Yi and Xu, Dongkuan}, title = {You Need Multiple Exiting: Dynamic Early Exiting for Accelerating Unified Vision Language Model}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10781-10791} }

CloSET: Modeling Clothed Humans on Continuous Surface With Explicit Template Decomposition

Hongwen Zhang,

Siyou Lin,

Ruizhi Shao,

Yuxiang Zhang,

Zerong Zheng,

Han Huang,

Yandong Guo,

Yebin Liu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Zhang_2023_CVPR, author = {Zhang, Hongwen and Lin, Siyou and Shao, Ruizhi and Zhang, Yuxiang and Zheng, Zerong and Huang, Han and Guo, Yandong and Liu, Yebin}, title = {CloSET: Modeling Clothed Humans on Continuous Surface With Explicit Template Decomposition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {501-511} }

BUOL: A Bottom-Up Framework With Occupancy-Aware Lifting for Panoptic 3D Scene Reconstruction From a Single Image

Tao Chu,

Pan Zhang,

Qiong Liu,

Jiaqi Wang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Chu_2023_CVPR, author = {Chu, Tao and Zhang, Pan and Liu, Qiong and Wang, Jiaqi}, title = {BUOL: A Bottom-Up Framework With Occupancy-Aware Lifting for Panoptic 3D Scene Reconstruction From a Single Image}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4937-4946} }

Hierarchical Video-Moment Retrieval and Step-Captioning

Abhay Zala,

Jaemin Cho,

Satwik Kottur,

Xilun Chen,

Barlas Oguz,

Yashar Mehdad,

Mohit Bansal

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Zala_2023_CVPR, author = {Zala, Abhay and Cho, Jaemin and Kottur, Satwik and Chen, Xilun and Oguz, Barlas and Mehdad, Yashar and Bansal, Mohit}, title = {Hierarchical Video-Moment Retrieval and Step-Captioning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {23056-23065} }

PROB: Probabilistic Objectness for Open World Object Detection

Orr Zohar,

Kuan-Chieh Wang,

Serena Yeung

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Zohar_2023_CVPR, author = {Zohar, Orr and Wang, Kuan-Chieh and Yeung, Serena}, title = {PROB: Probabilistic Objectness for Open World Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11444-11453} }

PD-Quant: Post-Training Quantization Based on Prediction Difference Metric

Jiawei Liu,

Lin Niu,

Zhihang Yuan,

Dawei Yang,

Xinggang Wang,

Wenyu Liu

[pdf] [supp]

[bibtex]

@InProceedings{Liu_2023_CVPR, author = {Liu, Jiawei and Niu, Lin and Yuan, Zhihang and Yang, Dawei and Wang, Xinggang and Liu, Wenyu}, title = {PD-Quant: Post-Training Quantization Based on Prediction Difference Metric}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {24427-24437} }

AUNet: Learning Relations Between Action Units for Face Forgery Detection

Weiming Bai,

Yufan Liu,

Zhipeng Zhang,

Bing Li,

Weiming Hu

[pdf] [supp]

[bibtex]

@InProceedings{Bai_2023_CVPR, author = {Bai, Weiming and Liu, Yufan and Zhang, Zhipeng and Li, Bing and Hu, Weiming}, title = {AUNet: Learning Relations Between Action Units for Face Forgery Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {24709-24719} }

SparseFusion: Distilling View-Conditioned Diffusion for 3D Reconstruction

Zhizhuo Zhou,

Shubham Tulsiani

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Zhou_2023_CVPR, author = {Zhou, Zhizhuo and Tulsiani, Shubham}, title = {SparseFusion: Distilling View-Conditioned Diffusion for 3D Reconstruction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12588-12597} }

PolyFormer: Referring Image Segmentation As Sequential Polygon Generation

Jiang Liu,

Hui Ding,

Zhaowei Cai,

Yuting Zhang,

Ravi Kumar Satzoda,

Vijay Mahadevan,

R. Manmatha

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Liu_2023_CVPR, author = {Liu, Jiang and Ding, Hui and Cai, Zhaowei and Zhang, Yuting and Satzoda, Ravi Kumar and Mahadevan, Vijay and Manmatha, R.}, title = {PolyFormer: Referring Image Segmentation As Sequential Polygon Generation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {18653-18663} }

Seeing What You Miss: Vision-Language Pre-Training With Semantic Completion Learning

Yatai Ji,

Rongcheng Tu,

Jie Jiang,

Weijie Kong,

Chengfei Cai,

Wenzhe Zhao,

Hongfa Wang,

Yujiu Yang,

Wei Liu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Ji_2023_CVPR, author = {Ji, Yatai and Tu, Rongcheng and Jiang, Jie and Kong, Weijie and Cai, Chengfei and Zhao, Wenzhe and Wang, Hongfa and Yang, Yujiu and Liu, Wei}, title = {Seeing What You Miss: Vision-Language Pre-Training With Semantic Completion Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6789-6798} }

Interactive Segmentation As Gaussion Process Classification

Minghao Zhou,

Hong Wang,

Qian Zhao,

Yuexiang Li,

Yawen Huang,

Deyu Meng,

Yefeng Zheng

[pdf] [supp]

[bibtex]

@InProceedings{Zhou_2023_CVPR, author = {Zhou, Minghao and Wang, Hong and Zhao, Qian and Li, Yuexiang and Huang, Yawen and Meng, Deyu and Zheng, Yefeng}, title = {Interactive Segmentation As Gaussion Process Classification}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {19488-19497} }

Differentiable Shadow Mapping for Efficient Inverse Graphics

Markus Worchel,

Marc Alexa

[pdf] [supp]

[bibtex]

@InProceedings{Worchel_2023_CVPR, author = {Worchel, Markus and Alexa, Marc}, title = {Differentiable Shadow Mapping for Efficient Inverse Graphics}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {142-153} }

Dynamic Focus-Aware Positional Queries for Semantic Segmentation

Haoyu He,

Jianfei Cai,

Zizheng Pan,

Jing Liu,

Jing Zhang,

Dacheng Tao,

Bohan Zhuang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{He_2023_CVPR, author = {He, Haoyu and Cai, Jianfei and Pan, Zizheng and Liu, Jing and Zhang, Jing and Tao, Dacheng and Zhuang, Bohan}, title = {Dynamic Focus-Aware Positional Queries for Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11299-11308} }

A Practical Stereo Depth System for Smart Glasses

Jialiang Wang,

Daniel Scharstein,

Akash Bapat,

Kevin Blackburn-Matzen,

Matthew Yu,

Jonathan Lehman,

Suhib Alsisan,

Yanghan Wang,

Sam Tsai,

Jan-Michael Frahm,

Zijian He,

Peter Vajda,

Michael F. Cohen,

Matt Uyttendaele

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Jialiang and Scharstein, Daniel and Bapat, Akash and Blackburn-Matzen, Kevin and Yu, Matthew and Lehman, Jonathan and Alsisan, Suhib and Wang, Yanghan and Tsai, Sam and Frahm, Jan-Michael and He, Zijian and Vajda, Peter and Cohen, Michael F. and Uyttendaele, Matt}, title = {A Practical Stereo Depth System for Smart Glasses}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {21498-21507} }

Understanding and Constructing Latent Modality Structures in Multi-Modal Representation Learning

Qian Jiang,

Changyou Chen,

Han Zhao,

Liqun Chen,

Qing Ping,

Son Dinh Tran,

Yi Xu,

Belinda Zeng,

Trishul Chilimbi

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Jiang_2023_CVPR, author = {Jiang, Qian and Chen, Changyou and Zhao, Han and Chen, Liqun and Ping, Qing and Tran, Son Dinh and Xu, Yi and Zeng, Belinda and Chilimbi, Trishul}, title = {Understanding and Constructing Latent Modality Structures in Multi-Modal Representation Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7661-7671} }

PointConvFormer: Revenge of the Point-Based Convolution

Wenxuan Wu,

Li Fuxin,

Qi Shan

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Wu_2023_CVPR, author = {Wu, Wenxuan and Fuxin, Li and Shan, Qi}, title = {PointConvFormer: Revenge of the Point-Based Convolution}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {21802-21813} }

Instant Volumetric Head Avatars

Wojciech Zielonka,

Timo Bolkart,

Justus Thies

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Zielonka_2023_CVPR, author = {Zielonka, Wojciech and Bolkart, Timo and Thies, Justus}, title = {Instant Volumetric Head Avatars}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4574-4584} }

HARP: Personalized Hand Reconstruction From a Monocular RGB Video

Korrawe Karunratanakul,

Sergey Prokudin,

Otmar Hilliges,

Siyu Tang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Karunratanakul_2023_CVPR, author = {Karunratanakul, Korrawe and Prokudin, Sergey and Hilliges, Otmar and Tang, Siyu}, title = {HARP: Personalized Hand Reconstruction From a Monocular RGB Video}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12802-12813} }

Variational Distribution Learning for Unsupervised Text-to-Image Generation

Minsoo Kang,

Doyup Lee,

Jiseob Kim,

Saehoon Kim,

Bohyung Han

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Kang_2023_CVPR, author = {Kang, Minsoo and Lee, Doyup and Kim, Jiseob and Kim, Saehoon and Han, Bohyung}, title = {Variational Distribution Learning for Unsupervised Text-to-Image Generation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {23380-23389} }

MetaMix: Towards Corruption-Robust Continual Learning With Temporally Self-Adaptive Data Transformation

Zhenyi Wang,

Li Shen,

Donglin Zhan,

Qiuling Suo,

Yanjun Zhu,

Tiehang Duan,

Mingchen Gao

[pdf] [supp]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Zhenyi and Shen, Li and Zhan, Donglin and Suo, Qiuling and Zhu, Yanjun and Duan, Tiehang and Gao, Mingchen}, title = {MetaMix: Towards Corruption-Robust Continual Learning With Temporally Self-Adaptive Data Transformation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {24521-24531} }

Ultra-High Resolution Segmentation With Ultra-Rich Context: A Novel Benchmark

Deyi Ji,

Feng Zhao,

Hongtao Lu,

Mingyuan Tao,

Jieping Ye

[pdf] [arXiv]

[bibtex]

@InProceedings{Ji_2023_CVPR, author = {Ji, Deyi and Zhao, Feng and Lu, Hongtao and Tao, Mingyuan and Ye, Jieping}, title = {Ultra-High Resolution Segmentation With Ultra-Rich Context: A Novel Benchmark}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {23621-23630} }

DART: Diversify-Aggregate-Repeat Training Improves Generalization of Neural Networks

Samyak Jain,

Sravanti Addepalli,

Pawan Kumar Sahu,

Priyam Dey,

R. Venkatesh Babu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Jain_2023_CVPR, author = {Jain, Samyak and Addepalli, Sravanti and Sahu, Pawan Kumar and Dey, Priyam and Babu, R. Venkatesh}, title = {DART: Diversify-Aggregate-Repeat Training Improves Generalization of Neural Networks}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16048-16059} }

Cross-Domain Image Captioning With Discriminative Finetuning

Roberto Dessì,

Michele Bevilacqua,

Eleonora Gualdoni,

Nathanaël Carraz Rakotonirina,

Francesca Franzon,

Marco Baroni

[pdf] [supp]

[bibtex]

@InProceedings{Dessi_2023_CVPR, author = {Dess{\`\i}, Roberto and Bevilacqua, Michele and Gualdoni, Eleonora and Rakotonirina, Nathana\"el Carraz and Franzon, Francesca and Baroni, Marco}, title = {Cross-Domain Image Captioning With Discriminative Finetuning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6935-6944} }

Accelerating Vision-Language Pretraining With Free Language Modeling

Teng Wang,

Yixiao Ge,

Feng Zheng,

Ran Cheng,

Ying Shan,

Xiaohu Qie,

Ping Luo

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Teng and Ge, Yixiao and Zheng, Feng and Cheng, Ran and Shan, Ying and Qie, Xiaohu and Luo, Ping}, title = {Accelerating Vision-Language Pretraining With Free Language Modeling}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {23161-23170} }

Efficient Mask Correction for Click-Based Interactive Image Segmentation

Fei Du,

Jianlong Yuan,

Zhibin Wang,

Fan Wang

[pdf] [supp]

[bibtex]

@InProceedings{Du_2023_CVPR, author = {Du, Fei and Yuan, Jianlong and Wang, Zhibin and Wang, Fan}, title = {Efficient Mask Correction for Click-Based Interactive Image Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {22773-22782} }

DBARF: Deep Bundle-Adjusting Generalizable Neural Radiance Fields

Yu Chen,

Gim Hee Lee

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Chen_2023_CVPR, author = {Chen, Yu and Lee, Gim Hee}, title = {DBARF: Deep Bundle-Adjusting Generalizable Neural Radiance Fields}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {24-34} }

EvShutter: Transforming Events for Unconstrained Rolling Shutter Correction

Julius Erbach,

Stepan Tulyakov,

Patricia Vitoria,

Alfredo Bochicchio,

Yuanyou Li

[pdf] [supp]

[bibtex]

@InProceedings{Erbach_2023_CVPR, author = {Erbach, Julius and Tulyakov, Stepan and Vitoria, Patricia and Bochicchio, Alfredo and Li, Yuanyou}, title = {EvShutter: Transforming Events for Unconstrained Rolling Shutter Correction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13904-13913} }

Graphics Capsule: Learning Hierarchical 3D Face Representations From 2D Images

Chang Yu,

Xiangyu Zhu,

Xiaomei Zhang,

Zhaoxiang Zhang,

Zhen Lei

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Yu_2023_CVPR, author = {Yu, Chang and Zhu, Xiangyu and Zhang, Xiaomei and Zhang, Zhaoxiang and Lei, Zhen}, title = {Graphics Capsule: Learning Hierarchical 3D Face Representations From 2D Images}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {20981-20990} }

Connecting the Dots: Floorplan Reconstruction Using Two-Level Queries

Yuanwen Yue,

Theodora Kontogianni,

Konrad Schindler,

Francis Engelmann

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Yue_2023_CVPR, author = {Yue, Yuanwen and Kontogianni, Theodora and Schindler, Konrad and Engelmann, Francis}, title = {Connecting the Dots: Floorplan Reconstruction Using Two-Level Queries}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {845-854} }

Analyzing and Diagnosing Pose Estimation With Attributions

Qiyuan He,

Linlin Yang,

Kerui Gu,

Qiuxia Lin,

Angela Yao

[pdf] [supp]

[bibtex]

@InProceedings{He_2023_CVPR, author = {He, Qiyuan and Yang, Linlin and Gu, Kerui and Lin, Qiuxia and Yao, Angela}, title = {Analyzing and Diagnosing Pose Estimation With Attributions}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4821-4830} }

Ambiguity-Resistant Semi-Supervised Learning for Dense Object Detection

Chang Liu,

Weiming Zhang,

Xiangru Lin,

Wei Zhang,

Xiao Tan,

Junyu Han,

Xiaomao Li,

Errui Ding,

Jingdong Wang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Liu_2023_CVPR, author = {Liu, Chang and Zhang, Weiming and Lin, Xiangru and Zhang, Wei and Tan, Xiao and Han, Junyu and Li, Xiaomao and Ding, Errui and Wang, Jingdong}, title = {Ambiguity-Resistant Semi-Supervised Learning for Dense Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15579-15588} }

Scalable, Detailed and Mask-Free Universal Photometric Stereo

Satoshi Ikehata

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Ikehata_2023_CVPR, author = {Ikehata, Satoshi}, title = {Scalable, Detailed and Mask-Free Universal Photometric Stereo}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13198-13207} }

Towards High-Quality and Efficient Video Super-Resolution via Spatial-Temporal Data Overfitting

Gen Li,

Jie Ji,

Minghai Qin,

Wei Niu,

Bin Ren,

Fatemeh Afghah,

Linke Guo,

Xiaolong Ma

[pdf] [arXiv]

[bibtex]

@InProceedings{Li_2023_CVPR, author = {Li, Gen and Ji, Jie and Qin, Minghai and Niu, Wei and Ren, Bin and Afghah, Fatemeh and Guo, Linke and Ma, Xiaolong}, title = {Towards High-Quality and Efficient Video Super-Resolution via Spatial-Temporal Data Overfitting}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10259-10269} }

Make-a-Story: Visual Memory Conditioned Consistent Story Generation

Tanzila Rahman,

Hsin-Ying Lee,

Jian Ren,

Sergey Tulyakov,

Shweta Mahajan,

Leonid Sigal

[pdf] [supp]

[bibtex]

@InProceedings{Rahman_2023_CVPR, author = {Rahman, Tanzila and Lee, Hsin-Ying and Ren, Jian and Tulyakov, Sergey and Mahajan, Shweta and Sigal, Leonid}, title = {Make-a-Story: Visual Memory Conditioned Consistent Story Generation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2493-2502} }

BiFormer: Vision Transformer With Bi-Level Routing Attention

Lei Zhu,

Xinjiang Wang,

Zhanghan Ke,

Wayne Zhang,

Rynson W.H. Lau

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Zhu_2023_CVPR, author = {Zhu, Lei and Wang, Xinjiang and Ke, Zhanghan and Zhang, Wayne and Lau, Rynson W.H.}, title = {BiFormer: Vision Transformer With Bi-Level Routing Attention}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10323-10333} }

Masked Autoencoders Enable Efficient Knowledge Distillers

Yutong Bai,

Zeyu Wang,

Junfei Xiao,

Chen Wei,

Huiyu Wang,

Alan L. Yuille,

Yuyin Zhou,

Cihang Xie

[pdf] [arXiv]

[bibtex]

@InProceedings{Bai_2023_CVPR, author = {Bai, Yutong and Wang, Zeyu and Xiao, Junfei and Wei, Chen and Wang, Huiyu and Yuille, Alan L. and Zhou, Yuyin and Xie, Cihang}, title = {Masked Autoencoders Enable Efficient Knowledge Distillers}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {24256-24265} }

TinyMIM: An Empirical Study of Distilling MIM Pre-Trained Models

Sucheng Ren,

Fangyun Wei,

Zheng Zhang,

Han Hu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Ren_2023_CVPR, author = {Ren, Sucheng and Wei, Fangyun and Zhang, Zheng and Hu, Han}, title = {TinyMIM: An Empirical Study of Distilling MIM Pre-Trained Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3687-3697} }

Persistent Nature: A Generative Model of Unbounded 3D Worlds

Lucy Chai,

Richard Tucker,

Zhengqi Li,

Phillip Isola,

Noah Snavely

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Chai_2023_CVPR, author = {Chai, Lucy and Tucker, Richard and Li, Zhengqi and Isola, Phillip and Snavely, Noah}, title = {Persistent Nature: A Generative Model of Unbounded 3D Worlds}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {20863-20874} }

OneFormer: One Transformer To Rule Universal Image Segmentation

Jitesh Jain,

Jiachen Li,

Mang Tik Chiu,

Ali Hassani,

Nikita Orlov,

Humphrey Shi

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Jain_2023_CVPR, author = {Jain, Jitesh and Li, Jiachen and Chiu, Mang Tik and Hassani, Ali and Orlov, Nikita and Shi, Humphrey}, title = {OneFormer: One Transformer To Rule Universal Image Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2989-2998} }

Hierarchical Neural Memory Network for Low Latency Event Processing

Ryuhei Hamaguchi,

Yasutaka Furukawa,

Masaki Onishi,

Ken Sakurada

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Hamaguchi_2023_CVPR, author = {Hamaguchi, Ryuhei and Furukawa, Yasutaka and Onishi, Masaki and Sakurada, Ken}, title = {Hierarchical Neural Memory Network for Low Latency Event Processing}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {22867-22876} }

Finding Geometric Models by Clustering in the Consensus Space

Daniel Barath,

Denys Rozumnyi,

Ivan Eichhardt,

Levente Hajder,

Jiri Matas

[pdf] [supp]

[bibtex]

@InProceedings{Barath_2023_CVPR, author = {Barath, Daniel and Rozumnyi, Denys and Eichhardt, Ivan and Hajder, Levente and Matas, Jiri}, title = {Finding Geometric Models by Clustering in the Consensus Space}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5414-5424} }

Leapfrog Diffusion Model for Stochastic Trajectory Prediction

Weibo Mao,

Chenxin Xu,

Qi Zhu,

Siheng Chen,

Yanfeng Wang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Mao_2023_CVPR, author = {Mao, Weibo and Xu, Chenxin and Zhu, Qi and Chen, Siheng and Wang, Yanfeng}, title = {Leapfrog Diffusion Model for Stochastic Trajectory Prediction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5517-5526} }

DaFKD: Domain-Aware Federated Knowledge Distillation

Haozhao Wang,

Yichen Li,

Wenchao Xu,

Ruixuan Li,

Yufeng Zhan,

Zhigang Zeng

[pdf] [supp]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Haozhao and Li, Yichen and Xu, Wenchao and Li, Ruixuan and Zhan, Yufeng and Zeng, Zhigang}, title = {DaFKD: Domain-Aware Federated Knowledge Distillation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {20412-20421} }

GeoLayoutLM: Geometric Pre-Training for Visual Information Extraction

Chuwei Luo,

Changxu Cheng,

Qi Zheng,

Cong Yao

[pdf] [arXiv]

[bibtex]

@InProceedings{Luo_2023_CVPR, author = {Luo, Chuwei and Cheng, Changxu and Zheng, Qi and Yao, Cong}, title = {GeoLayoutLM: Geometric Pre-Training for Visual Information Extraction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7092-7101} }

Class-Incremental Exemplar Compression for Class-Incremental Learning

Zilin Luo,

Yaoyao Liu,

Bernt Schiele,

Qianru Sun

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Luo_2023_CVPR, author = {Luo, Zilin and Liu, Yaoyao and Schiele, Bernt and Sun, Qianru}, title = {Class-Incremental Exemplar Compression for Class-Incremental Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11371-11380} }

Boost Vision Transformer With GPU-Friendly Sparsity and Quantization

Chong Yu,

Tao Chen,

Zhongxue Gan,

Jiayuan Fan

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Yu_2023_CVPR, author = {Yu, Chong and Chen, Tao and Gan, Zhongxue and Fan, Jiayuan}, title = {Boost Vision Transformer With GPU-Friendly Sparsity and Quantization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {22658-22668} }

Spectral Bayesian Uncertainty for Image Super-Resolution

Tao Liu,

Jun Cheng,

Shan Tan

[pdf] [supp]

[bibtex]

@InProceedings{Liu_2023_CVPR, author = {Liu, Tao and Cheng, Jun and Tan, Shan}, title = {Spectral Bayesian Uncertainty for Image Super-Resolution}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {18166-18175} }

Behind the Scenes: Density Fields for Single View Reconstruction

Felix Wimbauer,

Nan Yang,

Christian Rupprecht,

Daniel Cremers

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Wimbauer_2023_CVPR, author = {Wimbauer, Felix and Yang, Nan and Rupprecht, Christian and Cremers, Daniel}, title = {Behind the Scenes: Density Fields for Single View Reconstruction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9076-9086} }

StyleGAN Salon: Multi-View Latent Optimization for Pose-Invariant Hairstyle Transfer

Sasikarn Khwanmuang,

Pakkapon Phongthawee,

Patsorn Sangkloy,

Supasorn Suwajanakorn

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Khwanmuang_2023_CVPR, author = {Khwanmuang, Sasikarn and Phongthawee, Pakkapon and Sangkloy, Patsorn and Suwajanakorn, Supasorn}, title = {StyleGAN Salon: Multi-View Latent Optimization for Pose-Invariant Hairstyle Transfer}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8609-8618} }

Resource-Efficient RGBD Aerial Tracking

Jinyu Yang,

Shang Gao,

Zhe Li,

Feng Zheng,

Aleš Leonardis

[pdf] [supp]

[bibtex]

@InProceedings{Yang_2023_CVPR, author = {Yang, Jinyu and Gao, Shang and Li, Zhe and Zheng, Feng and Leonardis, Ale\v{s}}, title = {Resource-Efficient RGBD Aerial Tracking}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13374-13383} }

Mutual Information-Based Temporal Difference Learning for Human Pose Estimation in Video

Runyang Feng,

Yixing Gao,

Xueqing Ma,

Tze Ho Elden Tse,

Hyung Jin Chang

[pdf] [arXiv]

[bibtex]

@InProceedings{Feng_2023_CVPR, author = {Feng, Runyang and Gao, Yixing and Ma, Xueqing and Tse, Tze Ho Elden and Chang, Hyung Jin}, title = {Mutual Information-Based Temporal Difference Learning for Human Pose Estimation in Video}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {17131-17141} }

Bilateral Memory Consolidation for Continual Learning

Xing Nie,

Shixiong Xu,

Xiyan Liu,

Gaofeng Meng,

Chunlei Huo,

Shiming Xiang

[pdf] [supp]

[bibtex]

@InProceedings{Nie_2023_CVPR, author = {Nie, Xing and Xu, Shixiong and Liu, Xiyan and Meng, Gaofeng and Huo, Chunlei and Xiang, Shiming}, title = {Bilateral Memory Consolidation for Continual Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16026-16035} }

SynthVSR: Scaling Up Visual Speech Recognition With Synthetic Supervision

Xubo Liu,

Egor Lakomkin,

Konstantinos Vougioukas,

Pingchuan Ma,

Honglie Chen,

Ruiming Xie,

Morrie Doulaty,

Niko Moritz,

Jachym Kolar,

Stavros Petridis,

Maja Pantic,

Christian Fuegen

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Liu_2023_CVPR, author = {Liu, Xubo and Lakomkin, Egor and Vougioukas, Konstantinos and Ma, Pingchuan and Chen, Honglie and Xie, Ruiming and Doulaty, Morrie and Moritz, Niko and Kolar, Jachym and Petridis, Stavros and Pantic, Maja and Fuegen, Christian}, title = {SynthVSR: Scaling Up Visual Speech Recognition With Synthetic Supervision}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {18806-18815} }

BiasBed - Rigorous Texture Bias Evaluation

Nikolai Kalischek,

Rodrigo Caye Daudt,

Torben Peters,

Reinhard Furrer,

Jan D. Wegner,

Konrad Schindler

[pdf] [supp]

[bibtex]

@InProceedings{Kalischek_2023_CVPR, author = {Kalischek, Nikolai and Daudt, Rodrigo Caye and Peters, Torben and Furrer, Reinhard and Wegner, Jan D. and Schindler, Konrad}, title = {BiasBed - Rigorous Texture Bias Evaluation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {22221-22230} }

Open-Category Human-Object Interaction Pre-Training via Language Modeling Framework

Sipeng Zheng,

Boshen Xu,

Qin Jin

[pdf] [supp]

[bibtex]

@InProceedings{Zheng_2023_CVPR, author = {Zheng, Sipeng and Xu, Boshen and Jin, Qin}, title = {Open-Category Human-Object Interaction Pre-Training via Language Modeling Framework}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {19392-19402} }

SFD2: Semantic-Guided Feature Detection and Description

Fei Xue,

Ignas Budvytis,

Roberto Cipolla

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Xue_2023_CVPR, author = {Xue, Fei and Budvytis, Ignas and Cipolla, Roberto}, title = {SFD2: Semantic-Guided Feature Detection and Description}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5206-5216} }

Search-Map-Search: A Frame Selection Paradigm for Action Recognition

Mingjun Zhao,

Yakun Yu,

Xiaoli Wang,

Lei Yang,

Di Niu

[pdf] [supp]

[bibtex]

@InProceedings{Zhao_2023_CVPR, author = {Zhao, Mingjun and Yu, Yakun and Wang, Xiaoli and Yang, Lei and Niu, Di}, title = {Search-Map-Search: A Frame Selection Paradigm for Action Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10627-10636} }

Uncovering the Missing Pattern: Unified Framework Towards Trajectory Imputation and Prediction

Yi Xu,

Armin Bazarjani,

Hyung-gun Chi,

Chiho Choi,

Yun Fu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Xu_2023_CVPR, author = {Xu, Yi and Bazarjani, Armin and Chi, Hyung-gun and Choi, Chiho and Fu, Yun}, title = {Uncovering the Missing Pattern: Unified Framework Towards Trajectory Imputation and Prediction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9632-9643} }

CLIP for All Things Zero-Shot Sketch-Based Image Retrieval, Fine-Grained or Not

Aneeshan Sain,

Ayan Kumar Bhunia,

Pinaki Nath Chowdhury,

Subhadeep Koley,

Tao Xiang,

Yi-Zhe Song

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Sain_2023_CVPR, author = {Sain, Aneeshan and Bhunia, Ayan Kumar and Chowdhury, Pinaki Nath and Koley, Subhadeep and Xiang, Tao and Song, Yi-Zhe}, title = {CLIP for All Things Zero-Shot Sketch-Based Image Retrieval, Fine-Grained or Not}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2765-2775} }

FlexiViT: One Model for All Patch Sizes

Lucas Beyer,

Pavel Izmailov,

Alexander Kolesnikov,

Mathilde Caron,

Simon Kornblith,

Xiaohua Zhai,

Matthias Minderer,

Michael Tschannen,

Ibrahim Alabdulmohsin,

Filip Pavetic

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Beyer_2023_CVPR, author = {Beyer, Lucas and Izmailov, Pavel and Kolesnikov, Alexander and Caron, Mathilde and Kornblith, Simon and Zhai, Xiaohua and Minderer, Matthias and Tschannen, Michael and Alabdulmohsin, Ibrahim and Pavetic, Filip}, title = {FlexiViT: One Model for All Patch Sizes}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14496-14506} }

RIAV-MVS: Recurrent-Indexing an Asymmetric Volume for Multi-View Stereo

Changjiang Cai,

Pan Ji,

Qingan Yan,

Yi Xu

[pdf] [supp]

[bibtex]

@InProceedings{Cai_2023_CVPR, author = {Cai, Changjiang and Ji, Pan and Yan, Qingan and Xu, Yi}, title = {RIAV-MVS: Recurrent-Indexing an Asymmetric Volume for Multi-View Stereo}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {919-928} }

Structured Kernel Estimation for Photon-Limited Deconvolution

Yash Sanghvi,

Zhiyuan Mao,

Stanley H. Chan

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Sanghvi_2023_CVPR, author = {Sanghvi, Yash and Mao, Zhiyuan and Chan, Stanley H.}, title = {Structured Kernel Estimation for Photon-Limited Deconvolution}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9863-9872} }

Explicit Boundary Guided Semi-Push-Pull Contrastive Learning for Supervised Anomaly Detection

Xincheng Yao,

Ruoqi Li,

Jing Zhang,

Jun Sun,

Chongyang Zhang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Yao_2023_CVPR, author = {Yao, Xincheng and Li, Ruoqi and Zhang, Jing and Sun, Jun and Zhang, Chongyang}, title = {Explicit Boundary Guided Semi-Push-Pull Contrastive Learning for Supervised Anomaly Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {24490-24499} }

3D Video Loops From Asynchronous Input

Li Ma,

Xiaoyu Li,

Jing Liao,

Pedro V. Sander

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Ma_2023_CVPR, author = {Ma, Li and Li, Xiaoyu and Liao, Jing and Sander, Pedro V.}, title = {3D Video Loops From Asynchronous Input}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {310-320} }

Style Projected Clustering for Domain Generalized Semantic Segmentation

Wei Huang,

Chang Chen,

Yong Li,

Jiacheng Li,

Cheng Li,

Fenglong Song,

Youliang Yan,

Zhiwei Xiong

[pdf] [supp]

[bibtex]

@InProceedings{Huang_2023_CVPR, author = {Huang, Wei and Chen, Chang and Li, Yong and Li, Jiacheng and Li, Cheng and Song, Fenglong and Yan, Youliang and Xiong, Zhiwei}, title = {Style Projected Clustering for Domain Generalized Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3061-3071} }

DIP: Dual Incongruity Perceiving Network for Sarcasm Detection

Changsong Wen,

Guoli Jia,

Jufeng Yang

[pdf]

[bibtex]

@InProceedings{Wen_2023_CVPR, author = {Wen, Changsong and Jia, Guoli and Yang, Jufeng}, title = {DIP: Dual Incongruity Perceiving Network for Sarcasm Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2540-2550} }

Frame Interpolation Transformer and Uncertainty Guidance

Markus Plack,

Karlis Martins Briedis,

Abdelaziz Djelouah,

Matthias B. Hullin,

Markus Gross,

Christopher Schroers

[pdf] [supp]

[bibtex]

@InProceedings{Plack_2023_CVPR, author = {Plack, Markus and Briedis, Karlis Martins and Djelouah, Abdelaziz and Hullin, Matthias B. and Gross, Markus and Schroers, Christopher}, title = {Frame Interpolation Transformer and Uncertainty Guidance}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9811-9821} }

Learning To Generate Language-Supervised and Open-Vocabulary Scene Graph Using Pre-Trained Visual-Semantic Space

Yong Zhang,

Yingwei Pan,

Ting Yao,

Rui Huang,

Tao Mei,

Chang-Wen Chen

[pdf] [supp]

[bibtex]

@InProceedings{Zhang_2023_CVPR, author = {Zhang, Yong and Pan, Yingwei and Yao, Ting and Huang, Rui and Mei, Tao and Chen, Chang-Wen}, title = {Learning To Generate Language-Supervised and Open-Vocabulary Scene Graph Using Pre-Trained Visual-Semantic Space}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2915-2924} }

VectorFloorSeg: Two-Stream Graph Attention Network for Vectorized Roughcast Floorplan Segmentation

Bingchen Yang,

Haiyong Jiang,

Hao Pan,

Jun Xiao

[pdf] [supp]

[bibtex]

@InProceedings{Yang_2023_CVPR, author = {Yang, Bingchen and Jiang, Haiyong and Pan, Hao and Xiao, Jun}, title = {VectorFloorSeg: Two-Stream Graph Attention Network for Vectorized Roughcast Floorplan Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1358-1367} }

Neural Preset for Color Style Transfer

Zhanghan Ke,

Yuhao Liu,

Lei Zhu,

Nanxuan Zhao,

Rynson W.H. Lau

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Ke_2023_CVPR, author = {Ke, Zhanghan and Liu, Yuhao and Zhu, Lei and Zhao, Nanxuan and Lau, Rynson W.H.}, title = {Neural Preset for Color Style Transfer}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14173-14182} }

DeCo: Decomposition and Reconstruction for Compositional Temporal Grounding via Coarse-To-Fine Contrastive Ranking

Lijin Yang,

Quan Kong,

Hsuan-Kung Yang,

Wadim Kehl,

Yoichi Sato,

Norimasa Kobori

[pdf] [supp]

[bibtex]

@InProceedings{Yang_2023_CVPR, author = {Yang, Lijin and Kong, Quan and Yang, Hsuan-Kung and Kehl, Wadim and Sato, Yoichi and Kobori, Norimasa}, title = {DeCo: Decomposition and Reconstruction for Compositional Temporal Grounding via Coarse-To-Fine Contrastive Ranking}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {23130-23140} }

Dynamic Aggregated Network for Gait Recognition

Kang Ma,

Ying Fu,

Dezhi Zheng,

Chunshui Cao,

Xuecai Hu,

Yongzhen Huang

[pdf]

[bibtex]

@InProceedings{Ma_2023_CVPR, author = {Ma, Kang and Fu, Ying and Zheng, Dezhi and Cao, Chunshui and Hu, Xuecai and Huang, Yongzhen}, title = {Dynamic Aggregated Network for Gait Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {22076-22085} }

Wavelet Diffusion Models Are Fast and Scalable Image Generators

Hao Phung,

Quan Dao,

Anh Tran

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Phung_2023_CVPR, author = {Phung, Hao and Dao, Quan and Tran, Anh}, title = {Wavelet Diffusion Models Are Fast and Scalable Image Generators}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10199-10208} }

PA&DA: Jointly Sampling Path and Data for Consistent NAS

Shun Lu,

Yu Hu,

Longxing Yang,

Zihao Sun,

Jilin Mei,

Jianchao Tan,

Chengru Song

[pdf] [supp]

[bibtex]

@InProceedings{Lu_2023_CVPR, author = {Lu, Shun and Hu, Yu and Yang, Longxing and Sun, Zihao and Mei, Jilin and Tan, Jianchao and Song, Chengru}, title = {PA\&DA: Jointly Sampling Path and Data for Consistent NAS}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11940-11949} }

Sphere-Guided Training of Neural Implicit Surfaces

Andreea Dogaru,

Andrei-Timotei Ardelean,

Savva Ignatyev,

Egor Zakharov,

Evgeny Burnaev

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Dogaru_2023_CVPR, author = {Dogaru, Andreea and Ardelean, Andrei-Timotei and Ignatyev, Savva and Zakharov, Egor and Burnaev, Evgeny}, title = {Sphere-Guided Training of Neural Implicit Surfaces}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {20844-20853} }

3D Spatial Multimodal Knowledge Accumulation for Scene Graph Prediction in Point Cloud

Mingtao Feng,

Haoran Hou,

Liang Zhang,

Zijie Wu,

Yulan Guo,

Ajmal Mian

[pdf] [supp]

[bibtex]

@InProceedings{Feng_2023_CVPR, author = {Feng, Mingtao and Hou, Haoran and Zhang, Liang and Wu, Zijie and Guo, Yulan and Mian, Ajmal}, title = {3D Spatial Multimodal Knowledge Accumulation for Scene Graph Prediction in Point Cloud}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9182-9191} }

Extracting Motion and Appearance via Inter-Frame Attention for Efficient Video Frame Interpolation

Guozhen Zhang,

Yuhan Zhu,

Haonan Wang,

Youxin Chen,

Gangshan Wu,

Limin Wang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Zhang_2023_CVPR, author = {Zhang, Guozhen and Zhu, Yuhan and Wang, Haonan and Chen, Youxin and Wu, Gangshan and Wang, Limin}, title = {Extracting Motion and Appearance via Inter-Frame Attention for Efficient Video Frame Interpolation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5682-5692} }

Bias Mimicking: A Simple Sampling Approach for Bias Mitigation

Maan Qraitem,

Kate Saenko,

Bryan A. Plummer

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Qraitem_2023_CVPR, author = {Qraitem, Maan and Saenko, Kate and Plummer, Bryan A.}, title = {Bias Mimicking: A Simple Sampling Approach for Bias Mitigation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {20311-20320} }

ViTs for SITS: Vision Transformers for Satellite Image Time Series

Michail Tarasiou,

Erik Chavez,

Stefanos Zafeiriou

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Tarasiou_2023_CVPR, author = {Tarasiou, Michail and Chavez, Erik and Zafeiriou, Stefanos}, title = {ViTs for SITS: Vision Transformers for Satellite Image Time Series}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10418-10428} }

NoisyQuant: Noisy Bias-Enhanced Post-Training Activation Quantization for Vision Transformers

Yijiang Liu,

Huanrui Yang,

Zhen Dong,

Kurt Keutzer,

Li Du,

Shanghang Zhang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Liu_2023_CVPR, author = {Liu, Yijiang and Yang, Huanrui and Dong, Zhen and Keutzer, Kurt and Du, Li and Zhang, Shanghang}, title = {NoisyQuant: Noisy Bias-Enhanced Post-Training Activation Quantization for Vision Transformers}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {20321-20330} }

Semi-Supervised Stereo-Based 3D Object Detection via Cross-View Consensus

Wenhao Wu,

Hau San Wong,

Si Wu

[pdf] [supp]

[bibtex]

@InProceedings{Wu_2023_CVPR, author = {Wu, Wenhao and Wong, Hau San and Wu, Si}, title = {Semi-Supervised Stereo-Based 3D Object Detection via Cross-View Consensus}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {17471-17481} }

Minimizing Maximum Model Discrepancy for Transferable Black-Box Targeted Attacks

Anqi Zhao,

Tong Chu,

Yahao Liu,

Wen Li,

Jingjing Li,

Lixin Duan

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Zhao_2023_CVPR, author = {Zhao, Anqi and Chu, Tong and Liu, Yahao and Li, Wen and Li, Jingjing and Duan, Lixin}, title = {Minimizing Maximum Model Discrepancy for Transferable Black-Box Targeted Attacks}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8153-8162} }

Efficient Loss Function by Minimizing the Detrimental Effect of Floating-Point Errors on Gradient-Based Attacks

Yunrui Yu,

Cheng-Zhong Xu

[pdf] [supp]

[bibtex]

@InProceedings{Yu_2023_CVPR, author = {Yu, Yunrui and Xu, Cheng-Zhong}, title = {Efficient Loss Function by Minimizing the Detrimental Effect of Floating-Point Errors on Gradient-Based Attacks}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4056-4066} }

BAD-NeRF: Bundle Adjusted Deblur Neural Radiance Fields

Peng Wang,

Lingzhe Zhao,

Ruijie Ma,

Peidong Liu

[pdf] [supp]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Peng and Zhao, Lingzhe and Ma, Ruijie and Liu, Peidong}, title = {BAD-NeRF: Bundle Adjusted Deblur Neural Radiance Fields}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4170-4179} }

Video Compression With Entropy-Constrained Neural Representations

Carlos Gomes,

Roberto Azevedo,

Christopher Schroers

[pdf] [supp]

[bibtex]

@InProceedings{Gomes_2023_CVPR, author = {Gomes, Carlos and Azevedo, Roberto and Schroers, Christopher}, title = {Video Compression With Entropy-Constrained Neural Representations}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {18497-18506} }

Prompt, Generate, Then Cache: Cascade of Foundation Models Makes Strong Few-Shot Learners

Renrui Zhang,

Xiangfei Hu,

Bohao Li,

Siyuan Huang,

Hanqiu Deng,

Yu Qiao,

Peng Gao,

Hongsheng Li

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Zhang_2023_CVPR, author = {Zhang, Renrui and Hu, Xiangfei and Li, Bohao and Huang, Siyuan and Deng, Hanqiu and Qiao, Yu and Gao, Peng and Li, Hongsheng}, title = {Prompt, Generate, Then Cache: Cascade of Foundation Models Makes Strong Few-Shot Learners}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15211-15222} }

Deep Random Projector: Accelerated Deep Image Prior

Taihui Li,

Hengkang Wang,

Zhong Zhuang,

Ju Sun

[pdf] [supp]

[bibtex]

@InProceedings{Li_2023_CVPR, author = {Li, Taihui and Wang, Hengkang and Zhuang, Zhong and Sun, Ju}, title = {Deep Random Projector: Accelerated Deep Image Prior}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {18176-18185} }

SCPNet: Semantic Scene Completion on Point Cloud

Zhaoyang Xia,

Youquan Liu,

Xin Li,

Xinge Zhu,

Yuexin Ma,

Yikang Li,

Yuenan Hou,

Yu Qiao

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Xia_2023_CVPR, author = {Xia, Zhaoyang and Liu, Youquan and Li, Xin and Zhu, Xinge and Ma, Yuexin and Li, Yikang and Hou, Yuenan and Qiao, Yu}, title = {SCPNet: Semantic Scene Completion on Point Cloud}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {17642-17651} }

Revisiting Prototypical Network for Cross Domain Few-Shot Learning

Fei Zhou,

Peng Wang,

Lei Zhang,

Wei Wei,

Yanning Zhang

[pdf] [supp]

[bibtex]

@InProceedings{Zhou_2023_CVPR, author = {Zhou, Fei and Wang, Peng and Zhang, Lei and Wei, Wei and Zhang, Yanning}, title = {Revisiting Prototypical Network for Cross Domain Few-Shot Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {20061-20070} }

QPGesture: Quantization-Based and Phase-Guided Motion Matching for Natural Speech-Driven Gesture Generation

Sicheng Yang,

Zhiyong Wu,

Minglei Li,

Zhensong Zhang,

Lei Hao,

Weihong Bao,

Haolin Zhuang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Yang_2023_CVPR, author = {Yang, Sicheng and Wu, Zhiyong and Li, Minglei and Zhang, Zhensong and Hao, Lei and Bao, Weihong and Zhuang, Haolin}, title = {QPGesture: Quantization-Based and Phase-Guided Motion Matching for Natural Speech-Driven Gesture Generation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2321-2330} }

Multiscale Tensor Decomposition and Rendering Equation Encoding for View Synthesis

Kang Han,

Wei Xiang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Han_2023_CVPR, author = {Han, Kang and Xiang, Wei}, title = {Multiscale Tensor Decomposition and Rendering Equation Encoding for View Synthesis}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4232-4241} }

NS3D: Neuro-Symbolic Grounding of 3D Objects and Relations

Joy Hsu,

Jiayuan Mao,

Jiajun Wu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Hsu_2023_CVPR, author = {Hsu, Joy and Mao, Jiayuan and Wu, Jiajun}, title = {NS3D: Neuro-Symbolic Grounding of 3D Objects and Relations}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2614-2623} }

Learning Accurate 3D Shape Based on Stereo Polarimetric Imaging

Tianyu Huang,

Haoang Li,

Kejing He,

Congying Sui,

Bin Li,

Yun-Hui Liu

[pdf] [supp]

[bibtex]

@InProceedings{Huang_2023_CVPR, author = {Huang, Tianyu and Li, Haoang and He, Kejing and Sui, Congying and Li, Bin and Liu, Yun-Hui}, title = {Learning Accurate 3D Shape Based on Stereo Polarimetric Imaging}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {17287-17296} }

VideoMAE V2: Scaling Video Masked Autoencoders With Dual Masking

Limin Wang,

Bingkun Huang,

Zhiyu Zhao,

Zhan Tong,

Yinan He,

Yi Wang,

Yali Wang,

Yu Qiao

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Limin and Huang, Bingkun and Zhao, Zhiyu and Tong, Zhan and He, Yinan and Wang, Yi and Wang, Yali and Qiao, Yu}, title = {VideoMAE V2: Scaling Video Masked Autoencoders With Dual Masking}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14549-14560} }

GANmouflage: 3D Object Nondetection With Texture Fields

Rui Guo,

Jasmine Collins,

Oscar de Lima,

Andrew Owens

[pdf] [arXiv]

[bibtex]

@InProceedings{Guo_2023_CVPR, author = {Guo, Rui and Collins, Jasmine and de Lima, Oscar and Owens, Andrew}, title = {GANmouflage: 3D Object Nondetection With Texture Fields}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4702-4712} }

Perception and Semantic Aware Regularization for Sequential Confidence Calibration

Zhenghua Peng,

Yu Luo,

Tianshui Chen,

Keke Xu,

Shuangping Huang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Peng_2023_CVPR, author = {Peng, Zhenghua and Luo, Yu and Chen, Tianshui and Xu, Keke and Huang, Shuangping}, title = {Perception and Semantic Aware Regularization for Sequential Confidence Calibration}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10658-10668} }

Revisiting Residual Networks for Adversarial Robustness

Shihua Huang,

Zhichao Lu,

Kalyanmoy Deb,

Vishnu Naresh Boddeti

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Huang_2023_CVPR, author = {Huang, Shihua and Lu, Zhichao and Deb, Kalyanmoy and Boddeti, Vishnu Naresh}, title = {Revisiting Residual Networks for Adversarial Robustness}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8202-8211} }

RA-CLIP: Retrieval Augmented Contrastive Language-Image Pre-Training

Chen-Wei Xie,

Siyang Sun,

Xiong Xiong,

Yun Zheng,

Deli Zhao,

Jingren Zhou

[pdf] [supp]

[bibtex]

@InProceedings{Xie_2023_CVPR, author = {Xie, Chen-Wei and Sun, Siyang and Xiong, Xiong and Zheng, Yun and Zhao, Deli and Zhou, Jingren}, title = {RA-CLIP: Retrieval Augmented Contrastive Language-Image Pre-Training}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {19265-19274} }

PosterLayout: A New Benchmark and Approach for Content-Aware Visual-Textual Presentation Layout

Hsiao Yuan Hsu,

Xiangteng He,

Yuxin Peng,

Hao Kong,

Qing Zhang

[pdf] [arXiv]

[bibtex]

@InProceedings{Hsu_2023_CVPR, author = {Hsu, Hsiao Yuan and He, Xiangteng and Peng, Yuxin and Kong, Hao and Zhang, Qing}, title = {PosterLayout: A New Benchmark and Approach for Content-Aware Visual-Textual Presentation Layout}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6018-6026} }

A Practical Upper Bound for the Worst-Case Attribution Deviations

Fan Wang,

Adams Wai-Kin Kong

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Fan and Kong, Adams Wai-Kin}, title = {A Practical Upper Bound for the Worst-Case Attribution Deviations}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {24616-24625} }

A General Regret Bound of Preconditioned Gradient Method for DNN Training

Hongwei Yong,

Ying Sun,

Lei Zhang

[pdf] [supp]

[bibtex]

@InProceedings{Yong_2023_CVPR, author = {Yong, Hongwei and Sun, Ying and Zhang, Lei}, title = {A General Regret Bound of Preconditioned Gradient Method for DNN Training}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7866-7875} }

Teacher-Generated Spatial-Attention Labels Boost Robustness and Accuracy of Contrastive Models

Yushi Yao,

Chang Ye,

Junfeng He,

Gamaleldin F. Elsayed

[pdf] [supp]

[bibtex]

@InProceedings{Yao_2023_CVPR, author = {Yao, Yushi and Ye, Chang and He, Junfeng and Elsayed, Gamaleldin F.}, title = {Teacher-Generated Spatial-Attention Labels Boost Robustness and Accuracy of Contrastive Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {23282-23291} }

Exploring and Exploiting Uncertainty for Incomplete Multi-View Classification

Mengyao Xie,

Zongbo Han,

Changqing Zhang,

Yichen Bai,

Qinghua Hu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Xie_2023_CVPR, author = {Xie, Mengyao and Han, Zongbo and Zhang, Changqing and Bai, Yichen and Hu, Qinghua}, title = {Exploring and Exploiting Uncertainty for Incomplete Multi-View Classification}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {19873-19882} }

Vid2Seq: Large-Scale Pretraining of a Visual Language Model for Dense Video Captioning

Antoine Yang,

Arsha Nagrani,

Paul Hongsuck Seo,

Antoine Miech,

Jordi Pont-Tuset,

Ivan Laptev,

Josef Sivic,

Cordelia Schmid

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Yang_2023_CVPR, author = {Yang, Antoine and Nagrani, Arsha and Seo, Paul Hongsuck and Miech, Antoine and Pont-Tuset, Jordi and Laptev, Ivan and Sivic, Josef and Schmid, Cordelia}, title = {Vid2Seq: Large-Scale Pretraining of a Visual Language Model for Dense Video Captioning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10714-10726} }

Optimal Proposal Learning for Deployable End-to-End Pedestrian Detection

Xiaolin Song,

Binghui Chen,

Pengyu Li,

Jun-Yan He,

Biao Wang,

Yifeng Geng,

Xuansong Xie,

Honggang Zhang

[pdf]

[bibtex]

@InProceedings{Song_2023_CVPR, author = {Song, Xiaolin and Chen, Binghui and Li, Pengyu and He, Jun-Yan and Wang, Biao and Geng, Yifeng and Xie, Xuansong and Zhang, Honggang}, title = {Optimal Proposal Learning for Deployable End-to-End Pedestrian Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3250-3260} }

Discovering the Real Association: Multimodal Causal Reasoning in Video Question Answering

Chuanqi Zang,

Hanqing Wang,

Mingtao Pei,

Wei Liang

[pdf] [supp]

[bibtex]

@InProceedings{Zang_2023_CVPR, author = {Zang, Chuanqi and Wang, Hanqing and Pei, Mingtao and Liang, Wei}, title = {Discovering the Real Association: Multimodal Causal Reasoning in Video Question Answering}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {19027-19036} }

Temporal Interpolation Is All You Need for Dynamic Neural Radiance Fields

Sungheon Park,

Minjung Son,

Seokhwan Jang,

Young Chun Ahn,

Ji-Yeon Kim,

Nahyup Kang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Park_2023_CVPR, author = {Park, Sungheon and Son, Minjung and Jang, Seokhwan and Ahn, Young Chun and Kim, Ji-Yeon and Kang, Nahyup}, title = {Temporal Interpolation Is All You Need for Dynamic Neural Radiance Fields}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4212-4221} }

Graph Transformer GANs for Graph-Constrained House Generation

Hao Tang,

Zhenyu Zhang,

Humphrey Shi,

Bo Li,

Ling Shao,

Nicu Sebe,

Radu Timofte,

Luc Van Gool

[pdf] [arXiv]

[bibtex]

@InProceedings{Tang_2023_CVPR, author = {Tang, Hao and Zhang, Zhenyu and Shi, Humphrey and Li, Bo and Shao, Ling and Sebe, Nicu and Timofte, Radu and Van Gool, Luc}, title = {Graph Transformer GANs for Graph-Constrained House Generation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2173-2182} }

On the Benefits of 3D Pose and Tracking for Human Action Recognition

Jathushan Rajasegaran,

Georgios Pavlakos,

Angjoo Kanazawa,

Christoph Feichtenhofer,

Jitendra Malik

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Rajasegaran_2023_CVPR, author = {Rajasegaran, Jathushan and Pavlakos, Georgios and Kanazawa, Angjoo and Feichtenhofer, Christoph and Malik, Jitendra}, title = {On the Benefits of 3D Pose and Tracking for Human Action Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {640-649} }

How to Backdoor Diffusion Models?

Sheng-Yen Chou,

Pin-Yu Chen,

Tsung-Yi Ho

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Chou_2023_CVPR, author = {Chou, Sheng-Yen and Chen, Pin-Yu and Ho, Tsung-Yi}, title = {How to Backdoor Diffusion Models?}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4015-4024} }

ERNIE-ViLG 2.0: Improving Text-to-Image Diffusion Model With Knowledge-Enhanced Mixture-of-Denoising-Experts

Zhida Feng,

Zhenyu Zhang,

Xintong Yu,

Yewei Fang,

Lanxin Li,

Xuyi Chen,

Yuxiang Lu,

Jiaxiang Liu,

Weichong Yin,

Shikun Feng,

Yu Sun,

Li Chen,

Hao Tian,

Hua Wu,

Haifeng Wang

[pdf] [supp]

[bibtex]

@InProceedings{Feng_2023_CVPR, author = {Feng, Zhida and Zhang, Zhenyu and Yu, Xintong and Fang, Yewei and Li, Lanxin and Chen, Xuyi and Lu, Yuxiang and Liu, Jiaxiang and Yin, Weichong and Feng, Shikun and Sun, Yu and Chen, Li and Tian, Hao and Wu, Hua and Wang, Haifeng}, title = {ERNIE-ViLG 2.0: Improving Text-to-Image Diffusion Model With Knowledge-Enhanced Mixture-of-Denoising-Experts}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10135-10145} }

PACO: Parts and Attributes of Common Objects

Vignesh Ramanathan,

Anmol Kalia,

Vladan Petrovic,

Yi Wen,

Baixue Zheng,

Baishan Guo,

Rui Wang,

Aaron Marquez,

Rama Kovvuri,

Abhishek Kadian,

Amir Mousavi,

Yiwen Song,

Abhimanyu Dubey,

Dhruv Mahajan

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Ramanathan_2023_CVPR, author = {Ramanathan, Vignesh and Kalia, Anmol and Petrovic, Vladan and Wen, Yi and Zheng, Baixue and Guo, Baishan and Wang, Rui and Marquez, Aaron and Kovvuri, Rama and Kadian, Abhishek and Mousavi, Amir and Song, Yiwen and Dubey, Abhimanyu and Mahajan, Dhruv}, title = {PACO: Parts and Attributes of Common Objects}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7141-7151} }

Learning Transformations To Reduce the Geometric Shift in Object Detection

Vidit Vidit,

Martin Engilberge,

Mathieu Salzmann

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Vidit_2023_CVPR, author = {Vidit, Vidit and Engilberge, Martin and Salzmann, Mathieu}, title = {Learning Transformations To Reduce the Geometric Shift in Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {17441-17450} }

OReX: Object Reconstruction From Planar Cross-Sections Using Neural Fields

Haim Sawdayee,

Amir Vaxman,

Amit H. Bermano

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Sawdayee_2023_CVPR, author = {Sawdayee, Haim and Vaxman, Amir and Bermano, Amit H.}, title = {OReX: Object Reconstruction From Planar Cross-Sections Using Neural Fields}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {20854-20862} }

SPIn-NeRF: Multiview Segmentation and Perceptual Inpainting With Neural Radiance Fields

Ashkan Mirzaei,

Tristan Aumentado-Armstrong,

Konstantinos G. Derpanis,

Jonathan Kelly,

Marcus A. Brubaker,

Igor Gilitschenski,

Alex Levinshtein

[pdf] [supp]

[bibtex]

@InProceedings{Mirzaei_2023_CVPR, author = {Mirzaei, Ashkan and Aumentado-Armstrong, Tristan and Derpanis, Konstantinos G. and Kelly, Jonathan and Brubaker, Marcus A. and Gilitschenski, Igor and Levinshtein, Alex}, title = {SPIn-NeRF: Multiview Segmentation and Perceptual Inpainting With Neural Radiance Fields}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {20669-20679} }

Revisiting the Stack-Based Inverse Tone Mapping

Ning Zhang,

Yuyao Ye,

Yang Zhao,

Ronggang Wang

[pdf] [supp]

[bibtex]

@InProceedings{Zhang_2023_CVPR, author = {Zhang, Ning and Ye, Yuyao and Zhao, Yang and Wang, Ronggang}, title = {Revisiting the Stack-Based Inverse Tone Mapping}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9162-9171} }

Revisiting Rotation Averaging: Uncertainties and Robust Losses

Ganlin Zhang,

Viktor Larsson,

Daniel Barath

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Zhang_2023_CVPR, author = {Zhang, Ganlin and Larsson, Viktor and Barath, Daniel}, title = {Revisiting Rotation Averaging: Uncertainties and Robust Losses}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {17215-17224} }

Continuous Sign Language Recognition With Correlation Network

Lianyu Hu,

Liqing Gao,

Zekang Liu,

Wei Feng

[pdf] [arXiv]

[bibtex]

@InProceedings{Hu_2023_CVPR, author = {Hu, Lianyu and Gao, Liqing and Liu, Zekang and Feng, Wei}, title = {Continuous Sign Language Recognition With Correlation Network}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2529-2539} }

A Simple Framework for Text-Supervised Semantic Segmentation

Muyang Yi,

Quan Cui,

Hao Wu,

Cheng Yang,

Osamu Yoshie,

Hongtao Lu

[pdf] [supp]

[bibtex]

@InProceedings{Yi_2023_CVPR, author = {Yi, Muyang and Cui, Quan and Wu, Hao and Yang, Cheng and Yoshie, Osamu and Lu, Hongtao}, title = {A Simple Framework for Text-Supervised Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7071-7080} }

Exploiting Completeness and Uncertainty of Pseudo Labels for Weakly Supervised Video Anomaly Detection

Chen Zhang,

Guorong Li,

Yuankai Qi,

Shuhui Wang,

Laiyun Qing,

Qingming Huang,

Ming-Hsuan Yang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Zhang_2023_CVPR, author = {Zhang, Chen and Li, Guorong and Qi, Yuankai and Wang, Shuhui and Qing, Laiyun and Huang, Qingming and Yang, Ming-Hsuan}, title = {Exploiting Completeness and Uncertainty of Pseudo Labels for Weakly Supervised Video Anomaly Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16271-16280} }

PlenVDB: Memory Efficient VDB-Based Radiance Fields for Fast Training and Rendering

Han Yan,

Celong Liu,

Chao Ma,

Xing Mei

[pdf] [supp]

[bibtex]

@InProceedings{Yan_2023_CVPR, author = {Yan, Han and Liu, Celong and Ma, Chao and Mei, Xing}, title = {PlenVDB: Memory Efficient VDB-Based Radiance Fields for Fast Training and Rendering}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {88-96} }

Patch-Based 3D Natural Scene Generation From a Single Example

Weiyu Li,

Xuelin Chen,

Jue Wang,

Baoquan Chen

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Li_2023_CVPR, author = {Li, Weiyu and Chen, Xuelin and Wang, Jue and Chen, Baoquan}, title = {Patch-Based 3D Natural Scene Generation From a Single Example}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16762-16772} }

Full or Weak Annotations? An Adaptive Strategy for Budget-Constrained Annotation Campaigns

Javier Gamazo Tejero,

Martin S. Zinkernagel,

Sebastian Wolf,

Raphael Sznitman,

Pablo Márquez-Neila

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Tejero_2023_CVPR, author = {Tejero, Javier Gamazo and Zinkernagel, Martin S. and Wolf, Sebastian and Sznitman, Raphael and M\'arquez-Neila, Pablo}, title = {Full or Weak Annotations? An Adaptive Strategy for Budget-Constrained Annotation Campaigns}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11381-11391} }

Leveraging Hidden Positives for Unsupervised Semantic Segmentation

Hyun Seok Seong,

WonJun Moon,

SuBeen Lee,

Jae-Pil Heo

[pdf] [arXiv]

[bibtex]

@InProceedings{Seong_2023_CVPR, author = {Seong, Hyun Seok and Moon, WonJun and Lee, SuBeen and Heo, Jae-Pil}, title = {Leveraging Hidden Positives for Unsupervised Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {19540-19549} }

Backdoor Defense via Deconfounded Representation Learning

Zaixi Zhang,

Qi Liu,

Zhicai Wang,

Zepu Lu,

Qingyong Hu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Zhang_2023_CVPR, author = {Zhang, Zaixi and Liu, Qi and Wang, Zhicai and Lu, Zepu and Hu, Qingyong}, title = {Backdoor Defense via Deconfounded Representation Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12228-12238} }

LG-BPN: Local and Global Blind-Patch Network for Self-Supervised Real-World Denoising

Zichun Wang,

Ying Fu,

Ji Liu,

Yulun Zhang

[pdf]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Zichun and Fu, Ying and Liu, Ji and Zhang, Yulun}, title = {LG-BPN: Local and Global Blind-Patch Network for Self-Supervised Real-World Denoising}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {18156-18165} }

Efficient View Synthesis and 3D-Based Multi-Frame Denoising With Multiplane Feature Representations

Thomas Tanay,

Aleš Leonardis,

Matteo Maggioni

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Tanay_2023_CVPR, author = {Tanay, Thomas and Leonardis, Ale\v{s} and Maggioni, Matteo}, title = {Efficient View Synthesis and 3D-Based Multi-Frame Denoising With Multiplane Feature Representations}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {20898-20907} }

An Actor-Centric Causality Graph for Asynchronous Temporal Inference in Group Activity

Zhao Xie,

Tian Gao,

Kewei Wu,

Jiao Chang

[pdf] [supp]

[bibtex]

@InProceedings{Xie_2023_CVPR, author = {Xie, Zhao and Gao, Tian and Wu, Kewei and Chang, Jiao}, title = {An Actor-Centric Causality Graph for Asynchronous Temporal Inference in Group Activity}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6652-6661} }

Color Backdoor: A Robust Poisoning Attack in Color Space

Wenbo Jiang,

Hongwei Li,

Guowen Xu,

Tianwei Zhang

[pdf] [supp]

[bibtex]

@InProceedings{Jiang_2023_CVPR, author = {Jiang, Wenbo and Li, Hongwei and Xu, Guowen and Zhang, Tianwei}, title = {Color Backdoor: A Robust Poisoning Attack in Color Space}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8133-8142} }

HairStep: Transfer Synthetic to Real Using Strand and Depth Maps for Single-View 3D Hair Modeling

Yujian Zheng,

Zirong Jin,

Moran Li,

Haibin Huang,

Chongyang Ma,

Shuguang Cui,

Xiaoguang Han

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Zheng_2023_CVPR, author = {Zheng, Yujian and Jin, Zirong and Li, Moran and Huang, Haibin and Ma, Chongyang and Cui, Shuguang and Han, Xiaoguang}, title = {HairStep: Transfer Synthetic to Real Using Strand and Depth Maps for Single-View 3D Hair Modeling}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12726-12735} }

MoDAR: Using Motion Forecasting for 3D Object Detection in Point Cloud Sequences

Yingwei Li,

Charles R. Qi,

Yin Zhou,

Chenxi Liu,

Dragomir Anguelov

[pdf] [supp]

[bibtex]

@InProceedings{Li_2023_CVPR, author = {Li, Yingwei and Qi, Charles R. and Zhou, Yin and Liu, Chenxi and Anguelov, Dragomir}, title = {MoDAR: Using Motion Forecasting for 3D Object Detection in Point Cloud Sequences}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9329-9339} }

How You Feelin'? Learning Emotions and Mental States in Movie Scenes

Dhruv Srivastava,

Aditya Kumar Singh,

Makarand Tapaswi

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Srivastava_2023_CVPR, author = {Srivastava, Dhruv and Singh, Aditya Kumar and Tapaswi, Makarand}, title = {How You Feelin'? Learning Emotions and Mental States in Movie Scenes}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2517-2528} }

Dynamic Inference With Grounding Based Vision and Language Models

Burak Uzkent,

Amanmeet Garg,

Wentao Zhu,

Keval Doshi,

Jingru Yi,

Xiaolong Wang,

Mohamed Omar

[pdf] [supp]

[bibtex]

@InProceedings{Uzkent_2023_CVPR, author = {Uzkent, Burak and Garg, Amanmeet and Zhu, Wentao and Doshi, Keval and Yi, Jingru and Wang, Xiaolong and Omar, Mohamed}, title = {Dynamic Inference With Grounding Based Vision and Language Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2624-2633} }

ALSO: Automotive Lidar Self-Supervision by Occupancy Estimation

Alexandre Boulch,

Corentin Sautier,

Björn Michele,

Gilles Puy,

Renaud Marlet

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Boulch_2023_CVPR, author = {Boulch, Alexandre and Sautier, Corentin and Michele, Bj\"orn and Puy, Gilles and Marlet, Renaud}, title = {ALSO: Automotive Lidar Self-Supervision by Occupancy Estimation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13455-13465} }

Connecting Vision and Language With Video Localized Narratives

Paul Voigtlaender,

Soravit Changpinyo,

Jordi Pont-Tuset,

Radu Soricut,

Vittorio Ferrari

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Voigtlaender_2023_CVPR, author = {Voigtlaender, Paul and Changpinyo, Soravit and Pont-Tuset, Jordi and Soricut, Radu and Ferrari, Vittorio}, title = {Connecting Vision and Language With Video Localized Narratives}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2461-2471} }

Diverse Embedding Expansion Network and Low-Light Cross-Modality Benchmark for Visible-Infrared Person Re-Identification

Yukang Zhang,

Hanzi Wang

[pdf] [arXiv]

[bibtex]

@InProceedings{Zhang_2023_CVPR, author = {Zhang, Yukang and Wang, Hanzi}, title = {Diverse Embedding Expansion Network and Low-Light Cross-Modality Benchmark for Visible-Infrared Person Re-Identification}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2153-2162} }

Model Barrier: A Compact Un-Transferable Isolation Domain for Model Intellectual Property Protection

Lianyu Wang,

Meng Wang,

Daoqiang Zhang,

Huazhu Fu

[pdf] [arXiv]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Lianyu and Wang, Meng and Zhang, Daoqiang and Fu, Huazhu}, title = {Model Barrier: A Compact Un-Transferable Isolation Domain for Model Intellectual Property Protection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {20475-20484} }

Object Detection With Self-Supervised Scene Adaptation

Zekun Zhang,

Minh Hoai

[pdf] [supp]

[bibtex]

@InProceedings{Zhang_2023_CVPR, author = {Zhang, Zekun and Hoai, Minh}, title = {Object Detection With Self-Supervised Scene Adaptation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {21589-21599} }

Visual-Language Prompt Tuning With Knowledge-Guided Context Optimization

Hantao Yao,

Rui Zhang,

Changsheng Xu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Yao_2023_CVPR, author = {Yao, Hantao and Zhang, Rui and Xu, Changsheng}, title = {Visual-Language Prompt Tuning With Knowledge-Guided Context Optimization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6757-6767} }

Weakly Supervised Video Representation Learning With Unaligned Text for Sequential Videos

Sixun Dong,

Huazhang Hu,

Dongze Lian,

Weixin Luo,

Yicheng Qian,

Shenghua Gao

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Dong_2023_CVPR, author = {Dong, Sixun and Hu, Huazhang and Lian, Dongze and Luo, Weixin and Qian, Yicheng and Gao, Shenghua}, title = {Weakly Supervised Video Representation Learning With Unaligned Text for Sequential Videos}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2437-2447} }

Self-Positioning Point-Based Transformer for Point Cloud Understanding

Jinyoung Park,

Sanghyeok Lee,

Sihyeon Kim,

Yunyang Xiong,

Hyunwoo J. Kim

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Park_2023_CVPR, author = {Park, Jinyoung and Lee, Sanghyeok and Kim, Sihyeon and Xiong, Yunyang and Kim, Hyunwoo J.}, title = {Self-Positioning Point-Based Transformer for Point Cloud Understanding}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {21814-21823} }

Bootstrap Your Own Prior: Towards Distribution-Agnostic Novel Class Discovery

Muli Yang,

Liancheng Wang,

Cheng Deng,

Hanwang Zhang

[pdf] [supp]

[bibtex]

@InProceedings{Yang_2023_CVPR, author = {Yang, Muli and Wang, Liancheng and Deng, Cheng and Zhang, Hanwang}, title = {Bootstrap Your Own Prior: Towards Distribution-Agnostic Novel Class Discovery}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3459-3468} }

Learning To Generate Image Embeddings With User-Level Differential Privacy

Zheng Xu,

Maxwell Collins,

Yuxiao Wang,

Liviu Panait,

Sewoong Oh,

Sean Augenstein,

Ting Liu,

Florian Schroff,

H. Brendan McMahan

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Xu_2023_CVPR, author = {Xu, Zheng and Collins, Maxwell and Wang, Yuxiao and Panait, Liviu and Oh, Sewoong and Augenstein, Sean and Liu, Ting and Schroff, Florian and McMahan, H. Brendan}, title = {Learning To Generate Image Embeddings With User-Level Differential Privacy}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7969-7980} }

Open-Vocabulary Panoptic Segmentation With Text-to-Image Diffusion Models

Jiarui Xu,

Sifei Liu,

Arash Vahdat,

Wonmin Byeon,

Xiaolong Wang,

Shalini De Mello

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Xu_2023_CVPR, author = {Xu, Jiarui and Liu, Sifei and Vahdat, Arash and Byeon, Wonmin and Wang, Xiaolong and De Mello, Shalini}, title = {Open-Vocabulary Panoptic Segmentation With Text-to-Image Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2955-2966} }

Learning Open-Vocabulary Semantic Segmentation Models From Natural Language Supervision

Jilan Xu,

Junlin Hou,

Yuejie Zhang,

Rui Feng,

Yi Wang,

Yu Qiao,

Weidi Xie

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Xu_2023_CVPR, author = {Xu, Jilan and Hou, Junlin and Zhang, Yuejie and Feng, Rui and Wang, Yi and Qiao, Yu and Xie, Weidi}, title = {Learning Open-Vocabulary Semantic Segmentation Models From Natural Language Supervision}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2935-2944} }

Learning Dynamic Style Kernels for Artistic Style Transfer

Wenju Xu,

Chengjiang Long,

Yongwei Nie

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Xu_2023_CVPR, author = {Xu, Wenju and Long, Chengjiang and Nie, Yongwei}, title = {Learning Dynamic Style Kernels for Artistic Style Transfer}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10083-10092} }

DeepLSD: Line Segment Detection and Refinement With Deep Image Gradients

Rémi Pautrat,

Daniel Barath,

Viktor Larsson,

Martin R. Oswald,

Marc Pollefeys

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Pautrat_2023_CVPR, author = {Pautrat, R\'emi and Barath, Daniel and Larsson, Viktor and Oswald, Martin R. and Pollefeys, Marc}, title = {DeepLSD: Line Segment Detection and Refinement With Deep Image Gradients}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {17327-17336} }

OcTr: Octree-Based Transformer for 3D Object Detection

Chao Zhou,

Yanan Zhang,

Jiaxin Chen,

Di Huang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Zhou_2023_CVPR, author = {Zhou, Chao and Zhang, Yanan and Chen, Jiaxin and Huang, Di}, title = {OcTr: Octree-Based Transformer for 3D Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5166-5175} }

Chat2Map: Efficient Scene Mapping From Multi-Ego Conversations

Sagnik Majumder,

Hao Jiang,

Pierre Moulon,

Ethan Henderson,

Paul Calamia,

Kristen Grauman,

Vamsi Krishna Ithapu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Majumder_2023_CVPR, author = {Majumder, Sagnik and Jiang, Hao and Moulon, Pierre and Henderson, Ethan and Calamia, Paul and Grauman, Kristen and Ithapu, Vamsi Krishna}, title = {Chat2Map: Efficient Scene Mapping From Multi-Ego Conversations}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10554-10564} }

Learning Distortion Invariant Representation for Image Restoration From a Causality Perspective

Xin Li,

Bingchen Li,

Xin Jin,

Cuiling Lan,

Zhibo Chen

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Li_2023_CVPR, author = {Li, Xin and Li, Bingchen and Jin, Xin and Lan, Cuiling and Chen, Zhibo}, title = {Learning Distortion Invariant Representation for Image Restoration From a Causality Perspective}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1714-1724} }

MOT: Masked Optimal Transport for Partial Domain Adaptation

You-Wei Luo,

Chuan-Xian Ren

[pdf] [supp]

[bibtex]

@InProceedings{Luo_2023_CVPR, author = {Luo, You-Wei and Ren, Chuan-Xian}, title = {MOT: Masked Optimal Transport for Partial Domain Adaptation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3531-3540} }

Executing Your Commands via Motion Diffusion in Latent Space

Xin Chen,

Biao Jiang,

Wen Liu,

Zilong Huang,

Bin Fu,

Tao Chen,

Gang Yu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Chen_2023_CVPR, author = {Chen, Xin and Jiang, Biao and Liu, Wen and Huang, Zilong and Fu, Bin and Chen, Tao and Yu, Gang}, title = {Executing Your Commands via Motion Diffusion in Latent Space}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {18000-18010} }

GeoMAE: Masked Geometric Target Prediction for Self-Supervised Point Cloud Pre-Training

Xiaoyu Tian,

Haoxi Ran,

Yue Wang,

Hang Zhao

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Tian_2023_CVPR, author = {Tian, Xiaoyu and Ran, Haoxi and Wang, Yue and Zhao, Hang}, title = {GeoMAE: Masked Geometric Target Prediction for Self-Supervised Point Cloud Pre-Training}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13570-13580} }

Learning Conditional Attributes for Compositional Zero-Shot Learning

Qingsheng Wang,

Lingqiao Liu,

Chenchen Jing,

Hao Chen,

Guoqiang Liang,

Peng Wang,

Chunhua Shen

[pdf] [arXiv]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Qingsheng and Liu, Lingqiao and Jing, Chenchen and Chen, Hao and Liang, Guoqiang and Wang, Peng and Shen, Chunhua}, title = {Learning Conditional Attributes for Compositional Zero-Shot Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11197-11206} }

Complete 3D Human Reconstruction From a Single Incomplete Image

Junying Wang,

Jae Shin Yoon,

Tuanfeng Y. Wang,

Krishna Kumar Singh,

Ulrich Neumann

[pdf] [supp]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Junying and Yoon, Jae Shin and Wang, Tuanfeng Y. and Singh, Krishna Kumar and Neumann, Ulrich}, title = {Complete 3D Human Reconstruction From a Single Incomplete Image}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8748-8758} }

PVT-SSD: Single-Stage 3D Object Detector With Point-Voxel Transformer

Honghui Yang,

Wenxiao Wang,

Minghao Chen,

Binbin Lin,

Tong He,

Hua Chen,

Xiaofei He,

Wanli Ouyang

[pdf] [supp]

[bibtex]

@InProceedings{Yang_2023_CVPR, author = {Yang, Honghui and Wang, Wenxiao and Chen, Minghao and Lin, Binbin and He, Tong and Chen, Hua and He, Xiaofei and Ouyang, Wanli}, title = {PVT-SSD: Single-Stage 3D Object Detector With Point-Voxel Transformer}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13476-13487} }

Adaptive Human Matting for Dynamic Videos

Chung-Ching Lin,

Jiang Wang,

Kun Luo,

Kevin Lin,

Linjie Li,

Lijuan Wang,

Zicheng Liu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Lin_2023_CVPR, author = {Lin, Chung-Ching and Wang, Jiang and Luo, Kun and Lin, Kevin and Li, Linjie and Wang, Lijuan and Liu, Zicheng}, title = {Adaptive Human Matting for Dynamic Videos}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10229-10238} }

Learning Common Rationale To Improve Self-Supervised Representation for Fine-Grained Visual Recognition Problems

Yangyang Shu,

Anton van den Hengel,

Lingqiao Liu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Shu_2023_CVPR, author = {Shu, Yangyang and van den Hengel, Anton and Liu, Lingqiao}, title = {Learning Common Rationale To Improve Self-Supervised Representation for Fine-Grained Visual Recognition Problems}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11392-11401} }

Reconstructing Animatable Categories From Videos

Gengshan Yang,

Chaoyang Wang,

N. Dinesh Reddy,

Deva Ramanan

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Yang_2023_CVPR, author = {Yang, Gengshan and Wang, Chaoyang and Reddy, N. Dinesh and Ramanan, Deva}, title = {Reconstructing Animatable Categories From Videos}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16995-17005} }

UDE: A Unified Driving Engine for Human Motion Generation

Zixiang Zhou,

Baoyuan Wang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Zhou_2023_CVPR, author = {Zhou, Zixiang and Wang, Baoyuan}, title = {UDE: A Unified Driving Engine for Human Motion Generation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5632-5641} }

High-Fidelity 3D Human Digitization From Single 2K Resolution Images

Sang-Hun Han,

Min-Gyu Park,

Ju Hong Yoon,

Ju-Mi Kang,

Young-Jae Park,

Hae-Gon Jeon

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Han_2023_CVPR, author = {Han, Sang-Hun and Park, Min-Gyu and Yoon, Ju Hong and Kang, Ju-Mi and Park, Young-Jae and Jeon, Hae-Gon}, title = {High-Fidelity 3D Human Digitization From Single 2K Resolution Images}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12869-12879} }

Co-Salient Object Detection With Uncertainty-Aware Group Exchange-Masking

Yang Wu,

Huihui Song,

Bo Liu,

Kaihua Zhang,

Dong Liu

[pdf] [supp]

[bibtex]

@InProceedings{Wu_2023_CVPR, author = {Wu, Yang and Song, Huihui and Liu, Bo and Zhang, Kaihua and Liu, Dong}, title = {Co-Salient Object Detection With Uncertainty-Aware Group Exchange-Masking}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {19639-19648} }

Tangentially Elongated Gaussian Belief Propagation for Event-Based Incremental Optical Flow Estimation

Jun Nagata,

Yusuke Sekikawa

[pdf] [supp]

[bibtex]

@InProceedings{Nagata_2023_CVPR, author = {Nagata, Jun and Sekikawa, Yusuke}, title = {Tangentially Elongated Gaussian Belief Propagation for Event-Based Incremental Optical Flow Estimation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {21940-21949} }

Extracting Class Activation Maps From Non-Discriminative Features As Well

Zhaozheng Chen,

Qianru Sun

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Chen_2023_CVPR, author = {Chen, Zhaozheng and Sun, Qianru}, title = {Extracting Class Activation Maps From Non-Discriminative Features As Well}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3135-3144} }

BlendFields: Few-Shot Example-Driven Facial Modeling

Kacper Kania,

Stephan J. Garbin,

Andrea Tagliasacchi,

Virginia Estellers,

Kwang Moo Yi,

Julien Valentin,

Tomasz Trzciński,

Marek Kowalski

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Kania_2023_CVPR, author = {Kania, Kacper and Garbin, Stephan J. and Tagliasacchi, Andrea and Estellers, Virginia and Yi, Kwang Moo and Valentin, Julien and Trzci\'nski, Tomasz and Kowalski, Marek}, title = {BlendFields: Few-Shot Example-Driven Facial Modeling}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {404-415} }

Adaptive Sparse Pairwise Loss for Object Re-Identification

Xiao Zhou,

Yujie Zhong,

Zhen Cheng,

Fan Liang,

Lin Ma

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Zhou_2023_CVPR, author = {Zhou, Xiao and Zhong, Yujie and Cheng, Zhen and Liang, Fan and Ma, Lin}, title = {Adaptive Sparse Pairwise Loss for Object Re-Identification}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {19691-19701} }

NeFII: Inverse Rendering for Reflectance Decomposition With Near-Field Indirect Illumination

Haoqian Wu,

Zhipeng Hu,

Lincheng Li,

Yongqiang Zhang,

Changjie Fan,

Xin Yu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Wu_2023_CVPR, author = {Wu, Haoqian and Hu, Zhipeng and Li, Lincheng and Zhang, Yongqiang and Fan, Changjie and Yu, Xin}, title = {NeFII: Inverse Rendering for Reflectance Decomposition With Near-Field Indirect Illumination}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4295-4304} }

Towards Professional Level Crowd Annotation of Expert Domain Data

Pei Wang,

Nuno Vasconcelos

[pdf] [supp]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Pei and Vasconcelos, Nuno}, title = {Towards Professional Level Crowd Annotation of Expert Domain Data}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3166-3175} }

Fully Self-Supervised Depth Estimation From Defocus Clue

Haozhe Si,

Bin Zhao,

Dong Wang,

Yunpeng Gao,

Mulin Chen,

Zhigang Wang,

Xuelong Li

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Si_2023_CVPR, author = {Si, Haozhe and Zhao, Bin and Wang, Dong and Gao, Yunpeng and Chen, Mulin and Wang, Zhigang and Li, Xuelong}, title = {Fully Self-Supervised Depth Estimation From Defocus Clue}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9140-9149} }

Semi-Weakly Supervised Object Kinematic Motion Prediction

Gengxin Liu,

Qian Sun,

Haibin Huang,

Chongyang Ma,

Yulan Guo,

Li Yi,

Hui Huang,

Ruizhen Hu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Liu_2023_CVPR, author = {Liu, Gengxin and Sun, Qian and Huang, Haibin and Ma, Chongyang and Guo, Yulan and Yi, Li and Huang, Hui and Hu, Ruizhen}, title = {Semi-Weakly Supervised Object Kinematic Motion Prediction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {21726-21735} }

Learning a Simple Low-Light Image Enhancer From Paired Low-Light Instances

Zhenqi Fu,

Yan Yang,

Xiaotong Tu,

Yue Huang,

Xinghao Ding,

Kai-Kuang Ma

[pdf]

[bibtex]

@InProceedings{Fu_2023_CVPR, author = {Fu, Zhenqi and Yang, Yan and Tu, Xiaotong and Huang, Yue and Ding, Xinghao and Ma, Kai-Kuang}, title = {Learning a Simple Low-Light Image Enhancer From Paired Low-Light Instances}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {22252-22261} }

Deep Stereo Video Inpainting

Zhiliang Wu,

Changchang Sun,

Hanyu Xuan,

Yan Yan

[pdf]

[bibtex]

@InProceedings{Wu_2023_CVPR, author = {Wu, Zhiliang and Sun, Changchang and Xuan, Hanyu and Yan, Yan}, title = {Deep Stereo Video Inpainting}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5693-5702} }

Prompting Large Language Models With Answer Heuristics for Knowledge-Based Visual Question Answering

Zhenwei Shao,

Zhou Yu,

Meng Wang,

Jun Yu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Shao_2023_CVPR, author = {Shao, Zhenwei and Yu, Zhou and Wang, Meng and Yu, Jun}, title = {Prompting Large Language Models With Answer Heuristics for Knowledge-Based Visual Question Answering}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14974-14983} }

IFSeg: Image-Free Semantic Segmentation via Vision-Language Model

Sukmin Yun,

Seong Hyeon Park,

Paul Hongsuck Seo,

Jinwoo Shin

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Yun_2023_CVPR, author = {Yun, Sukmin and Park, Seong Hyeon and Seo, Paul Hongsuck and Shin, Jinwoo}, title = {IFSeg: Image-Free Semantic Segmentation via Vision-Language Model}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2967-2977} }

Improving Robustness of Semantic Segmentation to Motion-Blur Using Class-Centric Augmentation

Aakanksha,

A. N. Rajagopalan

[pdf] [supp]

[bibtex]

@InProceedings{Aakanksha_2023_CVPR, author = {Aakanksha and Rajagopalan, A. N.}, title = {Improving Robustness of Semantic Segmentation to Motion-Blur Using Class-Centric Augmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10470-10479} }

Progressive Open Space Expansion for Open-Set Model Attribution

Tianyun Yang,

Danding Wang,

Fan Tang,

Xinying Zhao,

Juan Cao,

Sheng Tang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Yang_2023_CVPR, author = {Yang, Tianyun and Wang, Danding and Tang, Fan and Zhao, Xinying and Cao, Juan and Tang, Sheng}, title = {Progressive Open Space Expansion for Open-Set Model Attribution}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15856-15865} }

Backdoor Cleansing With Unlabeled Data

Lu Pang,

Tao Sun,

Haibin Ling,

Chao Chen

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Pang_2023_CVPR, author = {Pang, Lu and Sun, Tao and Ling, Haibin and Chen, Chao}, title = {Backdoor Cleansing With Unlabeled Data}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12218-12227} }

Is BERT Blind? Exploring the Effect of Vision-and-Language Pretraining on Visual Language Understanding

Morris Alper,

Michael Fiman,

Hadar Averbuch-Elor

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Alper_2023_CVPR, author = {Alper, Morris and Fiman, Michael and Averbuch-Elor, Hadar}, title = {Is BERT Blind? Exploring the Effect of Vision-and-Language Pretraining on Visual Language Understanding}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6778-6788} }

PivoTAL: Prior-Driven Supervision for Weakly-Supervised Temporal Action Localization

Mamshad Nayeem Rizve,

Gaurav Mittal,

Ye Yu,

Matthew Hall,

Sandra Sajeev,

Mubarak Shah,

Mei Chen

[pdf] [supp]

[bibtex]

@InProceedings{Rizve_2023_CVPR, author = {Rizve, Mamshad Nayeem and Mittal, Gaurav and Yu, Ye and Hall, Matthew and Sajeev, Sandra and Shah, Mubarak and Chen, Mei}, title = {PivoTAL: Prior-Driven Supervision for Weakly-Supervised Temporal Action Localization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {22992-23002} }

Harmonious Feature Learning for Interactive Hand-Object Pose Estimation

Zhifeng Lin,

Changxing Ding,

Huan Yao,

Zengsheng Kuang,

Shaoli Huang

[pdf] [supp]

[bibtex]

@InProceedings{Lin_2023_CVPR, author = {Lin, Zhifeng and Ding, Changxing and Yao, Huan and Kuang, Zengsheng and Huang, Shaoli}, title = {Harmonious Feature Learning for Interactive Hand-Object Pose Estimation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12989-12998} }

3D GAN Inversion With Facial Symmetry Prior

Fei Yin,

Yong Zhang,

Xuan Wang,

Tengfei Wang,

Xiaoyu Li,

Yuan Gong,

Yanbo Fan,

Xiaodong Cun,

Ying Shan,

Cengiz Oztireli,

Yujiu Yang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Yin_2023_CVPR, author = {Yin, Fei and Zhang, Yong and Wang, Xuan and Wang, Tengfei and Li, Xiaoyu and Gong, Yuan and Fan, Yanbo and Cun, Xiaodong and Shan, Ying and Oztireli, Cengiz and Yang, Yujiu}, title = {3D GAN Inversion With Facial Symmetry Prior}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {342-351} }

CLOTH4D: A Dataset for Clothed Human Reconstruction

Xingxing Zou,

Xintong Han,

Waikeung Wong

[pdf] [supp]

[bibtex]

@InProceedings{Zou_2023_CVPR, author = {Zou, Xingxing and Han, Xintong and Wong, Waikeung}, title = {CLOTH4D: A Dataset for Clothed Human Reconstruction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12847-12857} }

SDFusion: Multimodal 3D Shape Completion, Reconstruction, and Generation

Yen-Chi Cheng,

Hsin-Ying Lee,

Sergey Tulyakov,

Alexander G. Schwing,

Liang-Yan Gui

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Cheng_2023_CVPR, author = {Cheng, Yen-Chi and Lee, Hsin-Ying and Tulyakov, Sergey and Schwing, Alexander G. and Gui, Liang-Yan}, title = {SDFusion: Multimodal 3D Shape Completion, Reconstruction, and Generation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4456-4465} }

SMAE: Few-Shot Learning for HDR Deghosting With Saturation-Aware Masked Autoencoders

Qingsen Yan,

Song Zhang,

Weiye Chen,

Hao Tang,

Yu Zhu,

Jinqiu Sun,

Luc Van Gool,

Yanning Zhang

[pdf] [arXiv]

[bibtex]

@InProceedings{Yan_2023_CVPR, author = {Yan, Qingsen and Zhang, Song and Chen, Weiye and Tang, Hao and Zhu, Yu and Sun, Jinqiu and Van Gool, Luc and Zhang, Yanning}, title = {SMAE: Few-Shot Learning for HDR Deghosting With Saturation-Aware Masked Autoencoders}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5775-5784} }

Improving Generalization With Domain Convex Game

Fangrui Lv,

Jian Liang,

Shuang Li,

Jinming Zhang,

Di Liu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Lv_2023_CVPR, author = {Lv, Fangrui and Liang, Jian and Li, Shuang and Zhang, Jinming and Liu, Di}, title = {Improving Generalization With Domain Convex Game}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {24315-24324} }

Learning To Render Novel Views From Wide-Baseline Stereo Pairs

Yilun Du,

Cameron Smith,

Ayush Tewari,

Vincent Sitzmann

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Du_2023_CVPR, author = {Du, Yilun and Smith, Cameron and Tewari, Ayush and Sitzmann, Vincent}, title = {Learning To Render Novel Views From Wide-Baseline Stereo Pairs}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4970-4980} }

TryOnDiffusion: A Tale of Two UNets

Luyang Zhu,

Dawei Yang,

Tyler Zhu,

Fitsum Reda,

William Chan,

Chitwan Saharia,

Mohammad Norouzi,

Ira Kemelmacher-Shlizerman

[pdf] [supp]

[bibtex]

@InProceedings{Zhu_2023_CVPR, author = {Zhu, Luyang and Yang, Dawei and Zhu, Tyler and Reda, Fitsum and Chan, William and Saharia, Chitwan and Norouzi, Mohammad and Kemelmacher-Shlizerman, Ira}, title = {TryOnDiffusion: A Tale of Two UNets}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4606-4615} }

Fair Scratch Tickets: Finding Fair Sparse Networks Without Weight Training

Pengwei Tang,

Wei Yao,

Zhicong Li,

Yong Liu

[pdf] [supp]

[bibtex]

@InProceedings{Tang_2023_CVPR, author = {Tang, Pengwei and Yao, Wei and Li, Zhicong and Liu, Yong}, title = {Fair Scratch Tickets: Finding Fair Sparse Networks Without Weight Training}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {24406-24416} }

Generative Bias for Robust Visual Question Answering

Jae Won Cho,

Dong-Jin Kim,

Hyeonggon Ryu,

In So Kweon

[pdf] [arXiv]

[bibtex]

@InProceedings{Cho_2023_CVPR, author = {Cho, Jae Won and Kim, Dong-Jin and Ryu, Hyeonggon and Kweon, In So}, title = {Generative Bias for Robust Visual Question Answering}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11681-11690} }

Data-Free Sketch-Based Image Retrieval

Abhra Chaudhuri,

Ayan Kumar Bhunia,

Yi-Zhe Song,

Anjan Dutta

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Chaudhuri_2023_CVPR, author = {Chaudhuri, Abhra and Bhunia, Ayan Kumar and Song, Yi-Zhe and Dutta, Anjan}, title = {Data-Free Sketch-Based Image Retrieval}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12084-12093} }

Multi-Object Manipulation via Object-Centric Neural Scattering Functions

Stephen Tian,

Yancheng Cai,

Hong-Xing Yu,

Sergey Zakharov,

Katherine Liu,

Adrien Gaidon,

Yunzhu Li,

Jiajun Wu

[pdf] [supp]

[bibtex]

@InProceedings{Tian_2023_CVPR, author = {Tian, Stephen and Cai, Yancheng and Yu, Hong-Xing and Zakharov, Sergey and Liu, Katherine and Gaidon, Adrien and Li, Yunzhu and Wu, Jiajun}, title = {Multi-Object Manipulation via Object-Centric Neural Scattering Functions}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9021-9031} }

The Wisdom of Crowds: Temporal Progressive Attention for Early Action Prediction

Alexandros Stergiou,

Dima Damen

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Stergiou_2023_CVPR, author = {Stergiou, Alexandros and Damen, Dima}, title = {The Wisdom of Crowds: Temporal Progressive Attention for Early Action Prediction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14709-14719} }

Invertible Neural Skinning

Yash Kant,

Aliaksandr Siarohin,

Riza Alp Guler,

Menglei Chai,

Jian Ren,

Sergey Tulyakov,

Igor Gilitschenski

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Kant_2023_CVPR, author = {Kant, Yash and Siarohin, Aliaksandr and Guler, Riza Alp and Chai, Menglei and Ren, Jian and Tulyakov, Sergey and Gilitschenski, Igor}, title = {Invertible Neural Skinning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8715-8725} }

Weakly Supervised Semantic Segmentation via Adversarial Learning of Classifier and Reconstructor

Hyeokjun Kweon,

Sung-Hoon Yoon,

Kuk-Jin Yoon

[pdf] [supp]

[bibtex]

@InProceedings{Kweon_2023_CVPR, author = {Kweon, Hyeokjun and Yoon, Sung-Hoon and Yoon, Kuk-Jin}, title = {Weakly Supervised Semantic Segmentation via Adversarial Learning of Classifier and Reconstructor}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11329-11339} }

Intrinsic Physical Concepts Discovery With Object-Centric Predictive Models

Qu Tang,

Xiangyu Zhu,

Zhen Lei,

Zhaoxiang Zhang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Tang_2023_CVPR, author = {Tang, Qu and Zhu, Xiangyu and Lei, Zhen and Zhang, Zhaoxiang}, title = {Intrinsic Physical Concepts Discovery With Object-Centric Predictive Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {23252-23261} }

Distilling Cross-Temporal Contexts for Continuous Sign Language Recognition

Leming Guo,

Wanli Xue,

Qing Guo,

Bo Liu,

Kaihua Zhang,

Tiantian Yuan,

Shengyong Chen

[pdf] [supp]

[bibtex]

@InProceedings{Guo_2023_CVPR, author = {Guo, Leming and Xue, Wanli and Guo, Qing and Liu, Bo and Zhang, Kaihua and Yuan, Tiantian and Chen, Shengyong}, title = {Distilling Cross-Temporal Contexts for Continuous Sign Language Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10771-10780} }

Automatic High Resolution Wire Segmentation and Removal

Mang Tik Chiu,

Xuaner Zhang,

Zijun Wei,

Yuqian Zhou,

Eli Shechtman,

Connelly Barnes,

Zhe Lin,

Florian Kainz,

Sohrab Amirghodsi,

Humphrey Shi

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Chiu_2023_CVPR, author = {Chiu, Mang Tik and Zhang, Xuaner and Wei, Zijun and Zhou, Yuqian and Shechtman, Eli and Barnes, Connelly and Lin, Zhe and Kainz, Florian and Amirghodsi, Sohrab and Shi, Humphrey}, title = {Automatic High Resolution Wire Segmentation and Removal}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2183-2192} }

The Resource Problem of Using Linear Layer Leakage Attack in Federated Learning

Joshua C. Zhao,

Ahmed Roushdy Elkordy,

Atul Sharma,

Yahya H. Ezzeldin,

Salman Avestimehr,

Saurabh Bagchi

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Zhao_2023_CVPR, author = {Zhao, Joshua C. and Elkordy, Ahmed Roushdy and Sharma, Atul and Ezzeldin, Yahya H. and Avestimehr, Salman and Bagchi, Saurabh}, title = {The Resource Problem of Using Linear Layer Leakage Attack in Federated Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3974-3983} }

Unsupervised Deep Probabilistic Approach for Partial Point Cloud Registration

Guofeng Mei,

Hao Tang,

Xiaoshui Huang,

Weijie Wang,

Juan Liu,

Jian Zhang,

Luc Van Gool,

Qiang Wu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Mei_2023_CVPR, author = {Mei, Guofeng and Tang, Hao and Huang, Xiaoshui and Wang, Weijie and Liu, Juan and Zhang, Jian and Van Gool, Luc and Wu, Qiang}, title = {Unsupervised Deep Probabilistic Approach for Partial Point Cloud Registration}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13611-13620} }

Towards Generalisable Video Moment Retrieval: Visual-Dynamic Injection to Image-Text Pre-Training

Dezhao Luo,

Jiabo Huang,

Shaogang Gong,

Hailin Jin,

Yang Liu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Luo_2023_CVPR, author = {Luo, Dezhao and Huang, Jiabo and Gong, Shaogang and Jin, Hailin and Liu, Yang}, title = {Towards Generalisable Video Moment Retrieval: Visual-Dynamic Injection to Image-Text Pre-Training}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {23045-23055} }

Learning Adaptive Dense Event Stereo From the Image Domain

Hoonhee Cho,

Jegyeong Cho,

Kuk-Jin Yoon

[pdf] [supp]

[bibtex]

@InProceedings{Cho_2023_CVPR, author = {Cho, Hoonhee and Cho, Jegyeong and Yoon, Kuk-Jin}, title = {Learning Adaptive Dense Event Stereo From the Image Domain}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {17797-17807} }

Foundation Model Drives Weakly Incremental Learning for Semantic Segmentation

Chaohui Yu,

Qiang Zhou,

Jingliang Li,

Jianlong Yuan,

Zhibin Wang,

Fan Wang

[pdf] [arXiv]

[bibtex]

@InProceedings{Yu_2023_CVPR, author = {Yu, Chaohui and Zhou, Qiang and Li, Jingliang and Yuan, Jianlong and Wang, Zhibin and Wang, Fan}, title = {Foundation Model Drives Weakly Incremental Learning for Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {23685-23694} }

Seeing a Rose in Five Thousand Ways

Yunzhi Zhang,

Shangzhe Wu,

Noah Snavely,

Jiajun Wu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Zhang_2023_CVPR, author = {Zhang, Yunzhi and Wu, Shangzhe and Snavely, Noah and Wu, Jiajun}, title = {Seeing a Rose in Five Thousand Ways}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {962-971} }

Neural Residual Radiance Fields for Streamably Free-Viewpoint Videos

Liao Wang,

Qiang Hu,

Qihan He,

Ziyu Wang,

Jingyi Yu,

Tinne Tuytelaars,

Lan Xu,

Minye Wu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Liao and Hu, Qiang and He, Qihan and Wang, Ziyu and Yu, Jingyi and Tuytelaars, Tinne and Xu, Lan and Wu, Minye}, title = {Neural Residual Radiance Fields for Streamably Free-Viewpoint Videos}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {76-87} }

ACSeg: Adaptive Conceptualization for Unsupervised Semantic Segmentation

Kehan Li,

Zhennan Wang,

Zesen Cheng,

Runyi Yu,

Yian Zhao,

Guoli Song,

Chang Liu,

Li Yuan,

Jie Chen

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Li_2023_CVPR, author = {Li, Kehan and Wang, Zhennan and Cheng, Zesen and Yu, Runyi and Zhao, Yian and Song, Guoli and Liu, Chang and Yuan, Li and Chen, Jie}, title = {ACSeg: Adaptive Conceptualization for Unsupervised Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7162-7172} }

NeRFVS: Neural Radiance Fields for Free View Synthesis via Geometry Scaffolds

Chen Yang,

Peihao Li,

Zanwei Zhou,

Shanxin Yuan,

Bingbing Liu,

Xiaokang Yang,

Weichao Qiu,

Wei Shen

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Yang_2023_CVPR, author = {Yang, Chen and Li, Peihao and Zhou, Zanwei and Yuan, Shanxin and Liu, Bingbing and Yang, Xiaokang and Qiu, Weichao and Shen, Wei}, title = {NeRFVS: Neural Radiance Fields for Free View Synthesis via Geometry Scaffolds}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16549-16558} }

Reproducible Scaling Laws for Contrastive Language-Image Learning

Mehdi Cherti,

Romain Beaumont,

Ross Wightman,

Mitchell Wortsman,

Gabriel Ilharco,

Cade Gordon,

Christoph Schuhmann,

Ludwig Schmidt,

Jenia Jitsev

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Cherti_2023_CVPR, author = {Cherti, Mehdi and Beaumont, Romain and Wightman, Ross and Wortsman, Mitchell and Ilharco, Gabriel and Gordon, Cade and Schuhmann, Christoph and Schmidt, Ludwig and Jitsev, Jenia}, title = {Reproducible Scaling Laws for Contrastive Language-Image Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2818-2829} }

Similarity Metric Learning for RGB-Infrared Group Re-Identification

Jianghao Xiong,

Jianhuang Lai

[pdf] [supp]

[bibtex]

@InProceedings{Xiong_2023_CVPR, author = {Xiong, Jianghao and Lai, Jianhuang}, title = {Similarity Metric Learning for RGB-Infrared Group Re-Identification}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13662-13671} }

Auto-CARD: Efficient and Robust Codec Avatar Driving for Real-Time Mobile Telepresence

Yonggan Fu,

Yuecheng Li,

Chenghui Li,

Jason Saragih,

Peizhao Zhang,

Xiaoliang Dai,

Yingyan (Celine) Lin

[pdf] [supp]

[bibtex]

@InProceedings{Fu_2023_CVPR, author = {Fu, Yonggan and Li, Yuecheng and Li, Chenghui and Saragih, Jason and Zhang, Peizhao and Dai, Xiaoliang and Lin, Yingyan (Celine)}, title = {Auto-CARD: Efficient and Robust Codec Avatar Driving for Real-Time Mobile Telepresence}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {21036-21045} }

Conjugate Product Graphs for Globally Optimal 2D-3D Shape Matching

Paul Roetzer,

Zorah Lähner,

Florian Bernard

[pdf] [supp]

[bibtex]

@InProceedings{Roetzer_2023_CVPR, author = {Roetzer, Paul and L\"ahner, Zorah and Bernard, Florian}, title = {Conjugate Product Graphs for Globally Optimal 2D-3D Shape Matching}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {21866-21875} }

PromptCAL: Contrastive Affinity Learning via Auxiliary Prompts for Generalized Novel Category Discovery

Sheng Zhang,

Salman Khan,

Zhiqiang Shen,

Muzammal Naseer,

Guangyi Chen,

Fahad Shahbaz Khan

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Zhang_2023_CVPR, author = {Zhang, Sheng and Khan, Salman and Shen, Zhiqiang and Naseer, Muzammal and Chen, Guangyi and Khan, Fahad Shahbaz}, title = {PromptCAL: Contrastive Affinity Learning via Auxiliary Prompts for Generalized Novel Category Discovery}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3479-3488} }

Train/Test-Time Adaptation With Retrieval

Luca Zancato,

Alessandro Achille,

Tian Yu Liu,

Matthew Trager,

Pramuditha Perera,

Stefano Soatto

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Zancato_2023_CVPR, author = {Zancato, Luca and Achille, Alessandro and Liu, Tian Yu and Trager, Matthew and Perera, Pramuditha and Soatto, Stefano}, title = {Train/Test-Time Adaptation With Retrieval}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15911-15921} }

ProxyFormer: Proxy Alignment Assisted Point Cloud Completion With Missing Part Sensitive Transformer

Shanshan Li,

Pan Gao,

Xiaoyang Tan,

Mingqiang Wei

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Li_2023_CVPR, author = {Li, Shanshan and Gao, Pan and Tan, Xiaoyang and Wei, Mingqiang}, title = {ProxyFormer: Proxy Alignment Assisted Point Cloud Completion With Missing Part Sensitive Transformer}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9466-9475} }

Mod-Squad: Designing Mixtures of Experts As Modular Multi-Task Learners

Zitian Chen,

Yikang Shen,

Mingyu Ding,

Zhenfang Chen,

Hengshuang Zhao,

Erik G. Learned-Miller,

Chuang Gan

[pdf] [supp]

[bibtex]

@InProceedings{Chen_2023_CVPR, author = {Chen, Zitian and Shen, Yikang and Ding, Mingyu and Chen, Zhenfang and Zhao, Hengshuang and Learned-Miller, Erik G. and Gan, Chuang}, title = {Mod-Squad: Designing Mixtures of Experts As Modular Multi-Task Learners}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11828-11837} }

Learning Customized Visual Models With Retrieval-Augmented Knowledge

Haotian Liu,

Kilho Son,

Jianwei Yang,

Ce Liu,

Jianfeng Gao,

Yong Jae Lee,

Chunyuan Li

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Liu_2023_CVPR, author = {Liu, Haotian and Son, Kilho and Yang, Jianwei and Liu, Ce and Gao, Jianfeng and Lee, Yong Jae and Li, Chunyuan}, title = {Learning Customized Visual Models With Retrieval-Augmented Knowledge}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15148-15158} }

Multi-Realism Image Compression With a Conditional Generator

Eirikur Agustsson,

David Minnen,

George Toderici,

Fabian Mentzer

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Agustsson_2023_CVPR, author = {Agustsson, Eirikur and Minnen, David and Toderici, George and Mentzer, Fabian}, title = {Multi-Realism Image Compression With a Conditional Generator}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {22324-22333} }

Run, Don't Walk: Chasing Higher FLOPS for Faster Neural Networks

Jierun Chen,

Shiu-hong Kao,

Hao He,

Weipeng Zhuo,

Song Wen,

Chul-Ho Lee,

S.-H. Gary Chan

[pdf] [supp]

[bibtex]

@InProceedings{Chen_2023_CVPR, author = {Chen, Jierun and Kao, Shiu-hong and He, Hao and Zhuo, Weipeng and Wen, Song and Lee, Chul-Ho and Chan, S.-H. Gary}, title = {Run, Don't Walk: Chasing Higher FLOPS for Faster Neural Networks}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12021-12031} }

A Unified Spatial-Angular Structured Light for Single-View Acquisition of Shape and Reflectance

Xianmin Xu,

Yuxin Lin,

Haoyang Zhou,

Chong Zeng,

Yaxin Yu,

Kun Zhou,

Hongzhi Wu

[pdf] [supp]

[bibtex]

@InProceedings{Xu_2023_CVPR, author = {Xu, Xianmin and Lin, Yuxin and Zhou, Haoyang and Zeng, Chong and Yu, Yaxin and Zhou, Kun and Wu, Hongzhi}, title = {A Unified Spatial-Angular Structured Light for Single-View Acquisition of Shape and Reflectance}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {206-215} }

Best of Both Worlds: Multimodal Contrastive Learning With Tabular and Imaging Data

Paul Hager,

Martin J. Menten,

Daniel Rueckert

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Hager_2023_CVPR, author = {Hager, Paul and Menten, Martin J. and Rueckert, Daniel}, title = {Best of Both Worlds: Multimodal Contrastive Learning With Tabular and Imaging Data}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {23924-23935} }

On the Difficulty of Unpaired Infrared-to-Visible Video Translation: Fine-Grained Content-Rich Patches Transfer

Zhenjie Yu,

Shuang Li,

Yirui Shen,

Chi Harold Liu,

Shuigen Wang

[pdf] [supp]

[bibtex]

@InProceedings{Yu_2023_CVPR, author = {Yu, Zhenjie and Li, Shuang and Shen, Yirui and Liu, Chi Harold and Wang, Shuigen}, title = {On the Difficulty of Unpaired Infrared-to-Visible Video Translation: Fine-Grained Content-Rich Patches Transfer}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1631-1640} }

Masked Images Are Counterfactual Samples for Robust Fine-Tuning

Yao Xiao,

Ziyi Tang,

Pengxu Wei,

Cong Liu,

Liang Lin

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Xiao_2023_CVPR, author = {Xiao, Yao and Tang, Ziyi and Wei, Pengxu and Liu, Cong and Lin, Liang}, title = {Masked Images Are Counterfactual Samples for Robust Fine-Tuning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {20301-20310} }

StepFormer: Self-Supervised Step Discovery and Localization in Instructional Videos

Nikita Dvornik,

Isma Hadji,

Ran Zhang,

Konstantinos G. Derpanis,

Richard P. Wildes,

Allan D. Jepson

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Dvornik_2023_CVPR, author = {Dvornik, Nikita and Hadji, Isma and Zhang, Ran and Derpanis, Konstantinos G. and Wildes, Richard P. and Jepson, Allan D.}, title = {StepFormer: Self-Supervised Step Discovery and Localization in Instructional Videos}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {18952-18961} }

Learning Procedure-Aware Video Representation From Instructional Videos and Their Narrations

Yiwu Zhong,

Licheng Yu,

Yang Bai,

Shangwen Li,

Xueting Yan,

Yin Li

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Zhong_2023_CVPR, author = {Zhong, Yiwu and Yu, Licheng and Bai, Yang and Li, Shangwen and Yan, Xueting and Li, Yin}, title = {Learning Procedure-Aware Video Representation From Instructional Videos and Their Narrations}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14825-14835} }

Open Vocabulary Semantic Segmentation With Patch Aligned Contrastive Learning

Jishnu Mukhoti,

Tsung-Yu Lin,

Omid Poursaeed,

Rui Wang,

Ashish Shah,

Philip H.S. Torr,

Ser-Nam Lim

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Mukhoti_2023_CVPR, author = {Mukhoti, Jishnu and Lin, Tsung-Yu and Poursaeed, Omid and Wang, Rui and Shah, Ashish and Torr, Philip H.S. and Lim, Ser-Nam}, title = {Open Vocabulary Semantic Segmentation With Patch Aligned Contrastive Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {19413-19423} }

CLIP the Gap: A Single Domain Generalization Approach for Object Detection

Vidit Vidit,

Martin Engilberge,

Mathieu Salzmann

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Vidit_2023_CVPR, author = {Vidit, Vidit and Engilberge, Martin and Salzmann, Mathieu}, title = {CLIP the Gap: A Single Domain Generalization Approach for Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3219-3229} }

Co-Training 2L Submodels for Visual Recognition

Hugo Touvron,

Matthieu Cord,

Maxime Oquab,

Piotr Bojanowski,

Jakob Verbeek,

Hervé Jégou

[pdf] [supp]

[bibtex]

@InProceedings{Touvron_2023_CVPR, author = {Touvron, Hugo and Cord, Matthieu and Oquab, Maxime and Bojanowski, Piotr and Verbeek, Jakob and J\'egou, Herv\'e}, title = {Co-Training 2L Submodels for Visual Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11701-11710} }

On the Importance of Accurate Geometry Data for Dense 3D Vision Tasks

HyunJun Jung,

Patrick Ruhkamp,

Guangyao Zhai,

Nikolas Brasch,

Yitong Li,

Yannick Verdie,

Jifei Song,

Yiren Zhou,

Anil Armagan,

Slobodan Ilic,

Aleš Leonardis,

Nassir Navab,

Benjamin Busam

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Jung_2023_CVPR, author = {Jung, HyunJun and Ruhkamp, Patrick and Zhai, Guangyao and Brasch, Nikolas and Li, Yitong and Verdie, Yannick and Song, Jifei and Zhou, Yiren and Armagan, Anil and Ilic, Slobodan and Leonardis, Ale\v{s} and Navab, Nassir and Busam, Benjamin}, title = {On the Importance of Accurate Geometry Data for Dense 3D Vision Tasks}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {780-791} }

Camouflaged Instance Segmentation via Explicit De-Camouflaging

Naisong Luo,

Yuwen Pan,

Rui Sun,

Tianzhu Zhang,

Zhiwei Xiong,

Feng Wu

[pdf] [supp]

[bibtex]

@InProceedings{Luo_2023_CVPR, author = {Luo, Naisong and Pan, Yuwen and Sun, Rui and Zhang, Tianzhu and Xiong, Zhiwei and Wu, Feng}, title = {Camouflaged Instance Segmentation via Explicit De-Camouflaging}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {17918-17927} }

Understanding Masked Autoencoders via Hierarchical Latent Variable Models

Lingjing Kong,

Martin Q. Ma,

Guangyi Chen,

Eric P. Xing,

Yuejie Chi,

Louis-Philippe Morency,

Kun Zhang

[pdf] [supp]

[bibtex]

@InProceedings{Kong_2023_CVPR, author = {Kong, Lingjing and Ma, Martin Q. and Chen, Guangyi and Xing, Eric P. and Chi, Yuejie and Morency, Louis-Philippe and Zhang, Kun}, title = {Understanding Masked Autoencoders via Hierarchical Latent Variable Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7918-7928} }

K-Planes: Explicit Radiance Fields in Space, Time, and Appearance

Sara Fridovich-Keil,

Giacomo Meanti,

Frederik Rahbæk Warburg,

Benjamin Recht,

Angjoo Kanazawa

[pdf] [supp]

[bibtex]

@InProceedings{Fridovich-Keil_2023_CVPR, author = {Fridovich-Keil, Sara and Meanti, Giacomo and Warburg, Frederik Rahb{\ae}k and Recht, Benjamin and Kanazawa, Angjoo}, title = {K-Planes: Explicit Radiance Fields in Space, Time, and Appearance}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12479-12488} }

Multi-Mode Online Knowledge Distillation for Self-Supervised Visual Representation Learning

Kaiyou Song,

Jin Xie,

Shan Zhang,

Zimeng Luo

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Song_2023_CVPR, author = {Song, Kaiyou and Xie, Jin and Zhang, Shan and Luo, Zimeng}, title = {Multi-Mode Online Knowledge Distillation for Self-Supervised Visual Representation Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11848-11857} }

Unbalanced Optimal Transport: A Unified Framework for Object Detection

Henri De Plaen,

Pierre-François De Plaen,

Johan A. K. Suykens,

Marc Proesmans,

Tinne Tuytelaars,

Luc Van Gool

[pdf] [supp]

[bibtex]

@InProceedings{De_Plaen_2023_CVPR, author = {De Plaen, Henri and De Plaen, Pierre-Fran\c{c}ois and Suykens, Johan A. K. and Proesmans, Marc and Tuytelaars, Tinne and Van Gool, Luc}, title = {Unbalanced Optimal Transport: A Unified Framework for Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3198-3207} }

Viewpoint Equivariance for Multi-View 3D Object Detection

Dian Chen,

Jie Li,

Vitor Guizilini,

Rares Andrei Ambrus,

Adrien Gaidon

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Chen_2023_CVPR, author = {Chen, Dian and Li, Jie and Guizilini, Vitor and Ambrus, Rares Andrei and Gaidon, Adrien}, title = {Viewpoint Equivariance for Multi-View 3D Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9213-9222} }

Photo Pre-Training, but for Sketch

Ke Li,

Kaiyue Pang,

Yi-Zhe Song

[pdf] [supp]

[bibtex]

@InProceedings{Li_2023_CVPR, author = {Li, Ke and Pang, Kaiyue and Song, Yi-Zhe}, title = {Photo Pre-Training, but for Sketch}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2754-2764} }

NeuralPCI: Spatio-Temporal Neural Field for 3D Point Cloud Multi-Frame Non-Linear Interpolation

Zehan Zheng,

Danni Wu,

Ruisi Lu,

Fan Lu,

Guang Chen,

Changjun Jiang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Zheng_2023_CVPR, author = {Zheng, Zehan and Wu, Danni and Lu, Ruisi and Lu, Fan and Chen, Guang and Jiang, Changjun}, title = {NeuralPCI: Spatio-Temporal Neural Field for 3D Point Cloud Multi-Frame Non-Linear Interpolation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {909-918} }

Bidirectional Cross-Modal Knowledge Exploration for Video Recognition With Pre-Trained Vision-Language Models

Wenhao Wu,

Xiaohan Wang,

Haipeng Luo,

Jingdong Wang,

Yi Yang,

Wanli Ouyang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Wu_2023_CVPR, author = {Wu, Wenhao and Wang, Xiaohan and Luo, Haipeng and Wang, Jingdong and Yang, Yi and Ouyang, Wanli}, title = {Bidirectional Cross-Modal Knowledge Exploration for Video Recognition With Pre-Trained Vision-Language Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6620-6630} }

Adaptive Plasticity Improvement for Continual Learning

Yan-Shuo Liang,

Wu-Jun Li

[pdf] [supp]

[bibtex]

@InProceedings{Liang_2023_CVPR, author = {Liang, Yan-Shuo and Li, Wu-Jun}, title = {Adaptive Plasticity Improvement for Continual Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7816-7825} }

Pic2Word: Mapping Pictures to Words for Zero-Shot Composed Image Retrieval

Kuniaki Saito,

Kihyuk Sohn,

Xiang Zhang,

Chun-Liang Li,

Chen-Yu Lee,

Kate Saenko,

Tomas Pfister

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Saito_2023_CVPR, author = {Saito, Kuniaki and Sohn, Kihyuk and Zhang, Xiang and Li, Chun-Liang and Lee, Chen-Yu and Saenko, Kate and Pfister, Tomas}, title = {Pic2Word: Mapping Pictures to Words for Zero-Shot Composed Image Retrieval}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {19305-19314} }

MMANet: Margin-Aware Distillation and Modality-Aware Regularization for Incomplete Multimodal Learning

Shicai Wei,

Chunbo Luo,

Yang Luo

[pdf] [arXiv]

[bibtex]

@InProceedings{Wei_2023_CVPR, author = {Wei, Shicai and Luo, Chunbo and Luo, Yang}, title = {MMANet: Margin-Aware Distillation and Modality-Aware Regularization for Incomplete Multimodal Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {20039-20049} }

Putting People in Their Place: Affordance-Aware Human Insertion Into Scenes

Sumith Kulal,

Tim Brooks,

Alex Aiken,

Jiajun Wu,

Jimei Yang,

Jingwan Lu,

Alexei A. Efros,

Krishna Kumar Singh

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Kulal_2023_CVPR, author = {Kulal, Sumith and Brooks, Tim and Aiken, Alex and Wu, Jiajun and Yang, Jimei and Lu, Jingwan and Efros, Alexei A. and Singh, Krishna Kumar}, title = {Putting People in Their Place: Affordance-Aware Human Insertion Into Scenes}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {17089-17099} }

3D Neural Field Generation Using Triplane Diffusion

J. Ryan Shue,

Eric Ryan Chan,

Ryan Po,

Zachary Ankner,

Jiajun Wu,

Gordon Wetzstein

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Shue_2023_CVPR, author = {Shue, J. Ryan and Chan, Eric Ryan and Po, Ryan and Ankner, Zachary and Wu, Jiajun and Wetzstein, Gordon}, title = {3D Neural Field Generation Using Triplane Diffusion}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {20875-20886} }

Regularized Vector Quantization for Tokenized Image Synthesis

Jiahui Zhang,

Fangneng Zhan,

Christian Theobalt,

Shijian Lu

[pdf] [arXiv]

[bibtex]

@InProceedings{Zhang_2023_CVPR, author = {Zhang, Jiahui and Zhan, Fangneng and Theobalt, Christian and Lu, Shijian}, title = {Regularized Vector Quantization for Tokenized Image Synthesis}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {18467-18476} }

Semantic Scene Completion With Cleaner Self

Fengyun Wang,

Dong Zhang,

Hanwang Zhang,

Jinhui Tang,

Qianru Sun

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Fengyun and Zhang, Dong and Zhang, Hanwang and Tang, Jinhui and Sun, Qianru}, title = {Semantic Scene Completion With Cleaner Self}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {867-877} }

Improving Image Recognition by Retrieving From Web-Scale Image-Text Data

Ahmet Iscen,

Alireza Fathi,

Cordelia Schmid

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Iscen_2023_CVPR, author = {Iscen, Ahmet and Fathi, Alireza and Schmid, Cordelia}, title = {Improving Image Recognition by Retrieving From Web-Scale Image-Text Data}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {19295-19304} }

Deep Factorized Metric Learning

Chengkun Wang,

Wenzhao Zheng,

Junlong Li,

Jie Zhou,

Jiwen Lu

[pdf]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Chengkun and Zheng, Wenzhao and Li, Junlong and Zhou, Jie and Lu, Jiwen}, title = {Deep Factorized Metric Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7672-7682} }

High-Fidelity 3D Face Generation From Natural Language Descriptions

Menghua Wu,

Hao Zhu,

Linjia Huang,

Yiyu Zhuang,

Yuanxun Lu,

Xun Cao

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Wu_2023_CVPR, author = {Wu, Menghua and Zhu, Hao and Huang, Linjia and Zhuang, Yiyu and Lu, Yuanxun and Cao, Xun}, title = {High-Fidelity 3D Face Generation From Natural Language Descriptions}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4521-4530} }

A Generalized Framework for Video Instance Segmentation

Miran Heo,

Sukjun Hwang,

Jeongseok Hyun,

Hanjung Kim,

Seoung Wug Oh,

Joon-Young Lee,

Seon Joo Kim

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Heo_2023_CVPR, author = {Heo, Miran and Hwang, Sukjun and Hyun, Jeongseok and Kim, Hanjung and Oh, Seoung Wug and Lee, Joon-Young and Kim, Seon Joo}, title = {A Generalized Framework for Video Instance Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14623-14632} }

Multi-Level Logit Distillation

Ying Jin,

Jiaqi Wang,

Dahua Lin

[pdf] [supp]

[bibtex]

@InProceedings{Jin_2023_CVPR, author = {Jin, Ying and Wang, Jiaqi and Lin, Dahua}, title = {Multi-Level Logit Distillation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {24276-24285} }

On Distillation of Guided Diffusion Models

Chenlin Meng,

Robin Rombach,

Ruiqi Gao,

Diederik Kingma,

Stefano Ermon,

Jonathan Ho,

Tim Salimans

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Meng_2023_CVPR, author = {Meng, Chenlin and Rombach, Robin and Gao, Ruiqi and Kingma, Diederik and Ermon, Stefano and Ho, Jonathan and Salimans, Tim}, title = {On Distillation of Guided Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14297-14306} }

Dual-Path Adaptation From Image to Video Transformers

Jungin Park,

Jiyoung Lee,

Kwanghoon Sohn

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Park_2023_CVPR, author = {Park, Jungin and Lee, Jiyoung and Sohn, Kwanghoon}, title = {Dual-Path Adaptation From Image to Video Transformers}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2203-2213} }

Towards Better Decision Forests: Forest Alternating Optimization

Miguel Á. Carreira-Perpiñán,

Magzhan Gabidolla,

Arman Zharmagambetov

[pdf] [supp]

[bibtex]

@InProceedings{Carreira-Perpinan_2023_CVPR, author = {Carreira-Perpi\~n\'an, Miguel \'A. and Gabidolla, Magzhan and Zharmagambetov, Arman}, title = {Towards Better Decision Forests: Forest Alternating Optimization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7589-7598} }

DA Wand: Distortion-Aware Selection Using Neural Mesh Parameterization

Richard Liu,

Noam Aigerman,

Vladimir G. Kim,

Rana Hanocka

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Liu_2023_CVPR, author = {Liu, Richard and Aigerman, Noam and Kim, Vladimir G. and Hanocka, Rana}, title = {DA Wand: Distortion-Aware Selection Using Neural Mesh Parameterization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16739-16749} }

Disentangled Representation Learning for Unsupervised Neural Quantization

Haechan Noh,

Sangeek Hyun,

Woojin Jeong,

Hanshin Lim,

Jae-Pil Heo

[pdf]

[bibtex]

@InProceedings{Noh_2023_CVPR, author = {Noh, Haechan and Hyun, Sangeek and Jeong, Woojin and Lim, Hanshin and Heo, Jae-Pil}, title = {Disentangled Representation Learning for Unsupervised Neural Quantization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12001-12010} }

Hierarchical Semantic Correspondence Networks for Video Paragraph Grounding

Chaolei Tan,

Zihang Lin,

Jian-Fang Hu,

Wei-Shi Zheng,

Jianhuang Lai

[pdf] [supp]

[bibtex]

@InProceedings{Tan_2023_CVPR, author = {Tan, Chaolei and Lin, Zihang and Hu, Jian-Fang and Zheng, Wei-Shi and Lai, Jianhuang}, title = {Hierarchical Semantic Correspondence Networks for Video Paragraph Grounding}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {18973-18982} }

Temporal Attention Unit: Towards Efficient Spatiotemporal Predictive Learning

Cheng Tan,

Zhangyang Gao,

Lirong Wu,

Yongjie Xu,

Jun Xia,

Siyuan Li,

Stan Z. Li

[pdf] [arXiv]

[bibtex]

@InProceedings{Tan_2023_CVPR, author = {Tan, Cheng and Gao, Zhangyang and Wu, Lirong and Xu, Yongjie and Xia, Jun and Li, Siyuan and Li, Stan Z.}, title = {Temporal Attention Unit: Towards Efficient Spatiotemporal Predictive Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {18770-18782} }

Zero-Shot Pose Transfer for Unrigged Stylized 3D Characters

Jiashun Wang,

Xueting Li,

Sifei Liu,

Shalini De Mello,

Orazio Gallo,

Xiaolong Wang,

Jan Kautz

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Jiashun and Li, Xueting and Liu, Sifei and De Mello, Shalini and Gallo, Orazio and Wang, Xiaolong and Kautz, Jan}, title = {Zero-Shot Pose Transfer for Unrigged Stylized 3D Characters}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8704-8714} }

Listening Human Behavior: 3D Human Pose Estimation With Acoustic Signals

Yuto Shibata,

Yutaka Kawashima,

Mariko Isogawa,

Go Irie,

Akisato Kimura,

Yoshimitsu Aoki

[pdf] [supp]

[bibtex]

@InProceedings{Shibata_2023_CVPR, author = {Shibata, Yuto and Kawashima, Yutaka and Isogawa, Mariko and Irie, Go and Kimura, Akisato and Aoki, Yoshimitsu}, title = {Listening Human Behavior: 3D Human Pose Estimation With Acoustic Signals}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13323-13332} }

Meta-Learning With a Geometry-Adaptive Preconditioner

Suhyun Kang,

Duhun Hwang,

Moonjung Eo,

Taesup Kim,

Wonjong Rhee

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Kang_2023_CVPR, author = {Kang, Suhyun and Hwang, Duhun and Eo, Moonjung and Kim, Taesup and Rhee, Wonjong}, title = {Meta-Learning With a Geometry-Adaptive Preconditioner}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16080-16090} }

Dynamic Graph Enhanced Contrastive Learning for Chest X-Ray Report Generation

Mingjie Li,

Bingqian Lin,

Zicong Chen,

Haokun Lin,

Xiaodan Liang,

Xiaojun Chang

[pdf]

[bibtex]

@InProceedings{Li_2023_CVPR, author = {Li, Mingjie and Lin, Bingqian and Chen, Zicong and Lin, Haokun and Liang, Xiaodan and Chang, Xiaojun}, title = {Dynamic Graph Enhanced Contrastive Learning for Chest X-Ray Report Generation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3334-3343} }

BiCro: Noisy Correspondence Rectification for Multi-Modality Data via Bi-Directional Cross-Modal Similarity Consistency

Shuo Yang,

Zhaopan Xu,

Kai Wang,

Yang You,

Hongxun Yao,

Tongliang Liu,

Min Xu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Yang_2023_CVPR, author = {Yang, Shuo and Xu, Zhaopan and Wang, Kai and You, Yang and Yao, Hongxun and Liu, Tongliang and Xu, Min}, title = {BiCro: Noisy Correspondence Rectification for Multi-Modality Data via Bi-Directional Cross-Modal Similarity Consistency}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {19883-19892} }

Transfer Knowledge From Head to Tail: Uncertainty Calibration Under Long-Tailed Distribution

Jiahao Chen,

Bing Su

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Chen_2023_CVPR, author = {Chen, Jiahao and Su, Bing}, title = {Transfer Knowledge From Head to Tail: Uncertainty Calibration Under Long-Tailed Distribution}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {19978-19987} }

FrustumFormer: Adaptive Instance-Aware Resampling for Multi-View 3D Detection

Yuqi Wang,

Yuntao Chen,

Zhaoxiang Zhang

[pdf] [arXiv]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Yuqi and Chen, Yuntao and Zhang, Zhaoxiang}, title = {FrustumFormer: Adaptive Instance-Aware Resampling for Multi-View 3D Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5096-5105} }

Global Vision Transformer Pruning With Hessian-Aware Saliency

Huanrui Yang,

Hongxu Yin,

Maying Shen,

Pavlo Molchanov,

Hai Li,

Jan Kautz

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Yang_2023_CVPR, author = {Yang, Huanrui and Yin, Hongxu and Shen, Maying and Molchanov, Pavlo and Li, Hai and Kautz, Jan}, title = {Global Vision Transformer Pruning With Hessian-Aware Saliency}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {18547-18557} }

Class-Conditional Sharpness-Aware Minimization for Deep Long-Tailed Recognition

Zhipeng Zhou,

Lanqing Li,

Peilin Zhao,

Pheng-Ann Heng,

Wei Gong

[pdf] [supp]

[bibtex]

@InProceedings{Zhou_2023_CVPR, author = {Zhou, Zhipeng and Li, Lanqing and Zhao, Peilin and Heng, Pheng-Ann and Gong, Wei}, title = {Class-Conditional Sharpness-Aware Minimization for Deep Long-Tailed Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3499-3509} }

ScarceNet: Animal Pose Estimation With Scarce Annotations

Chen Li,

Gim Hee Lee

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Li_2023_CVPR, author = {Li, Chen and Lee, Gim Hee}, title = {ScarceNet: Animal Pose Estimation With Scarce Annotations}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {17174-17183} }

OmniCity: Omnipotent City Understanding With Multi-Level and Multi-View Images

Weijia Li,

Yawen Lai,

Linning Xu,

Yuanbo Xiangli,

Jinhua Yu,

Conghui He,

Gui-Song Xia,

Dahua Lin

[pdf] [arXiv]

[bibtex]

@InProceedings{Li_2023_CVPR, author = {Li, Weijia and Lai, Yawen and Xu, Linning and Xiangli, Yuanbo and Yu, Jinhua and He, Conghui and Xia, Gui-Song and Lin, Dahua}, title = {OmniCity: Omnipotent City Understanding With Multi-Level and Multi-View Images}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {17397-17407} }

Efficient On-Device Training via Gradient Filtering

Yuedong Yang,

Guihong Li,

Radu Marculescu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Yang_2023_CVPR, author = {Yang, Yuedong and Li, Guihong and Marculescu, Radu}, title = {Efficient On-Device Training via Gradient Filtering}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3811-3820} }

SViTT: Temporal Learning of Sparse Video-Text Transformers

Yi Li,

Kyle Min,

Subarna Tripathi,

Nuno Vasconcelos

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Li_2023_CVPR, author = {Li, Yi and Min, Kyle and Tripathi, Subarna and Vasconcelos, Nuno}, title = {SViTT: Temporal Learning of Sparse Video-Text Transformers}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {18919-18929} }

NeuralDome: A Neural Modeling Pipeline on Multi-View Human-Object Interactions

Juze Zhang,

Haimin Luo,

Hongdi Yang,

Xinru Xu,

Qianyang Wu,

Ye Shi,

Jingyi Yu,

Lan Xu,

Jingya Wang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Zhang_2023_CVPR, author = {Zhang, Juze and Luo, Haimin and Yang, Hongdi and Xu, Xinru and Wu, Qianyang and Shi, Ye and Yu, Jingyi and Xu, Lan and Wang, Jingya}, title = {NeuralDome: A Neural Modeling Pipeline on Multi-View Human-Object Interactions}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8834-8845} }

3D Human Mesh Estimation From Virtual Markers

Xiaoxuan Ma,

Jiajun Su,

Chunyu Wang,

Wentao Zhu,

Yizhou Wang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Ma_2023_CVPR, author = {Ma, Xiaoxuan and Su, Jiajun and Wang, Chunyu and Zhu, Wentao and Wang, Yizhou}, title = {3D Human Mesh Estimation From Virtual Markers}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {534-543} }

CUDA: Convolution-Based Unlearnable Datasets

Vinu Sankar Sadasivan,

Mahdi Soltanolkotabi,

Soheil Feizi

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Sadasivan_2023_CVPR, author = {Sadasivan, Vinu Sankar and Soltanolkotabi, Mahdi and Feizi, Soheil}, title = {CUDA: Convolution-Based Unlearnable Datasets}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3862-3871} }

No One Left Behind: Improving the Worst Categories in Long-Tailed Learning

Yingxiao Du,

Jianxin Wu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Du_2023_CVPR, author = {Du, Yingxiao and Wu, Jianxin}, title = {No One Left Behind: Improving the Worst Categories in Long-Tailed Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15804-15813} }

Deep Fair Clustering via Maximizing and Minimizing Mutual Information: Theory, Algorithm and Metric

Pengxin Zeng,

Yunfan Li,

Peng Hu,

Dezhong Peng,

Jiancheng Lv,

Xi Peng

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Zeng_2023_CVPR, author = {Zeng, Pengxin and Li, Yunfan and Hu, Peng and Peng, Dezhong and Lv, Jiancheng and Peng, Xi}, title = {Deep Fair Clustering via Maximizing and Minimizing Mutual Information: Theory, Algorithm and Metric}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {23986-23995} }

MIANet: Aggregating Unbiased Instance and General Information for Few-Shot Semantic Segmentation

Yong Yang,

Qiong Chen,

Yuan Feng,

Tianlin Huang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Yang_2023_CVPR, author = {Yang, Yong and Chen, Qiong and Feng, Yuan and Huang, Tianlin}, title = {MIANet: Aggregating Unbiased Instance and General Information for Few-Shot Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7131-7140} }

High Fidelity 3D Hand Shape Reconstruction via Scalable Graph Frequency Decomposition

Tianyu Luan,

Yuanhao Zhai,

Jingjing Meng,

Zhong Li,

Zhang Chen,

Yi Xu,

Junsong Yuan

[pdf] [supp]

[bibtex]

@InProceedings{Luan_2023_CVPR, author = {Luan, Tianyu and Zhai, Yuanhao and Meng, Jingjing and Li, Zhong and Chen, Zhang and Xu, Yi and Yuan, Junsong}, title = {High Fidelity 3D Hand Shape Reconstruction via Scalable Graph Frequency Decomposition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16795-16804} }

COT: Unsupervised Domain Adaptation With Clustering and Optimal Transport

Yang Liu,

Zhipeng Zhou,

Baigui Sun

[pdf]

[bibtex]

@InProceedings{Liu_2023_CVPR, author = {Liu, Yang and Zhou, Zhipeng and Sun, Baigui}, title = {COT: Unsupervised Domain Adaptation With Clustering and Optimal Transport}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {19998-20007} }

Target-Referenced Reactive Grasping for Dynamic Objects

Jirong Liu,

Ruo Zhang,

Hao-Shu Fang,

Minghao Gou,

Hongjie Fang,

Chenxi Wang,

Sheng Xu,

Hengxu Yan,

Cewu Lu

[pdf] [supp]

[bibtex]

@InProceedings{Liu_2023_CVPR, author = {Liu, Jirong and Zhang, Ruo and Fang, Hao-Shu and Gou, Minghao and Fang, Hongjie and Wang, Chenxi and Xu, Sheng and Yan, Hengxu and Lu, Cewu}, title = {Target-Referenced Reactive Grasping for Dynamic Objects}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8824-8833} }

Learning To Exploit the Sequence-Specific Prior Knowledge for Image Processing Pipelines Optimization

Haina Qin,

Longfei Han,

Weihua Xiong,

Juan Wang,

Wentao Ma,

Bing Li,

Weiming Hu

[pdf] [supp]

[bibtex]

@InProceedings{Qin_2023_CVPR, author = {Qin, Haina and Han, Longfei and Xiong, Weihua and Wang, Juan and Ma, Wentao and Li, Bing and Hu, Weiming}, title = {Learning To Exploit the Sequence-Specific Prior Knowledge for Image Processing Pipelines Optimization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {22314-22323} }

Complexity-Guided Slimmable Decoder for Efficient Deep Video Compression

Zhihao Hu,

Dong Xu

[pdf] [supp]

[bibtex]

@InProceedings{Hu_2023_CVPR, author = {Hu, Zhihao and Xu, Dong}, title = {Complexity-Guided Slimmable Decoder for Efficient Deep Video Compression}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14358-14367} }

Lite-Mono: A Lightweight CNN and Transformer Architecture for Self-Supervised Monocular Depth Estimation

Ning Zhang,

Francesco Nex,

George Vosselman,

Norman Kerle

[pdf]

[bibtex]

@InProceedings{Zhang_2023_CVPR, author = {Zhang, Ning and Nex, Francesco and Vosselman, George and Kerle, Norman}, title = {Lite-Mono: A Lightweight CNN and Transformer Architecture for Self-Supervised Monocular Depth Estimation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {18537-18546} }

MarginMatch: Improving Semi-Supervised Learning with Pseudo-Margins

Tiberiu Sosea,

Cornelia Caragea

[pdf] [supp]

[bibtex]

@InProceedings{Sosea_2023_CVPR, author = {Sosea, Tiberiu and Caragea, Cornelia}, title = {MarginMatch: Improving Semi-Supervised Learning with Pseudo-Margins}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15773-15782} }

Neural Scene Chronology

Haotong Lin,

Qianqian Wang,

Ruojin Cai,

Sida Peng,

Hadar Averbuch-Elor,

Xiaowei Zhou,

Noah Snavely

[pdf]

[bibtex]

@InProceedings{Lin_2023_CVPR, author = {Lin, Haotong and Wang, Qianqian and Cai, Ruojin and Peng, Sida and Averbuch-Elor, Hadar and Zhou, Xiaowei and Snavely, Noah}, title = {Neural Scene Chronology}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {20752-20761} }

Starting From Non-Parametric Networks for 3D Point Cloud Analysis

Renrui Zhang,

Liuhui Wang,

Yali Wang,

Peng Gao,

Hongsheng Li,

Jianbo Shi

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Zhang_2023_CVPR, author = {Zhang, Renrui and Wang, Liuhui and Wang, Yali and Gao, Peng and Li, Hongsheng and Shi, Jianbo}, title = {Starting From Non-Parametric Networks for 3D Point Cloud Analysis}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5344-5353} }

Light Source Separation and Intrinsic Image Decomposition Under AC Illumination

Yusaku Yoshida,

Ryo Kawahara,

Takahiro Okabe

[pdf] [supp]

[bibtex]

@InProceedings{Yoshida_2023_CVPR, author = {Yoshida, Yusaku and Kawahara, Ryo and Okabe, Takahiro}, title = {Light Source Separation and Intrinsic Image Decomposition Under AC Illumination}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5735-5743} }

TIPI: Test Time Adaptation With Transformation Invariance

A. Tuan Nguyen,

Thanh Nguyen-Tang,

Ser-Nam Lim,

Philip H.S. Torr

[pdf] [supp]

[bibtex]

@InProceedings{Nguyen_2023_CVPR, author = {Nguyen, A. Tuan and Nguyen-Tang, Thanh and Lim, Ser-Nam and Torr, Philip H.S.}, title = {TIPI: Test Time Adaptation With Transformation Invariance}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {24162-24171} }

OTAvatar: One-Shot Talking Face Avatar With Controllable Tri-Plane Rendering

Zhiyuan Ma,

Xiangyu Zhu,

Guo-Jun Qi,

Zhen Lei,

Lei Zhang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Ma_2023_CVPR, author = {Ma, Zhiyuan and Zhu, Xiangyu and Qi, Guo-Jun and Lei, Zhen and Zhang, Lei}, title = {OTAvatar: One-Shot Talking Face Avatar With Controllable Tri-Plane Rendering}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16901-16910} }

Beyond Appearance: A Semantic Controllable Self-Supervised Learning Framework for Human-Centric Visual Tasks

Weihua Chen,

Xianzhe Xu,

Jian Jia,

Hao Luo,

Yaohua Wang,

Fan Wang,

Rong Jin,

Xiuyu Sun

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Chen_2023_CVPR, author = {Chen, Weihua and Xu, Xianzhe and Jia, Jian and Luo, Hao and Wang, Yaohua and Wang, Fan and Jin, Rong and Sun, Xiuyu}, title = {Beyond Appearance: A Semantic Controllable Self-Supervised Learning Framework for Human-Centric Visual Tasks}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15050-15061} }

Large-Capacity and Flexible Video Steganography via Invertible Neural Network

Chong Mou,

Youmin Xu,

Jiechong Song,

Chen Zhao,

Bernard Ghanem,

Jian Zhang

[pdf] [arXiv]

[bibtex]

@InProceedings{Mou_2023_CVPR, author = {Mou, Chong and Xu, Youmin and Song, Jiechong and Zhao, Chen and Ghanem, Bernard and Zhang, Jian}, title = {Large-Capacity and Flexible Video Steganography via Invertible Neural Network}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {22606-22615} }

CFA: Class-Wise Calibrated Fair Adversarial Training

Zeming Wei,

Yifei Wang,

Yiwen Guo,

Yisen Wang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Wei_2023_CVPR, author = {Wei, Zeming and Wang, Yifei and Guo, Yiwen and Wang, Yisen}, title = {CFA: Class-Wise Calibrated Fair Adversarial Training}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8193-8201} }

EVAL: Explainable Video Anomaly Localization

Ashish Singh,

Michael J. Jones,

Erik G. Learned-Miller

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Singh_2023_CVPR, author = {Singh, Ashish and Jones, Michael J. and Learned-Miller, Erik G.}, title = {EVAL: Explainable Video Anomaly Localization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {18717-18726} }

Position-Guided Text Prompt for Vision-Language Pre-Training

Jinpeng Wang,

Pan Zhou,

Mike Zheng Shou,

Shuicheng Yan

[pdf] [arXiv]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Jinpeng and Zhou, Pan and Shou, Mike Zheng and Yan, Shuicheng}, title = {Position-Guided Text Prompt for Vision-Language Pre-Training}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {23242-23251} }

HOLODIFFUSION: Training a 3D Diffusion Model Using 2D Images

Animesh Karnewar,

Andrea Vedaldi,

David Novotny,

Niloy J. Mitra

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Karnewar_2023_CVPR, author = {Karnewar, Animesh and Vedaldi, Andrea and Novotny, David and Mitra, Niloy J.}, title = {HOLODIFFUSION: Training a 3D Diffusion Model Using 2D Images}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {18423-18433} }

Stimulus Verification Is a Universal and Effective Sampler in Multi-Modal Human Trajectory Prediction

Jianhua Sun,

Yuxuan Li,

Liang Chai,

Cewu Lu

[pdf] [supp]

[bibtex]

@InProceedings{Sun_2023_CVPR, author = {Sun, Jianhua and Li, Yuxuan and Chai, Liang and Lu, Cewu}, title = {Stimulus Verification Is a Universal and Effective Sampler in Multi-Modal Human Trajectory Prediction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {22014-22023} }

3D Human Pose Estimation With Spatio-Temporal Criss-Cross Attention

Zhenhua Tang,

Zhaofan Qiu,

Yanbin Hao,

Richang Hong,

Ting Yao

[pdf] [supp]

[bibtex]

@InProceedings{Tang_2023_CVPR, author = {Tang, Zhenhua and Qiu, Zhaofan and Hao, Yanbin and Hong, Richang and Yao, Ting}, title = {3D Human Pose Estimation With Spatio-Temporal Criss-Cross Attention}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4790-4799} }

Plateau-Reduced Differentiable Path Tracing

Michael Fischer,

Tobias Ritschel

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Fischer_2023_CVPR, author = {Fischer, Michael and Ritschel, Tobias}, title = {Plateau-Reduced Differentiable Path Tracing}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4285-4294} }

LoGoNet: Towards Accurate 3D Object Detection With Local-to-Global Cross-Modal Fusion

Xin Li,

Tao Ma,

Yuenan Hou,

Botian Shi,

Yuchen Yang,

Youquan Liu,

Xingjiao Wu,

Qin Chen,

Yikang Li,

Yu Qiao,

Liang He

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Li_2023_CVPR, author = {Li, Xin and Ma, Tao and Hou, Yuenan and Shi, Botian and Yang, Yuchen and Liu, Youquan and Wu, Xingjiao and Chen, Qin and Li, Yikang and Qiao, Yu and He, Liang}, title = {LoGoNet: Towards Accurate 3D Object Detection With Local-to-Global Cross-Modal Fusion}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {17524-17534} }

ScaleKD: Distilling Scale-Aware Knowledge in Small Object Detector

Yichen Zhu,

Qiqi Zhou,

Ning Liu,

Zhiyuan Xu,

Zhicai Ou,

Xiaofeng Mou,

Jian Tang

[pdf]

[bibtex]

@InProceedings{Zhu_2023_CVPR, author = {Zhu, Yichen and Zhou, Qiqi and Liu, Ning and Xu, Zhiyuan and Ou, Zhicai and Mou, Xiaofeng and Tang, Jian}, title = {ScaleKD: Distilling Scale-Aware Knowledge in Small Object Detector}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {19723-19733} }

An Empirical Study of End-to-End Video-Language Transformers With Masked Visual Modeling

Tsu-Jui Fu,

Linjie Li,

Zhe Gan,

Kevin Lin,

William Yang Wang,

Lijuan Wang,

Zicheng Liu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Fu_2023_CVPR, author = {Fu, Tsu-Jui and Li, Linjie and Gan, Zhe and Lin, Kevin and Wang, William Yang and Wang, Lijuan and Liu, Zicheng}, title = {An Empirical Study of End-to-End Video-Language Transformers With Masked Visual Modeling}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {22898-22909} }

Glocal Energy-Based Learning for Few-Shot Open-Set Recognition

Haoyu Wang,

Guansong Pang,

Peng Wang,

Lei Zhang,

Wei Wei,

Yanning Zhang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Haoyu and Pang, Guansong and Wang, Peng and Zhang, Lei and Wei, Wei and Zhang, Yanning}, title = {Glocal Energy-Based Learning for Few-Shot Open-Set Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7507-7516} }

Revisiting Temporal Modeling for CLIP-Based Image-to-Video Knowledge Transferring

Ruyang Liu,

Jingjia Huang,

Ge Li,

Jiashi Feng,

Xinglong Wu,

Thomas H. Li

[pdf] [arXiv]

[bibtex]

@InProceedings{Liu_2023_CVPR, author = {Liu, Ruyang and Huang, Jingjia and Li, Ge and Feng, Jiashi and Wu, Xinglong and Li, Thomas H.}, title = {Revisiting Temporal Modeling for CLIP-Based Image-to-Video Knowledge Transferring}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6555-6564} }

MethaneMapper: Spectral Absorption Aware Hyperspectral Transformer for Methane Detection

Satish Kumar,

Ivan Arevalo,

ASM Iftekhar,

B S Manjunath

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Kumar_2023_CVPR, author = {Kumar, Satish and Arevalo, Ivan and Iftekhar, ASM and Manjunath, B S}, title = {MethaneMapper: Spectral Absorption Aware Hyperspectral Transformer for Methane Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {17609-17618} }

Autonomous Manipulation Learning for Similar Deformable Objects via Only One Demonstration

Yu Ren,

Ronghan Chen,

Yang Cong

[pdf]

[bibtex]

@InProceedings{Ren_2023_CVPR, author = {Ren, Yu and Chen, Ronghan and Cong, Yang}, title = {Autonomous Manipulation Learning for Similar Deformable Objects via Only One Demonstration}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {17069-17078} }

Representation Learning for Visual Object Tracking by Masked Appearance Transfer

Haojie Zhao,

Dong Wang,

Huchuan Lu

[pdf] [supp]

[bibtex]

@InProceedings{Zhao_2023_CVPR, author = {Zhao, Haojie and Wang, Dong and Lu, Huchuan}, title = {Representation Learning for Visual Object Tracking by Masked Appearance Transfer}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {18696-18705} }

EFEM: Equivariant Neural Field Expectation Maximization for 3D Object Segmentation Without Scene Supervision

Jiahui Lei,

Congyue Deng,

Karl Schmeckpeper,

Leonidas Guibas,

Kostas Daniilidis

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Lei_2023_CVPR, author = {Lei, Jiahui and Deng, Congyue and Schmeckpeper, Karl and Guibas, Leonidas and Daniilidis, Kostas}, title = {EFEM: Equivariant Neural Field Expectation Maximization for 3D Object Segmentation Without Scene Supervision}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4902-4912} }

Learning To Name Classes for Vision and Language Models

Sarah Parisot,

Yongxin Yang,

Steven McDonagh

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Parisot_2023_CVPR, author = {Parisot, Sarah and Yang, Yongxin and McDonagh, Steven}, title = {Learning To Name Classes for Vision and Language Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {23477-23486} }

ECON: Explicit Clothed Humans Optimized via Normal Integration

Yuliang Xiu,

Jinlong Yang,

Xu Cao,

Dimitrios Tzionas,

Michael J. Black

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Xiu_2023_CVPR, author = {Xiu, Yuliang and Yang, Jinlong and Cao, Xu and Tzionas, Dimitrios and Black, Michael J.}, title = {ECON: Explicit Clothed Humans Optimized via Normal Integration}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {512-523} }

Neural Fourier Filter Bank

Zhijie Wu,

Yuhe Jin,

Kwang Moo Yi

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Wu_2023_CVPR, author = {Wu, Zhijie and Jin, Yuhe and Yi, Kwang Moo}, title = {Neural Fourier Filter Bank}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14153-14163} }

F2-NeRF: Fast Neural Radiance Field Training With Free Camera Trajectories

Peng Wang,

Yuan Liu,

Zhaoxi Chen,

Lingjie Liu,

Ziwei Liu,

Taku Komura,

Christian Theobalt,

Wenping Wang

[pdf] [supp]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Peng and Liu, Yuan and Chen, Zhaoxi and Liu, Lingjie and Liu, Ziwei and Komura, Taku and Theobalt, Christian and Wang, Wenping}, title = {F2-NeRF: Fast Neural Radiance Field Training With Free Camera Trajectories}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4150-4159} }

NeRFInvertor: High Fidelity NeRF-GAN Inversion for Single-Shot Real Image Animation

Yu Yin,

Kamran Ghasedi,

HsiangTao Wu,

Jiaolong Yang,

Xin Tong,

Yun Fu

[pdf] [arXiv]

[bibtex]

@InProceedings{Yin_2023_CVPR, author = {Yin, Yu and Ghasedi, Kamran and Wu, HsiangTao and Yang, Jiaolong and Tong, Xin and Fu, Yun}, title = {NeRFInvertor: High Fidelity NeRF-GAN Inversion for Single-Shot Real Image Animation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8539-8548} }

Learning To Detect and Segment for Open Vocabulary Object Detection

Tao Wang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Tao}, title = {Learning To Detect and Segment for Open Vocabulary Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7051-7060} }

Disentangling Writer and Character Styles for Handwriting Generation

Gang Dai,

Yifan Zhang,

Qingfeng Wang,

Qing Du,

Zhuliang Yu,

Zhuoman Liu,

Shuangping Huang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Dai_2023_CVPR, author = {Dai, Gang and Zhang, Yifan and Wang, Qingfeng and Du, Qing and Yu, Zhuliang and Liu, Zhuoman and Huang, Shuangping}, title = {Disentangling Writer and Character Styles for Handwriting Generation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5977-5986} }

Nighttime Smartphone Reflective Flare Removal Using Optical Center Symmetry Prior

Yuekun Dai,

Yihang Luo,

Shangchen Zhou,

Chongyi Li,

Chen Change Loy

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Dai_2023_CVPR, author = {Dai, Yuekun and Luo, Yihang and Zhou, Shangchen and Li, Chongyi and Loy, Chen Change}, title = {Nighttime Smartphone Reflective Flare Removal Using Optical Center Symmetry Prior}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {20783-20791} }

StyleSync: High-Fidelity Generalized and Personalized Lip Sync in Style-Based Generator

Jiazhi Guan,

Zhanwang Zhang,

Hang Zhou,

Tianshu Hu,

Kaisiyuan Wang,

Dongliang He,

Haocheng Feng,

Jingtuo Liu,

Errui Ding,

Ziwei Liu,

Jingdong Wang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Guan_2023_CVPR, author = {Guan, Jiazhi and Zhang, Zhanwang and Zhou, Hang and Hu, Tianshu and Wang, Kaisiyuan and He, Dongliang and Feng, Haocheng and Liu, Jingtuo and Ding, Errui and Liu, Ziwei and Wang, Jingdong}, title = {StyleSync: High-Fidelity Generalized and Personalized Lip Sync in Style-Based Generator}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1505-1515} }

Balanced Spherical Grid for Egocentric View Synthesis

Changwoon Choi,

Sang Min Kim,

Young Min Kim

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Choi_2023_CVPR, author = {Choi, Changwoon and Kim, Sang Min and Kim, Young Min}, title = {Balanced Spherical Grid for Egocentric View Synthesis}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16590-16599} }

Box-Level Active Detection

Mengyao Lyu,

Jundong Zhou,

Hui Chen,

Yijie Huang,

Dongdong Yu,

Yaqian Li,

Yandong Guo,

Yuchen Guo,

Liuyu Xiang,

Guiguang Ding

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Lyu_2023_CVPR, author = {Lyu, Mengyao and Zhou, Jundong and Chen, Hui and Huang, Yijie and Yu, Dongdong and Li, Yaqian and Guo, Yandong and Guo, Yuchen and Xiang, Liuyu and Ding, Guiguang}, title = {Box-Level Active Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {23766-23775} }

Coreset Sampling From Open-Set for Fine-Grained Self-Supervised Learning

Sungnyun Kim,

Sangmin Bae,

Se-Young Yun

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Kim_2023_CVPR, author = {Kim, Sungnyun and Bae, Sangmin and Yun, Se-Young}, title = {Coreset Sampling From Open-Set for Fine-Grained Self-Supervised Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7537-7547} }

Trace and Pace: Controllable Pedestrian Animation via Guided Trajectory Diffusion

Davis Rempe,

Zhengyi Luo,

Xue Bin Peng,

Ye Yuan,

Kris Kitani,

Karsten Kreis,

Sanja Fidler,

Or Litany

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Rempe_2023_CVPR, author = {Rempe, Davis and Luo, Zhengyi and Bin Peng, Xue and Yuan, Ye and Kitani, Kris and Kreis, Karsten and Fidler, Sanja and Litany, Or}, title = {Trace and Pace: Controllable Pedestrian Animation via Guided Trajectory Diffusion}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13756-13766} }

Overlooked Factors in Concept-Based Explanations: Dataset Choice, Concept Learnability, and Human Capability

Vikram V. Ramaswamy,

Sunnie S. Y. Kim,

Ruth Fong,

Olga Russakovsky

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Ramaswamy_2023_CVPR, author = {Ramaswamy, Vikram V. and Kim, Sunnie S. Y. and Fong, Ruth and Russakovsky, Olga}, title = {Overlooked Factors in Concept-Based Explanations: Dataset Choice, Concept Learnability, and Human Capability}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10932-10941} }

Unsupervised 3D Shape Reconstruction by Part Retrieval and Assembly

Xianghao Xu,

Paul Guerrero,

Matthew Fisher,

Siddhartha Chaudhuri,

Daniel Ritchie

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Xu_2023_CVPR, author = {Xu, Xianghao and Guerrero, Paul and Fisher, Matthew and Chaudhuri, Siddhartha and Ritchie, Daniel}, title = {Unsupervised 3D Shape Reconstruction by Part Retrieval and Assembly}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8559-8567} }

SeqTrack: Sequence to Sequence Learning for Visual Object Tracking

Xin Chen,

Houwen Peng,

Dong Wang,

Huchuan Lu,

Han Hu

[pdf] [arXiv]

[bibtex]

@InProceedings{Chen_2023_CVPR, author = {Chen, Xin and Peng, Houwen and Wang, Dong and Lu, Huchuan and Hu, Han}, title = {SeqTrack: Sequence to Sequence Learning for Visual Object Tracking}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14572-14581} }

Self-Supervised Non-Uniform Kernel Estimation With Flow-Based Motion Prior for Blind Image Deblurring

Zhenxuan Fang,

Fangfang Wu,

Weisheng Dong,

Xin Li,

Jinjian Wu,

Guangming Shi

[pdf] [supp]

[bibtex]

@InProceedings{Fang_2023_CVPR, author = {Fang, Zhenxuan and Wu, Fangfang and Dong, Weisheng and Li, Xin and Wu, Jinjian and Shi, Guangming}, title = {Self-Supervised Non-Uniform Kernel Estimation With Flow-Based Motion Prior for Blind Image Deblurring}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {18105-18114} }

AutoLabel: CLIP-Based Framework for Open-Set Video Domain Adaptation

Giacomo Zara,

Subhankar Roy,

Paolo Rota,

Elisa Ricci

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Zara_2023_CVPR, author = {Zara, Giacomo and Roy, Subhankar and Rota, Paolo and Ricci, Elisa}, title = {AutoLabel: CLIP-Based Framework for Open-Set Video Domain Adaptation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11504-11513} }

Generative Semantic Segmentation

Jiaqi Chen,

Jiachen Lu,

Xiatian Zhu,

Li Zhang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Chen_2023_CVPR, author = {Chen, Jiaqi and Lu, Jiachen and Zhu, Xiatian and Zhang, Li}, title = {Generative Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7111-7120} }

Instant-NVR: Instant Neural Volumetric Rendering for Human-Object Interactions From Monocular RGBD Stream

Yuheng Jiang,

Kaixin Yao,

Zhuo Su,

Zhehao Shen,

Haimin Luo,

Lan Xu

[pdf]

[bibtex]

@InProceedings{Jiang_2023_CVPR, author = {Jiang, Yuheng and Yao, Kaixin and Su, Zhuo and Shen, Zhehao and Luo, Haimin and Xu, Lan}, title = {Instant-NVR: Instant Neural Volumetric Rendering for Human-Object Interactions From Monocular RGBD Stream}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {595-605} }

Aligning Step-by-Step Instructional Diagrams to Video Demonstrations

Jiahao Zhang,

Anoop Cherian,

Yanbin Liu,

Yizhak Ben-Shabat,

Cristian Rodriguez,

Stephen Gould

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Zhang_2023_CVPR, author = {Zhang, Jiahao and Cherian, Anoop and Liu, Yanbin and Ben-Shabat, Yizhak and Rodriguez, Cristian and Gould, Stephen}, title = {Aligning Step-by-Step Instructional Diagrams to Video Demonstrations}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2483-2492} }

Collecting Cross-Modal Presence-Absence Evidence for Weakly-Supervised Audio-Visual Event Perception

Junyu Gao,

Mengyuan Chen,

Changsheng Xu

[pdf]

[bibtex]

@InProceedings{Gao_2023_CVPR, author = {Gao, Junyu and Chen, Mengyuan and Xu, Changsheng}, title = {Collecting Cross-Modal Presence-Absence Evidence for Weakly-Supervised Audio-Visual Event Perception}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {18827-18836} }

High-Fidelity and Freely Controllable Talking Head Video Generation

Yue Gao,

Yuan Zhou,

Jinglu Wang,

Xiao Li,

Xiang Ming,

Yan Lu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Gao_2023_CVPR, author = {Gao, Yue and Zhou, Yuan and Wang, Jinglu and Li, Xiao and Ming, Xiang and Lu, Yan}, title = {High-Fidelity and Freely Controllable Talking Head Video Generation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5609-5619} }

Q-DETR: An Efficient Low-Bit Quantized Detection Transformer

Sheng Xu,

Yanjing Li,

Mingbao Lin,

Peng Gao,

Guodong Guo,

Jinhu Lü,

Baochang Zhang

[pdf]

[bibtex]

@InProceedings{Xu_2023_CVPR, author = {Xu, Sheng and Li, Yanjing and Lin, Mingbao and Gao, Peng and Guo, Guodong and L\"u, Jinhu and Zhang, Baochang}, title = {Q-DETR: An Efficient Low-Bit Quantized Detection Transformer}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3842-3851} }

DINER: Depth-Aware Image-Based NEural Radiance Fields

Malte Prinzler,

Otmar Hilliges,

Justus Thies

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Prinzler_2023_CVPR, author = {Prinzler, Malte and Hilliges, Otmar and Thies, Justus}, title = {DINER: Depth-Aware Image-Based NEural Radiance Fields}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12449-12459} }

Burstormer: Burst Image Restoration and Enhancement Transformer

Akshay Dudhane,

Syed Waqas Zamir,

Salman Khan,

Fahad Shahbaz Khan,

Ming-Hsuan Yang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Dudhane_2023_CVPR, author = {Dudhane, Akshay and Zamir, Syed Waqas and Khan, Salman and Khan, Fahad Shahbaz and Yang, Ming-Hsuan}, title = {Burstormer: Burst Image Restoration and Enhancement Transformer}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5703-5712} }

Progressive Transformation Learning for Leveraging Virtual Images in Training

Yi-Ting Shen,

Hyungtae Lee,

Heesung Kwon,

Shuvra S. Bhattacharyya

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Shen_2023_CVPR, author = {Shen, Yi-Ting and Lee, Hyungtae and Kwon, Heesung and Bhattacharyya, Shuvra S.}, title = {Progressive Transformation Learning for Leveraging Virtual Images in Training}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {835-844} }

Co-Speech Gesture Synthesis by Reinforcement Learning With Contrastive Pre-Trained Rewards

Mingyang Sun,

Mengchen Zhao,

Yaqing Hou,

Minglei Li,

Huang Xu,

Songcen Xu,

Jianye Hao

[pdf]

[bibtex]

@InProceedings{Sun_2023_CVPR, author = {Sun, Mingyang and Zhao, Mengchen and Hou, Yaqing and Li, Minglei and Xu, Huang and Xu, Songcen and Hao, Jianye}, title = {Co-Speech Gesture Synthesis by Reinforcement Learning With Contrastive Pre-Trained Rewards}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2331-2340} }

Reconstructing Signing Avatars From Video Using Linguistic Priors

Maria-Paola Forte,

Peter Kulits,

Chun-Hao P. Huang,

Vasileios Choutas,

Dimitrios Tzionas,

Katherine J. Kuchenbecker,

Michael J. Black

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Forte_2023_CVPR, author = {Forte, Maria-Paola and Kulits, Peter and Huang, Chun-Hao P. and Choutas, Vasileios and Tzionas, Dimitrios and Kuchenbecker, Katherine J. and Black, Michael J.}, title = {Reconstructing Signing Avatars From Video Using Linguistic Priors}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12791-12801} }

DeepMapping2: Self-Supervised Large-Scale LiDAR Map Optimization

Chao Chen,

Xinhao Liu,

Yiming Li,

Li Ding,

Chen Feng

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Chen_2023_CVPR, author = {Chen, Chao and Liu, Xinhao and Li, Yiming and Ding, Li and Feng, Chen}, title = {DeepMapping2: Self-Supervised Large-Scale LiDAR Map Optimization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9306-9316} }

SDC-UDA: Volumetric Unsupervised Domain Adaptation Framework for Slice-Direction Continuous Cross-Modality Medical Image Segmentation

Hyungseob Shin,

Hyeongyu Kim,

Sewon Kim,

Yohan Jun,

Taejoon Eo,

Dosik Hwang

[pdf] [supp]

[bibtex]

@InProceedings{Shin_2023_CVPR, author = {Shin, Hyungseob and Kim, Hyeongyu and Kim, Sewon and Jun, Yohan and Eo, Taejoon and Hwang, Dosik}, title = {SDC-UDA: Volumetric Unsupervised Domain Adaptation Framework for Slice-Direction Continuous Cross-Modality Medical Image Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7412-7421} }

DoNet: Deep De-Overlapping Network for Cytology Instance Segmentation

Hao Jiang,

Rushan Zhang,

Yanning Zhou,

Yumeng Wang,

Hao Chen

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Jiang_2023_CVPR, author = {Jiang, Hao and Zhang, Rushan and Zhou, Yanning and Wang, Yumeng and Chen, Hao}, title = {DoNet: Deep De-Overlapping Network for Cytology Instance Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15641-15650} }

AVFace: Towards Detailed Audio-Visual 4D Face Reconstruction

Aggelina Chatziagapi,

Dimitris Samaras

[pdf] [arXiv]

[bibtex]

@InProceedings{Chatziagapi_2023_CVPR, author = {Chatziagapi, Aggelina and Samaras, Dimitris}, title = {AVFace: Towards Detailed Audio-Visual 4D Face Reconstruction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16878-16889} }

Divide and Conquer: Answering Questions With Object Factorization and Compositional Reasoning

Shi Chen,

Qi Zhao

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Chen_2023_CVPR, author = {Chen, Shi and Zhao, Qi}, title = {Divide and Conquer: Answering Questions With Object Factorization and Compositional Reasoning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6736-6745} }

Instant Domain Augmentation for LiDAR Semantic Segmentation

Kwonyoung Ryu,

Soonmin Hwang,

Jaesik Park

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Ryu_2023_CVPR, author = {Ryu, Kwonyoung and Hwang, Soonmin and Park, Jaesik}, title = {Instant Domain Augmentation for LiDAR Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9350-9360} }

A Characteristic Function-Based Method for Bottom-Up Human Pose Estimation

Haoxuan Qu,

Yujun Cai,

Lin Geng Foo,

Ajay Kumar,

Jun Liu

[pdf] [supp]

[bibtex]

@InProceedings{Qu_2023_CVPR, author = {Qu, Haoxuan and Cai, Yujun and Foo, Lin Geng and Kumar, Ajay and Liu, Jun}, title = {A Characteristic Function-Based Method for Bottom-Up Human Pose Estimation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13009-13018} }

SceneTrilogy: On Human Scene-Sketch and Its Complementarity With Photo and Text

Pinaki Nath Chowdhury,

Ayan Kumar Bhunia,

Aneeshan Sain,

Subhadeep Koley,

Tao Xiang,

Yi-Zhe Song

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Chowdhury_2023_CVPR, author = {Chowdhury, Pinaki Nath and Bhunia, Ayan Kumar and Sain, Aneeshan and Koley, Subhadeep and Xiang, Tao and Song, Yi-Zhe}, title = {SceneTrilogy: On Human Scene-Sketch and Its Complementarity With Photo and Text}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10972-10983} }

ERM-KTP: Knowledge-Level Machine Unlearning via Knowledge Transfer

Shen Lin,

Xiaoyu Zhang,

Chenyang Chen,

Xiaofeng Chen,

Willy Susilo

[pdf]

[bibtex]

@InProceedings{Lin_2023_CVPR, author = {Lin, Shen and Zhang, Xiaoyu and Chen, Chenyang and Chen, Xiaofeng and Susilo, Willy}, title = {ERM-KTP: Knowledge-Level Machine Unlearning via Knowledge Transfer}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {20147-20155} }

RefSR-NeRF: Towards High Fidelity and Super Resolution View Synthesis

Xudong Huang,

Wei Li,

Jie Hu,

Hanting Chen,

Yunhe Wang

[pdf] [supp]

[bibtex]

@InProceedings{Huang_2023_CVPR, author = {Huang, Xudong and Li, Wei and Hu, Jie and Chen, Hanting and Wang, Yunhe}, title = {RefSR-NeRF: Towards High Fidelity and Super Resolution View Synthesis}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8244-8253} }

DATE: Domain Adaptive Product Seeker for E-Commerce

Haoyuan Li,

Hao Jiang,

Tao Jin,

Mengyan Li,

Yan Chen,

Zhijie Lin,

Yang Zhao,

Zhou Zhao

[pdf]

[bibtex]

@InProceedings{Li_2023_CVPR, author = {Li, Haoyuan and Jiang, Hao and Jin, Tao and Li, Mengyan and Chen, Yan and Lin, Zhijie and Zhao, Yang and Zhao, Zhou}, title = {DATE: Domain Adaptive Product Seeker for E-Commerce}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {19315-19324} }

Polarimetric iToF: Measuring High-Fidelity Depth Through Scattering Media

Daniel S. Jeon,

Andréas Meuleman,

Seung-Hwan Baek,

Min H. Kim

[pdf] [supp]

[bibtex]

@InProceedings{Jeon_2023_CVPR, author = {Jeon, Daniel S. and Meuleman, Andr\'eas and Baek, Seung-Hwan and Kim, Min H.}, title = {Polarimetric iToF: Measuring High-Fidelity Depth Through Scattering Media}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12353-12362} }

Jedi: Entropy-Based Localization and Removal of Adversarial Patches

Bilel Tarchoun,

Anouar Ben Khalifa,

Mohamed Ali Mahjoub,

Nael Abu-Ghazaleh,

Ihsen Alouani

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Tarchoun_2023_CVPR, author = {Tarchoun, Bilel and Ben Khalifa, Anouar and Mahjoub, Mohamed Ali and Abu-Ghazaleh, Nael and Alouani, Ihsen}, title = {Jedi: Entropy-Based Localization and Removal of Adversarial Patches}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4087-4095} }

Localized Semantic Feature Mixers for Efficient Pedestrian Detection in Autonomous Driving

Abdul Hannan Khan,

Mohammed Shariq Nawaz,

Andreas Dengel

[pdf]

[bibtex]

@InProceedings{Khan_2023_CVPR, author = {Khan, Abdul Hannan and Nawaz, Mohammed Shariq and Dengel, Andreas}, title = {Localized Semantic Feature Mixers for Efficient Pedestrian Detection in Autonomous Driving}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5476-5485} }

Self-Supervised Super-Plane for Neural 3D Reconstruction

Botao Ye,

Sifei Liu,

Xueting Li,

Ming-Hsuan Yang

[pdf] [supp]

[bibtex]

@InProceedings{Ye_2023_CVPR, author = {Ye, Botao and Liu, Sifei and Li, Xueting and Yang, Ming-Hsuan}, title = {Self-Supervised Super-Plane for Neural 3D Reconstruction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {21415-21424} }

DisCo-CLIP: A Distributed Contrastive Loss for Memory Efficient CLIP Training

Yihao Chen,

Xianbiao Qi,

Jianan Wang,

Lei Zhang

[pdf] [supp]

[bibtex]

@InProceedings{Chen_2023_CVPR, author = {Chen, Yihao and Qi, Xianbiao and Wang, Jianan and Zhang, Lei}, title = {DisCo-CLIP: A Distributed Contrastive Loss for Memory Efficient CLIP Training}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {22648-22657} }

GM-NeRF: Learning Generalizable Model-Based Neural Radiance Fields From Multi-View Images

Jianchuan Chen,

Wentao Yi,

Liqian Ma,

Xu Jia,

Huchuan Lu

[pdf] [supp]

[bibtex]

@InProceedings{Chen_2023_CVPR, author = {Chen, Jianchuan and Yi, Wentao and Ma, Liqian and Jia, Xu and Lu, Huchuan}, title = {GM-NeRF: Learning Generalizable Model-Based Neural Radiance Fields From Multi-View Images}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {20648-20658} }

VDN-NeRF: Resolving Shape-Radiance Ambiguity via View-Dependence Normalization

Bingfan Zhu,

Yanchao Yang,

Xulong Wang,

Youyi Zheng,

Leonidas Guibas

[pdf] [supp]

[bibtex]

@InProceedings{Zhu_2023_CVPR, author = {Zhu, Bingfan and Yang, Yanchao and Wang, Xulong and Zheng, Youyi and Guibas, Leonidas}, title = {VDN-NeRF: Resolving Shape-Radiance Ambiguity via View-Dependence Normalization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {35-45} }

Mobile User Interface Element Detection via Adaptively Prompt Tuning

Zhangxuan Gu,

Zhuoer Xu,

Haoxing Chen,

Jun Lan,

Changhua Meng,

Weiqiang Wang

[pdf] [arXiv]

[bibtex]

@InProceedings{Gu_2023_CVPR, author = {Gu, Zhangxuan and Xu, Zhuoer and Chen, Haoxing and Lan, Jun and Meng, Changhua and Wang, Weiqiang}, title = {Mobile User Interface Element Detection via Adaptively Prompt Tuning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11155-11164} }

Perspective Fields for Single Image Camera Calibration

Linyi Jin,

Jianming Zhang,

Yannick Hold-Geoffroy,

Oliver Wang,

Kevin Blackburn-Matzen,

Matthew Sticha,

David F. Fouhey

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Jin_2023_CVPR, author = {Jin, Linyi and Zhang, Jianming and Hold-Geoffroy, Yannick and Wang, Oliver and Blackburn-Matzen, Kevin and Sticha, Matthew and Fouhey, David F.}, title = {Perspective Fields for Single Image Camera Calibration}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {17307-17316} }

Sparse Multi-Modal Graph Transformer With Shared-Context Processing for Representation Learning of Giga-Pixel Images

Ramin Nakhli,

Puria Azadi Moghadam,

Haoyang Mi,

Hossein Farahani,

Alexander Baras,

Blake Gilks,

Ali Bashashati

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Nakhli_2023_CVPR, author = {Nakhli, Ramin and Moghadam, Puria Azadi and Mi, Haoyang and Farahani, Hossein and Baras, Alexander and Gilks, Blake and Bashashati, Ali}, title = {Sparse Multi-Modal Graph Transformer With Shared-Context Processing for Representation Learning of Giga-Pixel Images}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11547-11557} }

Generating Human Motion From Textual Descriptions With Discrete Representations

Jianrong Zhang,

Yangsong Zhang,

Xiaodong Cun,

Yong Zhang,

Hongwei Zhao,

Hongtao Lu,

Xi Shen,

Ying Shan

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Zhang_2023_CVPR, author = {Zhang, Jianrong and Zhang, Yangsong and Cun, Xiaodong and Zhang, Yong and Zhao, Hongwei and Lu, Hongtao and Shen, Xi and Shan, Ying}, title = {Generating Human Motion From Textual Descriptions With Discrete Representations}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14730-14740} }

Spatial-Temporal Concept Based Explanation of 3D ConvNets

Ying Ji,

Yu Wang,

Jien Kato

[pdf] [arXiv]

[bibtex]

@InProceedings{Ji_2023_CVPR, author = {Ji, Ying and Wang, Yu and Kato, Jien}, title = {Spatial-Temporal Concept Based Explanation of 3D ConvNets}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15444-15453} }

Robust Test-Time Adaptation in Dynamic Scenarios

Longhui Yuan,

Binhui Xie,

Shuang Li

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Yuan_2023_CVPR, author = {Yuan, Longhui and Xie, Binhui and Li, Shuang}, title = {Robust Test-Time Adaptation in Dynamic Scenarios}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15922-15932} }

Global and Local Mixture Consistency Cumulative Learning for Long-Tailed Visual Recognitions

Fei Du,

Peng Yang,

Qi Jia,

Fengtao Nan,

Xiaoting Chen,

Yun Yang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Du_2023_CVPR, author = {Du, Fei and Yang, Peng and Jia, Qi and Nan, Fengtao and Chen, Xiaoting and Yang, Yun}, title = {Global and Local Mixture Consistency Cumulative Learning for Long-Tailed Visual Recognitions}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15814-15823} }

NIRVANA: Neural Implicit Representations of Videos With Adaptive Networks and Autoregressive Patch-Wise Modeling

Shishira R. Maiya,

Sharath Girish,

Max Ehrlich,

Hanyu Wang,

Kwot Sin Lee,

Patrick Poirson,

Pengxiang Wu,

Chen Wang,

Abhinav Shrivastava

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Maiya_2023_CVPR, author = {Maiya, Shishira R. and Girish, Sharath and Ehrlich, Max and Wang, Hanyu and Lee, Kwot Sin and Poirson, Patrick and Wu, Pengxiang and Wang, Chen and Shrivastava, Abhinav}, title = {NIRVANA: Neural Implicit Representations of Videos With Adaptive Networks and Autoregressive Patch-Wise Modeling}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14378-14387} }

Towards Accurate Image Coding: Improved Autoregressive Image Generation With Dynamic Vector Quantization

Mengqi Huang,

Zhendong Mao,

Zhuowei Chen,

Yongdong Zhang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Huang_2023_CVPR, author = {Huang, Mengqi and Mao, Zhendong and Chen, Zhuowei and Zhang, Yongdong}, title = {Towards Accurate Image Coding: Improved Autoregressive Image Generation With Dynamic Vector Quantization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {22596-22605} }

Coaching a Teachable Student

Jimuyang Zhang,

Zanming Huang,

Eshed Ohn-Bar

[pdf]

[bibtex]

@InProceedings{Zhang_2023_CVPR, author = {Zhang, Jimuyang and Huang, Zanming and Ohn-Bar, Eshed}, title = {Coaching a Teachable Student}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7805-7815} }

Collaboration Helps Camera Overtake LiDAR in 3D Detection

Yue Hu,

Yifan Lu,

Runsheng Xu,

Weidi Xie,

Siheng Chen,

Yanfeng Wang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Hu_2023_CVPR, author = {Hu, Yue and Lu, Yifan and Xu, Runsheng and Xie, Weidi and Chen, Siheng and Wang, Yanfeng}, title = {Collaboration Helps Camera Overtake LiDAR in 3D Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9243-9252} }

RealImpact: A Dataset of Impact Sound Fields for Real Objects

Samuel Clarke,

Ruohan Gao,

Mason Wang,

Mark Rau,

Julia Xu,

Jui-Hsien Wang,

Doug L. James,

Jiajun Wu

[pdf] [supp]

[bibtex]

@InProceedings{Clarke_2023_CVPR, author = {Clarke, Samuel and Gao, Ruohan and Wang, Mason and Rau, Mark and Xu, Julia and Wang, Jui-Hsien and James, Doug L. and Wu, Jiajun}, title = {RealImpact: A Dataset of Impact Sound Fields for Real Objects}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1516-1525} }

ReCo: Region-Controlled Text-to-Image Generation

Zhengyuan Yang,

Jianfeng Wang,

Zhe Gan,

Linjie Li,

Kevin Lin,

Chenfei Wu,

Nan Duan,

Zicheng Liu,

Ce Liu,

Michael Zeng,

Lijuan Wang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Yang_2023_CVPR, author = {Yang, Zhengyuan and Wang, Jianfeng and Gan, Zhe and Li, Linjie and Lin, Kevin and Wu, Chenfei and Duan, Nan and Liu, Zicheng and Liu, Ce and Zeng, Michael and Wang, Lijuan}, title = {ReCo: Region-Controlled Text-to-Image Generation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14246-14255} }

WINNER: Weakly-Supervised hIerarchical decompositioN and aligNment for Spatio-tEmporal Video gRounding

Mengze Li,

Han Wang,

Wenqiao Zhang,

Jiaxu Miao,

Zhou Zhao,

Shengyu Zhang,

Wei Ji,

Fei Wu

[pdf]

[bibtex]

@InProceedings{Li_2023_CVPR, author = {Li, Mengze and Wang, Han and Zhang, Wenqiao and Miao, Jiaxu and Zhao, Zhou and Zhang, Shengyu and Ji, Wei and Wu, Fei}, title = {WINNER: Weakly-Supervised hIerarchical decompositioN and aligNment for Spatio-tEmporal Video gRounding}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {23090-23099} }

Preserving Linear Separability in Continual Learning by Backward Feature Projection

Qiao Gu,

Dongsub Shim,

Florian Shkurti

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Gu_2023_CVPR, author = {Gu, Qiao and Shim, Dongsub and Shkurti, Florian}, title = {Preserving Linear Separability in Continual Learning by Backward Feature Projection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {24286-24295} }

MHPL: Minimum Happy Points Learning for Active Source Free Domain Adaptation

Fan Wang,

Zhongyi Han,

Zhiyan Zhang,

Rundong He,

Yilong Yin

[pdf] [supp]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Fan and Han, Zhongyi and Zhang, Zhiyan and He, Rundong and Yin, Yilong}, title = {MHPL: Minimum Happy Points Learning for Active Source Free Domain Adaptation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {20008-20018} }

Fix the Noise: Disentangling Source Feature for Controllable Domain Translation

Dongyeun Lee,

Jae Young Lee,

Doyeon Kim,

Jaehyun Choi,

Jaejun Yoo,

Junmo Kim

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Lee_2023_CVPR, author = {Lee, Dongyeun and Lee, Jae Young and Kim, Doyeon and Choi, Jaehyun and Yoo, Jaejun and Kim, Junmo}, title = {Fix the Noise: Disentangling Source Feature for Controllable Domain Translation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14224-14234} }

Metadata-Based RAW Reconstruction via Implicit Neural Functions

Leyi Li,

Huijie Qiao,

Qi Ye,

Qinmin Yang

[pdf] [supp]

[bibtex]

@InProceedings{Li_2023_CVPR, author = {Li, Leyi and Qiao, Huijie and Ye, Qi and Yang, Qinmin}, title = {Metadata-Based RAW Reconstruction via Implicit Neural Functions}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {18196-18205} }

Uni-Perceiver v2: A Generalist Model for Large-Scale Vision and Vision-Language Tasks

Hao Li,

Jinguo Zhu,

Xiaohu Jiang,

Xizhou Zhu,

Hongsheng Li,

Chun Yuan,

Xiaohua Wang,

Yu Qiao,

Xiaogang Wang,

Wenhai Wang,

Jifeng Dai

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Li_2023_CVPR, author = {Li, Hao and Zhu, Jinguo and Jiang, Xiaohu and Zhu, Xizhou and Li, Hongsheng and Yuan, Chun and Wang, Xiaohua and Qiao, Yu and Wang, Xiaogang and Wang, Wenhai and Dai, Jifeng}, title = {Uni-Perceiver v2: A Generalist Model for Large-Scale Vision and Vision-Language Tasks}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2691-2700} }

Sparsely Annotated Semantic Segmentation With Adaptive Gaussian Mixtures

Linshan Wu,

Zhun Zhong,

Leyuan Fang,

Xingxin He,

Qiang Liu,

Jiayi Ma,

Hao Chen

[pdf] [supp]

[bibtex]

@InProceedings{Wu_2023_CVPR, author = {Wu, Linshan and Zhong, Zhun and Fang, Leyuan and He, Xingxin and Liu, Qiang and Ma, Jiayi and Chen, Hao}, title = {Sparsely Annotated Semantic Segmentation With Adaptive Gaussian Mixtures}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15454-15464} }

Multimodality Helps Unimodality: Cross-Modal Few-Shot Learning With Multimodal Models

Zhiqiu Lin,

Samuel Yu,

Zhiyi Kuang,

Deepak Pathak,

Deva Ramanan

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Lin_2023_CVPR, author = {Lin, Zhiqiu and Yu, Samuel and Kuang, Zhiyi and Pathak, Deepak and Ramanan, Deva}, title = {Multimodality Helps Unimodality: Cross-Modal Few-Shot Learning With Multimodal Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {19325-19337} }

Decompose More and Aggregate Better: Two Closer Looks at Frequency Representation Learning for Human Motion Prediction

Xuehao Gao,

Shaoyi Du,

Yang Wu,

Yang Yang

[pdf] [supp]

[bibtex]

@InProceedings{Gao_2023_CVPR, author = {Gao, Xuehao and Du, Shaoyi and Wu, Yang and Yang, Yang}, title = {Decompose More and Aggregate Better: Two Closer Looks at Frequency Representation Learning for Human Motion Prediction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6451-6460} }

Diversity-Aware Meta Visual Prompting

Qidong Huang,

Xiaoyi Dong,

Dongdong Chen,

Weiming Zhang,

Feifei Wang,

Gang Hua,

Nenghai Yu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Huang_2023_CVPR, author = {Huang, Qidong and Dong, Xiaoyi and Chen, Dongdong and Zhang, Weiming and Wang, Feifei and Hua, Gang and Yu, Nenghai}, title = {Diversity-Aware Meta Visual Prompting}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10878-10887} }

Affection: Learning Affective Explanations for Real-World Visual Data

Panos Achlioptas,

Maks Ovsjanikov,

Leonidas Guibas,

Sergey Tulyakov

[pdf] [arXiv]

[bibtex]

@InProceedings{Achlioptas_2023_CVPR, author = {Achlioptas, Panos and Ovsjanikov, Maks and Guibas, Leonidas and Tulyakov, Sergey}, title = {Affection: Learning Affective Explanations for Real-World Visual Data}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6641-6651} }

3D Highlighter: Localizing Regions on 3D Shapes via Text Descriptions

Dale Decatur,

Itai Lang,

Rana Hanocka

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Decatur_2023_CVPR, author = {Decatur, Dale and Lang, Itai and Hanocka, Rana}, title = {3D Highlighter: Localizing Regions on 3D Shapes via Text Descriptions}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {20930-20939} }

Iterative Geometry Encoding Volume for Stereo Matching

Gangwei Xu,

Xianqi Wang,

Xiaohuan Ding,

Xin Yang

[pdf] [arXiv]

[bibtex]

@InProceedings{Xu_2023_CVPR, author = {Xu, Gangwei and Wang, Xianqi and Ding, Xiaohuan and Yang, Xin}, title = {Iterative Geometry Encoding Volume for Stereo Matching}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {21919-21928} }

PLA: Language-Driven Open-Vocabulary 3D Scene Understanding

Runyu Ding,

Jihan Yang,

Chuhui Xue,

Wenqing Zhang,

Song Bai,

Xiaojuan Qi

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Ding_2023_CVPR, author = {Ding, Runyu and Yang, Jihan and Xue, Chuhui and Zhang, Wenqing and Bai, Song and Qi, Xiaojuan}, title = {PLA: Language-Driven Open-Vocabulary 3D Scene Understanding}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7010-7019} }

FaceLit: Neural 3D Relightable Faces

Anurag Ranjan,

Kwang Moo Yi,

Jen-Hao Rick Chang,

Oncel Tuzel

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Ranjan_2023_CVPR, author = {Ranjan, Anurag and Yi, Kwang Moo and Chang, Jen-Hao Rick and Tuzel, Oncel}, title = {FaceLit: Neural 3D Relightable Faces}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8619-8628} }

Visual Programming: Compositional Visual Reasoning Without Training

Tanmay Gupta,

Aniruddha Kembhavi

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Gupta_2023_CVPR, author = {Gupta, Tanmay and Kembhavi, Aniruddha}, title = {Visual Programming: Compositional Visual Reasoning Without Training}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14953-14962} }

InstMove: Instance Motion for Object-Centric Video Segmentation

Qihao Liu,

Junfeng Wu,

Yi Jiang,

Xiang Bai,

Alan L. Yuille,

Song Bai

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Liu_2023_CVPR, author = {Liu, Qihao and Wu, Junfeng and Jiang, Yi and Bai, Xiang and Yuille, Alan L. and Bai, Song}, title = {InstMove: Instance Motion for Object-Centric Video Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6344-6354} }

Real-Time Evaluation in Online Continual Learning: A New Hope

Yasir Ghunaim,

Adel Bibi,

Kumail Alhamoud,

Motasem Alfarra,

Hasan Abed Al Kader Hammoud,

Ameya Prabhu,

Philip H.S. Torr,

Bernard Ghanem

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Ghunaim_2023_CVPR, author = {Ghunaim, Yasir and Bibi, Adel and Alhamoud, Kumail and Alfarra, Motasem and Al Kader Hammoud, Hasan Abed and Prabhu, Ameya and Torr, Philip H.S. and Ghanem, Bernard}, title = {Real-Time Evaluation in Online Continual Learning: A New Hope}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11888-11897} }

GRES: Generalized Referring Expression Segmentation

Chang Liu,

Henghui Ding,

Xudong Jiang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Liu_2023_CVPR, author = {Liu, Chang and Ding, Henghui and Jiang, Xudong}, title = {GRES: Generalized Referring Expression Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {23592-23601} }

Towards Effective Adversarial Textured 3D Meshes on Physical Face Recognition

Xiao Yang,

Chang Liu,

Longlong Xu,

Yikai Wang,

Yinpeng Dong,

Ning Chen,

Hang Su,

Jun Zhu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Yang_2023_CVPR, author = {Yang, Xiao and Liu, Chang and Xu, Longlong and Wang, Yikai and Dong, Yinpeng and Chen, Ning and Su, Hang and Zhu, Jun}, title = {Towards Effective Adversarial Textured 3D Meshes on Physical Face Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4119-4128} }

BAAM: Monocular 3D Pose and Shape Reconstruction With Bi-Contextual Attention Module and Attention-Guided Modeling

Hyo-Jun Lee,

Hanul Kim,

Su-Min Choi,

Seong-Gyun Jeong,

Yeong Jun Koh

[pdf] [supp]

[bibtex]

@InProceedings{Lee_2023_CVPR, author = {Lee, Hyo-Jun and Kim, Hanul and Choi, Su-Min and Jeong, Seong-Gyun and Koh, Yeong Jun}, title = {BAAM: Monocular 3D Pose and Shape Reconstruction With Bi-Contextual Attention Module and Attention-Guided Modeling}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9011-9020} }

Freestyle Layout-to-Image Synthesis

Han Xue,

Zhiwu Huang,

Qianru Sun,

Li Song,

Wenjun Zhang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Xue_2023_CVPR, author = {Xue, Han and Huang, Zhiwu and Sun, Qianru and Song, Li and Zhang, Wenjun}, title = {Freestyle Layout-to-Image Synthesis}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14256-14266} }

Effective Ambiguity Attack Against Passport-Based DNN Intellectual Property Protection Schemes Through Fully Connected Layer Substitution

Yiming Chen,

Jinyu Tian,

Xiangyu Chen,

Jiantao Zhou

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Chen_2023_CVPR, author = {Chen, Yiming and Tian, Jinyu and Chen, Xiangyu and Zhou, Jiantao}, title = {Effective Ambiguity Attack Against Passport-Based DNN Intellectual Property Protection Schemes Through Fully Connected Layer Substitution}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8123-8132} }

Visual Dependency Transformers: Dependency Tree Emerges From Reversed Attention

Mingyu Ding,

Yikang Shen,

Lijie Fan,

Zhenfang Chen,

Zitian Chen,

Ping Luo,

Joshua B. Tenenbaum,

Chuang Gan

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Ding_2023_CVPR, author = {Ding, Mingyu and Shen, Yikang and Fan, Lijie and Chen, Zhenfang and Chen, Zitian and Luo, Ping and Tenenbaum, Joshua B. and Gan, Chuang}, title = {Visual Dependency Transformers: Dependency Tree Emerges From Reversed Attention}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14528-14539} }

Differentiable Architecture Search With Random Features

Xuanyang Zhang,

Yonggang Li,

Xiangyu Zhang,

Yongtao Wang,

Jian Sun

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Zhang_2023_CVPR, author = {Zhang, Xuanyang and Li, Yonggang and Zhang, Xiangyu and Wang, Yongtao and Sun, Jian}, title = {Differentiable Architecture Search With Random Features}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16060-16069} }

Open-Set Fine-Grained Retrieval via Prompting Vision-Language Evaluator

Shijie Wang,

Jianlong Chang,

Haojie Li,

Zhihui Wang,

Wanli Ouyang,

Qi Tian

[pdf]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Shijie and Chang, Jianlong and Li, Haojie and Wang, Zhihui and Ouyang, Wanli and Tian, Qi}, title = {Open-Set Fine-Grained Retrieval via Prompting Vision-Language Evaluator}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {19381-19391} }

Sibling-Attack: Rethinking Transferable Adversarial Attacks Against Face Recognition

Zexin Li,

Bangjie Yin,

Taiping Yao,

Junfeng Guo,

Shouhong Ding,

Simin Chen,

Cong Liu

[pdf] [supp]

[bibtex]

@InProceedings{Li_2023_CVPR, author = {Li, Zexin and Yin, Bangjie and Yao, Taiping and Guo, Junfeng and Ding, Shouhong and Chen, Simin and Liu, Cong}, title = {Sibling-Attack: Rethinking Transferable Adversarial Attacks Against Face Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {24626-24637} }

Enhanced Stable View Synthesis

Nishant Jain,

Suryansh Kumar,

Luc Van Gool

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Jain_2023_CVPR, author = {Jain, Nishant and Kumar, Suryansh and Van Gool, Luc}, title = {Enhanced Stable View Synthesis}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13208-13217} }

Breaching FedMD: Image Recovery via Paired-Logits Inversion Attack

Hideaki Takahashi,

Jingjing Liu,

Yang Liu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Takahashi_2023_CVPR, author = {Takahashi, Hideaki and Liu, Jingjing and Liu, Yang}, title = {Breaching FedMD: Image Recovery via Paired-Logits Inversion Attack}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12198-12207} }

TempSAL - Uncovering Temporal Information for Deep Saliency Prediction

Bahar Aydemir,

Ludo Hoffstetter,

Tong Zhang,

Mathieu Salzmann,

Sabine Süsstrunk

[pdf] [supp]

[bibtex]

@InProceedings{Aydemir_2023_CVPR, author = {Aydemir, Bahar and Hoffstetter, Ludo and Zhang, Tong and Salzmann, Mathieu and S\"usstrunk, Sabine}, title = {TempSAL - Uncovering Temporal Information for Deep Saliency Prediction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6461-6470} }

Biomechanics-Guided Facial Action Unit Detection Through Force Modeling

Zijun Cui,

Chenyi Kuang,

Tian Gao,

Kartik Talamadupula,

Qiang Ji

[pdf] [supp]

[bibtex]

@InProceedings{Cui_2023_CVPR, author = {Cui, Zijun and Kuang, Chenyi and Gao, Tian and Talamadupula, Kartik and Ji, Qiang}, title = {Biomechanics-Guided Facial Action Unit Detection Through Force Modeling}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8694-8703} }

Equiangular Basis Vectors

Yang Shen,

Xuhao Sun,

Xiu-Shen Wei

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Shen_2023_CVPR, author = {Shen, Yang and Sun, Xuhao and Wei, Xiu-Shen}, title = {Equiangular Basis Vectors}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11755-11765} }

PIRLNav: Pretraining With Imitation and RL Finetuning for ObjectNav

Ram Ramrakhya,

Dhruv Batra,

Erik Wijmans,

Abhishek Das

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Ramrakhya_2023_CVPR, author = {Ramrakhya, Ram and Batra, Dhruv and Wijmans, Erik and Das, Abhishek}, title = {PIRLNav: Pretraining With Imitation and RL Finetuning for ObjectNav}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {17896-17906} }

Megahertz Light Steering Without Moving Parts

Adithya Pediredla,

Srinivasa G. Narasimhan,

Maysamreza Chamanzar,

Ioannis Gkioulekas

[pdf] [supp]

[bibtex]

@InProceedings{Pediredla_2023_CVPR, author = {Pediredla, Adithya and Narasimhan, Srinivasa G. and Chamanzar, Maysamreza and Gkioulekas, Ioannis}, title = {Megahertz Light Steering Without Moving Parts}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1-12} }

Iterative Proposal Refinement for Weakly-Supervised Video Grounding

Meng Cao,

Fangyun Wei,

Can Xu,

Xiubo Geng,

Long Chen,

Can Zhang,

Yuexian Zou,

Tao Shen,

Daxin Jiang

[pdf] [supp]

[bibtex]

@InProceedings{Cao_2023_CVPR, author = {Cao, Meng and Wei, Fangyun and Xu, Can and Geng, Xiubo and Chen, Long and Zhang, Can and Zou, Yuexian and Shen, Tao and Jiang, Daxin}, title = {Iterative Proposal Refinement for Weakly-Supervised Video Grounding}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6524-6534} }

SCConv: Spatial and Channel Reconstruction Convolution for Feature Redundancy

Jiafeng Li,

Ying Wen,

Lianghua He

[pdf]

[bibtex]

@InProceedings{Li_2023_CVPR, author = {Li, Jiafeng and Wen, Ying and He, Lianghua}, title = {SCConv: Spatial and Channel Reconstruction Convolution for Feature Redundancy}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6153-6162} }

StyleGene: Crossover and Mutation of Region-Level Facial Genes for Kinship Face Synthesis

Hao Li,

Xianxu Hou,

Zepeng Huang,

Linlin Shen

[pdf] [supp]

[bibtex]

@InProceedings{Li_2023_CVPR, author = {Li, Hao and Hou, Xianxu and Huang, Zepeng and Shen, Linlin}, title = {StyleGene: Crossover and Mutation of Region-Level Facial Genes for Kinship Face Synthesis}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {20960-20969} }

Clothed Human Performance Capture With a Double-Layer Neural Radiance Fields

Kangkan Wang,

Guofeng Zhang,

Suxu Cong,

Jian Yang

[pdf] [supp]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Kangkan and Zhang, Guofeng and Cong, Suxu and Yang, Jian}, title = {Clothed Human Performance Capture With a Double-Layer Neural Radiance Fields}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {21098-21107} }

NeuFace: Realistic 3D Neural Face Rendering From Multi-View Images

Mingwu Zheng,

Haiyu Zhang,

Hongyu Yang,

Di Huang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Zheng_2023_CVPR, author = {Zheng, Mingwu and Zhang, Haiyu and Yang, Hongyu and Huang, Di}, title = {NeuFace: Realistic 3D Neural Face Rendering From Multi-View Images}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16868-16877} }

Cross-Guided Optimization of Radiance Fields With Multi-View Image Super-Resolution for High-Resolution Novel View Synthesis

Youngho Yoon,

Kuk-Jin Yoon

[pdf] [supp]

[bibtex]

@InProceedings{Yoon_2023_CVPR, author = {Yoon, Youngho and Yoon, Kuk-Jin}, title = {Cross-Guided Optimization of Radiance Fields With Multi-View Image Super-Resolution for High-Resolution Novel View Synthesis}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12428-12438} }

Unified Pose Sequence Modeling

Lin Geng Foo,

Tianjiao Li,

Hossein Rahmani,

Qiuhong Ke,

Jun Liu

[pdf]

[bibtex]

@InProceedings{Foo_2023_CVPR, author = {Foo, Lin Geng and Li, Tianjiao and Rahmani, Hossein and Ke, Qiuhong and Liu, Jun}, title = {Unified Pose Sequence Modeling}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13019-13030} }

Probability-Based Global Cross-Modal Upsampling for Pansharpening

Zeyu Zhu,

Xiangyong Cao,

Man Zhou,

Junhao Huang,

Deyu Meng

[pdf] [arXiv]

[bibtex]

@InProceedings{Zhu_2023_CVPR, author = {Zhu, Zeyu and Cao, Xiangyong and Zhou, Man and Huang, Junhao and Meng, Deyu}, title = {Probability-Based Global Cross-Modal Upsampling for Pansharpening}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14039-14048} }

Positive-Augmented Contrastive Learning for Image and Video Captioning Evaluation

Sara Sarto,

Manuele Barraco,

Marcella Cornia,

Lorenzo Baraldi,

Rita Cucchiara

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Sarto_2023_CVPR, author = {Sarto, Sara and Barraco, Manuele and Cornia, Marcella and Baraldi, Lorenzo and Cucchiara, Rita}, title = {Positive-Augmented Contrastive Learning for Image and Video Captioning Evaluation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6914-6924} }

Rethinking Domain Generalization for Face Anti-Spoofing: Separability and Alignment

Yiyou Sun,

Yaojie Liu,

Xiaoming Liu,

Yixuan Li,

Wen-Sheng Chu

[pdf] [supp]

[bibtex]

@InProceedings{Sun_2023_CVPR, author = {Sun, Yiyou and Liu, Yaojie and Liu, Xiaoming and Li, Yixuan and Chu, Wen-Sheng}, title = {Rethinking Domain Generalization for Face Anti-Spoofing: Separability and Alignment}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {24563-24574} }

SMOC-Net: Leveraging Camera Pose for Self-Supervised Monocular Object Pose Estimation

Tao Tan,

Qiulei Dong

[pdf]

[bibtex]

@InProceedings{Tan_2023_CVPR, author = {Tan, Tao and Dong, Qiulei}, title = {SMOC-Net: Leveraging Camera Pose for Self-Supervised Monocular Object Pose Estimation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {21307-21316} }

FAC: 3D Representation Learning via Foreground Aware Feature Contrast

Kangcheng Liu,

Aoran Xiao,

Xiaoqin Zhang,

Shijian Lu,

Ling Shao

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Liu_2023_CVPR, author = {Liu, Kangcheng and Xiao, Aoran and Zhang, Xiaoqin and Lu, Shijian and Shao, Ling}, title = {FAC: 3D Representation Learning via Foreground Aware Feature Contrast}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9476-9485} }

Improving Visual Representation Learning Through Perceptual Understanding

Samyakh Tukra,

Frederick Hoffman,

Ken Chatfield

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Tukra_2023_CVPR, author = {Tukra, Samyakh and Hoffman, Frederick and Chatfield, Ken}, title = {Improving Visual Representation Learning Through Perceptual Understanding}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14486-14495} }

3D Cinemagraphy From a Single Image

Xingyi Li,

Zhiguo Cao,

Huiqiang Sun,

Jianming Zhang,

Ke Xian,

Guosheng Lin

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Li_2023_CVPR, author = {Li, Xingyi and Cao, Zhiguo and Sun, Huiqiang and Zhang, Jianming and Xian, Ke and Lin, Guosheng}, title = {3D Cinemagraphy From a Single Image}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4595-4605} }

Learning Bottleneck Concepts in Image Classification

Bowen Wang,

Liangzhi Li,

Yuta Nakashima,

Hajime Nagahara

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Bowen and Li, Liangzhi and Nakashima, Yuta and Nagahara, Hajime}, title = {Learning Bottleneck Concepts in Image Classification}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10962-10971} }

Inversion-Based Style Transfer With Diffusion Models

Yuxin Zhang,

Nisha Huang,

Fan Tang,

Haibin Huang,

Chongyang Ma,

Weiming Dong,

Changsheng Xu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Zhang_2023_CVPR, author = {Zhang, Yuxin and Huang, Nisha and Tang, Fan and Huang, Haibin and Ma, Chongyang and Dong, Weiming and Xu, Changsheng}, title = {Inversion-Based Style Transfer With Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10146-10156} }

Learning Human Mesh Recovery in 3D Scenes

Zehong Shen,

Zhi Cen,

Sida Peng,

Qing Shuai,

Hujun Bao,

Xiaowei Zhou

[pdf]

[bibtex]

@InProceedings{Shen_2023_CVPR, author = {Shen, Zehong and Cen, Zhi and Peng, Sida and Shuai, Qing and Bao, Hujun and Zhou, Xiaowei}, title = {Learning Human Mesh Recovery in 3D Scenes}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {17038-17047} }

Learning Locally Editable Virtual Humans

Hsuan-I Ho,

Lixin Xue,

Jie Song,

Otmar Hilliges

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Ho_2023_CVPR, author = {Ho, Hsuan-I and Xue, Lixin and Song, Jie and Hilliges, Otmar}, title = {Learning Locally Editable Virtual Humans}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {21024-21035} }

Learning Imbalanced Data With Vision Transformers

Zhengzhuo Xu,

Ruikang Liu,

Shuo Yang,

Zenghao Chai,

Chun Yuan

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Xu_2023_CVPR, author = {Xu, Zhengzhuo and Liu, Ruikang and Yang, Shuo and Chai, Zenghao and Yuan, Chun}, title = {Learning Imbalanced Data With Vision Transformers}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15793-15803} }

AttriCLIP: A Non-Incremental Learner for Incremental Knowledge Learning

Runqi Wang,

Xiaoyue Duan,

Guoliang Kang,

Jianzhuang Liu,

Shaohui Lin,

Songcen Xu,

Jinhu Lü,

Baochang Zhang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Runqi and Duan, Xiaoyue and Kang, Guoliang and Liu, Jianzhuang and Lin, Shaohui and Xu, Songcen and L\"u, Jinhu and Zhang, Baochang}, title = {AttriCLIP: A Non-Incremental Learner for Incremental Knowledge Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3654-3663} }

PHA: Patch-Wise High-Frequency Augmentation for Transformer-Based Person Re-Identification

Guiwei Zhang,

Yongfei Zhang,

Tianyu Zhang,

Bo Li,

Shiliang Pu

[pdf]

[bibtex]

@InProceedings{Zhang_2023_CVPR, author = {Zhang, Guiwei and Zhang, Yongfei and Zhang, Tianyu and Li, Bo and Pu, Shiliang}, title = {PHA: Patch-Wise High-Frequency Augmentation for Transformer-Based Person Re-Identification}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14133-14142} }

StyleRes: Transforming the Residuals for Real Image Editing With StyleGAN

Hamza Pehlivan,

Yusuf Dalva,

Aysegul Dundar

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Pehlivan_2023_CVPR, author = {Pehlivan, Hamza and Dalva, Yusuf and Dundar, Aysegul}, title = {StyleRes: Transforming the Residuals for Real Image Editing With StyleGAN}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1828-1837} }

Diffusion Video Autoencoders: Toward Temporally Consistent Face Video Editing via Disentangled Video Encoding

Gyeongman Kim,

Hajin Shim,

Hyunsu Kim,

Yunjey Choi,

Junho Kim,

Eunho Yang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Kim_2023_CVPR, author = {Kim, Gyeongman and Shim, Hajin and Kim, Hyunsu and Choi, Yunjey and Kim, Junho and Yang, Eunho}, title = {Diffusion Video Autoencoders: Toward Temporally Consistent Face Video Editing via Disentangled Video Encoding}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6091-6100} }

Learning Instance-Level Representation for Large-Scale Multi-Modal Pretraining in E-Commerce

Yang Jin,

Yongzhi Li,

Zehuan Yuan,

Yadong Mu

[pdf] [supp]

[bibtex]

@InProceedings{Jin_2023_CVPR, author = {Jin, Yang and Li, Yongzhi and Yuan, Zehuan and Mu, Yadong}, title = {Learning Instance-Level Representation for Large-Scale Multi-Modal Pretraining in E-Commerce}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11060-11069} }

Conditional Text Image Generation With Diffusion Models

Yuanzhi Zhu,

Zhaohai Li,

Tianwei Wang,

Mengchao He,

Cong Yao

[pdf]

[bibtex]

@InProceedings{Zhu_2023_CVPR, author = {Zhu, Yuanzhi and Li, Zhaohai and Wang, Tianwei and He, Mengchao and Yao, Cong}, title = {Conditional Text Image Generation With Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14235-14245} }

AnchorFormer: Point Cloud Completion From Discriminative Nodes

Zhikai Chen,

Fuchen Long,

Zhaofan Qiu,

Ting Yao,

Wengang Zhou,

Jiebo Luo,

Tao Mei

[pdf]

[bibtex]

@InProceedings{Chen_2023_CVPR, author = {Chen, Zhikai and Long, Fuchen and Qiu, Zhaofan and Yao, Ting and Zhou, Wengang and Luo, Jiebo and Mei, Tao}, title = {AnchorFormer: Point Cloud Completion From Discriminative Nodes}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13581-13590} }

Co-SLAM: Joint Coordinate and Sparse Parametric Encodings for Neural Real-Time SLAM

Hengyi Wang,

Jingwen Wang,

Lourdes Agapito

[pdf] [supp]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Hengyi and Wang, Jingwen and Agapito, Lourdes}, title = {Co-SLAM: Joint Coordinate and Sparse Parametric Encodings for Neural Real-Time SLAM}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13293-13302} }

SIM: Semantic-Aware Instance Mask Generation for Box-Supervised Instance Segmentation

Ruihuang Li,

Chenhang He,

Yabin Zhang,

Shuai Li,

Liyi Chen,

Lei Zhang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Li_2023_CVPR, author = {Li, Ruihuang and He, Chenhang and Zhang, Yabin and Li, Shuai and Chen, Liyi and Zhang, Lei}, title = {SIM: Semantic-Aware Instance Mask Generation for Box-Supervised Instance Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7193-7203} }

Compression-Aware Video Super-Resolution

Yingwei Wang,

Takashi Isobe,

Xu Jia,

Xin Tao,

Huchuan Lu,

Yu-Wing Tai

[pdf]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Yingwei and Isobe, Takashi and Jia, Xu and Tao, Xin and Lu, Huchuan and Tai, Yu-Wing}, title = {Compression-Aware Video Super-Resolution}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2012-2021} }

PillarNeXt: Rethinking Network Designs for 3D Object Detection in LiDAR Point Clouds

Jinyu Li,

Chenxu Luo,

Xiaodong Yang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Li_2023_CVPR, author = {Li, Jinyu and Luo, Chenxu and Yang, Xiaodong}, title = {PillarNeXt: Rethinking Network Designs for 3D Object Detection in LiDAR Point Clouds}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {17567-17576} }

Regularization of Polynomial Networks for Image Recognition

Grigorios G. Chrysos,

Bohan Wang,

Jiankang Deng,

Volkan Cevher

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Chrysos_2023_CVPR, author = {Chrysos, Grigorios G. and Wang, Bohan and Deng, Jiankang and Cevher, Volkan}, title = {Regularization of Polynomial Networks for Image Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16123-16132} }

Incremental 3D Semantic Scene Graph Prediction From RGB Sequences

Shun-Cheng Wu,

Keisuke Tateno,

Nassir Navab,

Federico Tombari

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Wu_2023_CVPR, author = {Wu, Shun-Cheng and Tateno, Keisuke and Navab, Nassir and Tombari, Federico}, title = {Incremental 3D Semantic Scene Graph Prediction From RGB Sequences}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5064-5074} }

EfficientViT: Memory Efficient Vision Transformer With Cascaded Group Attention

Xinyu Liu,

Houwen Peng,

Ningxin Zheng,

Yuqing Yang,

Han Hu,

Yixuan Yuan

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Liu_2023_CVPR, author = {Liu, Xinyu and Peng, Houwen and Zheng, Ningxin and Yang, Yuqing and Hu, Han and Yuan, Yixuan}, title = {EfficientViT: Memory Efficient Vision Transformer With Cascaded Group Attention}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14420-14430} }

VLPD: Context-Aware Pedestrian Detection via Vision-Language Semantic Self-Supervision

Mengyin Liu,

Jie Jiang,

Chao Zhu,

Xu-Cheng Yin

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Liu_2023_CVPR, author = {Liu, Mengyin and Jiang, Jie and Zhu, Chao and Yin, Xu-Cheng}, title = {VLPD: Context-Aware Pedestrian Detection via Vision-Language Semantic Self-Supervision}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6662-6671} }

TexPose: Neural Texture Learning for Self-Supervised 6D Object Pose Estimation

Hanzhi Chen,

Fabian Manhardt,

Nassir Navab,

Benjamin Busam

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Chen_2023_CVPR, author = {Chen, Hanzhi and Manhardt, Fabian and Navab, Nassir and Busam, Benjamin}, title = {TexPose: Neural Texture Learning for Self-Supervised 6D Object Pose Estimation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4841-4852} }

LINe: Out-of-Distribution Detection by Leveraging Important Neurons

Yong Hyun Ahn,

Gyeong-Moon Park,

Seong Tae Kim

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Ahn_2023_CVPR, author = {Ahn, Yong Hyun and Park, Gyeong-Moon and Kim, Seong Tae}, title = {LINe: Out-of-Distribution Detection by Leveraging Important Neurons}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {19852-19862} }

DynIBaR: Neural Dynamic Image-Based Rendering

Zhengqi Li,

Qianqian Wang,

Forrester Cole,

Richard Tucker,

Noah Snavely

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Li_2023_CVPR, author = {Li, Zhengqi and Wang, Qianqian and Cole, Forrester and Tucker, Richard and Snavely, Noah}, title = {DynIBaR: Neural Dynamic Image-Based Rendering}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4273-4284} }

Unsupervised Object Localization: Observing the Background To Discover Objects

Oriane Siméoni,

Chloé Sekkat,

Gilles Puy,

Antonín Vobecký,

Éloi Zablocki,

Patrick Pérez

[pdf] [supp]

[bibtex]

@InProceedings{Simeoni_2023_CVPR, author = {Sim\'eoni, Oriane and Sekkat, Chlo\'e and Puy, Gilles and Vobeck\'y, Anton{\'\i}n and Zablocki, \'Eloi and P\'erez, Patrick}, title = {Unsupervised Object Localization: Observing the Background To Discover Objects}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3176-3186} }

Transforming Radiance Field With Lipschitz Network for Photorealistic 3D Scene Stylization

Zicheng Zhang,

Yinglu Liu,

Congying Han,

Yingwei Pan,

Tiande Guo,

Ting Yao

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Zhang_2023_CVPR, author = {Zhang, Zicheng and Liu, Yinglu and Han, Congying and Pan, Yingwei and Guo, Tiande and Yao, Ting}, title = {Transforming Radiance Field With Lipschitz Network for Photorealistic 3D Scene Stylization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {20712-20721} }

BEV-LaneDet: An Efficient 3D Lane Detection Based on Virtual Camera via Key-Points

Ruihao Wang,

Jian Qin,

Kaiying Li,

Yaochen Li,

Dong Cao,

Jintao Xu

[pdf] [supp]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Ruihao and Qin, Jian and Li, Kaiying and Li, Yaochen and Cao, Dong and Xu, Jintao}, title = {BEV-LaneDet: An Efficient 3D Lane Detection Based on Virtual Camera via Key-Points}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1002-1011} }

Self-Supervised 3D Scene Flow Estimation Guided by Superpoints

Yaqi Shen,

Le Hui,

Jin Xie,

Jian Yang

[pdf] [arXiv]

[bibtex]

@InProceedings{Shen_2023_CVPR, author = {Shen, Yaqi and Hui, Le and Xie, Jin and Yang, Jian}, title = {Self-Supervised 3D Scene Flow Estimation Guided by Superpoints}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5271-5280} }

DiffCollage: Parallel Generation of Large Content With Diffusion Models

Qinsheng Zhang,

Jiaming Song,

Xun Huang,

Yongxin Chen,

Ming-Yu Liu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Zhang_2023_CVPR, author = {Zhang, Qinsheng and Song, Jiaming and Huang, Xun and Chen, Yongxin and Liu, Ming-Yu}, title = {DiffCollage: Parallel Generation of Large Content With Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10188-10198} }

Efficient Second-Order Plane Adjustment

Lipu Zhou

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Zhou_2023_CVPR, author = {Zhou, Lipu}, title = {Efficient Second-Order Plane Adjustment}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13113-13121} }

Guided Depth Super-Resolution by Deep Anisotropic Diffusion

Nando Metzger,

Rodrigo Caye Daudt,

Konrad Schindler

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Metzger_2023_CVPR, author = {Metzger, Nando and Daudt, Rodrigo Caye and Schindler, Konrad}, title = {Guided Depth Super-Resolution by Deep Anisotropic Diffusion}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {18237-18246} }

Fresnel Microfacet BRDF: Unification of Polari-Radiometric Surface-Body Reflection

Tomoki Ichikawa,

Yoshiki Fukao,

Shohei Nobuhara,

Ko Nishino

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Ichikawa_2023_CVPR, author = {Ichikawa, Tomoki and Fukao, Yoshiki and Nobuhara, Shohei and Nishino, Ko}, title = {Fresnel Microfacet BRDF: Unification of Polari-Radiometric Surface-Body Reflection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16489-16497} }

A Unified Pyramid Recurrent Network for Video Frame Interpolation

Xin Jin,

Longhai Wu,

Jie Chen,

Youxin Chen,

Jayoon Koo,

Cheul-hee Hahm

[pdf] [arXiv]

[bibtex]

@InProceedings{Jin_2023_CVPR, author = {Jin, Xin and Wu, Longhai and Chen, Jie and Chen, Youxin and Koo, Jayoon and Hahm, Cheul-hee}, title = {A Unified Pyramid Recurrent Network for Video Frame Interpolation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1578-1587} }

Mofusion: A Framework for Denoising-Diffusion-Based Motion Synthesis

Rishabh Dabral,

Muhammad Hamza Mughal,

Vladislav Golyanik,

Christian Theobalt

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Dabral_2023_CVPR, author = {Dabral, Rishabh and Mughal, Muhammad Hamza and Golyanik, Vladislav and Theobalt, Christian}, title = {Mofusion: A Framework for Denoising-Diffusion-Based Motion Synthesis}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9760-9770} }

PoseFormerV2: Exploring Frequency Domain for Efficient and Robust 3D Human Pose Estimation

Qitao Zhao,

Ce Zheng,

Mengyuan Liu,

Pichao Wang,

Chen Chen

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Zhao_2023_CVPR, author = {Zhao, Qitao and Zheng, Ce and Liu, Mengyuan and Wang, Pichao and Chen, Chen}, title = {PoseFormerV2: Exploring Frequency Domain for Efficient and Robust 3D Human Pose Estimation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8877-8886} }

Mask3D: Pre-Training 2D Vision Transformers by Learning Masked 3D Priors

Ji Hou,

Xiaoliang Dai,

Zijian He,

Angela Dai,

Matthias Nießner

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Hou_2023_CVPR, author = {Hou, Ji and Dai, Xiaoliang and He, Zijian and Dai, Angela and Nie{\ss}ner, Matthias}, title = {Mask3D: Pre-Training 2D Vision Transformers by Learning Masked 3D Priors}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13510-13519} }

Physically Adversarial Infrared Patches With Learnable Shapes and Locations

Xingxing Wei,

Jie Yu,

Yao Huang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Wei_2023_CVPR, author = {Wei, Xingxing and Yu, Jie and Huang, Yao}, title = {Physically Adversarial Infrared Patches With Learnable Shapes and Locations}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12334-12342} }

DiffusioNeRF: Regularizing Neural Radiance Fields With Denoising Diffusion Models

Jamie Wynn,

Daniyar Turmukhambetov

[pdf] [arXiv]

[bibtex]

@InProceedings{Wynn_2023_CVPR, author = {Wynn, Jamie and Turmukhambetov, Daniyar}, title = {DiffusioNeRF: Regularizing Neural Radiance Fields With Denoising Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4180-4189} }

Exemplar-FreeSOLO: Enhancing Unsupervised Instance Segmentation With Exemplars

Taoseef Ishtiak,

Qing En,

Yuhong Guo

[pdf] [supp]

[bibtex]

@InProceedings{Ishtiak_2023_CVPR, author = {Ishtiak, Taoseef and En, Qing and Guo, Yuhong}, title = {Exemplar-FreeSOLO: Enhancing Unsupervised Instance Segmentation With Exemplars}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15424-15433} }

Multimodal Prompting With Missing Modalities for Visual Recognition

Yi-Lun Lee,

Yi-Hsuan Tsai,

Wei-Chen Chiu,

Chen-Yu Lee

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Lee_2023_CVPR, author = {Lee, Yi-Lun and Tsai, Yi-Hsuan and Chiu, Wei-Chen and Lee, Chen-Yu}, title = {Multimodal Prompting With Missing Modalities for Visual Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14943-14952} }

Edge-Aware Regional Message Passing Controller for Image Forgery Localization

Dong Li,

Jiaying Zhu,

Menglu Wang,

Jiawei Liu,

Xueyang Fu,

Zheng-Jun Zha

[pdf]

[bibtex]

@InProceedings{Li_2023_CVPR, author = {Li, Dong and Zhu, Jiaying and Wang, Menglu and Liu, Jiawei and Fu, Xueyang and Zha, Zheng-Jun}, title = {Edge-Aware Regional Message Passing Controller for Image Forgery Localization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8222-8232} }

Neural Koopman Pooling: Control-Inspired Temporal Dynamics Encoding for Skeleton-Based Action Recognition

Xinghan Wang,

Xin Xu,

Yadong Mu

[pdf] [supp]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Xinghan and Xu, Xin and Mu, Yadong}, title = {Neural Koopman Pooling: Control-Inspired Temporal Dynamics Encoding for Skeleton-Based Action Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10597-10607} }

Simulated Annealing in Early Layers Leads to Better Generalization

Amir M. Sarfi,

Zahra Karimpour,

Muawiz Chaudhary,

Nasir M. Khalid,

Mirco Ravanelli,

Sudhir Mudur,

Eugene Belilovsky

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Sarfi_2023_CVPR, author = {Sarfi, Amir M. and Karimpour, Zahra and Chaudhary, Muawiz and Khalid, Nasir M. and Ravanelli, Mirco and Mudur, Sudhir and Belilovsky, Eugene}, title = {Simulated Annealing in Early Layers Leads to Better Generalization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {20205-20214} }

Spatiotemporal Self-Supervised Learning for Point Clouds in the Wild

Yanhao Wu,

Tong Zhang,

Wei Ke,

Sabine Süsstrunk,

Mathieu Salzmann

[pdf] [arXiv]

[bibtex]

@InProceedings{Wu_2023_CVPR, author = {Wu, Yanhao and Zhang, Tong and Ke, Wei and S\"usstrunk, Sabine and Salzmann, Mathieu}, title = {Spatiotemporal Self-Supervised Learning for Point Clouds in the Wild}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5251-5260} }

Semi-Supervised Learning Made Simple With Self-Supervised Clustering

Enrico Fini,

Pietro Astolfi,

Karteek Alahari,

Xavier Alameda-Pineda,

Julien Mairal,

Moin Nabi,

Elisa Ricci

[pdf] [supp]

[bibtex]

@InProceedings{Fini_2023_CVPR, author = {Fini, Enrico and Astolfi, Pietro and Alahari, Karteek and Alameda-Pineda, Xavier and Mairal, Julien and Nabi, Moin and Ricci, Elisa}, title = {Semi-Supervised Learning Made Simple With Self-Supervised Clustering}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3187-3197} }

Blind Image Quality Assessment via Vision-Language Correspondence: A Multitask Learning Perspective

Weixia Zhang,

Guangtao Zhai,

Ying Wei,

Xiaokang Yang,

Kede Ma

[pdf] [arXiv]

[bibtex]

@InProceedings{Zhang_2023_CVPR, author = {Zhang, Weixia and Zhai, Guangtao and Wei, Ying and Yang, Xiaokang and Ma, Kede}, title = {Blind Image Quality Assessment via Vision-Language Correspondence: A Multitask Learning Perspective}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14071-14081} }

Exploring Data Geometry for Continual Learning

Zhi Gao,

Chen Xu,

Feng Li,

Yunde Jia,

Mehrtash Harandi,

Yuwei Wu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Gao_2023_CVPR, author = {Gao, Zhi and Xu, Chen and Li, Feng and Jia, Yunde and Harandi, Mehrtash and Wu, Yuwei}, title = {Exploring Data Geometry for Continual Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {24325-24334} }

Frequency-Modulated Point Cloud Rendering With Easy Editing

Yi Zhang,

Xiaoyang Huang,

Bingbing Ni,

Teng Li,

Wenjun Zhang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Zhang_2023_CVPR, author = {Zhang, Yi and Huang, Xiaoyang and Ni, Bingbing and Li, Teng and Zhang, Wenjun}, title = {Frequency-Modulated Point Cloud Rendering With Easy Editing}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {119-129} }

Integral Neural Networks

Kirill Solodskikh,

Azim Kurbanov,

Ruslan Aydarkhanov,

Irina Zhelavskaya,

Yury Parfenov,

Dehua Song,

Stamatios Lefkimmiatis

[pdf] [supp]

[bibtex]

@InProceedings{Solodskikh_2023_CVPR, author = {Solodskikh, Kirill and Kurbanov, Azim and Aydarkhanov, Ruslan and Zhelavskaya, Irina and Parfenov, Yury and Song, Dehua and Lefkimmiatis, Stamatios}, title = {Integral Neural Networks}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16113-16122} }

Learning Neural Parametric Head Models

Simon Giebenhain,

Tobias Kirschstein,

Markos Georgopoulos,

Martin Rünz,

Lourdes Agapito,

Matthias Nießner

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Giebenhain_2023_CVPR, author = {Giebenhain, Simon and Kirschstein, Tobias and Georgopoulos, Markos and R\"unz, Martin and Agapito, Lourdes and Nie{\ss}ner, Matthias}, title = {Learning Neural Parametric Head Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {21003-21012} }

Removing Objects From Neural Radiance Fields

Silvan Weder,

Guillermo Garcia-Hernando,

Áron Monszpart,

Marc Pollefeys,

Gabriel J. Brostow,

Michael Firman,

Sara Vicente

[pdf] [arXiv]

[bibtex]

@InProceedings{Weder_2023_CVPR, author = {Weder, Silvan and Garcia-Hernando, Guillermo and Monszpart, \'Aron and Pollefeys, Marc and Brostow, Gabriel J. and Firman, Michael and Vicente, Sara}, title = {Removing Objects From Neural Radiance Fields}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16528-16538} }

Few-Shot Referring Relationships in Videos

Yogesh Kumar,

Anand Mishra

[pdf]

[bibtex]

@InProceedings{Kumar_2023_CVPR, author = {Kumar, Yogesh and Mishra, Anand}, title = {Few-Shot Referring Relationships in Videos}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2289-2298} }

Structural Multiplane Image: Bridging Neural View Synthesis and 3D Reconstruction

Mingfang Zhang,

Jinglu Wang,

Xiao Li,

Yifei Huang,

Yoichi Sato,

Yan Lu

[pdf] [arXiv]

[bibtex]

@InProceedings{Zhang_2023_CVPR, author = {Zhang, Mingfang and Wang, Jinglu and Li, Xiao and Huang, Yifei and Sato, Yoichi and Lu, Yan}, title = {Structural Multiplane Image: Bridging Neural View Synthesis and 3D Reconstruction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16707-16716} }

Harmonious Teacher for Cross-Domain Object Detection

Jinhong Deng,

Dongli Xu,

Wen Li,

Lixin Duan

[pdf] [supp]

[bibtex]

@InProceedings{Deng_2023_CVPR, author = {Deng, Jinhong and Xu, Dongli and Li, Wen and Duan, Lixin}, title = {Harmonious Teacher for Cross-Domain Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {23829-23838} }

3D Human Pose Estimation via Intuitive Physics

Shashank Tripathi,

Lea Müller,

Chun-Hao P. Huang,

Omid Taheri,

Michael J. Black,

Dimitrios Tzionas

[pdf] [supp]

[bibtex]

@InProceedings{Tripathi_2023_CVPR, author = {Tripathi, Shashank and M\"uller, Lea and Huang, Chun-Hao P. and Taheri, Omid and Black, Michael J. and Tzionas, Dimitrios}, title = {3D Human Pose Estimation via Intuitive Physics}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4713-4725} }

SplineCam: Exact Visualization and Characterization of Deep Network Geometry and Decision Boundaries

Ahmed Imtiaz Humayun,

Randall Balestriero,

Guha Balakrishnan,

Richard G. Baraniuk

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Humayun_2023_CVPR, author = {Humayun, Ahmed Imtiaz and Balestriero, Randall and Balakrishnan, Guha and Baraniuk, Richard G.}, title = {SplineCam: Exact Visualization and Characterization of Deep Network Geometry and Decision Boundaries}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3789-3798} }

Learning To Predict Scene-Level Implicit 3D From Posed RGBD Data

Nilesh Kulkarni,

Linyi Jin,

Justin Johnson,

David F. Fouhey

[pdf] [supp]

[bibtex]

@InProceedings{Kulkarni_2023_CVPR, author = {Kulkarni, Nilesh and Jin, Linyi and Johnson, Justin and Fouhey, David F.}, title = {Learning To Predict Scene-Level Implicit 3D From Posed RGBD Data}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {17256-17265} }

EXCALIBUR: Encouraging and Evaluating Embodied Exploration

Hao Zhu,

Raghav Kapoor,

So Yeon Min,

Winson Han,

Jiatai Li,

Kaiwen Geng,

Graham Neubig,

Yonatan Bisk,

Aniruddha Kembhavi,

Luca Weihs

[pdf] [supp]

[bibtex]

@InProceedings{Zhu_2023_CVPR, author = {Zhu, Hao and Kapoor, Raghav and Min, So Yeon and Han, Winson and Li, Jiatai and Geng, Kaiwen and Neubig, Graham and Bisk, Yonatan and Kembhavi, Aniruddha and Weihs, Luca}, title = {EXCALIBUR: Encouraging and Evaluating Embodied Exploration}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14931-14942} }

Visual DNA: Representing and Comparing Images Using Distributions of Neuron Activations

Benjamin Ramtoula,

Matthew Gadd,

Paul Newman,

Daniele De Martini

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Ramtoula_2023_CVPR, author = {Ramtoula, Benjamin and Gadd, Matthew and Newman, Paul and De Martini, Daniele}, title = {Visual DNA: Representing and Comparing Images Using Distributions of Neuron Activations}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11113-11123} }

Recognizability Embedding Enhancement for Very Low-Resolution Face Recognition and Quality Estimation

Jacky Chen Long Chai,

Tiong-Sik Ng,

Cheng-Yaw Low,

Jaewoo Park,

Andrew Beng Jin Teoh

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Chai_2023_CVPR, author = {Chai, Jacky Chen Long and Ng, Tiong-Sik and Low, Cheng-Yaw and Park, Jaewoo and Teoh, Andrew Beng Jin}, title = {Recognizability Embedding Enhancement for Very Low-Resolution Face Recognition and Quality Estimation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9957-9967} }

Physical-World Optical Adversarial Attacks on 3D Face Recognition

Yanjie Li,

Yiquan Li,

Xuelong Dai,

Songtao Guo,

Bin Xiao

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Li_2023_CVPR, author = {Li, Yanjie and Li, Yiquan and Dai, Xuelong and Guo, Songtao and Xiao, Bin}, title = {Physical-World Optical Adversarial Attacks on 3D Face Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {24699-24708} }

Accelerating Dataset Distillation via Model Augmentation

Lei Zhang,

Jie Zhang,

Bowen Lei,

Subhabrata Mukherjee,

Xiang Pan,

Bo Zhao,

Caiwen Ding,

Yao Li,

Dongkuan Xu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Zhang_2023_CVPR, author = {Zhang, Lei and Zhang, Jie and Lei, Bowen and Mukherjee, Subhabrata and Pan, Xiang and Zhao, Bo and Ding, Caiwen and Li, Yao and Xu, Dongkuan}, title = {Accelerating Dataset Distillation via Model Augmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11950-11959} }

SE-ORNet: Self-Ensembling Orientation-Aware Network for Unsupervised Point Cloud Shape Correspondence

Jiacheng Deng,

Chuxin Wang,

Jiahao Lu,

Jianfeng He,

Tianzhu Zhang,

Jiyang Yu,

Zhe Zhang

[pdf]

[bibtex]

@InProceedings{Deng_2023_CVPR, author = {Deng, Jiacheng and Wang, Chuxin and Lu, Jiahao and He, Jianfeng and Zhang, Tianzhu and Yu, Jiyang and Zhang, Zhe}, title = {SE-ORNet: Self-Ensembling Orientation-Aware Network for Unsupervised Point Cloud Shape Correspondence}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5364-5373} }

Raw Image Reconstruction With Learned Compact Metadata

Yufei Wang,

Yi Yu,

Wenhan Yang,

Lanqing Guo,

Lap-Pui Chau,

Alex C. Kot,

Bihan Wen

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Yufei and Yu, Yi and Yang, Wenhan and Guo, Lanqing and Chau, Lap-Pui and Kot, Alex C. and Wen, Bihan}, title = {Raw Image Reconstruction With Learned Compact Metadata}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {18206-18215} }

Semi-Supervised Video Inpainting With Cycle Consistency Constraints

Zhiliang Wu,

Hanyu Xuan,

Changchang Sun,

Weili Guan,

Kang Zhang,

Yan Yan

[pdf] [arXiv]

[bibtex]

@InProceedings{Wu_2023_CVPR, author = {Wu, Zhiliang and Xuan, Hanyu and Sun, Changchang and Guan, Weili and Zhang, Kang and Yan, Yan}, title = {Semi-Supervised Video Inpainting With Cycle Consistency Constraints}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {22586-22595} }

Frame-Event Alignment and Fusion Network for High Frame Rate Tracking

Jiqing Zhang,

Yuanchen Wang,

Wenxi Liu,

Meng Li,

Jinpeng Bai,

Baocai Yin,

Xin Yang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Zhang_2023_CVPR, author = {Zhang, Jiqing and Wang, Yuanchen and Liu, Wenxi and Li, Meng and Bai, Jinpeng and Yin, Baocai and Yang, Xin}, title = {Frame-Event Alignment and Fusion Network for High Frame Rate Tracking}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9781-9790} }

A Bag-of-Prototypes Representation for Dataset-Level Applications

Weijie Tu,

Weijian Deng,

Tom Gedeon,

Liang Zheng

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Tu_2023_CVPR, author = {Tu, Weijie and Deng, Weijian and Gedeon, Tom and Zheng, Liang}, title = {A Bag-of-Prototypes Representation for Dataset-Level Applications}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2881-2892} }

Level-S$^2$fM: Structure From Motion on Neural Level Set of Implicit Surfaces

Yuxi Xiao,

Nan Xue,

Tianfu Wu,

Gui-Song Xia

[pdf] [supp]

[bibtex]

@InProceedings{Xiao_2023_CVPR, author = {Xiao, Yuxi and Xue, Nan and Wu, Tianfu and Xia, Gui-Song}, title = {Level-S\${\textasciicircum}2\$fM: Structure From Motion on Neural Level Set of Implicit Surfaces}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {17205-17214} }

Neuron Structure Modeling for Generalizable Remote Physiological Measurement

Hao Lu,

Zitong Yu,

Xuesong Niu,

Ying-Cong Chen

[pdf] [arXiv]

[bibtex]

@InProceedings{Lu_2023_CVPR, author = {Lu, Hao and Yu, Zitong and Niu, Xuesong and Chen, Ying-Cong}, title = {Neuron Structure Modeling for Generalizable Remote Physiological Measurement}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {18589-18599} }

Shape-Aware Text-Driven Layered Video Editing

Yao-Chih Lee,

Ji-Ze Genevieve Jang,

Yi-Ting Chen,

Elizabeth Qiu,

Jia-Bin Huang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Lee_2023_CVPR, author = {Lee, Yao-Chih and Jang, Ji-Ze Genevieve and Chen, Yi-Ting and Qiu, Elizabeth and Huang, Jia-Bin}, title = {Shape-Aware Text-Driven Layered Video Editing}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14317-14326} }

Out-of-Candidate Rectification for Weakly Supervised Semantic Segmentation

Zesen Cheng,

Pengchong Qiao,

Kehan Li,

Siheng Li,

Pengxu Wei,

Xiangyang Ji,

Li Yuan,

Chang Liu,

Jie Chen

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Cheng_2023_CVPR, author = {Cheng, Zesen and Qiao, Pengchong and Li, Kehan and Li, Siheng and Wei, Pengxu and Ji, Xiangyang and Yuan, Li and Liu, Chang and Chen, Jie}, title = {Out-of-Candidate Rectification for Weakly Supervised Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {23673-23684} }

Solving Relaxations of MAP-MRF Problems: Combinatorial In-Face Frank-Wolfe Directions

Vladimir Kolmogorov

[pdf] [arXiv]

[bibtex]

@InProceedings{Kolmogorov_2023_CVPR, author = {Kolmogorov, Vladimir}, title = {Solving Relaxations of MAP-MRF Problems: Combinatorial In-Face Frank-Wolfe Directions}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11980-11989} }

MEGANE: Morphable Eyeglass and Avatar Network

Junxuan Li,

Shunsuke Saito,

Tomas Simon,

Stephen Lombardi,

Hongdong Li,

Jason Saragih

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Li_2023_CVPR, author = {Li, Junxuan and Saito, Shunsuke and Simon, Tomas and Lombardi, Stephen and Li, Hongdong and Saragih, Jason}, title = {MEGANE: Morphable Eyeglass and Avatar Network}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12769-12779} }

Leverage Interactive Affinity for Affordance Learning

Hongchen Luo,

Wei Zhai,

Jing Zhang,

Yang Cao,

Dacheng Tao

[pdf] [supp]

[bibtex]

@InProceedings{Luo_2023_CVPR, author = {Luo, Hongchen and Zhai, Wei and Zhang, Jing and Cao, Yang and Tao, Dacheng}, title = {Leverage Interactive Affinity for Affordance Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6809-6819} }

Enhancing Multiple Reliability Measures via Nuisance-Extended Information Bottleneck

Jongheon Jeong,

Sihyun Yu,

Hankook Lee,

Jinwoo Shin

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Jeong_2023_CVPR, author = {Jeong, Jongheon and Yu, Sihyun and Lee, Hankook and Shin, Jinwoo}, title = {Enhancing Multiple Reliability Measures via Nuisance-Extended Information Bottleneck}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16206-16218} }

Rethinking the Approximation Error in 3D Surface Fitting for Point Cloud Normal Estimation

Hang Du,

Xuejun Yan,

Jingjing Wang,

Di Xie,

Shiliang Pu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Du_2023_CVPR, author = {Du, Hang and Yan, Xuejun and Wang, Jingjing and Xie, Di and Pu, Shiliang}, title = {Rethinking the Approximation Error in 3D Surface Fitting for Point Cloud Normal Estimation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9486-9495} }

Objaverse: A Universe of Annotated 3D Objects

Matt Deitke,

Dustin Schwenk,

Jordi Salvador,

Luca Weihs,

Oscar Michel,

Eli VanderBilt,

Ludwig Schmidt,

Kiana Ehsani,

Aniruddha Kembhavi,

Ali Farhadi

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Deitke_2023_CVPR, author = {Deitke, Matt and Schwenk, Dustin and Salvador, Jordi and Weihs, Luca and Michel, Oscar and VanderBilt, Eli and Schmidt, Ludwig and Ehsani, Kiana and Kembhavi, Aniruddha and Farhadi, Ali}, title = {Objaverse: A Universe of Annotated 3D Objects}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13142-13153} }

MonoATT: Online Monocular 3D Object Detection With Adaptive Token Transformer

Yunsong Zhou,

Hongzi Zhu,

Quan Liu,

Shan Chang,

Minyi Guo

[pdf] [arXiv]

[bibtex]

@InProceedings{Zhou_2023_CVPR, author = {Zhou, Yunsong and Zhu, Hongzi and Liu, Quan and Chang, Shan and Guo, Minyi}, title = {MonoATT: Online Monocular 3D Object Detection With Adaptive Token Transformer}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {17493-17503} }

Image Quality-Aware Diagnosis via Meta-Knowledge Co-Embedding

Haoxuan Che,

Siyu Chen,

Hao Chen

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Che_2023_CVPR, author = {Che, Haoxuan and Chen, Siyu and Chen, Hao}, title = {Image Quality-Aware Diagnosis via Meta-Knowledge Co-Embedding}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {19819-19829} }

A-Cap: Anticipation Captioning With Commonsense Knowledge

Duc Minh Vo,

Quoc-An Luong,

Akihiro Sugimoto,

Hideki Nakayama

[pdf] [supp]

[bibtex]

@InProceedings{Vo_2023_CVPR, author = {Vo, Duc Minh and Luong, Quoc-An and Sugimoto, Akihiro and Nakayama, Hideki}, title = {A-Cap: Anticipation Captioning With Commonsense Knowledge}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10824-10833} }

Learning 3D Representations From 2D Pre-Trained Models via Image-to-Point Masked Autoencoders

Renrui Zhang,

Liuhui Wang,

Yu Qiao,

Peng Gao,

Hongsheng Li

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Zhang_2023_CVPR, author = {Zhang, Renrui and Wang, Liuhui and Qiao, Yu and Gao, Peng and Li, Hongsheng}, title = {Learning 3D Representations From 2D Pre-Trained Models via Image-to-Point Masked Autoencoders}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {21769-21780} }

BEVFormer v2: Adapting Modern Image Backbones to Bird's-Eye-View Recognition via Perspective Supervision

Chenyu Yang,

Yuntao Chen,

Hao Tian,

Chenxin Tao,

Xizhou Zhu,

Zhaoxiang Zhang,

Gao Huang,

Hongyang Li,

Yu Qiao,

Lewei Lu,

Jie Zhou,

Jifeng Dai

[pdf] [supp]

[bibtex]

@InProceedings{Yang_2023_CVPR, author = {Yang, Chenyu and Chen, Yuntao and Tian, Hao and Tao, Chenxin and Zhu, Xizhou and Zhang, Zhaoxiang and Huang, Gao and Li, Hongyang and Qiao, Yu and Lu, Lewei and Zhou, Jie and Dai, Jifeng}, title = {BEVFormer v2: Adapting Modern Image Backbones to Bird's-Eye-View Recognition via Perspective Supervision}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {17830-17839} }

Object Discovery From Motion-Guided Tokens

Zhipeng Bao,

Pavel Tokmakov,

Yu-Xiong Wang,

Adrien Gaidon,

Martial Hebert

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Bao_2023_CVPR, author = {Bao, Zhipeng and Tokmakov, Pavel and Wang, Yu-Xiong and Gaidon, Adrien and Hebert, Martial}, title = {Object Discovery From Motion-Guided Tokens}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {22972-22981} }

Domain Generalized Stereo Matching via Hierarchical Visual Transformation

Tianyu Chang,

Xun Yang,

Tianzhu Zhang,

Meng Wang

[pdf] [supp]

[bibtex]

@InProceedings{Chang_2023_CVPR, author = {Chang, Tianyu and Yang, Xun and Zhang, Tianzhu and Wang, Meng}, title = {Domain Generalized Stereo Matching via Hierarchical Visual Transformation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9559-9568} }

Deep Semi-Supervised Metric Learning With Mixed Label Propagation

Furen Zhuang,

Pierre Moulin

[pdf]

[bibtex]

@InProceedings{Zhuang_2023_CVPR, author = {Zhuang, Furen and Moulin, Pierre}, title = {Deep Semi-Supervised Metric Learning With Mixed Label Propagation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3429-3438} }

Adapting Shortcut With Normalizing Flow: An Efficient Tuning Framework for Visual Recognition

Yaoming Wang,

Bowen Shi,

Xiaopeng Zhang,

Jin Li,

Yuchen Liu,

Wenrui Dai,

Chenglin Li,

Hongkai Xiong,

Qi Tian

[pdf] [supp]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Yaoming and Shi, Bowen and Zhang, Xiaopeng and Li, Jin and Liu, Yuchen and Dai, Wenrui and Li, Chenglin and Xiong, Hongkai and Tian, Qi}, title = {Adapting Shortcut With Normalizing Flow: An Efficient Tuning Framework for Visual Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15965-15974} }

Unpaired Image-to-Image Translation With Shortest Path Regularization

Shaoan Xie,

Yanwu Xu,

Mingming Gong,

Kun Zhang

[pdf]

[bibtex]

@InProceedings{Xie_2023_CVPR, author = {Xie, Shaoan and Xu, Yanwu and Gong, Mingming and Zhang, Kun}, title = {Unpaired Image-to-Image Translation With Shortest Path Regularization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10177-10187} }

MotionDiffuser: Controllable Multi-Agent Motion Prediction Using Diffusion

Chiyu “Max” Jiang,

Andre Cornman,

Cheolho Park,

Benjamin Sapp,

Yin Zhou,

Dragomir Anguelov

[pdf] [supp]

[bibtex]

@InProceedings{Jiang_2023_CVPR, author = {Jiang, Chiyu {\textquotedblleft}Max{\textquotedblright} and Cornman, Andre and Park, Cheolho and Sapp, Benjamin and Zhou, Yin and Anguelov, Dragomir}, title = {MotionDiffuser: Controllable Multi-Agent Motion Prediction Using Diffusion}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9644-9653} }

OVTrack: Open-Vocabulary Multiple Object Tracking

Siyuan Li,

Tobias Fischer,

Lei Ke,

Henghui Ding,

Martin Danelljan,

Fisher Yu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Li_2023_CVPR, author = {Li, Siyuan and Fischer, Tobias and Ke, Lei and Ding, Henghui and Danelljan, Martin and Yu, Fisher}, title = {OVTrack: Open-Vocabulary Multiple Object Tracking}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5567-5577} }

ConvNeXt V2: Co-Designing and Scaling ConvNets With Masked Autoencoders

Sanghyun Woo,

Shoubhik Debnath,

Ronghang Hu,

Xinlei Chen,

Zhuang Liu,

In So Kweon,

Saining Xie

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Woo_2023_CVPR, author = {Woo, Sanghyun and Debnath, Shoubhik and Hu, Ronghang and Chen, Xinlei and Liu, Zhuang and Kweon, In So and Xie, Saining}, title = {ConvNeXt V2: Co-Designing and Scaling ConvNets With Masked Autoencoders}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16133-16142} }

Hyperspherical Embedding for Point Cloud Completion

Junming Zhang,

Haomeng Zhang,

Ram Vasudevan,

Matthew Johnson-Roberson

[pdf] [supp]

[bibtex]

@InProceedings{Zhang_2023_CVPR, author = {Zhang, Junming and Zhang, Haomeng and Vasudevan, Ram and Johnson-Roberson, Matthew}, title = {Hyperspherical Embedding for Point Cloud Completion}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5323-5332} }

Event-Based Video Frame Interpolation With Cross-Modal Asymmetric Bidirectional Motion Fields

Taewoo Kim,

Yujeong Chae,

Hyun-Kurl Jang,

Kuk-Jin Yoon

[pdf] [supp]

[bibtex]

@InProceedings{Kim_2023_CVPR, author = {Kim, Taewoo and Chae, Yujeong and Jang, Hyun-Kurl and Yoon, Kuk-Jin}, title = {Event-Based Video Frame Interpolation With Cross-Modal Asymmetric Bidirectional Motion Fields}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {18032-18042} }

Unsupervised Deep Asymmetric Stereo Matching With Spatially-Adaptive Self-Similarity

Taeyong Song,

Sunok Kim,

Kwanghoon Sohn

[pdf] [supp]

[bibtex]

@InProceedings{Song_2023_CVPR, author = {Song, Taeyong and Kim, Sunok and Sohn, Kwanghoon}, title = {Unsupervised Deep Asymmetric Stereo Matching With Spatially-Adaptive Self-Similarity}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13672-13680} }

QuantArt: Quantizing Image Style Transfer Towards High Visual Fidelity

Siyu Huang,

Jie An,

Donglai Wei,

Jiebo Luo,

Hanspeter Pfister

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Huang_2023_CVPR, author = {Huang, Siyu and An, Jie and Wei, Donglai and Luo, Jiebo and Pfister, Hanspeter}, title = {QuantArt: Quantizing Image Style Transfer Towards High Visual Fidelity}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5947-5956} }

TWINS: A Fine-Tuning Framework for Improved Transferability of Adversarial Robustness and Generalization

Ziquan Liu,

Yi Xu,

Xiangyang Ji,

Antoni B. Chan

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Liu_2023_CVPR, author = {Liu, Ziquan and Xu, Yi and Ji, Xiangyang and Chan, Antoni B.}, title = {TWINS: A Fine-Tuning Framework for Improved Transferability of Adversarial Robustness and Generalization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16436-16446} }

VolRecon: Volume Rendering of Signed Ray Distance Functions for Generalizable Multi-View Reconstruction

Yufan Ren,

Fangjinhua Wang,

Tong Zhang,

Marc Pollefeys,

Sabine Süsstrunk

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Ren_2023_CVPR, author = {Ren, Yufan and Wang, Fangjinhua and Zhang, Tong and Pollefeys, Marc and S\"usstrunk, Sabine}, title = {VolRecon: Volume Rendering of Signed Ray Distance Functions for Generalizable Multi-View Reconstruction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16685-16695} }

Object-Aware Distillation Pyramid for Open-Vocabulary Object Detection

Luting Wang,

Yi Liu,

Penghui Du,

Zihan Ding,

Yue Liao,

Qiaosong Qi,

Biaolong Chen,

Si Liu

[pdf] [arXiv]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Luting and Liu, Yi and Du, Penghui and Ding, Zihan and Liao, Yue and Qi, Qiaosong and Chen, Biaolong and Liu, Si}, title = {Object-Aware Distillation Pyramid for Open-Vocabulary Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11186-11196} }

Evolved Part Masking for Self-Supervised Learning

Zhanzhou Feng,

Shiliang Zhang

[pdf] [supp]

[bibtex]

@InProceedings{Feng_2023_CVPR, author = {Feng, Zhanzhou and Zhang, Shiliang}, title = {Evolved Part Masking for Self-Supervised Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10386-10395} }

MV-JAR: Masked Voxel Jigsaw and Reconstruction for LiDAR-Based Self-Supervised Pre-Training

Runsen Xu,

Tai Wang,

Wenwei Zhang,

Runjian Chen,

Jinkun Cao,

Jiangmiao Pang,

Dahua Lin

[pdf] [supp]

[bibtex]

@InProceedings{Xu_2023_CVPR, author = {Xu, Runsen and Wang, Tai and Zhang, Wenwei and Chen, Runjian and Cao, Jinkun and Pang, Jiangmiao and Lin, Dahua}, title = {MV-JAR: Masked Voxel Jigsaw and Reconstruction for LiDAR-Based Self-Supervised Pre-Training}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13445-13454} }

SlowLiDAR: Increasing the Latency of LiDAR-Based Detection Using Adversarial Examples

Han Liu,

Yuhao Wu,

Zhiyuan Yu,

Yevgeniy Vorobeychik,

Ning Zhang

[pdf]

[bibtex]

@InProceedings{Liu_2023_CVPR, author = {Liu, Han and Wu, Yuhao and Yu, Zhiyuan and Vorobeychik, Yevgeniy and Zhang, Ning}, title = {SlowLiDAR: Increasing the Latency of LiDAR-Based Detection Using Adversarial Examples}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5146-5155} }

Learning a Sparse Transformer Network for Effective Image Deraining

Xiang Chen,

Hao Li,

Mingqiang Li,

Jinshan Pan

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Chen_2023_CVPR, author = {Chen, Xiang and Li, Hao and Li, Mingqiang and Pan, Jinshan}, title = {Learning a Sparse Transformer Network for Effective Image Deraining}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5896-5905} }

Open-Set Semantic Segmentation for Point Clouds via Adversarial Prototype Framework

Jianan Li,

Qiulei Dong

[pdf] [supp]

[bibtex]

@InProceedings{Li_2023_CVPR, author = {Li, Jianan and Dong, Qiulei}, title = {Open-Set Semantic Segmentation for Point Clouds via Adversarial Prototype Framework}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9425-9434} }

CutMIB: Boosting Light Field Super-Resolution via Multi-View Image Blending

Zeyu Xiao,

Yutong Liu,

Ruisheng Gao,

Zhiwei Xiong

[pdf] [supp]

[bibtex]

@InProceedings{Xiao_2023_CVPR, author = {Xiao, Zeyu and Liu, Yutong and Gao, Ruisheng and Xiong, Zhiwei}, title = {CutMIB: Boosting Light Field Super-Resolution via Multi-View Image Blending}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1672-1682} }

Learning Attention As Disentangler for Compositional Zero-Shot Learning

Shaozhe Hao,

Kai Han,

Kwan-Yee K. Wong

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Hao_2023_CVPR, author = {Hao, Shaozhe and Han, Kai and Wong, Kwan-Yee K.}, title = {Learning Attention As Disentangler for Compositional Zero-Shot Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15315-15324} }

DA-DETR: Domain Adaptive Detection Transformer With Information Fusion

Jingyi Zhang,

Jiaxing Huang,

Zhipeng Luo,

Gongjie Zhang,

Xiaoqin Zhang,

Shijian Lu

[pdf] [supp]

[bibtex]

@InProceedings{Zhang_2023_CVPR, author = {Zhang, Jingyi and Huang, Jiaxing and Luo, Zhipeng and Zhang, Gongjie and Zhang, Xiaoqin and Lu, Shijian}, title = {DA-DETR: Domain Adaptive Detection Transformer With Information Fusion}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {23787-23798} }

Energy-Efficient Adaptive 3D Sensing

Brevin Tilmon,

Zhanghao Sun,

Sanjeev J. Koppal,

Yicheng Wu,

Georgios Evangelidis,

Ramzi Zahreddine,

Gurunandan Krishnan,

Sizhuo Ma,

Jian Wang

[pdf] [supp]

[bibtex]

@InProceedings{Tilmon_2023_CVPR, author = {Tilmon, Brevin and Sun, Zhanghao and Koppal, Sanjeev J. and Wu, Yicheng and Evangelidis, Georgios and Zahreddine, Ramzi and Krishnan, Gurunandan and Ma, Sizhuo and Wang, Jian}, title = {Energy-Efficient Adaptive 3D Sensing}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5054-5063} }

CR-FIQA: Face Image Quality Assessment by Learning Sample Relative Classifiability

Fadi Boutros,

Meiling Fang,

Marcel Klemt,

Biying Fu,

Naser Damer

[pdf] [supp]

[bibtex]

@InProceedings{Boutros_2023_CVPR, author = {Boutros, Fadi and Fang, Meiling and Klemt, Marcel and Fu, Biying and Damer, Naser}, title = {CR-FIQA: Face Image Quality Assessment by Learning Sample Relative Classifiability}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5836-5845} }

Endpoints Weight Fusion for Class Incremental Semantic Segmentation

Jia-Wen Xiao,

Chang-Bin Zhang,

Jiekang Feng,

Xialei Liu,

Joost van de Weijer,

Ming-Ming Cheng

[pdf] [supp]

[bibtex]

@InProceedings{Xiao_2023_CVPR, author = {Xiao, Jia-Wen and Zhang, Chang-Bin and Feng, Jiekang and Liu, Xialei and van de Weijer, Joost and Cheng, Ming-Ming}, title = {Endpoints Weight Fusion for Class Incremental Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7204-7213} }

GeneCIS: A Benchmark for General Conditional Image Similarity

Sagar Vaze,

Nicolas Carion,

Ishan Misra

[pdf] [supp]

[bibtex]

@InProceedings{Vaze_2023_CVPR, author = {Vaze, Sagar and Carion, Nicolas and Misra, Ishan}, title = {GeneCIS: A Benchmark for General Conditional Image Similarity}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6862-6872} }

MetaViewer: Towards a Unified Multi-View Representation

Ren Wang,

Haoliang Sun,

Yuling Ma,

Xiaoming Xi,

Yilong Yin

[pdf] [arXiv]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Ren and Sun, Haoliang and Ma, Yuling and Xi, Xiaoming and Yin, Yilong}, title = {MetaViewer: Towards a Unified Multi-View Representation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11590-11599} }

MD-VQA: Multi-Dimensional Quality Assessment for UGC Live Videos

Zicheng Zhang,

Wei Wu,

Wei Sun,

Danyang Tu,

Wei Lu,

Xiongkuo Min,

Ying Chen,

Guangtao Zhai

[pdf]

[bibtex]

@InProceedings{Zhang_2023_CVPR, author = {Zhang, Zicheng and Wu, Wei and Sun, Wei and Tu, Danyang and Lu, Wei and Min, Xiongkuo and Chen, Ying and Zhai, Guangtao}, title = {MD-VQA: Multi-Dimensional Quality Assessment for UGC Live Videos}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1746-1755} }

Vision Transformers Are Good Mask Auto-Labelers

Shiyi Lan,

Xitong Yang,

Zhiding Yu,

Zuxuan Wu,

Jose M. Alvarez,

Anima Anandkumar

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Lan_2023_CVPR, author = {Lan, Shiyi and Yang, Xitong and Yu, Zhiding and Wu, Zuxuan and Alvarez, Jose M. and Anandkumar, Anima}, title = {Vision Transformers Are Good Mask Auto-Labelers}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {23745-23755} }

Neural Transformation Fields for Arbitrary-Styled Font Generation

Bin Fu,

Junjun He,

Jianjun Wang,

Yu Qiao

[pdf] [supp]

[bibtex]

@InProceedings{Fu_2023_CVPR, author = {Fu, Bin and He, Junjun and Wang, Jianjun and Qiao, Yu}, title = {Neural Transformation Fields for Arbitrary-Styled Font Generation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {22438-22447} }

Spring: A High-Resolution High-Detail Dataset and Benchmark for Scene Flow, Optical Flow and Stereo

Lukas Mehl,

Jenny Schmalfuss,

Azin Jahedi,

Yaroslava Nalivayko,

Andrés Bruhn

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Mehl_2023_CVPR, author = {Mehl, Lukas and Schmalfuss, Jenny and Jahedi, Azin and Nalivayko, Yaroslava and Bruhn, Andr\'es}, title = {Spring: A High-Resolution High-Detail Dataset and Benchmark for Scene Flow, Optical Flow and Stereo}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4981-4991} }

EDICT: Exact Diffusion Inversion via Coupled Transformations

Bram Wallace,

Akash Gokul,

Nikhil Naik

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Wallace_2023_CVPR, author = {Wallace, Bram and Gokul, Akash and Naik, Nikhil}, title = {EDICT: Exact Diffusion Inversion via Coupled Transformations}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {22532-22541} }

Natural Language-Assisted Sign Language Recognition

Ronglai Zuo,

Fangyun Wei,

Brian Mak

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Zuo_2023_CVPR, author = {Zuo, Ronglai and Wei, Fangyun and Mak, Brian}, title = {Natural Language-Assisted Sign Language Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14890-14900} }

MAESTER: Masked Autoencoder Guided Segmentation at Pixel Resolution for Accurate, Self-Supervised Subcellular Structure Recognition

Ronald Xie,

Kuan Pang,

Gary D. Bader,

Bo Wang

[pdf] [supp]

[bibtex]

@InProceedings{Xie_2023_CVPR, author = {Xie, Ronald and Pang, Kuan and Bader, Gary D. and Wang, Bo}, title = {MAESTER: Masked Autoencoder Guided Segmentation at Pixel Resolution for Accurate, Self-Supervised Subcellular Structure Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3292-3301} }

Learning Semantic Relationship Among Instances for Image-Text Matching

Zheren Fu,

Zhendong Mao,

Yan Song,

Yongdong Zhang

[pdf]

[bibtex]

@InProceedings{Fu_2023_CVPR, author = {Fu, Zheren and Mao, Zhendong and Song, Yan and Zhang, Yongdong}, title = {Learning Semantic Relationship Among Instances for Image-Text Matching}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15159-15168} }

AeDet: Azimuth-Invariant Multi-View 3D Object Detection

Chengjian Feng,

Zequn Jie,

Yujie Zhong,

Xiangxiang Chu,

Lin Ma

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Feng_2023_CVPR, author = {Feng, Chengjian and Jie, Zequn and Zhong, Yujie and Chu, Xiangxiang and Ma, Lin}, title = {AeDet: Azimuth-Invariant Multi-View 3D Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {21580-21588} }

OCELOT: Overlapped Cell on Tissue Dataset for Histopathology

Jeongun Ryu,

Aaron Valero Puche,

JaeWoong Shin,

Seonwook Park,

Biagio Brattoli,

Jinhee Lee,

Wonkyung Jung,

Soo Ick Cho,

Kyunghyun Paeng,

Chan-Young Ock,

Donggeun Yoo,

Sérgio Pereira

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Ryu_2023_CVPR, author = {Ryu, Jeongun and Puche, Aaron Valero and Shin, JaeWoong and Park, Seonwook and Brattoli, Biagio and Lee, Jinhee and Jung, Wonkyung and Cho, Soo Ick and Paeng, Kyunghyun and Ock, Chan-Young and Yoo, Donggeun and Pereira, S\'ergio}, title = {OCELOT: Overlapped Cell on Tissue Dataset for Histopathology}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {23902-23912} }

Global-to-Local Modeling for Video-Based 3D Human Pose and Shape Estimation

Xiaolong Shen,

Zongxin Yang,

Xiaohan Wang,

Jianxin Ma,

Chang Zhou,

Yi Yang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Shen_2023_CVPR, author = {Shen, Xiaolong and Yang, Zongxin and Wang, Xiaohan and Ma, Jianxin and Zhou, Chang and Yang, Yi}, title = {Global-to-Local Modeling for Video-Based 3D Human Pose and Shape Estimation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8887-8896} }

BEDLAM: A Synthetic Dataset of Bodies Exhibiting Detailed Lifelike Animated Motion

Michael J. Black,

Priyanka Patel,

Joachim Tesch,

Jinlong Yang

[pdf] [supp]

[bibtex]

@InProceedings{Black_2023_CVPR, author = {Black, Michael J. and Patel, Priyanka and Tesch, Joachim and Yang, Jinlong}, title = {BEDLAM: A Synthetic Dataset of Bodies Exhibiting Detailed Lifelike Animated Motion}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8726-8737} }

Self-Supervised Image-to-Point Distillation via Semantically Tolerant Contrastive Loss

Anas Mahmoud,

Jordan S. K. Hu,

Tianshu Kuai,

Ali Harakeh,

Liam Paull,

Steven L. Waslander

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Mahmoud_2023_CVPR, author = {Mahmoud, Anas and Hu, Jordan S. K. and Kuai, Tianshu and Harakeh, Ali and Paull, Liam and Waslander, Steven L.}, title = {Self-Supervised Image-to-Point Distillation via Semantically Tolerant Contrastive Loss}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7102-7110} }

ProtoCon: Pseudo-Label Refinement via Online Clustering and Prototypical Consistency for Efficient Semi-Supervised Learning

Islam Nassar,

Munawar Hayat,

Ehsan Abbasnejad,

Hamid Rezatofighi,

Gholamreza Haffari

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Nassar_2023_CVPR, author = {Nassar, Islam and Hayat, Munawar and Abbasnejad, Ehsan and Rezatofighi, Hamid and Haffari, Gholamreza}, title = {ProtoCon: Pseudo-Label Refinement via Online Clustering and Prototypical Consistency for Efficient Semi-Supervised Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11641-11650} }

Image Super-Resolution Using T-Tetromino Pixels

Simon Grosche,

Andy Regensky,

Jürgen Seiler,

André Kaup

[pdf]

[bibtex]

@InProceedings{Grosche_2023_CVPR, author = {Grosche, Simon and Regensky, Andy and Seiler, J\"urgen and Kaup, Andr\'e}, title = {Image Super-Resolution Using T-Tetromino Pixels}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9989-9998} }

GFIE: A Dataset and Baseline for Gaze-Following From 2D to 3D in Indoor Environments

Zhengxi Hu,

Yuxue Yang,

Xiaolin Zhai,

Dingye Yang,

Bohan Zhou,

Jingtai Liu

[pdf] [supp]

[bibtex]

@InProceedings{Hu_2023_CVPR, author = {Hu, Zhengxi and Yang, Yuxue and Zhai, Xiaolin and Yang, Dingye and Zhou, Bohan and Liu, Jingtai}, title = {GFIE: A Dataset and Baseline for Gaze-Following From 2D to 3D in Indoor Environments}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8907-8916} }

Efficient Robust Principal Component Analysis via Block Krylov Iteration and CUR Decomposition

Shun Fang,

Zhengqin Xu,

Shiqian Wu,

Shoulie Xie

[pdf] [supp]

[bibtex]

@InProceedings{Fang_2023_CVPR, author = {Fang, Shun and Xu, Zhengqin and Wu, Shiqian and Xie, Shoulie}, title = {Efficient Robust Principal Component Analysis via Block Krylov Iteration and CUR Decomposition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1348-1357} }

VIVE3D: Viewpoint-Independent Video Editing Using 3D-Aware GANs

Anna Frühstück,

Nikolaos Sarafianos,

Yuanlu Xu,

Peter Wonka,

Tony Tung

[pdf] [supp]

[bibtex]

@InProceedings{Fruhstuck_2023_CVPR, author = {Fr\"uhst\"uck, Anna and Sarafianos, Nikolaos and Xu, Yuanlu and Wonka, Peter and Tung, Tony}, title = {VIVE3D: Viewpoint-Independent Video Editing Using 3D-Aware GANs}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4446-4455} }

Unsupervised Sampling Promoting for Stochastic Human Trajectory Prediction

Guangyi Chen,

Zhenhao Chen,

Shunxing Fan,

Kun Zhang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Chen_2023_CVPR, author = {Chen, Guangyi and Chen, Zhenhao and Fan, Shunxing and Zhang, Kun}, title = {Unsupervised Sampling Promoting for Stochastic Human Trajectory Prediction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {17874-17884} }

BKinD-3D: Self-Supervised 3D Keypoint Discovery From Multi-View Videos

Jennifer J. Sun,

Lili Karashchuk,

Amil Dravid,

Serim Ryou,

Sonia Fereidooni,

John C. Tuthill,

Aggelos Katsaggelos,

Bingni W. Brunton,

Georgia Gkioxari,

Ann Kennedy,

Yisong Yue,

Pietro Perona

[pdf] [supp]

[bibtex]

@InProceedings{Sun_2023_CVPR, author = {Sun, Jennifer J. and Karashchuk, Lili and Dravid, Amil and Ryou, Serim and Fereidooni, Sonia and Tuthill, John C. and Katsaggelos, Aggelos and Brunton, Bingni W. and Gkioxari, Georgia and Kennedy, Ann and Yue, Yisong and Perona, Pietro}, title = {BKinD-3D: Self-Supervised 3D Keypoint Discovery From Multi-View Videos}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9001-9010} }

StyleRF: Zero-Shot 3D Style Transfer of Neural Radiance Fields

Kunhao Liu,

Fangneng Zhan,

Yiwen Chen,

Jiahui Zhang,

Yingchen Yu,

Abdulmotaleb El Saddik,

Shijian Lu,

Eric P. Xing

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Liu_2023_CVPR, author = {Liu, Kunhao and Zhan, Fangneng and Chen, Yiwen and Zhang, Jiahui and Yu, Yingchen and El Saddik, Abdulmotaleb and Lu, Shijian and Xing, Eric P.}, title = {StyleRF: Zero-Shot 3D Style Transfer of Neural Radiance Fields}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8338-8348} }

Accidental Light Probes

Hong-Xing Yu,

Samir Agarwala,

Charles Herrmann,

Richard Szeliski,

Noah Snavely,

Jiajun Wu,

Deqing Sun

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Yu_2023_CVPR, author = {Yu, Hong-Xing and Agarwala, Samir and Herrmann, Charles and Szeliski, Richard and Snavely, Noah and Wu, Jiajun and Sun, Deqing}, title = {Accidental Light Probes}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12521-12530} }

Iterative Vision-and-Language Navigation

Jacob Krantz,

Shurjo Banerjee,

Wang Zhu,

Jason Corso,

Peter Anderson,

Stefan Lee,

Jesse Thomason

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Krantz_2023_CVPR, author = {Krantz, Jacob and Banerjee, Shurjo and Zhu, Wang and Corso, Jason and Anderson, Peter and Lee, Stefan and Thomason, Jesse}, title = {Iterative Vision-and-Language Navigation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14921-14930} }

DPE: Disentanglement of Pose and Expression for General Video Portrait Editing

Youxin Pang,

Yong Zhang,

Weize Quan,

Yanbo Fan,

Xiaodong Cun,

Ying Shan,

Dong-Ming Yan

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Pang_2023_CVPR, author = {Pang, Youxin and Zhang, Yong and Quan, Weize and Fan, Yanbo and Cun, Xiaodong and Shan, Ying and Yan, Dong-Ming}, title = {DPE: Disentanglement of Pose and Expression for General Video Portrait Editing}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {427-436} }

Adversarial Counterfactual Visual Explanations

Guillaume Jeanneret,

Loïc Simon,

Frédéric Jurie

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Jeanneret_2023_CVPR, author = {Jeanneret, Guillaume and Simon, Lo{\"\i}c and Jurie, Fr\'ed\'eric}, title = {Adversarial Counterfactual Visual Explanations}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16425-16435} }

MaLP: Manipulation Localization Using a Proactive Scheme

Vishal Asnani,

Xi Yin,

Tal Hassner,

Xiaoming Liu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Asnani_2023_CVPR, author = {Asnani, Vishal and Yin, Xi and Hassner, Tal and Liu, Xiaoming}, title = {MaLP: Manipulation Localization Using a Proactive Scheme}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12343-12352} }

Safe Latent Diffusion: Mitigating Inappropriate Degeneration in Diffusion Models

Patrick Schramowski,

Manuel Brack,

Björn Deiseroth,

Kristian Kersting

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Schramowski_2023_CVPR, author = {Schramowski, Patrick and Brack, Manuel and Deiseroth, Bj\"orn and Kersting, Kristian}, title = {Safe Latent Diffusion: Mitigating Inappropriate Degeneration in Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {22522-22531} }

MM-Diffusion: Learning Multi-Modal Diffusion Models for Joint Audio and Video Generation

Ludan Ruan,

Yiyang Ma,

Huan Yang,

Huiguo He,

Bei Liu,

Jianlong Fu,

Nicholas Jing Yuan,

Qin Jin,

Baining Guo

[pdf] [supp]

[bibtex]

@InProceedings{Ruan_2023_CVPR, author = {Ruan, Ludan and Ma, Yiyang and Yang, Huan and He, Huiguo and Liu, Bei and Fu, Jianlong and Yuan, Nicholas Jing and Jin, Qin and Guo, Baining}, title = {MM-Diffusion: Learning Multi-Modal Diffusion Models for Joint Audio and Video Generation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10219-10228} }

HexPlane: A Fast Representation for Dynamic Scenes

Ang Cao,

Justin Johnson

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Cao_2023_CVPR, author = {Cao, Ang and Johnson, Justin}, title = {HexPlane: A Fast Representation for Dynamic Scenes}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {130-141} }

Boosting Semi-Supervised Learning by Exploiting All Unlabeled Data

Yuhao Chen,

Xin Tan,

Borui Zhao,

Zhaowei Chen,

Renjie Song,

Jiajun Liang,

Xuequan Lu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Chen_2023_CVPR, author = {Chen, Yuhao and Tan, Xin and Zhao, Borui and Chen, Zhaowei and Song, Renjie and Liang, Jiajun and Lu, Xuequan}, title = {Boosting Semi-Supervised Learning by Exploiting All Unlabeled Data}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7548-7557} }

Novel-View Acoustic Synthesis

Changan Chen,

Alexander Richard,

Roman Shapovalov,

Vamsi Krishna Ithapu,

Natalia Neverova,

Kristen Grauman,

Andrea Vedaldi

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Chen_2023_CVPR, author = {Chen, Changan and Richard, Alexander and Shapovalov, Roman and Ithapu, Vamsi Krishna and Neverova, Natalia and Grauman, Kristen and Vedaldi, Andrea}, title = {Novel-View Acoustic Synthesis}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6409-6419} }

Robust Generalization Against Photon-Limited Corruptions via Worst-Case Sharpness Minimization

Zhuo Huang,

Miaoxi Zhu,

Xiaobo Xia,

Li Shen,

Jun Yu,

Chen Gong,

Bo Han,

Bo Du,

Tongliang Liu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Huang_2023_CVPR, author = {Huang, Zhuo and Zhu, Miaoxi and Xia, Xiaobo and Shen, Li and Yu, Jun and Gong, Chen and Han, Bo and Du, Bo and Liu, Tongliang}, title = {Robust Generalization Against Photon-Limited Corruptions via Worst-Case Sharpness Minimization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16175-16185} }

Point2Pix: Photo-Realistic Point Cloud Rendering via Neural Radiance Fields

Tao Hu,

Xiaogang Xu,

Shu Liu,

Jiaya Jia

[pdf] [arXiv]

[bibtex]

@InProceedings{Hu_2023_CVPR, author = {Hu, Tao and Xu, Xiaogang and Liu, Shu and Jia, Jiaya}, title = {Point2Pix: Photo-Realistic Point Cloud Rendering via Neural Radiance Fields}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8349-8358} }

Superclass Learning With Representation Enhancement

Zeyu Gan,

Suyun Zhao,

Jinlong Kang,

Liyuan Shang,

Hong Chen,

Cuiping Li

[pdf] [supp]

[bibtex]

@InProceedings{Gan_2023_CVPR, author = {Gan, Zeyu and Zhao, Suyun and Kang, Jinlong and Shang, Liyuan and Chen, Hong and Li, Cuiping}, title = {Superclass Learning With Representation Enhancement}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {24060-24069} }

Visual Prompt Tuning for Generative Transfer Learning

Kihyuk Sohn,

Huiwen Chang,

José Lezama,

Luisa Polania,

Han Zhang,

Yuan Hao,

Irfan Essa,

Lu Jiang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Sohn_2023_CVPR, author = {Sohn, Kihyuk and Chang, Huiwen and Lezama, Jos\'e and Polania, Luisa and Zhang, Han and Hao, Yuan and Essa, Irfan and Jiang, Lu}, title = {Visual Prompt Tuning for Generative Transfer Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {19840-19851} }

NICO++: Towards Better Benchmarking for Domain Generalization

Xingxuan Zhang,

Yue He,

Renzhe Xu,

Han Yu,

Zheyan Shen,

Peng Cui

[pdf] [supp]

[bibtex]

@InProceedings{Zhang_2023_CVPR, author = {Zhang, Xingxuan and He, Yue and Xu, Renzhe and Yu, Han and Shen, Zheyan and Cui, Peng}, title = {NICO++: Towards Better Benchmarking for Domain Generalization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16036-16047} }

CHMATCH: Contrastive Hierarchical Matching and Robust Adaptive Threshold Boosted Semi-Supervised Learning

Jianlong Wu,

Haozhe Yang,

Tian Gan,

Ning Ding,

Feijun Jiang,

Liqiang Nie

[pdf] [supp]

[bibtex]

@InProceedings{Wu_2023_CVPR, author = {Wu, Jianlong and Yang, Haozhe and Gan, Tian and Ding, Ning and Jiang, Feijun and Nie, Liqiang}, title = {CHMATCH: Contrastive Hierarchical Matching and Robust Adaptive Threshold Boosted Semi-Supervised Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15762-15772} }

Neural Dependencies Emerging From Learning Massive Categories

Ruili Feng,

Kecheng Zheng,

Kai Zhu,

Yujun Shen,

Jian Zhao,

Yukun Huang,

Deli Zhao,

Jingren Zhou,

Michael Jordan,

Zheng-Jun Zha

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Feng_2023_CVPR, author = {Feng, Ruili and Zheng, Kecheng and Zhu, Kai and Shen, Yujun and Zhao, Jian and Huang, Yukun and Zhao, Deli and Zhou, Jingren and Jordan, Michael and Zha, Zheng-Jun}, title = {Neural Dependencies Emerging From Learning Massive Categories}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11711-11720} }

ReLight My NeRF: A Dataset for Novel View Synthesis and Relighting of Real World Objects

Marco Toschi,

Riccardo De Matteo,

Riccardo Spezialetti,

Daniele De Gregorio,

Luigi Di Stefano,

Samuele Salti

[pdf] [arXiv]

[bibtex]

@InProceedings{Toschi_2023_CVPR, author = {Toschi, Marco and De Matteo, Riccardo and Spezialetti, Riccardo and De Gregorio, Daniele and Di Stefano, Luigi and Salti, Samuele}, title = {ReLight My NeRF: A Dataset for Novel View Synthesis and Relighting of Real World Objects}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {20762-20772} }

ARCTIC: A Dataset for Dexterous Bimanual Hand-Object Manipulation

Zicong Fan,

Omid Taheri,

Dimitrios Tzionas,

Muhammed Kocabas,

Manuel Kaufmann,

Michael J. Black,

Otmar Hilliges

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Fan_2023_CVPR, author = {Fan, Zicong and Taheri, Omid and Tzionas, Dimitrios and Kocabas, Muhammed and Kaufmann, Manuel and Black, Michael J. and Hilliges, Otmar}, title = {ARCTIC: A Dataset for Dexterous Bimanual Hand-Object Manipulation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12943-12954} }

Constrained Evolutionary Diffusion Filter for Monocular Endoscope Tracking

Xiongbiao Luo

[pdf]

[bibtex]

@InProceedings{Luo_2023_CVPR, author = {Luo, Xiongbiao}, title = {Constrained Evolutionary Diffusion Filter for Monocular Endoscope Tracking}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4747-4756} }

MAGVIT: Masked Generative Video Transformer

Lijun Yu,

Yong Cheng,

Kihyuk Sohn,

José Lezama,

Han Zhang,

Huiwen Chang,

Alexander G. Hauptmann,

Ming-Hsuan Yang,

Yuan Hao,

Irfan Essa,

Lu Jiang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Yu_2023_CVPR, author = {Yu, Lijun and Cheng, Yong and Sohn, Kihyuk and Lezama, Jos\'e and Zhang, Han and Chang, Huiwen and Hauptmann, Alexander G. and Yang, Ming-Hsuan and Hao, Yuan and Essa, Irfan and Jiang, Lu}, title = {MAGVIT: Masked Generative Video Transformer}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10459-10469} }

Content-Aware Token Sharing for Efficient Semantic Segmentation With Vision Transformers

Chenyang Lu,

Daan de Geus,

Gijs Dubbelman

[pdf] [supp]

[bibtex]

@InProceedings{Lu_2023_CVPR, author = {Lu, Chenyang and de Geus, Daan and Dubbelman, Gijs}, title = {Content-Aware Token Sharing for Efficient Semantic Segmentation With Vision Transformers}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {23631-23640} }

Toward Accurate Post-Training Quantization for Image Super Resolution

Zhijun Tu,

Jie Hu,

Hanting Chen,

Yunhe Wang

[pdf] [supp]

[bibtex]

@InProceedings{Tu_2023_CVPR, author = {Tu, Zhijun and Hu, Jie and Chen, Hanting and Wang, Yunhe}, title = {Toward Accurate Post-Training Quantization for Image Super Resolution}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5856-5865} }

Hidden Gems: 4D Radar Scene Flow Learning Using Cross-Modal Supervision

Fangqiang Ding,

Andras Palffy,

Dariu M. Gavrila,

Chris Xiaoxuan Lu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Ding_2023_CVPR, author = {Ding, Fangqiang and Palffy, Andras and Gavrila, Dariu M. and Lu, Chris Xiaoxuan}, title = {Hidden Gems: 4D Radar Scene Flow Learning Using Cross-Modal Supervision}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9340-9349} }

OmniMAE: Single Model Masked Pretraining on Images and Videos

Rohit Girdhar,

Alaaeldin El-Nouby,

Mannat Singh,

Kalyan Vasudev Alwala,

Armand Joulin,

Ishan Misra

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Girdhar_2023_CVPR, author = {Girdhar, Rohit and El-Nouby, Alaaeldin and Singh, Mannat and Alwala, Kalyan Vasudev and Joulin, Armand and Misra, Ishan}, title = {OmniMAE: Single Model Masked Pretraining on Images and Videos}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10406-10417} }

Omnimatte3D: Associating Objects and Their Effects in Unconstrained Monocular Video

Mohammed Suhail,

Erika Lu,

Zhengqi Li,

Noah Snavely,

Leonid Sigal,

Forrester Cole

[pdf] [supp]

[bibtex]

@InProceedings{Suhail_2023_CVPR, author = {Suhail, Mohammed and Lu, Erika and Li, Zhengqi and Snavely, Noah and Sigal, Leonid and Cole, Forrester}, title = {Omnimatte3D: Associating Objects and Their Effects in Unconstrained Monocular Video}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {630-639} }

Real-Time Neural Light Field on Mobile Devices

Junli Cao,

Huan Wang,

Pavlo Chemerys,

Vladislav Shakhrai,

Ju Hu,

Yun Fu,

Denys Makoviichuk,

Sergey Tulyakov,

Jian Ren

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Cao_2023_CVPR, author = {Cao, Junli and Wang, Huan and Chemerys, Pavlo and Shakhrai, Vladislav and Hu, Ju and Fu, Yun and Makoviichuk, Denys and Tulyakov, Sergey and Ren, Jian}, title = {Real-Time Neural Light Field on Mobile Devices}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8328-8337} }

Incrementer: Transformer for Class-Incremental Semantic Segmentation With Knowledge Distillation Focusing on Old Class

Chao Shang,

Hongliang Li,

Fanman Meng,

Qingbo Wu,

Heqian Qiu,

Lanxiao Wang

[pdf]

[bibtex]

@InProceedings{Shang_2023_CVPR, author = {Shang, Chao and Li, Hongliang and Meng, Fanman and Wu, Qingbo and Qiu, Heqian and Wang, Lanxiao}, title = {Incrementer: Transformer for Class-Incremental Semantic Segmentation With Knowledge Distillation Focusing on Old Class}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7214-7224} }

End-to-End Video Matting With Trimap Propagation

Wei-Lun Huang,

Ming-Sui Lee

[pdf] [supp]

[bibtex]

@InProceedings{Huang_2023_CVPR, author = {Huang, Wei-Lun and Lee, Ming-Sui}, title = {End-to-End Video Matting With Trimap Propagation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14337-14347} }

DropMAE: Masked Autoencoders With Spatial-Attention Dropout for Tracking Tasks

Qiangqiang Wu,

Tianyu Yang,

Ziquan Liu,

Baoyuan Wu,

Ying Shan,

Antoni B. Chan

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Wu_2023_CVPR, author = {Wu, Qiangqiang and Yang, Tianyu and Liu, Ziquan and Wu, Baoyuan and Shan, Ying and Chan, Antoni B.}, title = {DropMAE: Masked Autoencoders With Spatial-Attention Dropout for Tracking Tasks}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14561-14571} }

Are Binary Annotations Sufficient? Video Moment Retrieval via Hierarchical Uncertainty-Based Active Learning

Wei Ji,

Renjie Liang,

Zhedong Zheng,

Wenqiao Zhang,

Shengyu Zhang,

Juncheng Li,

Mengze Li,

Tat-seng Chua

[pdf]

[bibtex]

@InProceedings{Ji_2023_CVPR, author = {Ji, Wei and Liang, Renjie and Zheng, Zhedong and Zhang, Wenqiao and Zhang, Shengyu and Li, Juncheng and Li, Mengze and Chua, Tat-seng}, title = {Are Binary Annotations Sufficient? Video Moment Retrieval via Hierarchical Uncertainty-Based Active Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {23013-23022} }

High-Fidelity Clothed Avatar Reconstruction From a Single Image

Tingting Liao,

Xiaomei Zhang,

Yuliang Xiu,

Hongwei Yi,

Xudong Liu,

Guo-Jun Qi,

Yong Zhang,

Xuan Wang,

Xiangyu Zhu,

Zhen Lei

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Liao_2023_CVPR, author = {Liao, Tingting and Zhang, Xiaomei and Xiu, Yuliang and Yi, Hongwei and Liu, Xudong and Qi, Guo-Jun and Zhang, Yong and Wang, Xuan and Zhu, Xiangyu and Lei, Zhen}, title = {High-Fidelity Clothed Avatar Reconstruction From a Single Image}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8662-8672} }

Zero-Shot Object Counting

Jingyi Xu,

Hieu Le,

Vu Nguyen,

Viresh Ranjan,

Dimitris Samaras

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Xu_2023_CVPR, author = {Xu, Jingyi and Le, Hieu and Nguyen, Vu and Ranjan, Viresh and Samaras, Dimitris}, title = {Zero-Shot Object Counting}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15548-15557} }

Patch-Mix Transformer for Unsupervised Domain Adaptation: A Game Perspective

Jinjing Zhu,

Haotian Bai,

Lin Wang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Zhu_2023_CVPR, author = {Zhu, Jinjing and Bai, Haotian and Wang, Lin}, title = {Patch-Mix Transformer for Unsupervised Domain Adaptation: A Game Perspective}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3561-3571} }

Implicit Diffusion Models for Continuous Super-Resolution

Sicheng Gao,

Xuhui Liu,

Bohan Zeng,

Sheng Xu,

Yanjing Li,

Xiaoyan Luo,

Jianzhuang Liu,

Xiantong Zhen,

Baochang Zhang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Gao_2023_CVPR, author = {Gao, Sicheng and Liu, Xuhui and Zeng, Bohan and Xu, Sheng and Li, Yanjing and Luo, Xiaoyan and Liu, Jianzhuang and Zhen, Xiantong and Zhang, Baochang}, title = {Implicit Diffusion Models for Continuous Super-Resolution}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10021-10030} }

VGFlow: Visibility Guided Flow Network for Human Reposing

Rishabh Jain,

Krishna Kumar Singh,

Mayur Hemani,

Jingwan Lu,

Mausoom Sarkar,

Duygu Ceylan,

Balaji Krishnamurthy

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Jain_2023_CVPR, author = {Jain, Rishabh and Singh, Krishna Kumar and Hemani, Mayur and Lu, Jingwan and Sarkar, Mausoom and Ceylan, Duygu and Krishnamurthy, Balaji}, title = {VGFlow: Visibility Guided Flow Network for Human Reposing}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {21088-21097} }

Phase-Shifting Coder: Predicting Accurate Orientation in Oriented Object Detection

Yi Yu,

Feipeng Da

[pdf] [arXiv]

[bibtex]

@InProceedings{Yu_2023_CVPR, author = {Yu, Yi and Da, Feipeng}, title = {Phase-Shifting Coder: Predicting Accurate Orientation in Oriented Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13354-13363} }

Improving Selective Visual Question Answering by Learning From Your Peers

Corentin Dancette,

Spencer Whitehead,

Rishabh Maheshwary,

Ramakrishna Vedantam,

Stefan Scherer,

Xinlei Chen,

Matthieu Cord,

Marcus Rohrbach

[pdf] [supp]

[bibtex]

@InProceedings{Dancette_2023_CVPR, author = {Dancette, Corentin and Whitehead, Spencer and Maheshwary, Rishabh and Vedantam, Ramakrishna and Scherer, Stefan and Chen, Xinlei and Cord, Matthieu and Rohrbach, Marcus}, title = {Improving Selective Visual Question Answering by Learning From Your Peers}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {24049-24059} }

CAMS: CAnonicalized Manipulation Spaces for Category-Level Functional Hand-Object Manipulation Synthesis

Juntian Zheng,

Qingyuan Zheng,

Lixing Fang,

Yun Liu,

Li Yi

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Zheng_2023_CVPR, author = {Zheng, Juntian and Zheng, Qingyuan and Fang, Lixing and Liu, Yun and Yi, Li}, title = {CAMS: CAnonicalized Manipulation Spaces for Category-Level Functional Hand-Object Manipulation Synthesis}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {585-594} }

Neural Lens Modeling

Wenqi Xian,

Aljaž Božič,

Noah Snavely,

Christoph Lassner

[pdf] [supp]

[bibtex]

@InProceedings{Xian_2023_CVPR, author = {Xian, Wenqi and Bo\v{z}i\v{c}, Alja\v{z} and Snavely, Noah and Lassner, Christoph}, title = {Neural Lens Modeling}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8435-8445} }

CoralStyleCLIP: Co-Optimized Region and Layer Selection for Image Editing

Ambareesh Revanur,

Debraj Basu,

Shradha Agrawal,

Dhwanit Agarwal,

Deepak Pai

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Revanur_2023_CVPR, author = {Revanur, Ambareesh and Basu, Debraj and Agrawal, Shradha and Agarwal, Dhwanit and Pai, Deepak}, title = {CoralStyleCLIP: Co-Optimized Region and Layer Selection for Image Editing}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12695-12704} }

GLeaD: Improving GANs With a Generator-Leading Task

Qingyan Bai,

Ceyuan Yang,

Yinghao Xu,

Xihui Liu,

Yujiu Yang,

Yujun Shen

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Bai_2023_CVPR, author = {Bai, Qingyan and Yang, Ceyuan and Xu, Yinghao and Liu, Xihui and Yang, Yujiu and Shen, Yujun}, title = {GLeaD: Improving GANs With a Generator-Leading Task}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12094-12104} }

GALIP: Generative Adversarial CLIPs for Text-to-Image Synthesis

Ming Tao,

Bing-Kun Bao,

Hao Tang,

Changsheng Xu

[pdf] [arXiv]

[bibtex]

@InProceedings{Tao_2023_CVPR, author = {Tao, Ming and Bao, Bing-Kun and Tang, Hao and Xu, Changsheng}, title = {GALIP: Generative Adversarial CLIPs for Text-to-Image Synthesis}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14214-14223} }

Look, Radiate, and Learn: Self-Supervised Localisation via Radio-Visual Correspondence

Mohammed Alloulah,

Maximilian Arnold

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Alloulah_2023_CVPR, author = {Alloulah, Mohammed and Arnold, Maximilian}, title = {Look, Radiate, and Learn: Self-Supervised Localisation via Radio-Visual Correspondence}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {17430-17440} }

Multiplicative Fourier Level of Detail

Yishun Dou,

Zhong Zheng,

Qiaoqiao Jin,

Bingbing Ni

[pdf] [supp]

[bibtex]

@InProceedings{Dou_2023_CVPR, author = {Dou, Yishun and Zheng, Zhong and Jin, Qiaoqiao and Ni, Bingbing}, title = {Multiplicative Fourier Level of Detail}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1808-1817} }

Indiscernible Object Counting in Underwater Scenes

Guolei Sun,

Zhaochong An,

Yun Liu,

Ce Liu,

Christos Sakaridis,

Deng-Ping Fan,

Luc Van Gool

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Sun_2023_CVPR, author = {Sun, Guolei and An, Zhaochong and Liu, Yun and Liu, Ce and Sakaridis, Christos and Fan, Deng-Ping and Van Gool, Luc}, title = {Indiscernible Object Counting in Underwater Scenes}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13791-13801} }

Shape-Erased Feature Learning for Visible-Infrared Person Re-Identification

Jiawei Feng,

Ancong Wu,

Wei-Shi Zheng

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Feng_2023_CVPR, author = {Feng, Jiawei and Wu, Ancong and Zheng, Wei-Shi}, title = {Shape-Erased Feature Learning for Visible-Infrared Person Re-Identification}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {22752-22761} }

Relational Context Learning for Human-Object Interaction Detection

Sanghyun Kim,

Deunsol Jung,

Minsu Cho

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Kim_2023_CVPR, author = {Kim, Sanghyun and Jung, Deunsol and Cho, Minsu}, title = {Relational Context Learning for Human-Object Interaction Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2925-2934} }

Low-Light Image Enhancement via Structure Modeling and Guidance

Xiaogang Xu,

Ruixing Wang,

Jiangbo Lu

[pdf] [arXiv]

[bibtex]

@InProceedings{Xu_2023_CVPR, author = {Xu, Xiaogang and Wang, Ruixing and Lu, Jiangbo}, title = {Low-Light Image Enhancement via Structure Modeling and Guidance}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9893-9903} }

On Calibrating Semantic Segmentation Models: Analyses and an Algorithm

Dongdong Wang,

Boqing Gong,

Liqiang Wang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Dongdong and Gong, Boqing and Wang, Liqiang}, title = {On Calibrating Semantic Segmentation Models: Analyses and an Algorithm}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {23652-23662} }

Visual Atoms: Pre-Training Vision Transformers With Sinusoidal Waves

Sora Takashima,

Ryo Hayamizu,

Nakamasa Inoue,

Hirokatsu Kataoka,

Rio Yokota

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Takashima_2023_CVPR, author = {Takashima, Sora and Hayamizu, Ryo and Inoue, Nakamasa and Kataoka, Hirokatsu and Yokota, Rio}, title = {Visual Atoms: Pre-Training Vision Transformers With Sinusoidal Waves}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {18579-18588} }

Multi-Label Compound Expression Recognition: C-EXPR Database & Network

Dimitrios Kollias

[pdf] [supp]

[bibtex]

@InProceedings{Kollias_2023_CVPR, author = {Kollias, Dimitrios}, title = {Multi-Label Compound Expression Recognition: C-EXPR Database \& Network}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5589-5598} }

Masked Autoencoding Does Not Help Natural Language Supervision at Scale

Floris Weers,

Vaishaal Shankar,

Angelos Katharopoulos,

Yinfei Yang,

Tom Gunter

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Weers_2023_CVPR, author = {Weers, Floris and Shankar, Vaishaal and Katharopoulos, Angelos and Yang, Yinfei and Gunter, Tom}, title = {Masked Autoencoding Does Not Help Natural Language Supervision at Scale}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {23432-23444} }

CORA: Adapting CLIP for Open-Vocabulary Detection With Region Prompting and Anchor Pre-Matching

Xiaoshi Wu,

Feng Zhu,

Rui Zhao,

Hongsheng Li

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Wu_2023_CVPR, author = {Wu, Xiaoshi and Zhu, Feng and Zhao, Rui and Li, Hongsheng}, title = {CORA: Adapting CLIP for Open-Vocabulary Detection With Region Prompting and Anchor Pre-Matching}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7031-7040} }

3DAvatarGAN: Bridging Domains for Personalized Editable Avatars

Rameen Abdal,

Hsin-Ying Lee,

Peihao Zhu,

Menglei Chai,

Aliaksandr Siarohin,

Peter Wonka,

Sergey Tulyakov

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Abdal_2023_CVPR, author = {Abdal, Rameen and Lee, Hsin-Ying and Zhu, Peihao and Chai, Menglei and Siarohin, Aliaksandr and Wonka, Peter and Tulyakov, Sergey}, title = {3DAvatarGAN: Bridging Domains for Personalized Editable Avatars}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4552-4562} }

Physics-Driven Diffusion Models for Impact Sound Synthesis From Videos

Kun Su,

Kaizhi Qian,

Eli Shlizerman,

Antonio Torralba,

Chuang Gan

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Su_2023_CVPR, author = {Su, Kun and Qian, Kaizhi and Shlizerman, Eli and Torralba, Antonio and Gan, Chuang}, title = {Physics-Driven Diffusion Models for Impact Sound Synthesis From Videos}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9749-9759} }

Transductive Few-Shot Learning With Prototype-Based Label Propagation by Iterative Graph Refinement

Hao Zhu,

Piotr Koniusz

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Zhu_2023_CVPR, author = {Zhu, Hao and Koniusz, Piotr}, title = {Transductive Few-Shot Learning With Prototype-Based Label Propagation by Iterative Graph Refinement}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {23996-24006} }

Discriminative Co-Saliency and Background Mining Transformer for Co-Salient Object Detection

Long Li,

Junwei Han,

Ni Zhang,

Nian Liu,

Salman Khan,

Hisham Cholakkal,

Rao Muhammad Anwer,

Fahad Shahbaz Khan

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Li_2023_CVPR, author = {Li, Long and Han, Junwei and Zhang, Ni and Liu, Nian and Khan, Salman and Cholakkal, Hisham and Anwer, Rao Muhammad and Khan, Fahad Shahbaz}, title = {Discriminative Co-Saliency and Background Mining Transformer for Co-Salient Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7247-7256} }

Alias-Free Convnets: Fractional Shift Invariance via Polynomial Activations

Hagay Michaeli,

Tomer Michaeli,

Daniel Soudry

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Michaeli_2023_CVPR, author = {Michaeli, Hagay and Michaeli, Tomer and Soudry, Daniel}, title = {Alias-Free Convnets: Fractional Shift Invariance via Polynomial Activations}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16333-16342} }

Binary Latent Diffusion

Ze Wang,

Jiang Wang,

Zicheng Liu,

Qiang Qiu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Ze and Wang, Jiang and Liu, Zicheng and Qiu, Qiang}, title = {Binary Latent Diffusion}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {22576-22585} }

Person Image Synthesis via Denoising Diffusion Model

Ankan Kumar Bhunia,

Salman Khan,

Hisham Cholakkal,

Rao Muhammad Anwer,

Jorma Laaksonen,

Mubarak Shah,

Fahad Shahbaz Khan

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Bhunia_2023_CVPR, author = {Bhunia, Ankan Kumar and Khan, Salman and Cholakkal, Hisham and Anwer, Rao Muhammad and Laaksonen, Jorma and Shah, Mubarak and Khan, Fahad Shahbaz}, title = {Person Image Synthesis via Denoising Diffusion Model}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5968-5976} }

Shortcomings of Top-Down Randomization-Based Sanity Checks for Evaluations of Deep Neural Network Explanations

Alexander Binder,

Leander Weber,

Sebastian Lapuschkin,

Grégoire Montavon,

Klaus-Robert Müller,

Wojciech Samek

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Binder_2023_CVPR, author = {Binder, Alexander and Weber, Leander and Lapuschkin, Sebastian and Montavon, Gr\'egoire and M\"uller, Klaus-Robert and Samek, Wojciech}, title = {Shortcomings of Top-Down Randomization-Based Sanity Checks for Evaluations of Deep Neural Network Explanations}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16143-16152} }

Neural Part Priors: Learning To Optimize Part-Based Object Completion in RGB-D Scans

Aleksei Bokhovkin,

Angela Dai

[pdf] [supp]

[bibtex]

@InProceedings{Bokhovkin_2023_CVPR, author = {Bokhovkin, Aleksei and Dai, Angela}, title = {Neural Part Priors: Learning To Optimize Part-Based Object Completion in RGB-D Scans}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9032-9042} }

Adaptive Assignment for Geometry Aware Local Feature Matching

Dihe Huang,

Ying Chen,

Yong Liu,

Jianlin Liu,

Shang Xu,

Wenlong Wu,

Yikang Ding,

Fan Tang,

Chengjie Wang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Huang_2023_CVPR, author = {Huang, Dihe and Chen, Ying and Liu, Yong and Liu, Jianlin and Xu, Shang and Wu, Wenlong and Ding, Yikang and Tang, Fan and Wang, Chengjie}, title = {Adaptive Assignment for Geometry Aware Local Feature Matching}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5425-5434} }

Initialization Noise in Image Gradients and Saliency Maps

Ann-Christin Woerl,

Jan Disselhoff,

Michael Wand

[pdf] [supp]

[bibtex]

@InProceedings{Woerl_2023_CVPR, author = {Woerl, Ann-Christin and Disselhoff, Jan and Wand, Michael}, title = {Initialization Noise in Image Gradients and Saliency Maps}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1766-1775} }

FLAG3D: A 3D Fitness Activity Dataset With Language Instruction

Yansong Tang,

Jinpeng Liu,

Aoyang Liu,

Bin Yang,

Wenxun Dai,

Yongming Rao,

Jiwen Lu,

Jie Zhou,

Xiu Li

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Tang_2023_CVPR, author = {Tang, Yansong and Liu, Jinpeng and Liu, Aoyang and Yang, Bin and Dai, Wenxun and Rao, Yongming and Lu, Jiwen and Zhou, Jie and Li, Xiu}, title = {FLAG3D: A 3D Fitness Activity Dataset With Language Instruction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {22106-22117} }

Implicit Neural Head Synthesis via Controllable Local Deformation Fields

Chuhan Chen,

Matthew O’Toole,

Gaurav Bharaj,

Pablo Garrido

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Chen_2023_CVPR, author = {Chen, Chuhan and O{\textquoteright}Toole, Matthew and Bharaj, Gaurav and Garrido, Pablo}, title = {Implicit Neural Head Synthesis via Controllable Local Deformation Fields}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {416-426} }

NeuralUDF: Learning Unsigned Distance Fields for Multi-View Reconstruction of Surfaces With Arbitrary Topologies

Xiaoxiao Long,

Cheng Lin,

Lingjie Liu,

Yuan Liu,

Peng Wang,

Christian Theobalt,

Taku Komura,

Wenping Wang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Long_2023_CVPR, author = {Long, Xiaoxiao and Lin, Cheng and Liu, Lingjie and Liu, Yuan and Wang, Peng and Theobalt, Christian and Komura, Taku and Wang, Wenping}, title = {NeuralUDF: Learning Unsigned Distance Fields for Multi-View Reconstruction of Surfaces With Arbitrary Topologies}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {20834-20843} }

Towards Trustable Skin Cancer Diagnosis via Rewriting Model's Decision

Siyuan Yan,

Zhen Yu,

Xuelin Zhang,

Dwarikanath Mahapatra,

Shekhar S. Chandra,

Monika Janda,

Peter Soyer,

Zongyuan Ge

[pdf] [supp]

[bibtex]

@InProceedings{Yan_2023_CVPR, author = {Yan, Siyuan and Yu, Zhen and Zhang, Xuelin and Mahapatra, Dwarikanath and Chandra, Shekhar S. and Janda, Monika and Soyer, Peter and Ge, Zongyuan}, title = {Towards Trustable Skin Cancer Diagnosis via Rewriting Model's Decision}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11568-11577} }

Curricular Object Manipulation in LiDAR-Based Object Detection

Ziyue Zhu,

Qiang Meng,

Xiao Wang,

Ke Wang,

Liujiang Yan,

Jian Yang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Zhu_2023_CVPR, author = {Zhu, Ziyue and Meng, Qiang and Wang, Xiao and Wang, Ke and Yan, Liujiang and Yang, Jian}, title = {Curricular Object Manipulation in LiDAR-Based Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1125-1135} }

Collaborative Static and Dynamic Vision-Language Streams for Spatio-Temporal Video Grounding

Zihang Lin,

Chaolei Tan,

Jian-Fang Hu,

Zhi Jin,

Tiancai Ye,

Wei-Shi Zheng

[pdf] [supp]

[bibtex]

@InProceedings{Lin_2023_CVPR, author = {Lin, Zihang and Tan, Chaolei and Hu, Jian-Fang and Jin, Zhi and Ye, Tiancai and Zheng, Wei-Shi}, title = {Collaborative Static and Dynamic Vision-Language Streams for Spatio-Temporal Video Grounding}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {23100-23109} }

Shape-Constraint Recurrent Flow for 6D Object Pose Estimation

Yang Hai,

Rui Song,

Jiaojiao Li,

Yinlin Hu

[pdf]

[bibtex]

@InProceedings{Hai_2023_CVPR, author = {Hai, Yang and Song, Rui and Li, Jiaojiao and Hu, Yinlin}, title = {Shape-Constraint Recurrent Flow for 6D Object Pose Estimation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4831-4840} }

FeatER: An Efficient Network for Human Reconstruction via Feature Map-Based TransformER

Ce Zheng,

Matias Mendieta,

Taojiannan Yang,

Guo-Jun Qi,

Chen Chen

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Zheng_2023_CVPR, author = {Zheng, Ce and Mendieta, Matias and Yang, Taojiannan and Qi, Guo-Jun and Chen, Chen}, title = {FeatER: An Efficient Network for Human Reconstruction via Feature Map-Based TransformER}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13945-13954} }

Micron-BERT: BERT-Based Facial Micro-Expression Recognition

Xuan-Bac Nguyen,

Chi Nhan Duong,

Xin Li,

Susan Gauch,

Han-Seok Seo,

Khoa Luu

[pdf]

[bibtex]

@InProceedings{Nguyen_2023_CVPR, author = {Nguyen, Xuan-Bac and Duong, Chi Nhan and Li, Xin and Gauch, Susan and Seo, Han-Seok and Luu, Khoa}, title = {Micron-BERT: BERT-Based Facial Micro-Expression Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1482-1492} }

Residual Degradation Learning Unfolding Framework With Mixing Priors Across Spectral and Spatial for Compressive Spectral Imaging

Yubo Dong,

Dahua Gao,

Tian Qiu,

Yuyan Li,

Minxi Yang,

Guangming Shi

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Dong_2023_CVPR, author = {Dong, Yubo and Gao, Dahua and Qiu, Tian and Li, Yuyan and Yang, Minxi and Shi, Guangming}, title = {Residual Degradation Learning Unfolding Framework With Mixing Priors Across Spectral and Spatial for Compressive Spectral Imaging}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {22262-22271} }

Visibility Constrained Wide-Band Illumination Spectrum Design for Seeing-in-the-Dark

Muyao Niu,

Zhuoxiao Li,

Zhihang Zhong,

Yinqiang Zheng

[pdf] [arXiv]

[bibtex]

@InProceedings{Niu_2023_CVPR, author = {Niu, Muyao and Li, Zhuoxiao and Zhong, Zhihang and Zheng, Yinqiang}, title = {Visibility Constrained Wide-Band Illumination Spectrum Design for Seeing-in-the-Dark}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13976-13985} }

PanelNet: Understanding 360 Indoor Environment via Panel Representation

Haozheng Yu,

Lu He,

Bing Jian,

Weiwei Feng,

Shan Liu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Yu_2023_CVPR, author = {Yu, Haozheng and He, Lu and Jian, Bing and Feng, Weiwei and Liu, Shan}, title = {PanelNet: Understanding 360 Indoor Environment via Panel Representation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {878-887} }

Learning With Noisy Labels via Self-Supervised Adversarial Noisy Masking

Yuanpeng Tu,

Boshen Zhang,

Yuxi Li,

Liang Liu,

Jian Li,

Jiangning Zhang,

Yabiao Wang,

Chengjie Wang,

Cai Rong Zhao

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Tu_2023_CVPR, author = {Tu, Yuanpeng and Zhang, Boshen and Li, Yuxi and Liu, Liang and Li, Jian and Zhang, Jiangning and Wang, Yabiao and Wang, Chengjie and Zhao, Cai Rong}, title = {Learning With Noisy Labels via Self-Supervised Adversarial Noisy Masking}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16186-16195} }

PoseExaminer: Automated Testing of Out-of-Distribution Robustness in Human Pose and Shape Estimation

Qihao Liu,

Adam Kortylewski,

Alan L. Yuille

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Liu_2023_CVPR, author = {Liu, Qihao and Kortylewski, Adam and Yuille, Alan L.}, title = {PoseExaminer: Automated Testing of Out-of-Distribution Robustness in Human Pose and Shape Estimation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {672-681} }

GamutMLP: A Lightweight MLP for Color Loss Recovery

Hoang M. Le,

Brian Price,

Scott Cohen,

Michael S. Brown

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Le_2023_CVPR, author = {Le, Hoang M. and Price, Brian and Cohen, Scott and Brown, Michael S.}, title = {GamutMLP: A Lightweight MLP for Color Loss Recovery}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {18268-18277} }

Instance-Aware Domain Generalization for Face Anti-Spoofing

Qianyu Zhou,

Ke-Yue Zhang,

Taiping Yao,

Xuequan Lu,

Ran Yi,

Shouhong Ding,

Lizhuang Ma

[pdf] [arXiv]

[bibtex]

@InProceedings{Zhou_2023_CVPR, author = {Zhou, Qianyu and Zhang, Ke-Yue and Yao, Taiping and Lu, Xuequan and Yi, Ran and Ding, Shouhong and Ma, Lizhuang}, title = {Instance-Aware Domain Generalization for Face Anti-Spoofing}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {20453-20463} }

GANHead: Towards Generative Animatable Neural Head Avatars

Sijing Wu,

Yichao Yan,

Yunhao Li,

Yuhao Cheng,

Wenhan Zhu,

Ke Gao,

Xiaobo Li,

Guangtao Zhai

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Wu_2023_CVPR, author = {Wu, Sijing and Yan, Yichao and Li, Yunhao and Cheng, Yuhao and Zhu, Wenhan and Gao, Ke and Li, Xiaobo and Zhai, Guangtao}, title = {GANHead: Towards Generative Animatable Neural Head Avatars}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {437-447} }

Towards Domain Generalization for Multi-View 3D Object Detection in Bird-Eye-View

Shuo Wang,

Xinhai Zhao,

Hai-Ming Xu,

Zehui Chen,

Dameng Yu,

Jiahao Chang,

Zhen Yang,

Feng Zhao

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Shuo and Zhao, Xinhai and Xu, Hai-Ming and Chen, Zehui and Yu, Dameng and Chang, Jiahao and Yang, Zhen and Zhao, Feng}, title = {Towards Domain Generalization for Multi-View 3D Object Detection in Bird-Eye-View}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13333-13342} }

Robust and Scalable Gaussian Process Regression and Its Applications

Yifan Lu,

Jiayi Ma,

Leyuan Fang,

Xin Tian,

Junjun Jiang

[pdf] [supp]

[bibtex]

@InProceedings{Lu_2023_CVPR, author = {Lu, Yifan and Ma, Jiayi and Fang, Leyuan and Tian, Xin and Jiang, Junjun}, title = {Robust and Scalable Gaussian Process Regression and Its Applications}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {21950-21959} }

Deep Dive Into Gradients: Better Optimization for 3D Object Detection With Gradient-Corrected IoU Supervision

Qi Ming,

Lingjuan Miao,

Zhe Ma,

Lin Zhao,

Zhiqiang Zhou,

Xuhui Huang,

Yuanpei Chen,

Yufei Guo

[pdf]

[bibtex]

@InProceedings{Ming_2023_CVPR, author = {Ming, Qi and Miao, Lingjuan and Ma, Zhe and Zhao, Lin and Zhou, Zhiqiang and Huang, Xuhui and Chen, Yuanpei and Guo, Yufei}, title = {Deep Dive Into Gradients: Better Optimization for 3D Object Detection With Gradient-Corrected IoU Supervision}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5136-5145} }

Doubly Right Object Recognition: A Why Prompt for Visual Rationales

Chengzhi Mao,

Revant Teotia,

Amrutha Sundar,

Sachit Menon,

Junfeng Yang,

Xin Wang,

Carl Vondrick

[pdf] [arXiv]

[bibtex]

@InProceedings{Mao_2023_CVPR, author = {Mao, Chengzhi and Teotia, Revant and Sundar, Amrutha and Menon, Sachit and Yang, Junfeng and Wang, Xin and Vondrick, Carl}, title = {Doubly Right Object Recognition: A Why Prompt for Visual Rationales}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2722-2732} }

Shepherding Slots to Objects: Towards Stable and Robust Object-Centric Learning

Jinwoo Kim,

Janghyuk Choi,

Ho-Jin Choi,

Seon Joo Kim

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Kim_2023_CVPR, author = {Kim, Jinwoo and Choi, Janghyuk and Choi, Ho-Jin and Kim, Seon Joo}, title = {Shepherding Slots to Objects: Towards Stable and Robust Object-Centric Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {19198-19207} }

High-Fidelity Event-Radiance Recovery via Transient Event Frequency

Jin Han,

Yuta Asano,

Boxin Shi,

Yinqiang Zheng,

Imari Sato

[pdf] [supp]

[bibtex]

@InProceedings{Han_2023_CVPR, author = {Han, Jin and Asano, Yuta and Shi, Boxin and Zheng, Yinqiang and Sato, Imari}, title = {High-Fidelity Event-Radiance Recovery via Transient Event Frequency}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {20616-20625} }

NeMo: Learning 3D Neural Motion Fields From Multiple Video Instances of the Same Action

Kuan-Chieh Wang,

Zhenzhen Weng,

Maria Xenochristou,

João Pedro Araújo,

Jeffrey Gu,

Karen Liu,

Serena Yeung

[pdf] [supp]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Kuan-Chieh and Weng, Zhenzhen and Xenochristou, Maria and Ara\'ujo, Jo\~ao Pedro and Gu, Jeffrey and Liu, Karen and Yeung, Serena}, title = {NeMo: Learning 3D Neural Motion Fields From Multiple Video Instances of the Same Action}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {22129-22138} }

RIATIG: Reliable and Imperceptible Adversarial Text-to-Image Generation With Natural Prompts

Han Liu,

Yuhao Wu,

Shixuan Zhai,

Bo Yuan,

Ning Zhang

[pdf]

[bibtex]

@InProceedings{Liu_2023_CVPR, author = {Liu, Han and Wu, Yuhao and Zhai, Shixuan and Yuan, Bo and Zhang, Ning}, title = {RIATIG: Reliable and Imperceptible Adversarial Text-to-Image Generation With Natural Prompts}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {20585-20594} }

Distilling Neural Fields for Real-Time Articulated Shape Reconstruction

Jeff Tan,

Gengshan Yang,

Deva Ramanan

[pdf]

[bibtex]

@InProceedings{Tan_2023_CVPR, author = {Tan, Jeff and Yang, Gengshan and Ramanan, Deva}, title = {Distilling Neural Fields for Real-Time Articulated Shape Reconstruction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4692-4701} }

GLIGEN: Open-Set Grounded Text-to-Image Generation

Yuheng Li,

Haotian Liu,

Qingyang Wu,

Fangzhou Mu,

Jianwei Yang,

Jianfeng Gao,

Chunyuan Li,

Yong Jae Lee

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Li_2023_CVPR, author = {Li, Yuheng and Liu, Haotian and Wu, Qingyang and Mu, Fangzhou and Yang, Jianwei and Gao, Jianfeng and Li, Chunyuan and Lee, Yong Jae}, title = {GLIGEN: Open-Set Grounded Text-to-Image Generation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {22511-22521} }

Q: How To Specialize Large Vision-Language Models to Data-Scarce VQA Tasks? A: Self-Train on Unlabeled Images!

Zaid Khan,

Vijay Kumar BG,

Samuel Schulter,

Xiang Yu,

Yun Fu,

Manmohan Chandraker

[pdf]

[bibtex]

@InProceedings{Khan_2023_CVPR, author = {Khan, Zaid and BG, Vijay Kumar and Schulter, Samuel and Yu, Xiang and Fu, Yun and Chandraker, Manmohan}, title = {Q: How To Specialize Large Vision-Language Models to Data-Scarce VQA Tasks? A: Self-Train on Unlabeled Images!}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15005-15015} }

IPCC-TP: Utilizing Incremental Pearson Correlation Coefficient for Joint Multi-Agent Trajectory Prediction

Dekai Zhu,

Guangyao Zhai,

Yan Di,

Fabian Manhardt,

Hendrik Berkemeyer,

Tuan Tran,

Nassir Navab,

Federico Tombari,

Benjamin Busam

[pdf] [supp]

[bibtex]

@InProceedings{Zhu_2023_CVPR, author = {Zhu, Dekai and Zhai, Guangyao and Di, Yan and Manhardt, Fabian and Berkemeyer, Hendrik and Tran, Tuan and Navab, Nassir and Tombari, Federico and Busam, Benjamin}, title = {IPCC-TP: Utilizing Incremental Pearson Correlation Coefficient for Joint Multi-Agent Trajectory Prediction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5507-5516} }

Improving Robust Generalization by Direct PAC-Bayesian Bound Minimization

Zifan Wang,

Nan Ding,

Tomer Levinboim,

Xi Chen,

Radu Soricut

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Zifan and Ding, Nan and Levinboim, Tomer and Chen, Xi and Soricut, Radu}, title = {Improving Robust Generalization by Direct PAC-Bayesian Bound Minimization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16458-16468} }

MobileOne: An Improved One Millisecond Mobile Backbone

Pavan Kumar Anasosalu Vasu,

James Gabriel,

Jeff Zhu,

Oncel Tuzel,

Anurag Ranjan

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Vasu_2023_CVPR, author = {Vasu, Pavan Kumar Anasosalu and Gabriel, James and Zhu, Jeff and Tuzel, Oncel and Ranjan, Anurag}, title = {MobileOne: An Improved One Millisecond Mobile Backbone}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7907-7917} }

A Data-Based Perspective on Transfer Learning

Saachi Jain,

Hadi Salman,

Alaa Khaddaj,

Eric Wong,

Sung Min Park,

Aleksander Mądry

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Jain_2023_CVPR, author = {Jain, Saachi and Salman, Hadi and Khaddaj, Alaa and Wong, Eric and Park, Sung Min and M\k{a}dry, Aleksander}, title = {A Data-Based Perspective on Transfer Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3613-3622} }

AssemblyHands: Towards Egocentric Activity Understanding via 3D Hand Pose Estimation

Takehiko Ohkawa,

Kun He,

Fadime Sener,

Tomas Hodan,

Luan Tran,

Cem Keskin

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Ohkawa_2023_CVPR, author = {Ohkawa, Takehiko and He, Kun and Sener, Fadime and Hodan, Tomas and Tran, Luan and Keskin, Cem}, title = {AssemblyHands: Towards Egocentric Activity Understanding via 3D Hand Pose Estimation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12999-13008} }

Scene-Aware Egocentric 3D Human Pose Estimation

Jian Wang,

Diogo Luvizon,

Weipeng Xu,

Lingjie Liu,

Kripasindhu Sarkar,

Christian Theobalt

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Jian and Luvizon, Diogo and Xu, Weipeng and Liu, Lingjie and Sarkar, Kripasindhu and Theobalt, Christian}, title = {Scene-Aware Egocentric 3D Human Pose Estimation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13031-13040} }

Learning Geometry-Aware Representations by Sketching

Hyundo Lee,

Inwoo Hwang,

Hyunsung Go,

Won-Seok Choi,

Kibeom Kim,

Byoung-Tak Zhang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Lee_2023_CVPR, author = {Lee, Hyundo and Hwang, Inwoo and Go, Hyunsung and Choi, Won-Seok and Kim, Kibeom and Zhang, Byoung-Tak}, title = {Learning Geometry-Aware Representations by Sketching}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {23315-23326} }

SVFormer: Semi-Supervised Video Transformer for Action Recognition

Zhen Xing,

Qi Dai,

Han Hu,

Jingjing Chen,

Zuxuan Wu,

Yu-Gang Jiang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Xing_2023_CVPR, author = {Xing, Zhen and Dai, Qi and Hu, Han and Chen, Jingjing and Wu, Zuxuan and Jiang, Yu-Gang}, title = {SVFormer: Semi-Supervised Video Transformer for Action Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {18816-18826} }

X-Avatar: Expressive Human Avatars

Kaiyue Shen,

Chen Guo,

Manuel Kaufmann,

Juan Jose Zarate,

Julien Valentin,

Jie Song,

Otmar Hilliges

[pdf] [supp]

[bibtex]

@InProceedings{Shen_2023_CVPR, author = {Shen, Kaiyue and Guo, Chen and Kaufmann, Manuel and Zarate, Juan Jose and Valentin, Julien and Song, Jie and Hilliges, Otmar}, title = {X-Avatar: Expressive Human Avatars}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16911-16921} }

AccelIR: Task-Aware Image Compression for Accelerating Neural Restoration

Juncheol Ye,

Hyunho Yeo,

Jinwoo Park,

Dongsu Han

[pdf] [supp]

[bibtex]

@InProceedings{Ye_2023_CVPR, author = {Ye, Juncheol and Yeo, Hyunho and Park, Jinwoo and Han, Dongsu}, title = {AccelIR: Task-Aware Image Compression for Accelerating Neural Restoration}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {18216-18226} }

BEV-Guided Multi-Modality Fusion for Driving Perception

Yunze Man,

Liang-Yan Gui,

Yu-Xiong Wang

[pdf] [supp]

[bibtex]

@InProceedings{Man_2023_CVPR, author = {Man, Yunze and Gui, Liang-Yan and Wang, Yu-Xiong}, title = {BEV-Guided Multi-Modality Fusion for Driving Perception}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {21960-21969} }

Meta-Explore: Exploratory Hierarchical Vision-and-Language Navigation Using Scene Object Spectrum Grounding

Minyoung Hwang,

Jaeyeon Jeong,

Minsoo Kim,

Yoonseon Oh,

Songhwai Oh

[pdf] [supp]

[bibtex]

@InProceedings{Hwang_2023_CVPR, author = {Hwang, Minyoung and Jeong, Jaeyeon and Kim, Minsoo and Oh, Yoonseon and Oh, Songhwai}, title = {Meta-Explore: Exploratory Hierarchical Vision-and-Language Navigation Using Scene Object Spectrum Grounding}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6683-6693} }

Proximal Splitting Adversarial Attack for Semantic Segmentation

Jérôme Rony,

Jean-Christophe Pesquet,

Ismail Ben Ayed

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Rony_2023_CVPR, author = {Rony, J\'er\^ome and Pesquet, Jean-Christophe and Ben Ayed, Ismail}, title = {Proximal Splitting Adversarial Attack for Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {20524-20533} }

Improved Test-Time Adaptation for Domain Generalization

Liang Chen,

Yong Zhang,

Yibing Song,

Ying Shan,

Lingqiao Liu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Chen_2023_CVPR, author = {Chen, Liang and Zhang, Yong and Song, Yibing and Shan, Ying and Liu, Lingqiao}, title = {Improved Test-Time Adaptation for Domain Generalization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {24172-24182} }

Recovering 3D Hand Mesh Sequence From a Single Blurry Image: A New Dataset and Temporal Unfolding

Yeonguk Oh,

JoonKyu Park,

Jaeha Kim,

Gyeongsik Moon,

Kyoung Mu Lee

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Oh_2023_CVPR, author = {Oh, Yeonguk and Park, JoonKyu and Kim, Jaeha and Moon, Gyeongsik and Lee, Kyoung Mu}, title = {Recovering 3D Hand Mesh Sequence From a Single Blurry Image: A New Dataset and Temporal Unfolding}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {554-563} }

NaQ: Leveraging Narrations As Queries To Supervise Episodic Memory

Santhosh Kumar Ramakrishnan,

Ziad Al-Halah,

Kristen Grauman

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Ramakrishnan_2023_CVPR, author = {Ramakrishnan, Santhosh Kumar and Al-Halah, Ziad and Grauman, Kristen}, title = {NaQ: Leveraging Narrations As Queries To Supervise Episodic Memory}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6694-6703} }

Correspondence Transformers With Asymmetric Feature Learning and Matching Flow Super-Resolution

Yixuan Sun,

Dongyang Zhao,

Zhangyue Yin,

Yiwen Huang,

Tao Gui,

Wenqiang Zhang,

Weifeng Ge

[pdf] [supp]

[bibtex]

@InProceedings{Sun_2023_CVPR, author = {Sun, Yixuan and Zhao, Dongyang and Yin, Zhangyue and Huang, Yiwen and Gui, Tao and Zhang, Wenqiang and Ge, Weifeng}, title = {Correspondence Transformers With Asymmetric Feature Learning and Matching Flow Super-Resolution}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {17787-17796} }

Adjustment and Alignment for Unbiased Open Set Domain Adaptation

Wuyang Li,

Jie Liu,

Bo Han,

Yixuan Yuan

[pdf] [supp]

[bibtex]

@InProceedings{Li_2023_CVPR, author = {Li, Wuyang and Liu, Jie and Han, Bo and Yuan, Yixuan}, title = {Adjustment and Alignment for Unbiased Open Set Domain Adaptation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {24110-24119} }

FedSeg: Class-Heterogeneous Federated Learning for Semantic Segmentation

Jiaxu Miao,

Zongxin Yang,

Leilei Fan,

Yi Yang

[pdf] [supp]

[bibtex]

@InProceedings{Miao_2023_CVPR, author = {Miao, Jiaxu and Yang, Zongxin and Fan, Leilei and Yang, Yi}, title = {FedSeg: Class-Heterogeneous Federated Learning for Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8042-8052} }

NeuralField-LDM: Scene Generation With Hierarchical Latent Diffusion Models

Seung Wook Kim,

Bradley Brown,

Kangxue Yin,

Karsten Kreis,

Katja Schwarz,

Daiqing Li,

Robin Rombach,

Antonio Torralba,

Sanja Fidler

[pdf] [supp]

[bibtex]

@InProceedings{Kim_2023_CVPR, author = {Kim, Seung Wook and Brown, Bradley and Yin, Kangxue and Kreis, Karsten and Schwarz, Katja and Li, Daiqing and Rombach, Robin and Torralba, Antonio and Fidler, Sanja}, title = {NeuralField-LDM: Scene Generation With Hierarchical Latent Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8496-8506} }

DPF: Learning Dense Prediction Fields With Weak Supervision

Xiaoxue Chen,

Yuhang Zheng,

Yupeng Zheng,

Qiang Zhou,

Hao Zhao,

Guyue Zhou,

Ya-Qin Zhang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Chen_2023_CVPR, author = {Chen, Xiaoxue and Zheng, Yuhang and Zheng, Yupeng and Zhou, Qiang and Zhao, Hao and Zhou, Guyue and Zhang, Ya-Qin}, title = {DPF: Learning Dense Prediction Fields With Weak Supervision}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15347-15357} }

Fast Monocular Scene Reconstruction With Global-Sparse Local-Dense Grids

Wei Dong,

Christopher Choy,

Charles Loop,

Or Litany,

Yuke Zhu,

Anima Anandkumar

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Dong_2023_CVPR, author = {Dong, Wei and Choy, Christopher and Loop, Charles and Litany, Or and Zhu, Yuke and Anandkumar, Anima}, title = {Fast Monocular Scene Reconstruction With Global-Sparse Local-Dense Grids}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4263-4272} }

Thermal Spread Functions (TSF): Physics-Guided Material Classification

Aniket Dashpute,

Vishwanath Saragadam,

Emma Alexander,

Florian Willomitzer,

Aggelos Katsaggelos,

Ashok Veeraraghavan,

Oliver Cossairt

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Dashpute_2023_CVPR, author = {Dashpute, Aniket and Saragadam, Vishwanath and Alexander, Emma and Willomitzer, Florian and Katsaggelos, Aggelos and Veeraraghavan, Ashok and Cossairt, Oliver}, title = {Thermal Spread Functions (TSF): Physics-Guided Material Classification}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1641-1650} }

ESLAM: Efficient Dense SLAM System Based on Hybrid Representation of Signed Distance Fields

Mohammad Mahdi Johari,

Camilla Carta,

François Fleuret

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Johari_2023_CVPR, author = {Johari, Mohammad Mahdi and Carta, Camilla and Fleuret, Fran\c{c}ois}, title = {ESLAM: Efficient Dense SLAM System Based on Hybrid Representation of Signed Distance Fields}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {17408-17419} }

CNVid-3.5M: Build, Filter, and Pre-Train the Large-Scale Public Chinese Video-Text Dataset

Tian Gan,

Qing Wang,

Xingning Dong,

Xiangyuan Ren,

Liqiang Nie,

Qingpei Guo

[pdf] [supp]

[bibtex]

@InProceedings{Gan_2023_CVPR, author = {Gan, Tian and Wang, Qing and Dong, Xingning and Ren, Xiangyuan and Nie, Liqiang and Guo, Qingpei}, title = {CNVid-3.5M: Build, Filter, and Pre-Train the Large-Scale Public Chinese Video-Text Dataset}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14815-14824} }

Unsupervised Space-Time Network for Temporally-Consistent Segmentation of Multiple Motions

Etienne Meunier,

Patrick Bouthemy

[pdf] [supp]

[bibtex]

@InProceedings{Meunier_2023_CVPR, author = {Meunier, Etienne and Bouthemy, Patrick}, title = {Unsupervised Space-Time Network for Temporally-Consistent Segmentation of Multiple Motions}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {22139-22148} }

Unsupervised 3D Point Cloud Representation Learning by Triangle Constrained Contrast for Autonomous Driving

Bo Pang,

Hongchi Xia,

Cewu Lu

[pdf] [supp]

[bibtex]

@InProceedings{Pang_2023_CVPR, author = {Pang, Bo and Xia, Hongchi and Lu, Cewu}, title = {Unsupervised 3D Point Cloud Representation Learning by Triangle Constrained Contrast for Autonomous Driving}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5229-5239} }

iDisc: Internal Discretization for Monocular Depth Estimation

Luigi Piccinelli,

Christos Sakaridis,

Fisher Yu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Piccinelli_2023_CVPR, author = {Piccinelli, Luigi and Sakaridis, Christos and Yu, Fisher}, title = {iDisc: Internal Discretization for Monocular Depth Estimation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {21477-21487} }

Balancing Logit Variation for Long-Tailed Semantic Segmentation

Yuchao Wang,

Jingjing Fei,

Haochen Wang,

Wei Li,

Tianpeng Bao,

Liwei Wu,

Rui Zhao,

Yujun Shen

[pdf] [supp]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Yuchao and Fei, Jingjing and Wang, Haochen and Li, Wei and Bao, Tianpeng and Wu, Liwei and Zhao, Rui and Shen, Yujun}, title = {Balancing Logit Variation for Long-Tailed Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {19561-19573} }

Prompt-Guided Zero-Shot Anomaly Action Recognition Using Pretrained Deep Skeleton Features

Fumiaki Sato,

Ryo Hachiuma,

Taiki Sekii

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Sato_2023_CVPR, author = {Sato, Fumiaki and Hachiuma, Ryo and Sekii, Taiki}, title = {Prompt-Guided Zero-Shot Anomaly Action Recognition Using Pretrained Deep Skeleton Features}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6471-6480} }

iQuery: Instruments As Queries for Audio-Visual Sound Separation

Jiaben Chen,

Renrui Zhang,

Dongze Lian,

Jiaqi Yang,

Ziyao Zeng,

Jianbo Shi

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Chen_2023_CVPR, author = {Chen, Jiaben and Zhang, Renrui and Lian, Dongze and Yang, Jiaqi and Zeng, Ziyao and Shi, Jianbo}, title = {iQuery: Instruments As Queries for Audio-Visual Sound Separation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14675-14686} }

Sampling Is Matter: Point-Guided 3D Human Mesh Reconstruction

Jeonghwan Kim,

Mi-Gyeong Gwon,

Hyunwoo Park,

Hyukmin Kwon,

Gi-Mun Um,

Wonjun Kim

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Kim_2023_CVPR, author = {Kim, Jeonghwan and Gwon, Mi-Gyeong and Park, Hyunwoo and Kwon, Hyukmin and Um, Gi-Mun and Kim, Wonjun}, title = {Sampling Is Matter: Point-Guided 3D Human Mesh Reconstruction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12880-12889} }

Efficient Multimodal Fusion via Interactive Prompting

Yaowei Li,

Ruijie Quan,

Linchao Zhu,

Yi Yang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Li_2023_CVPR, author = {Li, Yaowei and Quan, Ruijie and Zhu, Linchao and Yang, Yi}, title = {Efficient Multimodal Fusion via Interactive Prompting}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2604-2613} }

Look Around for Anomalies: Weakly-Supervised Anomaly Detection via Context-Motion Relational Learning

MyeongAh Cho,

Minjung Kim,

Sangwon Hwang,

Chaewon Park,

Kyungjae Lee,

Sangyoun Lee

[pdf] [supp]

[bibtex]

@InProceedings{Cho_2023_CVPR, author = {Cho, MyeongAh and Kim, Minjung and Hwang, Sangwon and Park, Chaewon and Lee, Kyungjae and Lee, Sangyoun}, title = {Look Around for Anomalies: Weakly-Supervised Anomaly Detection via Context-Motion Relational Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12137-12146} }

Depth Estimation From Indoor Panoramas With Neural Scene Representation

Wenjie Chang,

Yueyi Zhang,

Zhiwei Xiong

[pdf] [supp]

[bibtex]

@InProceedings{Chang_2023_CVPR, author = {Chang, Wenjie and Zhang, Yueyi and Xiong, Zhiwei}, title = {Depth Estimation From Indoor Panoramas With Neural Scene Representation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {899-908} }

Task-Specific Fine-Tuning via Variational Information Bottleneck for Weakly-Supervised Pathology Whole Slide Image Classification

Honglin Li,

Chenglu Zhu,

Yunlong Zhang,

Yuxuan Sun,

Zhongyi Shui,

Wenwei Kuang,

Sunyi Zheng,

Lin Yang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Li_2023_CVPR, author = {Li, Honglin and Zhu, Chenglu and Zhang, Yunlong and Sun, Yuxuan and Shui, Zhongyi and Kuang, Wenwei and Zheng, Sunyi and Yang, Lin}, title = {Task-Specific Fine-Tuning via Variational Information Bottleneck for Weakly-Supervised Pathology Whole Slide Image Classification}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7454-7463} }

Detecting Everything in the Open World: Towards Universal Object Detection

Zhenyu Wang,

Yali Li,

Xi Chen,

Ser-Nam Lim,

Antonio Torralba,

Hengshuang Zhao,

Shengjin Wang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Zhenyu and Li, Yali and Chen, Xi and Lim, Ser-Nam and Torralba, Antonio and Zhao, Hengshuang and Wang, Shengjin}, title = {Detecting Everything in the Open World: Towards Universal Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11433-11443} }

Single Image Depth Prediction Made Better: A Multivariate Gaussian Take

Ce Liu,

Suryansh Kumar,

Shuhang Gu,

Radu Timofte,

Luc Van Gool

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Liu_2023_CVPR, author = {Liu, Ce and Kumar, Suryansh and Gu, Shuhang and Timofte, Radu and Van Gool, Luc}, title = {Single Image Depth Prediction Made Better: A Multivariate Gaussian Take}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {17346-17356} }

NUWA-LIP: Language-Guided Image Inpainting With Defect-Free VQGAN

Minheng Ni,

Xiaoming Li,

Wangmeng Zuo

[pdf] [supp]

[bibtex]

@InProceedings{Ni_2023_CVPR, author = {Ni, Minheng and Li, Xiaoming and Zuo, Wangmeng}, title = {NUWA-LIP: Language-Guided Image Inpainting With Defect-Free VQGAN}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14183-14192} }

One-Shot Model for Mixed-Precision Quantization

Ivan Koryakovskiy,

Alexandra Yakovleva,

Valentin Buchnev,

Temur Isaev,

Gleb Odinokikh

[pdf] [supp]

[bibtex]

@InProceedings{Koryakovskiy_2023_CVPR, author = {Koryakovskiy, Ivan and Yakovleva, Alexandra and Buchnev, Valentin and Isaev, Temur and Odinokikh, Gleb}, title = {One-Shot Model for Mixed-Precision Quantization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7939-7949} }

MARLIN: Masked Autoencoder for Facial Video Representation LearnINg

Zhixi Cai,

Shreya Ghosh,

Kalin Stefanov,

Abhinav Dhall,

Jianfei Cai,

Hamid Rezatofighi,

Reza Haffari,

Munawar Hayat

[pdf] [arXiv]

[bibtex]

@InProceedings{Cai_2023_CVPR, author = {Cai, Zhixi and Ghosh, Shreya and Stefanov, Kalin and Dhall, Abhinav and Cai, Jianfei and Rezatofighi, Hamid and Haffari, Reza and Hayat, Munawar}, title = {MARLIN: Masked Autoencoder for Facial Video Representation LearnINg}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1493-1504} }

Language Adaptive Weight Generation for Multi-Task Visual Grounding

Wei Su,

Peihan Miao,

Huanzhang Dou,

Gaoang Wang,

Liang Qiao,

Zheyang Li,

Xi Li

[pdf] [supp]

[bibtex]

@InProceedings{Su_2023_CVPR, author = {Su, Wei and Miao, Peihan and Dou, Huanzhang and Wang, Gaoang and Qiao, Liang and Li, Zheyang and Li, Xi}, title = {Language Adaptive Weight Generation for Multi-Task Visual Grounding}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10857-10866} }

Continuous Intermediate Token Learning With Implicit Motion Manifold for Keyframe Based Motion Interpolation

Clinton A. Mo,

Kun Hu,

Chengjiang Long,

Zhiyong Wang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Mo_2023_CVPR, author = {Mo, Clinton A. and Hu, Kun and Long, Chengjiang and Wang, Zhiyong}, title = {Continuous Intermediate Token Learning With Implicit Motion Manifold for Keyframe Based Motion Interpolation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13894-13903} }

Dynamic Coarse-To-Fine Learning for Oriented Tiny Object Detection

Chang Xu,

Jian Ding,

Jinwang Wang,

Wen Yang,

Huai Yu,

Lei Yu,

Gui-Song Xia

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Xu_2023_CVPR, author = {Xu, Chang and Ding, Jian and Wang, Jinwang and Yang, Wen and Yu, Huai and Yu, Lei and Xia, Gui-Song}, title = {Dynamic Coarse-To-Fine Learning for Oriented Tiny Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7318-7328} }

Controllable Mesh Generation Through Sparse Latent Point Diffusion Models

Zhaoyang Lyu,

Jinyi Wang,

Yuwei An,

Ya Zhang,

Dahua Lin,

Bo Dai

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Lyu_2023_CVPR, author = {Lyu, Zhaoyang and Wang, Jinyi and An, Yuwei and Zhang, Ya and Lin, Dahua and Dai, Bo}, title = {Controllable Mesh Generation Through Sparse Latent Point Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {271-280} }

Query-Centric Trajectory Prediction

Zikang Zhou,

Jianping Wang,

Yung-Hui Li,

Yu-Kai Huang

[pdf] [supp]

[bibtex]

@InProceedings{Zhou_2023_CVPR, author = {Zhou, Zikang and Wang, Jianping and Li, Yung-Hui and Huang, Yu-Kai}, title = {Query-Centric Trajectory Prediction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {17863-17873} }

The Enemy of My Enemy Is My Friend: Exploring Inverse Adversaries for Improving Adversarial Training

Junhao Dong,

Seyed-Mohsen Moosavi-Dezfooli,

Jianhuang Lai,

Xiaohua Xie

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Dong_2023_CVPR, author = {Dong, Junhao and Moosavi-Dezfooli, Seyed-Mohsen and Lai, Jianhuang and Xie, Xiaohua}, title = {The Enemy of My Enemy Is My Friend: Exploring Inverse Adversaries for Improving Adversarial Training}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {24678-24687} }

Look Before You Match: Instance Understanding Matters in Video Object Segmentation

Junke Wang,

Dongdong Chen,

Zuxuan Wu,

Chong Luo,

Chuanxin Tang,

Xiyang Dai,

Yucheng Zhao,

Yujia Xie,

Lu Yuan,

Yu-Gang Jiang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Junke and Chen, Dongdong and Wu, Zuxuan and Luo, Chong and Tang, Chuanxin and Dai, Xiyang and Zhao, Yucheng and Xie, Yujia and Yuan, Lu and Jiang, Yu-Gang}, title = {Look Before You Match: Instance Understanding Matters in Video Object Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2268-2278} }

SGLoc: Scene Geometry Encoding for Outdoor LiDAR Localization

Wen Li,

Shangshu Yu,

Cheng Wang,

Guosheng Hu,

Siqi Shen,

Chenglu Wen

[pdf] [supp]

[bibtex]

@InProceedings{Li_2023_CVPR, author = {Li, Wen and Yu, Shangshu and Wang, Cheng and Hu, Guosheng and Shen, Siqi and Wen, Chenglu}, title = {SGLoc: Scene Geometry Encoding for Outdoor LiDAR Localization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9286-9295} }

Boundary Unlearning: Rapid Forgetting of Deep Networks via Shifting the Decision Boundary

Min Chen,

Weizhuo Gao,

Gaoyang Liu,

Kai Peng,

Chen Wang

[pdf]

[bibtex]

@InProceedings{Chen_2023_CVPR, author = {Chen, Min and Gao, Weizhuo and Liu, Gaoyang and Peng, Kai and Wang, Chen}, title = {Boundary Unlearning: Rapid Forgetting of Deep Networks via Shifting the Decision Boundary}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7766-7775} }

Bridging Search Region Interaction With Template for RGB-T Tracking

Tianrui Hui,

Zizheng Xun,

Fengguang Peng,

Junshi Huang,

Xiaoming Wei,

Xiaolin Wei,

Jiao Dai,

Jizhong Han,

Si Liu

[pdf]

[bibtex]

@InProceedings{Hui_2023_CVPR, author = {Hui, Tianrui and Xun, Zizheng and Peng, Fengguang and Huang, Junshi and Wei, Xiaoming and Wei, Xiaolin and Dai, Jiao and Han, Jizhong and Liu, Si}, title = {Bridging Search Region Interaction With Template for RGB-T Tracking}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13630-13639} }

Indescribable Multi-Modal Spatial Evaluator

Lingke Kong,

X. Sharon Qi,

Qijin Shen,

Jiacheng Wang,

Jingyi Zhang,

Yanle Hu,

Qichao Zhou

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Kong_2023_CVPR, author = {Kong, Lingke and Qi, X. Sharon and Shen, Qijin and Wang, Jiacheng and Zhang, Jingyi and Hu, Yanle and Zhou, Qichao}, title = {Indescribable Multi-Modal Spatial Evaluator}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9853-9862} }

ImageBind: One Embedding Space To Bind Them All

Rohit Girdhar,

Alaaeldin El-Nouby,

Zhuang Liu,

Mannat Singh,

Kalyan Vasudev Alwala,

Armand Joulin,

Ishan Misra

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Girdhar_2023_CVPR, author = {Girdhar, Rohit and El-Nouby, Alaaeldin and Liu, Zhuang and Singh, Mannat and Alwala, Kalyan Vasudev and Joulin, Armand and Misra, Ishan}, title = {ImageBind: One Embedding Space To Bind Them All}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15180-15190} }

Orthogonal Annotation Benefits Barely-Supervised Medical Image Segmentation

Heng Cai,

Shumeng Li,

Lei Qi,

Qian Yu,

Yinghuan Shi,

Yang Gao

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Cai_2023_CVPR, author = {Cai, Heng and Li, Shumeng and Qi, Lei and Yu, Qian and Shi, Yinghuan and Gao, Yang}, title = {Orthogonal Annotation Benefits Barely-Supervised Medical Image Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3302-3311} }

Exploring Motion Ambiguity and Alignment for High-Quality Video Frame Interpolation

Kun Zhou,

Wenbo Li,

Xiaoguang Han,

Jiangbo Lu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Zhou_2023_CVPR, author = {Zhou, Kun and Li, Wenbo and Han, Xiaoguang and Lu, Jiangbo}, title = {Exploring Motion Ambiguity and Alignment for High-Quality Video Frame Interpolation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {22169-22179} }

Knowledge Distillation for 6D Pose Estimation by Aligning Distributions of Local Predictions

Shuxuan Guo,

Yinlin Hu,

Jose M. Alvarez,

Mathieu Salzmann

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Guo_2023_CVPR, author = {Guo, Shuxuan and Hu, Yinlin and Alvarez, Jose M. and Salzmann, Mathieu}, title = {Knowledge Distillation for 6D Pose Estimation by Aligning Distributions of Local Predictions}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {18633-18642} }

Three Guidelines You Should Know for Universally Slimmable Self-Supervised Learning

Yun-Hao Cao,

Peiqin Sun,

Shuchang Zhou

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Cao_2023_CVPR, author = {Cao, Yun-Hao and Sun, Peiqin and Zhou, Shuchang}, title = {Three Guidelines You Should Know for Universally Slimmable Self-Supervised Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15742-15751} }

Adaptive Annealing for Robust Geometric Estimation

Chitturi Sidhartha,

Lalit Manam,

Venu Madhav Govindu

[pdf] [supp]

[bibtex]

@InProceedings{Sidhartha_2023_CVPR, author = {Sidhartha, Chitturi and Manam, Lalit and Govindu, Venu Madhav}, title = {Adaptive Annealing for Robust Geometric Estimation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {21929-21939} }

MetaFusion: Infrared and Visible Image Fusion via Meta-Feature Embedding From Object Detection

Wenda Zhao,

Shigeng Xie,

Fan Zhao,

You He,

Huchuan Lu

[pdf]

[bibtex]

@InProceedings{Zhao_2023_CVPR, author = {Zhao, Wenda and Xie, Shigeng and Zhao, Fan and He, You and Lu, Huchuan}, title = {MetaFusion: Infrared and Visible Image Fusion via Meta-Feature Embedding From Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13955-13965} }

Spectral Enhanced Rectangle Transformer for Hyperspectral Image Denoising

Miaoyu Li,

Ji Liu,

Ying Fu,

Yulun Zhang,

Dejing Dou

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Li_2023_CVPR, author = {Li, Miaoyu and Liu, Ji and Fu, Ying and Zhang, Yulun and Dou, Dejing}, title = {Spectral Enhanced Rectangle Transformer for Hyperspectral Image Denoising}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5805-5814} }

End-to-End Vectorized HD-Map Construction With Piecewise Bezier Curve

Limeng Qiao,

Wenjie Ding,

Xi Qiu,

Chi Zhang

[pdf] [supp]

[bibtex]

@InProceedings{Qiao_2023_CVPR, author = {Qiao, Limeng and Ding, Wenjie and Qiu, Xi and Zhang, Chi}, title = {End-to-End Vectorized HD-Map Construction With Piecewise Bezier Curve}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13218-13228} }

PointListNet: Deep Learning on 3D Point Lists

Hehe Fan,

Linchao Zhu,

Yi Yang,

Mohan Kankanhalli

[pdf] [supp]

[bibtex]

@InProceedings{Fan_2023_CVPR, author = {Fan, Hehe and Zhu, Linchao and Yang, Yi and Kankanhalli, Mohan}, title = {PointListNet: Deep Learning on 3D Point Lists}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {17692-17701} }

On Data Scaling in Masked Image Modeling

Zhenda Xie,

Zheng Zhang,

Yue Cao,

Yutong Lin,

Yixuan Wei,

Qi Dai,

Han Hu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Xie_2023_CVPR, author = {Xie, Zhenda and Zhang, Zheng and Cao, Yue and Lin, Yutong and Wei, Yixuan and Dai, Qi and Hu, Han}, title = {On Data Scaling in Masked Image Modeling}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10365-10374} }

Upcycling Models Under Domain and Category Shift

Sanqing Qu,

Tianpei Zou,

Florian Röhrbein,

Cewu Lu,

Guang Chen,

Dacheng Tao,

Changjun Jiang

[pdf] [supp]

[bibtex]

@InProceedings{Qu_2023_CVPR, author = {Qu, Sanqing and Zou, Tianpei and R\"ohrbein, Florian and Lu, Cewu and Chen, Guang and Tao, Dacheng and Jiang, Changjun}, title = {Upcycling Models Under Domain and Category Shift}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {20019-20028} }

Single Domain Generalization for LiDAR Semantic Segmentation

Hyeonseong Kim,

Yoonsu Kang,

Changgyoon Oh,

Kuk-Jin Yoon

[pdf] [supp]

[bibtex]

@InProceedings{Kim_2023_CVPR, author = {Kim, Hyeonseong and Kang, Yoonsu and Oh, Changgyoon and Yoon, Kuk-Jin}, title = {Single Domain Generalization for LiDAR Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {17587-17598} }

Balanced Energy Regularization Loss for Out-of-Distribution Detection

Hyunjun Choi,

Hawook Jeong,

Jin Young Choi

[pdf] [supp]

[bibtex]

@InProceedings{Choi_2023_CVPR, author = {Choi, Hyunjun and Jeong, Hawook and Choi, Jin Young}, title = {Balanced Energy Regularization Loss for Out-of-Distribution Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15691-15700} }

3D-Aware Face Swapping

Yixuan Li,

Chao Ma,

Yichao Yan,

Wenhan Zhu,

Xiaokang Yang

[pdf] [supp]

[bibtex]

@InProceedings{Li_2023_CVPR, author = {Li, Yixuan and Ma, Chao and Yan, Yichao and Zhu, Wenhan and Yang, Xiaokang}, title = {3D-Aware Face Swapping}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12705-12714} }

UMat: Uncertainty-Aware Single Image High Resolution Material Capture

Carlos Rodriguez-Pardo,

Henar Domínguez-Elvira,

David Pascual-Hernández,

Elena Garces

[pdf]

[bibtex]

@InProceedings{Rodriguez-Pardo_2023_CVPR, author = {Rodriguez-Pardo, Carlos and Dom{\'\i}nguez-Elvira, Henar and Pascual-Hern\'andez, David and Garces, Elena}, title = {UMat: Uncertainty-Aware Single Image High Resolution Material Capture}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5764-5774} }

Similarity Maps for Self-Training Weakly-Supervised Phrase Grounding

Tal Shaharabany,

Lior Wolf

[pdf]

[bibtex]

@InProceedings{Shaharabany_2023_CVPR, author = {Shaharabany, Tal and Wolf, Lior}, title = {Similarity Maps for Self-Training Weakly-Supervised Phrase Grounding}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6925-6934} }

SCOOP: Self-Supervised Correspondence and Optimization-Based Scene Flow

Itai Lang,

Dror Aiger,

Forrester Cole,

Shai Avidan,

Michael Rubinstein

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Lang_2023_CVPR, author = {Lang, Itai and Aiger, Dror and Cole, Forrester and Avidan, Shai and Rubinstein, Michael}, title = {SCOOP: Self-Supervised Correspondence and Optimization-Based Scene Flow}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5281-5290} }

SLACK: Stable Learning of Augmentations With Cold-Start and KL Regularization

Juliette Marrie,

Michael Arbel,

Diane Larlus,

Julien Mairal

[pdf] [supp]

[bibtex]

@InProceedings{Marrie_2023_CVPR, author = {Marrie, Juliette and Arbel, Michael and Larlus, Diane and Mairal, Julien}, title = {SLACK: Stable Learning of Augmentations With Cold-Start and KL Regularization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {24306-24314} }

Gradient Norm Aware Minimization Seeks First-Order Flatness and Improves Generalization

Xingxuan Zhang,

Renzhe Xu,

Han Yu,

Hao Zou,

Peng Cui

[pdf] [arXiv]

[bibtex]

@InProceedings{Zhang_2023_CVPR, author = {Zhang, Xingxuan and Xu, Renzhe and Yu, Han and Zou, Hao and Cui, Peng}, title = {Gradient Norm Aware Minimization Seeks First-Order Flatness and Improves Generalization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {20247-20257} }

Phone2Proc: Bringing Robust Robots Into Our Chaotic World

Matt Deitke,

Rose Hendrix,

Ali Farhadi,

Kiana Ehsani,

Aniruddha Kembhavi

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Deitke_2023_CVPR, author = {Deitke, Matt and Hendrix, Rose and Farhadi, Ali and Ehsani, Kiana and Kembhavi, Aniruddha}, title = {Phone2Proc: Bringing Robust Robots Into Our Chaotic World}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9665-9675} }

Latency Matters: Real-Time Action Forecasting Transformer

Harshayu Girase,

Nakul Agarwal,

Chiho Choi,

Karttikeya Mangalam

[pdf] [supp]

[bibtex]

@InProceedings{Girase_2023_CVPR, author = {Girase, Harshayu and Agarwal, Nakul and Choi, Chiho and Mangalam, Karttikeya}, title = {Latency Matters: Real-Time Action Forecasting Transformer}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {18759-18769} }

HierVL: Learning Hierarchical Video-Language Embeddings

Kumar Ashutosh,

Rohit Girdhar,

Lorenzo Torresani,

Kristen Grauman

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Ashutosh_2023_CVPR, author = {Ashutosh, Kumar and Girdhar, Rohit and Torresani, Lorenzo and Grauman, Kristen}, title = {HierVL: Learning Hierarchical Video-Language Embeddings}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {23066-23078} }

GraVoS: Voxel Selection for 3D Point-Cloud Detection

Oren Shrout,

Yizhak Ben-Shabat,

Ayellet Tal

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Shrout_2023_CVPR, author = {Shrout, Oren and Ben-Shabat, Yizhak and Tal, Ayellet}, title = {GraVoS: Voxel Selection for 3D Point-Cloud Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {21684-21693} }

Learning Articulated Shape With Keypoint Pseudo-Labels From Web Images

Anastasis Stathopoulos,

Georgios Pavlakos,

Ligong Han,

Dimitris N. Metaxas

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Stathopoulos_2023_CVPR, author = {Stathopoulos, Anastasis and Pavlakos, Georgios and Han, Ligong and Metaxas, Dimitris N.}, title = {Learning Articulated Shape With Keypoint Pseudo-Labels From Web Images}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13092-13101} }

Rethinking Image Super Resolution From Long-Tailed Distribution Learning Perspective

Yuanbiao Gou,

Peng Hu,

Jiancheng Lv,

Hongyuan Zhu,

Xi Peng

[pdf] [supp]

[bibtex]

@InProceedings{Gou_2023_CVPR, author = {Gou, Yuanbiao and Hu, Peng and Lv, Jiancheng and Zhu, Hongyuan and Peng, Xi}, title = {Rethinking Image Super Resolution From Long-Tailed Distribution Learning Perspective}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14327-14336} }

RobustNeRF: Ignoring Distractors With Robust Losses

Sara Sabour,

Suhani Vora,

Daniel Duckworth,

Ivan Krasin,

David J. Fleet,

Andrea Tagliasacchi

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Sabour_2023_CVPR, author = {Sabour, Sara and Vora, Suhani and Duckworth, Daniel and Krasin, Ivan and Fleet, David J. and Tagliasacchi, Andrea}, title = {RobustNeRF: Ignoring Distractors With Robust Losses}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {20626-20636} }

Spherical Transformer for LiDAR-Based 3D Recognition

Xin Lai,

Yukang Chen,

Fanbin Lu,

Jianhui Liu,

Jiaya Jia

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Lai_2023_CVPR, author = {Lai, Xin and Chen, Yukang and Lu, Fanbin and Liu, Jianhui and Jia, Jiaya}, title = {Spherical Transformer for LiDAR-Based 3D Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {17545-17555} }

Human-Art: A Versatile Human-Centric Dataset Bridging Natural and Artificial Scenes

Xuan Ju,

Ailing Zeng,

Jianan Wang,

Qiang Xu,

Lei Zhang

[pdf] [supp]

[bibtex]

@InProceedings{Ju_2023_CVPR, author = {Ju, Xuan and Zeng, Ailing and Wang, Jianan and Xu, Qiang and Zhang, Lei}, title = {Human-Art: A Versatile Human-Centric Dataset Bridging Natural and Artificial Scenes}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {618-629} }

Watch or Listen: Robust Audio-Visual Speech Recognition With Visual Corruption Modeling and Reliability Scoring

Joanna Hong,

Minsu Kim,

Jeongsoo Choi,

Yong Man Ro

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Hong_2023_CVPR, author = {Hong, Joanna and Kim, Minsu and Choi, Jeongsoo and Ro, Yong Man}, title = {Watch or Listen: Robust Audio-Visual Speech Recognition With Visual Corruption Modeling and Reliability Scoring}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {18783-18794} }

Turning a CLIP Model Into a Scene Text Detector

Wenwen Yu,

Yuliang Liu,

Wei Hua,

Deqiang Jiang,

Bo Ren,

Xiang Bai

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Yu_2023_CVPR, author = {Yu, Wenwen and Liu, Yuliang and Hua, Wei and Jiang, Deqiang and Ren, Bo and Bai, Xiang}, title = {Turning a CLIP Model Into a Scene Text Detector}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6978-6988} }

VisFusion: Visibility-Aware Online 3D Scene Reconstruction From Videos

Huiyu Gao,

Wei Mao,

Miaomiao Liu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Gao_2023_CVPR, author = {Gao, Huiyu and Mao, Wei and Liu, Miaomiao}, title = {VisFusion: Visibility-Aware Online 3D Scene Reconstruction From Videos}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {17317-17326} }

SCOTCH and SODA: A Transformer Video Shadow Detection Framework

Lihao Liu,

Jean Prost,

Lei Zhu,

Nicolas Papadakis,

Pietro Liò,

Carola-Bibiane Schönlieb,

Angelica I. Aviles-Rivero

[pdf] [arXiv]

[bibtex]

@InProceedings{Liu_2023_CVPR, author = {Liu, Lihao and Prost, Jean and Zhu, Lei and Papadakis, Nicolas and Li\`o, Pietro and Sch\"onlieb, Carola-Bibiane and Aviles-Rivero, Angelica I.}, title = {SCOTCH and SODA: A Transformer Video Shadow Detection Framework}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10449-10458} }

RODIN: A Generative Model for Sculpting 3D Digital Avatars Using Diffusion

Tengfei Wang,

Bo Zhang,

Ting Zhang,

Shuyang Gu,

Jianmin Bao,

Tadas Baltrusaitis,

Jingjing Shen,

Dong Chen,

Fang Wen,

Qifeng Chen,

Baining Guo

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Tengfei and Zhang, Bo and Zhang, Ting and Gu, Shuyang and Bao, Jianmin and Baltrusaitis, Tadas and Shen, Jingjing and Chen, Dong and Wen, Fang and Chen, Qifeng and Guo, Baining}, title = {RODIN: A Generative Model for Sculpting 3D Digital Avatars Using Diffusion}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4563-4573} }

On the Pitfall of Mixup for Uncertainty Calibration

Deng-Bao Wang,

Lanqing Li,

Peilin Zhao,

Pheng-Ann Heng,

Min-Ling Zhang

[pdf] [supp]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Deng-Bao and Li, Lanqing and Zhao, Peilin and Heng, Pheng-Ann and Zhang, Min-Ling}, title = {On the Pitfall of Mixup for Uncertainty Calibration}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7609-7618} }

Feature Shrinkage Pyramid for Camouflaged Object Detection With Transformers

Zhou Huang,

Hang Dai,

Tian-Zhu Xiang,

Shuo Wang,

Huai-Xin Chen,

Jie Qin,

Huan Xiong

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Huang_2023_CVPR, author = {Huang, Zhou and Dai, Hang and Xiang, Tian-Zhu and Wang, Shuo and Chen, Huai-Xin and Qin, Jie and Xiong, Huan}, title = {Feature Shrinkage Pyramid for Camouflaged Object Detection With Transformers}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5557-5566} }

Matching Is Not Enough: A Two-Stage Framework for Category-Agnostic Pose Estimation

Min Shi,

Zihao Huang,

Xianzheng Ma,

Xiaowei Hu,

Zhiguo Cao

[pdf] [supp]

[bibtex]

@InProceedings{Shi_2023_CVPR, author = {Shi, Min and Huang, Zihao and Ma, Xianzheng and Hu, Xiaowei and Cao, Zhiguo}, title = {Matching Is Not Enough: A Two-Stage Framework for Category-Agnostic Pose Estimation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7308-7317} }

High-Fidelity Guided Image Synthesis With Latent Diffusion Models

Jaskirat Singh,

Stephen Gould,

Liang Zheng

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Singh_2023_CVPR, author = {Singh, Jaskirat and Gould, Stephen and Zheng, Liang}, title = {High-Fidelity Guided Image Synthesis With Latent Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5997-6006} }

CodeTalker: Speech-Driven 3D Facial Animation With Discrete Motion Prior

Jinbo Xing,

Menghan Xia,

Yuechen Zhang,

Xiaodong Cun,

Jue Wang,

Tien-Tsin Wong

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Xing_2023_CVPR, author = {Xing, Jinbo and Xia, Menghan and Zhang, Yuechen and Cun, Xiaodong and Wang, Jue and Wong, Tien-Tsin}, title = {CodeTalker: Speech-Driven 3D Facial Animation With Discrete Motion Prior}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12780-12790} }

Towards Transferable Targeted Adversarial Examples

Zhibo Wang,

Hongshan Yang,

Yunhe Feng,

Peng Sun,

Hengchang Guo,

Zhifei Zhang,

Kui Ren

[pdf]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Zhibo and Yang, Hongshan and Feng, Yunhe and Sun, Peng and Guo, Hengchang and Zhang, Zhifei and Ren, Kui}, title = {Towards Transferable Targeted Adversarial Examples}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {20534-20543} }

Semi-Supervised Parametric Real-World Image Harmonization

Ke Wang,

Michaël Gharbi,

He Zhang,

Zhihao Xia,

Eli Shechtman

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Ke and Gharbi, Micha\"el and Zhang, He and Xia, Zhihao and Shechtman, Eli}, title = {Semi-Supervised Parametric Real-World Image Harmonization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5927-5936} }

C-SFDA: A Curriculum Learning Aided Self-Training Framework for Efficient Source Free Domain Adaptation

Nazmul Karim,

Niluthpol Chowdhury Mithun,

Abhinav Rajvanshi,

Han-pang Chiu,

Supun Samarasekera,

Nazanin Rahnavard

[pdf] [supp]

[bibtex]

@InProceedings{Karim_2023_CVPR, author = {Karim, Nazmul and Mithun, Niluthpol Chowdhury and Rajvanshi, Abhinav and Chiu, Han-pang and Samarasekera, Supun and Rahnavard, Nazanin}, title = {C-SFDA: A Curriculum Learning Aided Self-Training Framework for Efficient Source Free Domain Adaptation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {24120-24131} }

Learning Visibility Field for Detailed 3D Human Reconstruction and Relighting

Ruichen Zheng,

Peng Li,

Haoqian Wang,

Tao Yu

[pdf] [arXiv]

[bibtex]

@InProceedings{Zheng_2023_CVPR, author = {Zheng, Ruichen and Li, Peng and Wang, Haoqian and Yu, Tao}, title = {Learning Visibility Field for Detailed 3D Human Reconstruction and Relighting}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {216-226} }

Improving Zero-Shot Generalization and Robustness of Multi-Modal Models

Yunhao Ge,

Jie Ren,

Andrew Gallagher,

Yuxiao Wang,

Ming-Hsuan Yang,

Hartwig Adam,

Laurent Itti,

Balaji Lakshminarayanan,

Jiaping Zhao

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Ge_2023_CVPR, author = {Ge, Yunhao and Ren, Jie and Gallagher, Andrew and Wang, Yuxiao and Yang, Ming-Hsuan and Adam, Hartwig and Itti, Laurent and Lakshminarayanan, Balaji and Zhao, Jiaping}, title = {Improving Zero-Shot Generalization and Robustness of Multi-Modal Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11093-11101} }

Improving Robustness of Vision Transformers by Reducing Sensitivity To Patch Corruptions

Yong Guo,

David Stutz,

Bernt Schiele

[pdf] [supp]

[bibtex]

@InProceedings{Guo_2023_CVPR, author = {Guo, Yong and Stutz, David and Schiele, Bernt}, title = {Improving Robustness of Vision Transformers by Reducing Sensitivity To Patch Corruptions}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4108-4118} }

VecFontSDF: Learning To Reconstruct and Synthesize High-Quality Vector Fonts via Signed Distance Functions

Zeqing Xia,

Bojun Xiong,

Zhouhui Lian

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Xia_2023_CVPR, author = {Xia, Zeqing and Xiong, Bojun and Lian, Zhouhui}, title = {VecFontSDF: Learning To Reconstruct and Synthesize High-Quality Vector Fonts via Signed Distance Functions}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1848-1857} }

MSF: Motion-Guided Sequential Fusion for Efficient 3D Object Detection From Point Cloud Sequences

Chenhang He,

Ruihuang Li,

Yabin Zhang,

Shuai Li,

Lei Zhang

[pdf] [arXiv]

[bibtex]

@InProceedings{He_2023_CVPR, author = {He, Chenhang and Li, Ruihuang and Zhang, Yabin and Li, Shuai and Zhang, Lei}, title = {MSF: Motion-Guided Sequential Fusion for Efficient 3D Object Detection From Point Cloud Sequences}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5196-5205} }

Modeling the Distributional Uncertainty for Salient Object Detection Models

Xinyu Tian,

Jing Zhang,

Mochu Xiang,

Yuchao Dai

[pdf]

[bibtex]

@InProceedings{Tian_2023_CVPR, author = {Tian, Xinyu and Zhang, Jing and Xiang, Mochu and Dai, Yuchao}, title = {Modeling the Distributional Uncertainty for Salient Object Detection Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {19660-19670} }

Kernel Aware Resampler

Michael Bernasconi,

Abdelaziz Djelouah,

Farnood Salehi,

Markus Gross,

Christopher Schroers

[pdf] [supp]

[bibtex]

@InProceedings{Bernasconi_2023_CVPR, author = {Bernasconi, Michael and Djelouah, Abdelaziz and Salehi, Farnood and Gross, Markus and Schroers, Christopher}, title = {Kernel Aware Resampler}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {22347-22355} }

LaserMix for Semi-Supervised LiDAR Semantic Segmentation

Lingdong Kong,

Jiawei Ren,

Liang Pan,

Ziwei Liu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Kong_2023_CVPR, author = {Kong, Lingdong and Ren, Jiawei and Pan, Liang and Liu, Ziwei}, title = {LaserMix for Semi-Supervised LiDAR Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {21705-21715} }

CODA-Prompt: COntinual Decomposed Attention-Based Prompting for Rehearsal-Free Continual Learning

James Seale Smith,

Leonid Karlinsky,

Vyshnavi Gutta,

Paola Cascante-Bonilla,

Donghyun Kim,

Assaf Arbelle,

Rameswar Panda,

Rogerio Feris,

Zsolt Kira

[pdf] [supp]

[bibtex]

@InProceedings{Smith_2023_CVPR, author = {Smith, James Seale and Karlinsky, Leonid and Gutta, Vyshnavi and Cascante-Bonilla, Paola and Kim, Donghyun and Arbelle, Assaf and Panda, Rameswar and Feris, Rogerio and Kira, Zsolt}, title = {CODA-Prompt: COntinual Decomposed Attention-Based Prompting for Rehearsal-Free Continual Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11909-11919} }

HypLiLoc: Towards Effective LiDAR Pose Regression With Hyperbolic Fusion

Sijie Wang,

Qiyu Kang,

Rui She,

Wei Wang,

Kai Zhao,

Yang Song,

Wee Peng Tay

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Sijie and Kang, Qiyu and She, Rui and Wang, Wei and Zhao, Kai and Song, Yang and Tay, Wee Peng}, title = {HypLiLoc: Towards Effective LiDAR Pose Regression With Hyperbolic Fusion}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5176-5185} }

Complementary Intrinsics From Neural Radiance Fields and CNNs for Outdoor Scene Relighting

Siqi Yang,

Xuanning Cui,

Yongjie Zhu,

Jiajun Tang,

Si Li,

Zhaofei Yu,

Boxin Shi

[pdf] [supp]

[bibtex]

@InProceedings{Yang_2023_CVPR, author = {Yang, Siqi and Cui, Xuanning and Zhu, Yongjie and Tang, Jiajun and Li, Si and Yu, Zhaofei and Shi, Boxin}, title = {Complementary Intrinsics From Neural Radiance Fields and CNNs for Outdoor Scene Relighting}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16600-16609} }

Real-Time Multi-Person Eyeblink Detection in the Wild for Untrimmed Video

Wenzheng Zeng,

Yang Xiao,

Sicheng Wei,

Jinfang Gan,

Xintao Zhang,

Zhiguo Cao,

Zhiwen Fang,

Joey Tianyi Zhou

[pdf] [arXiv]

[bibtex]

@InProceedings{Zeng_2023_CVPR, author = {Zeng, Wenzheng and Xiao, Yang and Wei, Sicheng and Gan, Jinfang and Zhang, Xintao and Cao, Zhiguo and Fang, Zhiwen and Zhou, Joey Tianyi}, title = {Real-Time Multi-Person Eyeblink Detection in the Wild for Untrimmed Video}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13854-13863} }

Category Query Learning for Human-Object Interaction Classification

Chi Xie,

Fangao Zeng,

Yue Hu,

Shuang Liang,

Yichen Wei

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Xie_2023_CVPR, author = {Xie, Chi and Zeng, Fangao and Hu, Yue and Liang, Shuang and Wei, Yichen}, title = {Category Query Learning for Human-Object Interaction Classification}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15275-15284} }

MDQE: Mining Discriminative Query Embeddings To Segment Occluded Instances on Challenging Videos

Minghan Li,

Shuai Li,

Wangmeng Xiang,

Lei Zhang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Li_2023_CVPR, author = {Li, Minghan and Li, Shuai and Xiang, Wangmeng and Zhang, Lei}, title = {MDQE: Mining Discriminative Query Embeddings To Segment Occluded Instances on Challenging Videos}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10524-10533} }

Are We Ready for Vision-Centric Driving Streaming Perception? The ASAP Benchmark

Xiaofeng Wang,

Zheng Zhu,

Yunpeng Zhang,

Guan Huang,

Yun Ye,

Wenbo Xu,

Ziwei Chen,

Xingang Wang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Xiaofeng and Zhu, Zheng and Zhang, Yunpeng and Huang, Guan and Ye, Yun and Xu, Wenbo and Chen, Ziwei and Wang, Xingang}, title = {Are We Ready for Vision-Centric Driving Streaming Perception? The ASAP Benchmark}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9600-9610} }

Robust Model-Based Face Reconstruction Through Weakly-Supervised Outlier Segmentation

Chunlu Li,

Andreas Morel-Forster,

Thomas Vetter,

Bernhard Egger,

Adam Kortylewski

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Li_2023_CVPR, author = {Li, Chunlu and Morel-Forster, Andreas and Vetter, Thomas and Egger, Bernhard and Kortylewski, Adam}, title = {Robust Model-Based Face Reconstruction Through Weakly-Supervised Outlier Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {372-381} }

Not All Image Regions Matter: Masked Vector Quantization for Autoregressive Image Generation

Mengqi Huang,

Zhendong Mao,

Quan Wang,

Yongdong Zhang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Huang_2023_CVPR, author = {Huang, Mengqi and Mao, Zhendong and Wang, Quan and Zhang, Yongdong}, title = {Not All Image Regions Matter: Masked Vector Quantization for Autoregressive Image Generation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2002-2011} }

Masked Video Distillation: Rethinking Masked Feature Modeling for Self-Supervised Video Representation Learning

Rui Wang,

Dongdong Chen,

Zuxuan Wu,

Yinpeng Chen,

Xiyang Dai,

Mengchen Liu,

Lu Yuan,

Yu-Gang Jiang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Rui and Chen, Dongdong and Wu, Zuxuan and Chen, Yinpeng and Dai, Xiyang and Liu, Mengchen and Yuan, Lu and Jiang, Yu-Gang}, title = {Masked Video Distillation: Rethinking Masked Feature Modeling for Self-Supervised Video Representation Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6312-6322} }

Transformer-Based Unified Recognition of Two Hands Manipulating Objects

Hoseong Cho,

Chanwoo Kim,

Jihyeon Kim,

Seongyeong Lee,

Elkhan Ismayilzada,

Seungryul Baek

[pdf] [supp]

[bibtex]

@InProceedings{Cho_2023_CVPR, author = {Cho, Hoseong and Kim, Chanwoo and Kim, Jihyeon and Lee, Seongyeong and Ismayilzada, Elkhan and Baek, Seungryul}, title = {Transformer-Based Unified Recognition of Two Hands Manipulating Objects}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4769-4778} }

Azimuth Super-Resolution for FMCW Radar in Autonomous Driving

Yu-Jhe Li,

Shawn Hunt,

Jinhyung Park,

Matthew O’Toole,

Kris Kitani

[pdf]

[bibtex]

@InProceedings{Li_2023_CVPR, author = {Li, Yu-Jhe and Hunt, Shawn and Park, Jinhyung and O{\textquoteright}Toole, Matthew and Kitani, Kris}, title = {Azimuth Super-Resolution for FMCW Radar in Autonomous Driving}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {17504-17513} }

PDPP:Projected Diffusion for Procedure Planning in Instructional Videos

Hanlin Wang,

Yilu Wu,

Sheng Guo,

Limin Wang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Hanlin and Wu, Yilu and Guo, Sheng and Wang, Limin}, title = {PDPP:Projected Diffusion for Procedure Planning in Instructional Videos}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14836-14845} }

RangeViT: Towards Vision Transformers for 3D Semantic Segmentation in Autonomous Driving

Angelika Ando,

Spyros Gidaris,

Andrei Bursuc,

Gilles Puy,

Alexandre Boulch,

Renaud Marlet

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Ando_2023_CVPR, author = {Ando, Angelika and Gidaris, Spyros and Bursuc, Andrei and Puy, Gilles and Boulch, Alexandre and Marlet, Renaud}, title = {RangeViT: Towards Vision Transformers for 3D Semantic Segmentation in Autonomous Driving}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5240-5250} }

ProTeGe: Untrimmed Pretraining for Video Temporal Grounding by Video Temporal Grounding

Lan Wang,

Gaurav Mittal,

Sandra Sajeev,

Ye Yu,

Matthew Hall,

Vishnu Naresh Boddeti,

Mei Chen

[pdf] [supp]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Lan and Mittal, Gaurav and Sajeev, Sandra and Yu, Ye and Hall, Matthew and Boddeti, Vishnu Naresh and Chen, Mei}, title = {ProTeGe: Untrimmed Pretraining for Video Temporal Grounding by Video Temporal Grounding}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6575-6585} }

VQACL: A Novel Visual Question Answering Continual Learning Setting

Xi Zhang,

Feifei Zhang,

Changsheng Xu

[pdf] [supp]

[bibtex]

@InProceedings{Zhang_2023_CVPR, author = {Zhang, Xi and Zhang, Feifei and Xu, Changsheng}, title = {VQACL: A Novel Visual Question Answering Continual Learning Setting}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {19102-19112} }

Efficient Map Sparsification Based on 2D and 3D Discretized Grids

Xiaoyu Zhang,

Yun-Hui Liu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Zhang_2023_CVPR, author = {Zhang, Xiaoyu and Liu, Yun-Hui}, title = {Efficient Map Sparsification Based on 2D and 3D Discretized Grids}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12470-12478} }

High-Res Facial Appearance Capture From Polarized Smartphone Images

Dejan Azinović,

Olivier Maury,

Christophe Hery,

Matthias Nießner,

Justus Thies

[pdf] [supp]

[bibtex]

@InProceedings{Azinovic_2023_CVPR, author = {Azinovi\'c, Dejan and Maury, Olivier and Hery, Christophe and Nie{\ss}ner, Matthias and Thies, Justus}, title = {High-Res Facial Appearance Capture From Polarized Smartphone Images}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16836-16846} }

JAWS: Just a Wild Shot for Cinematic Transfer in Neural Radiance Fields

Xi Wang,

Robin Courant,

Jinglei Shi,

Eric Marchand,

Marc Christie

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Xi and Courant, Robin and Shi, Jinglei and Marchand, Eric and Christie, Marc}, title = {JAWS: Just a Wild Shot for Cinematic Transfer in Neural Radiance Fields}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16933-16942} }

Class Attention Transfer Based Knowledge Distillation

Ziyao Guo,

Haonan Yan,

Hui Li,

Xiaodong Lin

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Guo_2023_CVPR, author = {Guo, Ziyao and Yan, Haonan and Li, Hui and Lin, Xiaodong}, title = {Class Attention Transfer Based Knowledge Distillation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11868-11877} }

EfficientSCI: Densely Connected Network With Space-Time Factorization for Large-Scale Video Snapshot Compressive Imaging

Lishun Wang,

Miao Cao,

Xin Yuan

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Lishun and Cao, Miao and Yuan, Xin}, title = {EfficientSCI: Densely Connected Network With Space-Time Factorization for Large-Scale Video Snapshot Compressive Imaging}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {18477-18486} }

Exploring Incompatible Knowledge Transfer in Few-Shot Image Generation

Yunqing Zhao,

Chao Du,

Milad Abdollahzadeh,

Tianyu Pang,

Min Lin,

Shuicheng Yan,

Ngai-Man Cheung

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Zhao_2023_CVPR, author = {Zhao, Yunqing and Du, Chao and Abdollahzadeh, Milad and Pang, Tianyu and Lin, Min and Yan, Shuicheng and Cheung, Ngai-Man}, title = {Exploring Incompatible Knowledge Transfer in Few-Shot Image Generation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7380-7391} }

Temporally Consistent Online Depth Estimation Using Point-Based Fusion

Numair Khan,

Eric Penner,

Douglas Lanman,

Lei Xiao

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Khan_2023_CVPR, author = {Khan, Numair and Penner, Eric and Lanman, Douglas and Xiao, Lei}, title = {Temporally Consistent Online Depth Estimation Using Point-Based Fusion}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9119-9129} }

Generalizable Implicit Neural Representations via Instance Pattern Composers

Chiheon Kim,

Doyup Lee,

Saehoon Kim,

Minsu Cho,

Wook-Shin Han

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Kim_2023_CVPR, author = {Kim, Chiheon and Lee, Doyup and Kim, Saehoon and Cho, Minsu and Han, Wook-Shin}, title = {Generalizable Implicit Neural Representations via Instance Pattern Composers}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11808-11817} }

MotionTrack: Learning Robust Short-Term and Long-Term Motions for Multi-Object Tracking

Zheng Qin,

Sanping Zhou,

Le Wang,

Jinghai Duan,

Gang Hua,

Wei Tang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Qin_2023_CVPR, author = {Qin, Zheng and Zhou, Sanping and Wang, Le and Duan, Jinghai and Hua, Gang and Tang, Wei}, title = {MotionTrack: Learning Robust Short-Term and Long-Term Motions for Multi-Object Tracking}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {17939-17948} }

3D Registration With Maximal Cliques

Xiyu Zhang,

Jiaqi Yang,

Shikun Zhang,

Yanning Zhang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Zhang_2023_CVPR, author = {Zhang, Xiyu and Yang, Jiaqi and Zhang, Shikun and Zhang, Yanning}, title = {3D Registration With Maximal Cliques}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {17745-17754} }

What Can Human Sketches Do for Object Detection?

Pinaki Nath Chowdhury,

Ayan Kumar Bhunia,

Aneeshan Sain,

Subhadeep Koley,

Tao Xiang,

Yi-Zhe Song

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Chowdhury_2023_CVPR, author = {Chowdhury, Pinaki Nath and Bhunia, Ayan Kumar and Sain, Aneeshan and Koley, Subhadeep and Xiang, Tao and Song, Yi-Zhe}, title = {What Can Human Sketches Do for Object Detection?}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15083-15094} }

Identity-Preserving Talking Face Generation With Landmark and Appearance Priors

Weizhi Zhong,

Chaowei Fang,

Yinqi Cai,

Pengxu Wei,

Gangming Zhao,

Liang Lin,

Guanbin Li

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Zhong_2023_CVPR, author = {Zhong, Weizhi and Fang, Chaowei and Cai, Yinqi and Wei, Pengxu and Zhao, Gangming and Lin, Liang and Li, Guanbin}, title = {Identity-Preserving Talking Face Generation With Landmark and Appearance Priors}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9729-9738} }

All-in-One Image Restoration for Unknown Degradations Using Adaptive Discriminative Filters for Specific Degradations

Dongwon Park,

Byung Hyun Lee,

Se Young Chun

[pdf] [supp]

[bibtex]

@InProceedings{Park_2023_CVPR, author = {Park, Dongwon and Lee, Byung Hyun and Chun, Se Young}, title = {All-in-One Image Restoration for Unknown Degradations Using Adaptive Discriminative Filters for Specific Degradations}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5815-5824} }

Weakly Supervised Segmentation With Point Annotations for Histopathology Images via Contrast-Based Variational Model

Hongrun Zhang,

Liam Burrows,

Yanda Meng,

Declan Sculthorpe,

Abhik Mukherjee,

Sarah E. Coupland,

Ke Chen,

Yalin Zheng

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Zhang_2023_CVPR, author = {Zhang, Hongrun and Burrows, Liam and Meng, Yanda and Sculthorpe, Declan and Mukherjee, Abhik and Coupland, Sarah E. and Chen, Ke and Zheng, Yalin}, title = {Weakly Supervised Segmentation With Point Annotations for Histopathology Images via Contrast-Based Variational Model}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15630-15640} }

Efficient RGB-T Tracking via Cross-Modality Distillation

Tianlu Zhang,

Hongyuan Guo,

Qiang Jiao,

Qiang Zhang,

Jungong Han

[pdf] [supp]

[bibtex]

@InProceedings{Zhang_2023_CVPR, author = {Zhang, Tianlu and Guo, Hongyuan and Jiao, Qiang and Zhang, Qiang and Han, Jungong}, title = {Efficient RGB-T Tracking via Cross-Modality Distillation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5404-5413} }

MetaPortrait: Identity-Preserving Talking Head Generation With Fast Personalized Adaptation

Bowen Zhang,

Chenyang Qi,

Pan Zhang,

Bo Zhang,

HsiangTao Wu,

Dong Chen,

Qifeng Chen,

Yong Wang,

Fang Wen

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Zhang_2023_CVPR, author = {Zhang, Bowen and Qi, Chenyang and Zhang, Pan and Zhang, Bo and Wu, HsiangTao and Chen, Dong and Chen, Qifeng and Wang, Yong and Wen, Fang}, title = {MetaPortrait: Identity-Preserving Talking Head Generation With Fast Personalized Adaptation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {22096-22105} }

UniHCP: A Unified Model for Human-Centric Perceptions

Yuanzheng Ci,

Yizhou Wang,

Meilin Chen,

Shixiang Tang,

Lei Bai,

Feng Zhu,

Rui Zhao,

Fengwei Yu,

Donglian Qi,

Wanli Ouyang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Ci_2023_CVPR, author = {Ci, Yuanzheng and Wang, Yizhou and Chen, Meilin and Tang, Shixiang and Bai, Lei and Zhu, Feng and Zhao, Rui and Yu, Fengwei and Qi, Donglian and Ouyang, Wanli}, title = {UniHCP: A Unified Model for Human-Centric Perceptions}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {17840-17852} }

Passive Micron-Scale Time-of-Flight With Sunlight Interferometry

Alankar Kotwal,

Anat Levin,

Ioannis Gkioulekas

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Kotwal_2023_CVPR, author = {Kotwal, Alankar and Levin, Anat and Gkioulekas, Ioannis}, title = {Passive Micron-Scale Time-of-Flight With Sunlight Interferometry}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4139-4149} }

VoxelNeXt: Fully Sparse VoxelNet for 3D Object Detection and Tracking

Yukang Chen,

Jianhui Liu,

Xiangyu Zhang,

Xiaojuan Qi,

Jiaya Jia

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Chen_2023_CVPR, author = {Chen, Yukang and Liu, Jianhui and Zhang, Xiangyu and Qi, Xiaojuan and Jia, Jiaya}, title = {VoxelNeXt: Fully Sparse VoxelNet for 3D Object Detection and Tracking}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {21674-21683} }

Behavioral Analysis of Vision-and-Language Navigation Agents

Zijiao Yang,

Arjun Majumdar,

Stefan Lee

[pdf] [supp]

[bibtex]

@InProceedings{Yang_2023_CVPR, author = {Yang, Zijiao and Majumdar, Arjun and Lee, Stefan}, title = {Behavioral Analysis of Vision-and-Language Navigation Agents}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2574-2582} }

Zero-Shot Generative Model Adaptation via Image-Specific Prompt Learning

Jiayi Guo,

Chaofei Wang,

You Wu,

Eric Zhang,

Kai Wang,

Xingqian Xu,

Shiji Song,

Humphrey Shi,

Gao Huang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Guo_2023_CVPR, author = {Guo, Jiayi and Wang, Chaofei and Wu, You and Zhang, Eric and Wang, Kai and Xu, Xingqian and Song, Shiji and Shi, Humphrey and Huang, Gao}, title = {Zero-Shot Generative Model Adaptation via Image-Specific Prompt Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11494-11503} }

CelebV-Text: A Large-Scale Facial Text-Video Dataset

Jianhui Yu,

Hao Zhu,

Liming Jiang,

Chen Change Loy,

Weidong Cai,

Wayne Wu

[pdf] [supp]

[bibtex]

@InProceedings{Yu_2023_CVPR, author = {Yu, Jianhui and Zhu, Hao and Jiang, Liming and Loy, Chen Change and Cai, Weidong and Wu, Wayne}, title = {CelebV-Text: A Large-Scale Facial Text-Video Dataset}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14805-14814} }

Bias in Pruned Vision Models: In-Depth Analysis and Countermeasures

Eugenia Iofinova,

Alexandra Peste,

Dan Alistarh

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Iofinova_2023_CVPR, author = {Iofinova, Eugenia and Peste, Alexandra and Alistarh, Dan}, title = {Bias in Pruned Vision Models: In-Depth Analysis and Countermeasures}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {24364-24373} }

AttentionShift: Iteratively Estimated Part-Based Attention Map for Pointly Supervised Instance Segmentation

Mingxiang Liao,

Zonghao Guo,

Yuze Wang,

Peng Yuan,

Bailan Feng,

Fang Wan

[pdf] [supp]

[bibtex]

@InProceedings{Liao_2023_CVPR, author = {Liao, Mingxiang and Guo, Zonghao and Wang, Yuze and Yuan, Peng and Feng, Bailan and Wan, Fang}, title = {AttentionShift: Iteratively Estimated Part-Based Attention Map for Pointly Supervised Instance Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {19519-19528} }

Unsupervised Volumetric Animation

Aliaksandr Siarohin,

Willi Menapace,

Ivan Skorokhodov,

Kyle Olszewski,

Jian Ren,

Hsin-Ying Lee,

Menglei Chai,

Sergey Tulyakov

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Siarohin_2023_CVPR, author = {Siarohin, Aliaksandr and Menapace, Willi and Skorokhodov, Ivan and Olszewski, Kyle and Ren, Jian and Lee, Hsin-Ying and Chai, Menglei and Tulyakov, Sergey}, title = {Unsupervised Volumetric Animation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4658-4669} }

Hard Patches Mining for Masked Image Modeling

Haochen Wang,

Kaiyou Song,

Junsong Fan,

Yuxi Wang,

Jin Xie,

Zhaoxiang Zhang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Haochen and Song, Kaiyou and Fan, Junsong and Wang, Yuxi and Xie, Jin and Zhang, Zhaoxiang}, title = {Hard Patches Mining for Masked Image Modeling}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10375-10385} }

PlaneDepth: Self-Supervised Depth Estimation via Orthogonal Planes

Ruoyu Wang,

Zehao Yu,

Shenghua Gao

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Ruoyu and Yu, Zehao and Gao, Shenghua}, title = {PlaneDepth: Self-Supervised Depth Estimation via Orthogonal Planes}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {21425-21434} }

Diffusion-SDF: Text-To-Shape via Voxelized Diffusion

Muheng Li,

Yueqi Duan,

Jie Zhou,

Jiwen Lu

[pdf] [supp]

[bibtex]

@InProceedings{Li_2023_CVPR, author = {Li, Muheng and Duan, Yueqi and Zhou, Jie and Lu, Jiwen}, title = {Diffusion-SDF: Text-To-Shape via Voxelized Diffusion}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12642-12651} }

Compositor: Bottom-Up Clustering and Compositing for Robust Part and Object Segmentation

Ju He,

Jieneng Chen,

Ming-Xian Lin,

Qihang Yu,

Alan L. Yuille

[pdf]

[bibtex]

@InProceedings{He_2023_CVPR, author = {He, Ju and Chen, Jieneng and Lin, Ming-Xian and Yu, Qihang and Yuille, Alan L.}, title = {Compositor: Bottom-Up Clustering and Compositing for Robust Part and Object Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11259-11268} }

Semantic-Conditional Diffusion Networks for Image Captioning

Jianjie Luo,

Yehao Li,

Yingwei Pan,

Ting Yao,

Jianlin Feng,

Hongyang Chao,

Tao Mei

[pdf] [arXiv]

[bibtex]

@InProceedings{Luo_2023_CVPR, author = {Luo, Jianjie and Li, Yehao and Pan, Yingwei and Yao, Ting and Feng, Jianlin and Chao, Hongyang and Mei, Tao}, title = {Semantic-Conditional Diffusion Networks for Image Captioning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {23359-23368} }

Unite and Conquer: Plug & Play Multi-Modal Synthesis Using Diffusion Models

Nithin Gopalakrishnan Nair,

Wele Gedara Chaminda Bandara,

Vishal M. Patel

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Nair_2023_CVPR, author = {Nair, Nithin Gopalakrishnan and Bandara, Wele Gedara Chaminda and Patel, Vishal M.}, title = {Unite and Conquer: Plug \& Play Multi-Modal Synthesis Using Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6070-6079} }

TranSG: Transformer-Based Skeleton Graph Prototype Contrastive Learning With Structure-Trajectory Prompted Reconstruction for Person Re-Identification

Haocong Rao,

Chunyan Miao

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Rao_2023_CVPR, author = {Rao, Haocong and Miao, Chunyan}, title = {TranSG: Transformer-Based Skeleton Graph Prototype Contrastive Learning With Structure-Trajectory Prompted Reconstruction for Person Re-Identification}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {22118-22128} }

All Are Worth Words: A ViT Backbone for Diffusion Models

Fan Bao,

Shen Nie,

Kaiwen Xue,

Yue Cao,

Chongxuan Li,

Hang Su,

Jun Zhu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Bao_2023_CVPR, author = {Bao, Fan and Nie, Shen and Xue, Kaiwen and Cao, Yue and Li, Chongxuan and Su, Hang and Zhu, Jun}, title = {All Are Worth Words: A ViT Backbone for Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {22669-22679} }

ZBS: Zero-Shot Background Subtraction via Instance-Level Background Modeling and Foreground Selection

Yongqi An,

Xu Zhao,

Tao Yu,

Haiyun Guo,

Chaoyang Zhao,

Ming Tang,

Jinqiao Wang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{An_2023_CVPR, author = {An, Yongqi and Zhao, Xu and Yu, Tao and Guo, Haiyun and Zhao, Chaoyang and Tang, Ming and Wang, Jinqiao}, title = {ZBS: Zero-Shot Background Subtraction via Instance-Level Background Modeling and Foreground Selection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6355-6364} }

MobileBrick: Building LEGO for 3D Reconstruction on Mobile Devices

Kejie Li,

Jia-Wang Bian,

Robert Castle,

Philip H.S. Torr,

Victor Adrian Prisacariu

[pdf] [arXiv]

[bibtex]

@InProceedings{Li_2023_CVPR, author = {Li, Kejie and Bian, Jia-Wang and Castle, Robert and Torr, Philip H.S. and Prisacariu, Victor Adrian}, title = {MobileBrick: Building LEGO for 3D Reconstruction on Mobile Devices}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4892-4901} }

GKEAL: Gaussian Kernel Embedded Analytic Learning for Few-Shot Class Incremental Task

Huiping Zhuang,

Zhenyu Weng,

Run He,

Zhiping Lin,

Ziqian Zeng

[pdf] [supp]

[bibtex]

@InProceedings{Zhuang_2023_CVPR, author = {Zhuang, Huiping and Weng, Zhenyu and He, Run and Lin, Zhiping and Zeng, Ziqian}, title = {GKEAL: Gaussian Kernel Embedded Analytic Learning for Few-Shot Class Incremental Task}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7746-7755} }

SteerNeRF: Accelerating NeRF Rendering via Smooth Viewpoint Trajectory

Sicheng Li,

Hao Li,

Yue Wang,

Yiyi Liao,

Lu Yu

[pdf] [arXiv]

[bibtex]

@InProceedings{Li_2023_CVPR, author = {Li, Sicheng and Li, Hao and Wang, Yue and Liao, Yiyi and Yu, Lu}, title = {SteerNeRF: Accelerating NeRF Rendering via Smooth Viewpoint Trajectory}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {20701-20711} }

Active Exploration of Multimodal Complementarity for Few-Shot Action Recognition

Yuyang Wanyan,

Xiaoshan Yang,

Chaofan Chen,

Changsheng Xu

[pdf]

[bibtex]

@InProceedings{Wanyan_2023_CVPR, author = {Wanyan, Yuyang and Yang, Xiaoshan and Chen, Chaofan and Xu, Changsheng}, title = {Active Exploration of Multimodal Complementarity for Few-Shot Action Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6492-6502} }

Magic3D: High-Resolution Text-to-3D Content Creation

Chen-Hsuan Lin,

Jun Gao,

Luming Tang,

Towaki Takikawa,

Xiaohui Zeng,

Xun Huang,

Karsten Kreis,

Sanja Fidler,

Ming-Yu Liu,

Tsung-Yi Lin

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Lin_2023_CVPR, author = {Lin, Chen-Hsuan and Gao, Jun and Tang, Luming and Takikawa, Towaki and Zeng, Xiaohui and Huang, Xun and Kreis, Karsten and Fidler, Sanja and Liu, Ming-Yu and Lin, Tsung-Yi}, title = {Magic3D: High-Resolution Text-to-3D Content Creation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {300-309} }

Boundary-Aware Backward-Compatible Representation via Adversarial Learning in Image Retrieval

Tan Pan,

Furong Xu,

Xudong Yang,

Sifeng He,

Chen Jiang,

Qingpei Guo,

Feng Qian,

Xiaobo Zhang,

Yuan Cheng,

Lei Yang,

Wei Chu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Pan_2023_CVPR, author = {Pan, Tan and Xu, Furong and Yang, Xudong and He, Sifeng and Jiang, Chen and Guo, Qingpei and Qian, Feng and Zhang, Xiaobo and Cheng, Yuan and Yang, Lei and Chu, Wei}, title = {Boundary-Aware Backward-Compatible Representation via Adversarial Learning in Image Retrieval}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15201-15210} }

Spatial-Frequency Mutual Learning for Face Super-Resolution

Chenyang Wang,

Junjun Jiang,

Zhiwei Zhong,

Xianming Liu

[pdf]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Chenyang and Jiang, Junjun and Zhong, Zhiwei and Liu, Xianming}, title = {Spatial-Frequency Mutual Learning for Face Super-Resolution}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {22356-22366} }

Sketch2Saliency: Learning To Detect Salient Objects From Human Drawings

Ayan Kumar Bhunia,

Subhadeep Koley,

Amandeep Kumar,

Aneeshan Sain,

Pinaki Nath Chowdhury,

Tao Xiang,

Yi-Zhe Song

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Bhunia_2023_CVPR, author = {Bhunia, Ayan Kumar and Koley, Subhadeep and Kumar, Amandeep and Sain, Aneeshan and Chowdhury, Pinaki Nath and Xiang, Tao and Song, Yi-Zhe}, title = {Sketch2Saliency: Learning To Detect Salient Objects From Human Drawings}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2733-2743} }

Efficient Frequency Domain-Based Transformers for High-Quality Image Deblurring

Lingshun Kong,

Jiangxin Dong,

Jianjun Ge,

Mingqiang Li,

Jinshan Pan

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Kong_2023_CVPR, author = {Kong, Lingshun and Dong, Jiangxin and Ge, Jianjun and Li, Mingqiang and Pan, Jinshan}, title = {Efficient Frequency Domain-Based Transformers for High-Quality Image Deblurring}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5886-5895} }

Distilling Focal Knowledge From Imperfect Expert for 3D Object Detection

Jia Zeng,

Li Chen,

Hanming Deng,

Lewei Lu,

Junchi Yan,

Yu Qiao,

Hongyang Li

[pdf] [supp]

[bibtex]

@InProceedings{Zeng_2023_CVPR, author = {Zeng, Jia and Chen, Li and Deng, Hanming and Lu, Lewei and Yan, Junchi and Qiao, Yu and Li, Hongyang}, title = {Distilling Focal Knowledge From Imperfect Expert for 3D Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {992-1001} }

ULIP: Learning a Unified Representation of Language, Images, and Point Clouds for 3D Understanding

Le Xue,

Mingfei Gao,

Chen Xing,

Roberto Martín-Martín,

Jiajun Wu,

Caiming Xiong,

Ran Xu,

Juan Carlos Niebles,

Silvio Savarese

[pdf] [supp]

[bibtex]

@InProceedings{Xue_2023_CVPR, author = {Xue, Le and Gao, Mingfei and Xing, Chen and Mart{\'\i}n-Mart{\'\i}n, Roberto and Wu, Jiajun and Xiong, Caiming and Xu, Ran and Niebles, Juan Carlos and Savarese, Silvio}, title = {ULIP: Learning a Unified Representation of Language, Images, and Point Clouds for 3D Understanding}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1179-1189} }

Being Comes From Not-Being: Open-Vocabulary Text-to-Motion Generation With Wordless Training

Junfan Lin,

Jianlong Chang,

Lingbo Liu,

Guanbin Li,

Liang Lin,

Qi Tian,

Chang-Wen Chen

[pdf] [supp]

[bibtex]

@InProceedings{Lin_2023_CVPR, author = {Lin, Junfan and Chang, Jianlong and Liu, Lingbo and Li, Guanbin and Lin, Liang and Tian, Qi and Chen, Chang-Wen}, title = {Being Comes From Not-Being: Open-Vocabulary Text-to-Motion Generation With Wordless Training}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {23222-23231} }

Deep Learning of Partial Graph Matching via Differentiable Top-K

Runzhong Wang,

Ziao Guo,

Shaofei Jiang,

Xiaokang Yang,

Junchi Yan

[pdf] [supp]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Runzhong and Guo, Ziao and Jiang, Shaofei and Yang, Xiaokang and Yan, Junchi}, title = {Deep Learning of Partial Graph Matching via Differentiable Top-K}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6272-6281} }

Super-CLEVR: A Virtual Benchmark To Diagnose Domain Robustness in Visual Reasoning

Zhuowan Li,

Xingrui Wang,

Elias Stengel-Eskin,

Adam Kortylewski,

Wufei Ma,

Benjamin Van Durme,

Alan L. Yuille

[pdf] [supp]

[bibtex]

@InProceedings{Li_2023_CVPR, author = {Li, Zhuowan and Wang, Xingrui and Stengel-Eskin, Elias and Kortylewski, Adam and Ma, Wufei and Van Durme, Benjamin and Yuille, Alan L.}, title = {Super-CLEVR: A Virtual Benchmark To Diagnose Domain Robustness in Visual Reasoning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14963-14973} }

MonoHuman: Animatable Human Neural Field From Monocular Video

Zhengming Yu,

Wei Cheng,

Xian Liu,

Wayne Wu,

Kwan-Yee Lin

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Yu_2023_CVPR, author = {Yu, Zhengming and Cheng, Wei and Liu, Xian and Wu, Wayne and Lin, Kwan-Yee}, title = {MonoHuman: Animatable Human Neural Field From Monocular Video}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16943-16953} }

Sliced Optimal Partial Transport

Yikun Bai,

Bernhard Schmitzer,

Matthew Thorpe,

Soheil Kolouri

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Bai_2023_CVPR, author = {Bai, Yikun and Schmitzer, Bernhard and Thorpe, Matthew and Kolouri, Soheil}, title = {Sliced Optimal Partial Transport}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13681-13690} }

Siamese DETR

Zeren Chen,

Gengshi Huang,

Wei Li,

Jianing Teng,

Kun Wang,

Jing Shao,

Chen Change Loy,

Lu Sheng

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Chen_2023_CVPR, author = {Chen, Zeren and Huang, Gengshi and Li, Wei and Teng, Jianing and Wang, Kun and Shao, Jing and Loy, Chen Change and Sheng, Lu}, title = {Siamese DETR}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15722-15731} }

SINE: Semantic-Driven Image-Based NeRF Editing With Prior-Guided Editing Field

Chong Bao,

Yinda Zhang,

Bangbang Yang,

Tianxing Fan,

Zesong Yang,

Hujun Bao,

Guofeng Zhang,

Zhaopeng Cui

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Bao_2023_CVPR, author = {Bao, Chong and Zhang, Yinda and Yang, Bangbang and Fan, Tianxing and Yang, Zesong and Bao, Hujun and Zhang, Guofeng and Cui, Zhaopeng}, title = {SINE: Semantic-Driven Image-Based NeRF Editing With Prior-Guided Editing Field}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {20919-20929} }

Turning Strengths Into Weaknesses: A Certified Robustness Inspired Attack Framework Against Graph Neural Networks

Binghui Wang,

Meng Pang,

Yun Dong

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Binghui and Pang, Meng and Dong, Yun}, title = {Turning Strengths Into Weaknesses: A Certified Robustness Inspired Attack Framework Against Graph Neural Networks}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16394-16403} }

Demystifying Causal Features on Adversarial Examples and Causal Inoculation for Robust Network by Adversarial Instrumental Variable Regression

Junho Kim,

Byung-Kwan Lee,

Yong Man Ro

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Kim_2023_CVPR, author = {Kim, Junho and Lee, Byung-Kwan and Ro, Yong Man}, title = {Demystifying Causal Features on Adversarial Examples and Causal Inoculation for Robust Network by Adversarial Instrumental Variable Regression}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12302-12312} }

NVTC: Nonlinear Vector Transform Coding

Runsen Feng,

Zongyu Guo,

Weiping Li,

Zhibo Chen

[pdf] [supp]

[bibtex]

@InProceedings{Feng_2023_CVPR, author = {Feng, Runsen and Guo, Zongyu and Li, Weiping and Chen, Zhibo}, title = {NVTC: Nonlinear Vector Transform Coding}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6101-6110} }

B-Spline Texture Coefficients Estimator for Screen Content Image Super-Resolution

Byeonghyun Pak,

Jaewon Lee,

Kyong Hwan Jin

[pdf] [supp]

[bibtex]

@InProceedings{Pak_2023_CVPR, author = {Pak, Byeonghyun and Lee, Jaewon and Jin, Kyong Hwan}, title = {B-Spline Texture Coefficients Estimator for Screen Content Image Super-Resolution}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10062-10071} }

MetaCLUE: Towards Comprehensive Visual Metaphors Research

Arjun R. Akula,

Brendan Driscoll,

Pradyumna Narayana,

Soravit Changpinyo,

Zhiwei Jia,

Suyash Damle,

Garima Pruthi,

Sugato Basu,

Leonidas Guibas,

William T. Freeman,

Yuanzhen Li,

Varun Jampani

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Akula_2023_CVPR, author = {Akula, Arjun R. and Driscoll, Brendan and Narayana, Pradyumna and Changpinyo, Soravit and Jia, Zhiwei and Damle, Suyash and Pruthi, Garima and Basu, Sugato and Guibas, Leonidas and Freeman, William T. and Li, Yuanzhen and Jampani, Varun}, title = {MetaCLUE: Towards Comprehensive Visual Metaphors Research}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {23201-23211} }

Towards End-to-End Generative Modeling of Long Videos With Memory-Efficient Bidirectional Transformers

Jaehoon Yoo,

Semin Kim,

Doyup Lee,

Chiheon Kim,

Seunghoon Hong

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Yoo_2023_CVPR, author = {Yoo, Jaehoon and Kim, Semin and Lee, Doyup and Kim, Chiheon and Hong, Seunghoon}, title = {Towards End-to-End Generative Modeling of Long Videos With Memory-Efficient Bidirectional Transformers}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {22888-22897} }

Domain Expansion of Image Generators

Yotam Nitzan,

Michaël Gharbi,

Richard Zhang,

Taesung Park,

Jun-Yan Zhu,

Daniel Cohen-Or,

Eli Shechtman

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Nitzan_2023_CVPR, author = {Nitzan, Yotam and Gharbi, Micha\"el and Zhang, Richard and Park, Taesung and Zhu, Jun-Yan and Cohen-Or, Daniel and Shechtman, Eli}, title = {Domain Expansion of Image Generators}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15933-15942} }

On the Effectiveness of Partial Variance Reduction in Federated Learning With Heterogeneous Data

Bo Li,

Mikkel N. Schmidt,

Tommy S. Alstrøm,

Sebastian U. Stich

[pdf] [supp]

[bibtex]

@InProceedings{Li_2023_CVPR, author = {Li, Bo and Schmidt, Mikkel N. and Alstr{\o}m, Tommy S. and Stich, Sebastian U.}, title = {On the Effectiveness of Partial Variance Reduction in Federated Learning With Heterogeneous Data}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3964-3973} }

Point Cloud Forecasting as a Proxy for 4D Occupancy Forecasting

Tarasha Khurana,

Peiyun Hu,

David Held,

Deva Ramanan

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Khurana_2023_CVPR, author = {Khurana, Tarasha and Hu, Peiyun and Held, David and Ramanan, Deva}, title = {Point Cloud Forecasting as a Proxy for 4D Occupancy Forecasting}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1116-1124} }

Masked Representation Learning for Domain Generalized Stereo Matching

Zhibo Rao,

Bangshu Xiong,

Mingyi He,

Yuchao Dai,

Renjie He,

Zhelun Shen,

Xing Li

[pdf] [supp]

[bibtex]

@InProceedings{Rao_2023_CVPR, author = {Rao, Zhibo and Xiong, Bangshu and He, Mingyi and Dai, Yuchao and He, Renjie and Shen, Zhelun and Li, Xing}, title = {Masked Representation Learning for Domain Generalized Stereo Matching}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5435-5444} }

LVQAC: Lattice Vector Quantization Coupled With Spatially Adaptive Companding for Efficient Learned Image Compression

Xi Zhang,

Xiaolin Wu

[pdf] [arXiv]

[bibtex]

@InProceedings{Zhang_2023_CVPR, author = {Zhang, Xi and Wu, Xiaolin}, title = {LVQAC: Lattice Vector Quantization Coupled With Spatially Adaptive Companding for Efficient Learned Image Compression}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10239-10248} }

You Can Ground Earlier Than See: An Effective and Efficient Pipeline for Temporal Sentence Grounding in Compressed Videos

Xiang Fang,

Daizong Liu,

Pan Zhou,

Guoshun Nan

[pdf] [arXiv]

[bibtex]

@InProceedings{Fang_2023_CVPR, author = {Fang, Xiang and Liu, Daizong and Zhou, Pan and Nan, Guoshun}, title = {You Can Ground Earlier Than See: An Effective and Efficient Pipeline for Temporal Sentence Grounding in Compressed Videos}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2448-2460} }

EqMotion: Equivariant Multi-Agent Motion Prediction With Invariant Interaction Reasoning

Chenxin Xu,

Robby T. Tan,

Yuhong Tan,

Siheng Chen,

Yu Guang Wang,

Xinchao Wang,

Yanfeng Wang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Xu_2023_CVPR, author = {Xu, Chenxin and Tan, Robby T. and Tan, Yuhong and Chen, Siheng and Wang, Yu Guang and Wang, Xinchao and Wang, Yanfeng}, title = {EqMotion: Equivariant Multi-Agent Motion Prediction With Invariant Interaction Reasoning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1410-1420} }

Fine-Grained Face Swapping via Regional GAN Inversion

Zhian Liu,

Maomao Li,

Yong Zhang,

Cairong Wang,

Qi Zhang,

Jue Wang,

Yongwei Nie

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Liu_2023_CVPR, author = {Liu, Zhian and Li, Maomao and Zhang, Yong and Wang, Cairong and Zhang, Qi and Wang, Jue and Nie, Yongwei}, title = {Fine-Grained Face Swapping via Regional GAN Inversion}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8578-8587} }

Taming Diffusion Models for Audio-Driven Co-Speech Gesture Generation

Lingting Zhu,

Xian Liu,

Xuanyu Liu,

Rui Qian,

Ziwei Liu,

Lequan Yu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Zhu_2023_CVPR, author = {Zhu, Lingting and Liu, Xian and Liu, Xuanyu and Qian, Rui and Liu, Ziwei and Yu, Lequan}, title = {Taming Diffusion Models for Audio-Driven Co-Speech Gesture Generation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10544-10553} }

FlowFormer++: Masked Cost Volume Autoencoding for Pretraining Optical Flow Estimation

Xiaoyu Shi,

Zhaoyang Huang,

Dasong Li,

Manyuan Zhang,

Ka Chun Cheung,

Simon See,

Hongwei Qin,

Jifeng Dai,

Hongsheng Li

[pdf]

[bibtex]

@InProceedings{Shi_2023_CVPR, author = {Shi, Xiaoyu and Huang, Zhaoyang and Li, Dasong and Zhang, Manyuan and Cheung, Ka Chun and See, Simon and Qin, Hongwei and Dai, Jifeng and Li, Hongsheng}, title = {FlowFormer++: Masked Cost Volume Autoencoding for Pretraining Optical Flow Estimation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1599-1610} }

NeRFLix: High-Quality Neural View Synthesis by Learning a Degradation-Driven Inter-Viewpoint MiXer

Kun Zhou,

Wenbo Li,

Yi Wang,

Tao Hu,

Nianjuan Jiang,

Xiaoguang Han,

Jiangbo Lu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Zhou_2023_CVPR, author = {Zhou, Kun and Li, Wenbo and Wang, Yi and Hu, Tao and Jiang, Nianjuan and Han, Xiaoguang and Lu, Jiangbo}, title = {NeRFLix: High-Quality Neural View Synthesis by Learning a Degradation-Driven Inter-Viewpoint MiXer}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12363-12374} }

HaLP: Hallucinating Latent Positives for Skeleton-Based Self-Supervised Learning of Actions

Anshul Shah,

Aniket Roy,

Ketul Shah,

Shlok Mishra,

David Jacobs,

Anoop Cherian,

Rama Chellappa

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Shah_2023_CVPR, author = {Shah, Anshul and Roy, Aniket and Shah, Ketul and Mishra, Shlok and Jacobs, David and Cherian, Anoop and Chellappa, Rama}, title = {HaLP: Hallucinating Latent Positives for Skeleton-Based Self-Supervised Learning of Actions}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {18846-18856} }

STMixer: A One-Stage Sparse Action Detector

Tao Wu,

Mengqi Cao,

Ziteng Gao,

Gangshan Wu,

Limin Wang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Wu_2023_CVPR, author = {Wu, Tao and Cao, Mengqi and Gao, Ziteng and Wu, Gangshan and Wang, Limin}, title = {STMixer: A One-Stage Sparse Action Detector}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14720-14729} }

3D Human Keypoints Estimation From Point Clouds in the Wild Without Human Labels

Zhenzhen Weng,

Alexander S. Gorban,

Jingwei Ji,

Mahyar Najibi,

Yin Zhou,

Dragomir Anguelov

[pdf]

[bibtex]

@InProceedings{Weng_2023_CVPR, author = {Weng, Zhenzhen and Gorban, Alexander S. and Ji, Jingwei and Najibi, Mahyar and Zhou, Yin and Anguelov, Dragomir}, title = {3D Human Keypoints Estimation From Point Clouds in the Wild Without Human Labels}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1158-1167} }

Where Is My Spot? Few-Shot Image Generation via Latent Subspace Optimization

Chenxi Zheng,

Bangzhen Liu,

Huaidong Zhang,

Xuemiao Xu,

Shengfeng He

[pdf] [supp]

[bibtex]

@InProceedings{Zheng_2023_CVPR, author = {Zheng, Chenxi and Liu, Bangzhen and Zhang, Huaidong and Xu, Xuemiao and He, Shengfeng}, title = {Where Is My Spot? Few-Shot Image Generation via Latent Subspace Optimization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3272-3281} }

FLEX: Full-Body Grasping Without Full-Body Grasps

Purva Tendulkar,

Dídac Surís,

Carl Vondrick

[pdf] [supp]

[bibtex]

@InProceedings{Tendulkar_2023_CVPR, author = {Tendulkar, Purva and Sur{\'\i}s, D{\'\i}dac and Vondrick, Carl}, title = {FLEX: Full-Body Grasping Without Full-Body Grasps}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {21179-21189} }

Genie: Show Me the Data for Quantization

Yongkweon Jeon,

Chungman Lee,

Ho-young Kim

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Jeon_2023_CVPR, author = {Jeon, Yongkweon and Lee, Chungman and Kim, Ho-young}, title = {Genie: Show Me the Data for Quantization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12064-12073} }

EVA: Exploring the Limits of Masked Visual Representation Learning at Scale

Yuxin Fang,

Wen Wang,

Binhui Xie,

Quan Sun,

Ledell Wu,

Xinggang Wang,

Tiejun Huang,

Xinlong Wang,

Yue Cao

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Fang_2023_CVPR, author = {Fang, Yuxin and Wang, Wen and Xie, Binhui and Sun, Quan and Wu, Ledell and Wang, Xinggang and Huang, Tiejun and Wang, Xinlong and Cao, Yue}, title = {EVA: Exploring the Limits of Masked Visual Representation Learning at Scale}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {19358-19369} }

TopNet: Transformer-Based Object Placement Network for Image Compositing

Sijie Zhu,

Zhe Lin,

Scott Cohen,

Jason Kuen,

Zhifei Zhang,

Chen Chen

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Zhu_2023_CVPR, author = {Zhu, Sijie and Lin, Zhe and Cohen, Scott and Kuen, Jason and Zhang, Zhifei and Chen, Chen}, title = {TopNet: Transformer-Based Object Placement Network for Image Compositing}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1838-1847} }

Discrete Point-Wise Attack Is Not Enough: Generalized Manifold Adversarial Attack for Face Recognition

Qian Li,

Yuxiao Hu,

Ye Liu,

Dongxiao Zhang,

Xin Jin,

Yuntian Chen

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Li_2023_CVPR, author = {Li, Qian and Hu, Yuxiao and Liu, Ye and Zhang, Dongxiao and Jin, Xin and Chen, Yuntian}, title = {Discrete Point-Wise Attack Is Not Enough: Generalized Manifold Adversarial Attack for Face Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {20575-20584} }

Gloss Attention for Gloss-Free Sign Language Translation

Aoxiong Yin,

Tianyun Zhong,

Li Tang,

Weike Jin,

Tao Jin,

Zhou Zhao

[pdf] [supp]

[bibtex]

@InProceedings{Yin_2023_CVPR, author = {Yin, Aoxiong and Zhong, Tianyun and Tang, Li and Jin, Weike and Jin, Tao and Zhao, Zhou}, title = {Gloss Attention for Gloss-Free Sign Language Translation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2551-2562} }

Multi-Agent Automated Machine Learning

Zhaozhi Wang,

Kefan Su,

Jian Zhang,

Huizhu Jia,

Qixiang Ye,

Xiaodong Xie,

Zongqing Lu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Zhaozhi and Su, Kefan and Zhang, Jian and Jia, Huizhu and Ye, Qixiang and Xie, Xiaodong and Lu, Zongqing}, title = {Multi-Agent Automated Machine Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11960-11969} }

Robot Structure Prior Guided Temporal Attention for Camera-to-Robot Pose Estimation From Image Sequence

Yang Tian,

Jiyao Zhang,

Zekai Yin,

Hao Dong

[pdf]

[bibtex]

@InProceedings{Tian_2023_CVPR, author = {Tian, Yang and Zhang, Jiyao and Yin, Zekai and Dong, Hao}, title = {Robot Structure Prior Guided Temporal Attention for Camera-to-Robot Pose Estimation From Image Sequence}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8917-8926} }

FREDOM: Fairness Domain Adaptation Approach to Semantic Scene Understanding

Thanh-Dat Truong,

Ngan Le,

Bhiksha Raj,

Jackson Cothren,

Khoa Luu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Truong_2023_CVPR, author = {Truong, Thanh-Dat and Le, Ngan and Raj, Bhiksha and Cothren, Jackson and Luu, Khoa}, title = {FREDOM: Fairness Domain Adaptation Approach to Semantic Scene Understanding}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {19988-19997} }

IMP: Iterative Matching and Pose Estimation With Adaptive Pooling

Fei Xue,

Ignas Budvytis,

Roberto Cipolla

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Xue_2023_CVPR, author = {Xue, Fei and Budvytis, Ignas and Cipolla, Roberto}, title = {IMP: Iterative Matching and Pose Estimation With Adaptive Pooling}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {21317-21326} }

HRDFuse: Monocular 360deg Depth Estimation by Collaboratively Learning Holistic-With-Regional Depth Distributions

Hao Ai,

Zidong Cao,

Yan-Pei Cao,

Ying Shan,

Lin Wang

[pdf] [supp]

[bibtex]

@InProceedings{Ai_2023_CVPR, author = {Ai, Hao and Cao, Zidong and Cao, Yan-Pei and Shan, Ying and Wang, Lin}, title = {HRDFuse: Monocular 360deg Depth Estimation by Collaboratively Learning Holistic-With-Regional Depth Distributions}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13273-13282} }

Revisiting Rolling Shutter Bundle Adjustment: Toward Accurate and Fast Solution

Bangyan Liao,

Delin Qu,

Yifei Xue,

Huiqing Zhang,

Yizhen Lao

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Liao_2023_CVPR, author = {Liao, Bangyan and Qu, Delin and Xue, Yifei and Zhang, Huiqing and Lao, Yizhen}, title = {Revisiting Rolling Shutter Bundle Adjustment: Toward Accurate and Fast Solution}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4863-4871} }

StructVPR: Distill Structural Knowledge With Weighting Samples for Visual Place Recognition

Yanqing Shen,

Sanping Zhou,

Jingwen Fu,

Ruotong Wang,

Shitao Chen,

Nanning Zheng

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Shen_2023_CVPR, author = {Shen, Yanqing and Zhou, Sanping and Fu, Jingwen and Wang, Ruotong and Chen, Shitao and Zheng, Nanning}, title = {StructVPR: Distill Structural Knowledge With Weighting Samples for Visual Place Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11217-11226} }

PATS: Patch Area Transportation With Subdivision for Local Feature Matching

Junjie Ni,

Yijin Li,

Zhaoyang Huang,

Hongsheng Li,

Hujun Bao,

Zhaopeng Cui,

Guofeng Zhang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Ni_2023_CVPR, author = {Ni, Junjie and Li, Yijin and Huang, Zhaoyang and Li, Hongsheng and Bao, Hujun and Cui, Zhaopeng and Zhang, Guofeng}, title = {PATS: Patch Area Transportation With Subdivision for Local Feature Matching}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {17776-17786} }

Learning Human-to-Robot Handovers From Point Clouds

Sammy Christen,

Wei Yang,

Claudia Pérez-D’Arpino,

Otmar Hilliges,

Dieter Fox,

Yu-Wei Chao

[pdf] [supp]

[bibtex]

@InProceedings{Christen_2023_CVPR, author = {Christen, Sammy and Yang, Wei and P\'erez-D{\textquoteright}Arpino, Claudia and Hilliges, Otmar and Fox, Dieter and Chao, Yu-Wei}, title = {Learning Human-to-Robot Handovers From Point Clouds}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9654-9664} }

MEDIC: Remove Model Backdoors via Importance Driven Cloning

Qiuling Xu,

Guanhong Tao,

Jean Honorio,

Yingqi Liu,

Shengwei An,

Guangyu Shen,

Siyuan Cheng,

Xiangyu Zhang

[pdf] [supp]

[bibtex]

@InProceedings{Xu_2023_CVPR, author = {Xu, Qiuling and Tao, Guanhong and Honorio, Jean and Liu, Yingqi and An, Shengwei and Shen, Guangyu and Cheng, Siyuan and Zhang, Xiangyu}, title = {MEDIC: Remove Model Backdoors via Importance Driven Cloning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {20485-20494} }

Context-Aware Relative Object Queries To Unify Video Instance and Panoptic Segmentation

Anwesa Choudhuri,

Girish Chowdhary,

Alexander G. Schwing

[pdf] [supp]

[bibtex]

@InProceedings{Choudhuri_2023_CVPR, author = {Choudhuri, Anwesa and Chowdhary, Girish and Schwing, Alexander G.}, title = {Context-Aware Relative Object Queries To Unify Video Instance and Panoptic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6377-6386} }

Score Jacobian Chaining: Lifting Pretrained 2D Diffusion Models for 3D Generation

Haochen Wang,

Xiaodan Du,

Jiahao Li,

Raymond A. Yeh,

Greg Shakhnarovich

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Haochen and Du, Xiaodan and Li, Jiahao and Yeh, Raymond A. and Shakhnarovich, Greg}, title = {Score Jacobian Chaining: Lifting Pretrained 2D Diffusion Models for 3D Generation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12619-12629} }

Role of Transients in Two-Bounce Non-Line-of-Sight Imaging

Siddharth Somasundaram,

Akshat Dave,

Connor Henley,

Ashok Veeraraghavan,

Ramesh Raskar

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Somasundaram_2023_CVPR, author = {Somasundaram, Siddharth and Dave, Akshat and Henley, Connor and Veeraraghavan, Ashok and Raskar, Ramesh}, title = {Role of Transients in Two-Bounce Non-Line-of-Sight Imaging}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9192-9201} }

SimpleNet: A Simple Network for Image Anomaly Detection and Localization

Zhikang Liu,

Yiming Zhou,

Yuansheng Xu,

Zilei Wang

[pdf] [arXiv]

[bibtex]

@InProceedings{Liu_2023_CVPR, author = {Liu, Zhikang and Zhou, Yiming and Xu, Yuansheng and Wang, Zilei}, title = {SimpleNet: A Simple Network for Image Anomaly Detection and Localization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {20402-20411} }

Elastic Aggregation for Federated Optimization

Dengsheng Chen,

Jie Hu,

Vince Junkai Tan,

Xiaoming Wei,

Enhua Wu

[pdf] [supp]

[bibtex]

@InProceedings{Chen_2023_CVPR, author = {Chen, Dengsheng and Hu, Jie and Tan, Vince Junkai and Wei, Xiaoming and Wu, Enhua}, title = {Elastic Aggregation for Federated Optimization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12187-12197} }

G-MSM: Unsupervised Multi-Shape Matching With Graph-Based Affinity Priors

Marvin Eisenberger,

Aysim Toker,

Laura Leal-Taixé,

Daniel Cremers

[pdf] [supp]

[bibtex]

@InProceedings{Eisenberger_2023_CVPR, author = {Eisenberger, Marvin and Toker, Aysim and Leal-Taix\'e, Laura and Cremers, Daniel}, title = {G-MSM: Unsupervised Multi-Shape Matching With Graph-Based Affinity Priors}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {22762-22772} }

Enhancing Deformable Local Features by Jointly Learning To Detect and Describe Keypoints

Guilherme Potje,

Felipe Cadar,

André Araujo,

Renato Martins,

Erickson R. Nascimento

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Potje_2023_CVPR, author = {Potje, Guilherme and Cadar, Felipe and Araujo, Andr\'e and Martins, Renato and Nascimento, Erickson R.}, title = {Enhancing Deformable Local Features by Jointly Learning To Detect and Describe Keypoints}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1306-1315} }

ObjectMatch: Robust Registration Using Canonical Object Correspondences

Can Gümeli,

Angela Dai,

Matthias Nießner

[pdf] [supp]

[bibtex]

@InProceedings{Gumeli_2023_CVPR, author = {G\"umeli, Can and Dai, Angela and Nie{\ss}ner, Matthias}, title = {ObjectMatch: Robust Registration Using Canonical Object Correspondences}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13082-13091} }

Siamese Image Modeling for Self-Supervised Vision Representation Learning

Chenxin Tao,

Xizhou Zhu,

Weijie Su,

Gao Huang,

Bin Li,

Jie Zhou,

Yu Qiao,

Xiaogang Wang,

Jifeng Dai

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Tao_2023_CVPR, author = {Tao, Chenxin and Zhu, Xizhou and Su, Weijie and Huang, Gao and Li, Bin and Zhou, Jie and Qiao, Yu and Wang, Xiaogang and Dai, Jifeng}, title = {Siamese Image Modeling for Self-Supervised Vision Representation Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2132-2141} }

Generating Part-Aware Editable 3D Shapes Without 3D Supervision

Konstantinos Tertikas,

Despoina Paschalidou,

Boxiao Pan,

Jeong Joon Park,

Mikaela Angelina Uy,

Ioannis Emiris,

Yannis Avrithis,

Leonidas Guibas

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Tertikas_2023_CVPR, author = {Tertikas, Konstantinos and Paschalidou, Despoina and Pan, Boxiao and Park, Jeong Joon and Uy, Mikaela Angelina and Emiris, Ioannis and Avrithis, Yannis and Guibas, Leonidas}, title = {Generating Part-Aware Editable 3D Shapes Without 3D Supervision}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4466-4478} }

Center Focusing Network for Real-Time LiDAR Panoptic Segmentation

Xiaoyan Li,

Gang Zhang,

Boyue Wang,

Yongli Hu,

Baocai Yin

[pdf] [supp]

[bibtex]

@InProceedings{Li_2023_CVPR, author = {Li, Xiaoyan and Zhang, Gang and Wang, Boyue and Hu, Yongli and Yin, Baocai}, title = {Center Focusing Network for Real-Time LiDAR Panoptic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13425-13434} }

High-Fidelity Facial Avatar Reconstruction From Monocular Video With Generative Priors

Yunpeng Bai,

Yanbo Fan,

Xuan Wang,

Yong Zhang,

Jingxiang Sun,

Chun Yuan,

Ying Shan

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Bai_2023_CVPR, author = {Bai, Yunpeng and Fan, Yanbo and Wang, Xuan and Zhang, Yong and Sun, Jingxiang and Yuan, Chun and Shan, Ying}, title = {High-Fidelity Facial Avatar Reconstruction From Monocular Video With Generative Priors}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4541-4551} }

Mixed Autoencoder for Self-Supervised Visual Representation Learning

Kai Chen,

Zhili Liu,

Lanqing Hong,

Hang Xu,

Zhenguo Li,

Dit-Yan Yeung

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Chen_2023_CVPR, author = {Chen, Kai and Liu, Zhili and Hong, Lanqing and Xu, Hang and Li, Zhenguo and Yeung, Dit-Yan}, title = {Mixed Autoencoder for Self-Supervised Visual Representation Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {22742-22751} }

Restoration of Hand-Drawn Architectural Drawings Using Latent Space Mapping With Degradation Generator

Nakkwan Choi,

Seungjae Lee,

Yongsik Lee,

Seungjoon Yang

[pdf] [supp]

[bibtex]

@InProceedings{Choi_2023_CVPR, author = {Choi, Nakkwan and Lee, Seungjae and Lee, Yongsik and Yang, Seungjoon}, title = {Restoration of Hand-Drawn Architectural Drawings Using Latent Space Mapping With Degradation Generator}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14164-14172} }

CABM: Content-Aware Bit Mapping for Single Image Super-Resolution Network With Large Input

Senmao Tian,

Ming Lu,

Jiaming Liu,

Yandong Guo,

Yurong Chen,

Shunli Zhang

[pdf] [arXiv]

[bibtex]

@InProceedings{Tian_2023_CVPR, author = {Tian, Senmao and Lu, Ming and Liu, Jiaming and Guo, Yandong and Chen, Yurong and Zhang, Shunli}, title = {CABM: Content-Aware Bit Mapping for Single Image Super-Resolution Network With Large Input}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1756-1765} }

Decoupling MaxLogit for Out-of-Distribution Detection

Zihan Zhang,

Xiang Xiang

[pdf] [supp]

[bibtex]

@InProceedings{Zhang_2023_CVPR, author = {Zhang, Zihan and Xiang, Xiang}, title = {Decoupling MaxLogit for Out-of-Distribution Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3388-3397} }

ProphNet: Efficient Agent-Centric Motion Forecasting With Anchor-Informed Proposals

Xishun Wang,

Tong Su,

Fang Da,

Xiaodong Yang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Xishun and Su, Tong and Da, Fang and Yang, Xiaodong}, title = {ProphNet: Efficient Agent-Centric Motion Forecasting With Anchor-Informed Proposals}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {21995-22003} }

Generalizing Dataset Distillation via Deep Generative Prior

George Cazenavette,

Tongzhou Wang,

Antonio Torralba,

Alexei A. Efros,

Jun-Yan Zhu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Cazenavette_2023_CVPR, author = {Cazenavette, George and Wang, Tongzhou and Torralba, Antonio and Efros, Alexei A. and Zhu, Jun-Yan}, title = {Generalizing Dataset Distillation via Deep Generative Prior}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3739-3748} }

Few-Shot Class-Incremental Learning via Class-Aware Bilateral Distillation

Linglan Zhao,

Jing Lu,

Yunlu Xu,

Zhanzhan Cheng,

Dashan Guo,

Yi Niu,

Xiangzhong Fang

[pdf] [supp]

[bibtex]

@InProceedings{Zhao_2023_CVPR, author = {Zhao, Linglan and Lu, Jing and Xu, Yunlu and Cheng, Zhanzhan and Guo, Dashan and Niu, Yi and Fang, Xiangzhong}, title = {Few-Shot Class-Incremental Learning via Class-Aware Bilateral Distillation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11838-11847} }

Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo

Yuesong Wang,

Zhaojie Zeng,

Tao Guan,

Wei Yang,

Zhuo Chen,

Wenkai Liu,

Luoyuan Xu,

Yawei Luo

[pdf] [supp]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Yuesong and Zeng, Zhaojie and Guan, Tao and Yang, Wei and Chen, Zhuo and Liu, Wenkai and Xu, Luoyuan and Luo, Yawei}, title = {Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1621-1630} }

Detection of Out-of-Distribution Samples Using Binary Neuron Activation Patterns

Bartłomiej Olber,

Krystian Radlak,

Adam Popowicz,

Michal Szczepankiewicz,

Krystian Chachuła

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Olber_2023_CVPR, author = {Olber, Bart{\l}omiej and Radlak, Krystian and Popowicz, Adam and Szczepankiewicz, Michal and Chachu{\l}a, Krystian}, title = {Detection of Out-of-Distribution Samples Using Binary Neuron Activation Patterns}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3378-3387} }

SeaThru-NeRF: Neural Radiance Fields in Scattering Media

Deborah Levy,

Amit Peleg,

Naama Pearl,

Dan Rosenbaum,

Derya Akkaynak,

Simon Korman,

Tali Treibitz

[pdf] [supp]

[bibtex]

@InProceedings{Levy_2023_CVPR, author = {Levy, Deborah and Peleg, Amit and Pearl, Naama and Rosenbaum, Dan and Akkaynak, Derya and Korman, Simon and Treibitz, Tali}, title = {SeaThru-NeRF: Neural Radiance Fields in Scattering Media}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {56-65} }

Learning Multi-Modal Class-Specific Tokens for Weakly Supervised Dense Object Localization

Lian Xu,

Wanli Ouyang,

Mohammed Bennamoun,

Farid Boussaid,

Dan Xu

[pdf] [supp]

[bibtex]

@InProceedings{Xu_2023_CVPR, author = {Xu, Lian and Ouyang, Wanli and Bennamoun, Mohammed and Boussaid, Farid and Xu, Dan}, title = {Learning Multi-Modal Class-Specific Tokens for Weakly Supervised Dense Object Localization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {19596-19605} }

Learning To Dub Movies via Hierarchical Prosody Models

Gaoxiang Cong,

Liang Li,

Yuankai Qi,

Zheng-Jun Zha,

Qi Wu,

Wenyu Wang,

Bin Jiang,

Ming-Hsuan Yang,

Qingming Huang

[pdf] [arXiv]

[bibtex]

@InProceedings{Cong_2023_CVPR, author = {Cong, Gaoxiang and Li, Liang and Qi, Yuankai and Zha, Zheng-Jun and Wu, Qi and Wang, Wenyu and Jiang, Bin and Yang, Ming-Hsuan and Huang, Qingming}, title = {Learning To Dub Movies via Hierarchical Prosody Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14687-14697} }

DiffusionRig: Learning Personalized Priors for Facial Appearance Editing

Zheng Ding,

Xuaner Zhang,

Zhihao Xia,

Lars Jebe,

Zhuowen Tu,

Xiuming Zhang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Ding_2023_CVPR, author = {Ding, Zheng and Zhang, Xuaner and Xia, Zhihao and Jebe, Lars and Tu, Zhuowen and Zhang, Xiuming}, title = {DiffusionRig: Learning Personalized Priors for Facial Appearance Editing}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12736-12746} }

Delving StyleGAN Inversion for Image Editing: A Foundation Latent Space Viewpoint

Hongyu Liu,

Yibing Song,

Qifeng Chen

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Liu_2023_CVPR, author = {Liu, Hongyu and Song, Yibing and Chen, Qifeng}, title = {Delving StyleGAN Inversion for Image Editing: A Foundation Latent Space Viewpoint}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10072-10082} }

MixMAE: Mixed and Masked Autoencoder for Efficient Pretraining of Hierarchical Vision Transformers

Jihao Liu,

Xin Huang,

Jinliang Zheng,

Yu Liu,

Hongsheng Li

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Liu_2023_CVPR, author = {Liu, Jihao and Huang, Xin and Zheng, Jinliang and Liu, Yu and Li, Hongsheng}, title = {MixMAE: Mixed and Masked Autoencoder for Efficient Pretraining of Hierarchical Vision Transformers}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6252-6261} }

Human Pose Estimation in Extremely Low-Light Conditions

Sohyun Lee,

Jaesung Rim,

Boseung Jeong,

Geonu Kim,

Byungju Woo,

Haechan Lee,

Sunghyun Cho,

Suha Kwak

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Lee_2023_CVPR, author = {Lee, Sohyun and Rim, Jaesung and Jeong, Boseung and Kim, Geonu and Woo, Byungju and Lee, Haechan and Cho, Sunghyun and Kwak, Suha}, title = {Human Pose Estimation in Extremely Low-Light Conditions}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {704-714} }

EventNeRF: Neural Radiance Fields From a Single Colour Event Camera

Viktor Rudnev,

Mohamed Elgharib,

Christian Theobalt,

Vladislav Golyanik

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Rudnev_2023_CVPR, author = {Rudnev, Viktor and Elgharib, Mohamed and Theobalt, Christian and Golyanik, Vladislav}, title = {EventNeRF: Neural Radiance Fields From a Single Colour Event Camera}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4992-5002} }

Neighborhood Attention Transformer

Ali Hassani,

Steven Walton,

Jiachen Li,

Shen Li,

Humphrey Shi

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Hassani_2023_CVPR, author = {Hassani, Ali and Walton, Steven and Li, Jiachen and Li, Shen and Shi, Humphrey}, title = {Neighborhood Attention Transformer}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6185-6194} }

Enlarging Instance-Specific and Class-Specific Information for Open-Set Action Recognition

Jun Cen,

Shiwei Zhang,

Xiang Wang,

Yixuan Pei,

Zhiwu Qing,

Yingya Zhang,

Qifeng Chen

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Cen_2023_CVPR, author = {Cen, Jun and Zhang, Shiwei and Wang, Xiang and Pei, Yixuan and Qing, Zhiwu and Zhang, Yingya and Chen, Qifeng}, title = {Enlarging Instance-Specific and Class-Specific Information for Open-Set Action Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15295-15304} }

Decoupled Semantic Prototypes Enable Learning From Diverse Annotation Types for Semi-Weakly Segmentation in Expert-Driven Domains

Simon Reiß,

Constantin Seibold,

Alexander Freytag,

Erik Rodner,

Rainer Stiefelhagen

[pdf] [supp]

[bibtex]

@InProceedings{Reiss_2023_CVPR, author = {Rei{\ss}, Simon and Seibold, Constantin and Freytag, Alexander and Rodner, Erik and Stiefelhagen, Rainer}, title = {Decoupled Semantic Prototypes Enable Learning From Diverse Annotation Types for Semi-Weakly Segmentation in Expert-Driven Domains}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15495-15506} }

Progressive Spatio-Temporal Alignment for Efficient Event-Based Motion Estimation

Xueyan Huang,

Yueyi Zhang,

Zhiwei Xiong

[pdf] [supp]

[bibtex]

@InProceedings{Huang_2023_CVPR, author = {Huang, Xueyan and Zhang, Yueyi and Xiong, Zhiwei}, title = {Progressive Spatio-Temporal Alignment for Efficient Event-Based Motion Estimation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1537-1546} }

Trap Attention: Monocular Depth Estimation With Manual Traps

Chao Ning,

Hongping Gan

[pdf] [supp]

[bibtex]

@InProceedings{Ning_2023_CVPR, author = {Ning, Chao and Gan, Hongping}, title = {Trap Attention: Monocular Depth Estimation With Manual Traps}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5033-5043} }

Iterative Next Boundary Detection for Instance Segmentation of Tree Rings in Microscopy Images of Shrub Cross Sections

Alexander Gillert,

Giulia Resente,

Alba Anadon-Rosell,

Martin Wilmking,

Uwe Freiherr von Lukas

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Gillert_2023_CVPR, author = {Gillert, Alexander and Resente, Giulia and Anadon-Rosell, Alba and Wilmking, Martin and von Lukas, Uwe Freiherr}, title = {Iterative Next Boundary Detection for Instance Segmentation of Tree Rings in Microscopy Images of Shrub Cross Sections}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14540-14548} }

Learning and Aggregating Lane Graphs for Urban Automated Driving

Martin Büchner,

Jannik Zürn,

Ion-George Todoran,

Abhinav Valada,

Wolfram Burgard

[pdf] [supp]

[bibtex]

@InProceedings{Buchner_2023_CVPR, author = {B\"uchner, Martin and Z\"urn, Jannik and Todoran, Ion-George and Valada, Abhinav and Burgard, Wolfram}, title = {Learning and Aggregating Lane Graphs for Urban Automated Driving}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13415-13424} }

Universal Instance Perception As Object Discovery and Retrieval

Bin Yan,

Yi Jiang,

Jiannan Wu,

Dong Wang,

Ping Luo,

Zehuan Yuan,

Huchuan Lu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Yan_2023_CVPR, author = {Yan, Bin and Jiang, Yi and Wu, Jiannan and Wang, Dong and Luo, Ping and Yuan, Zehuan and Lu, Huchuan}, title = {Universal Instance Perception As Object Discovery and Retrieval}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15325-15336} }

GlassesGAN: Eyewear Personalization Using Synthetic Appearance Discovery and Targeted Subspace Modeling

Richard Plesh,

Peter Peer,

Vitomir Struc

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Plesh_2023_CVPR, author = {Plesh, Richard and Peer, Peter and Struc, Vitomir}, title = {GlassesGAN: Eyewear Personalization Using Synthetic Appearance Discovery and Targeted Subspace Modeling}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16847-16857} }

Representing Volumetric Videos As Dynamic MLP Maps

Sida Peng,

Yunzhi Yan,

Qing Shuai,

Hujun Bao,

Xiaowei Zhou

[pdf] [arXiv]

[bibtex]

@InProceedings{Peng_2023_CVPR, author = {Peng, Sida and Yan, Yunzhi and Shuai, Qing and Bao, Hujun and Zhou, Xiaowei}, title = {Representing Volumetric Videos As Dynamic MLP Maps}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4252-4262} }

Deep Hashing With Minimal-Distance-Separated Hash Centers

Liangdao Wang,

Yan Pan,

Cong Liu,

Hanjiang Lai,

Jian Yin,

Ye Liu

[pdf] [supp]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Liangdao and Pan, Yan and Liu, Cong and Lai, Hanjiang and Yin, Jian and Liu, Ye}, title = {Deep Hashing With Minimal-Distance-Separated Hash Centers}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {23455-23464} }

Video-Text As Game Players: Hierarchical Banzhaf Interaction for Cross-Modal Representation Learning

Peng Jin,

Jinfa Huang,

Pengfei Xiong,

Shangxuan Tian,

Chang Liu,

Xiangyang Ji,

Li Yuan,

Jie Chen

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Jin_2023_CVPR, author = {Jin, Peng and Huang, Jinfa and Xiong, Pengfei and Tian, Shangxuan and Liu, Chang and Ji, Xiangyang and Yuan, Li and Chen, Jie}, title = {Video-Text As Game Players: Hierarchical Banzhaf Interaction for Cross-Modal Representation Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2472-2482} }

VL-SAT: Visual-Linguistic Semantics Assisted Training for 3D Semantic Scene Graph Prediction in Point Cloud

Ziqin Wang,

Bowen Cheng,

Lichen Zhao,

Dong Xu,

Yang Tang,

Lu Sheng

[pdf] [supp]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Ziqin and Cheng, Bowen and Zhao, Lichen and Xu, Dong and Tang, Yang and Sheng, Lu}, title = {VL-SAT: Visual-Linguistic Semantics Assisted Training for 3D Semantic Scene Graph Prediction in Point Cloud}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {21560-21569} }

Learning Emotion Representations From Verbal and Nonverbal Communication

Sitao Zhang,

Yimu Pan,

James Z. Wang

[pdf] [supp]

[bibtex]

@InProceedings{Zhang_2023_CVPR, author = {Zhang, Sitao and Pan, Yimu and Wang, James Z.}, title = {Learning Emotion Representations From Verbal and Nonverbal Communication}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {18993-19004} }

Transferable Adversarial Attacks on Vision Transformers With Token Gradient Regularization

Jianping Zhang,

Yizhan Huang,

Weibin Wu,

Michael R. Lyu

[pdf] [arXiv]

[bibtex]

@InProceedings{Zhang_2023_CVPR, author = {Zhang, Jianping and Huang, Yizhan and Wu, Weibin and Lyu, Michael R.}, title = {Transferable Adversarial Attacks on Vision Transformers With Token Gradient Regularization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16415-16424} }

MCF: Mutual Correction Framework for Semi-Supervised Medical Image Segmentation

Yongchao Wang,

Bin Xiao,

Xiuli Bi,

Weisheng Li,

Xinbo Gao

[pdf]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Yongchao and Xiao, Bin and Bi, Xiuli and Li, Weisheng and Gao, Xinbo}, title = {MCF: Mutual Correction Framework for Semi-Supervised Medical Image Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15651-15660} }

Blur Interpolation Transformer for Real-World Motion From Blur

Zhihang Zhong,

Mingdeng Cao,

Xiang Ji,

Yinqiang Zheng,

Imari Sato

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Zhong_2023_CVPR, author = {Zhong, Zhihang and Cao, Mingdeng and Ji, Xiang and Zheng, Yinqiang and Sato, Imari}, title = {Blur Interpolation Transformer for Real-World Motion From Blur}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5713-5723} }

Rethinking Few-Shot Medical Segmentation: A Vector Quantization View

Shiqi Huang,

Tingfa Xu,

Ning Shen,

Feng Mu,

Jianan Li

[pdf] [supp]

[bibtex]

@InProceedings{Huang_2023_CVPR, author = {Huang, Shiqi and Xu, Tingfa and Shen, Ning and Mu, Feng and Li, Jianan}, title = {Rethinking Few-Shot Medical Segmentation: A Vector Quantization View}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3072-3081} }

Event-Based Shape From Polarization

Manasi Muglikar,

Leonard Bauersfeld,

Diederik Paul Moeys,

Davide Scaramuzza

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Muglikar_2023_CVPR, author = {Muglikar, Manasi and Bauersfeld, Leonard and Moeys, Diederik Paul and Scaramuzza, Davide}, title = {Event-Based Shape From Polarization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1547-1556} }

Architectural Backdoors in Neural Networks

Mikel Bober-Irizar,

Ilia Shumailov,

Yiren Zhao,

Robert Mullins,

Nicolas Papernot

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Bober-Irizar_2023_CVPR, author = {Bober-Irizar, Mikel and Shumailov, Ilia and Zhao, Yiren and Mullins, Robert and Papernot, Nicolas}, title = {Architectural Backdoors in Neural Networks}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {24595-24604} }

ARO-Net: Learning Implicit Fields From Anchored Radial Observations

Yizhi Wang,

Zeyu Huang,

Ariel Shamir,

Hui Huang,

Hao Zhang,

Ruizhen Hu

[pdf] [supp]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Yizhi and Huang, Zeyu and Shamir, Ariel and Huang, Hui and Zhang, Hao and Hu, Ruizhen}, title = {ARO-Net: Learning Implicit Fields From Anchored Radial Observations}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3572-3581} }

All in One: Exploring Unified Video-Language Pre-Training

Jinpeng Wang,

Yixiao Ge,

Rui Yan,

Yuying Ge,

Kevin Qinghong Lin,

Satoshi Tsutsui,

Xudong Lin,

Guanyu Cai,

Jianping Wu,

Ying Shan,

Xiaohu Qie,

Mike Zheng Shou

[pdf] [arXiv]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Jinpeng and Ge, Yixiao and Yan, Rui and Ge, Yuying and Lin, Kevin Qinghong and Tsutsui, Satoshi and Lin, Xudong and Cai, Guanyu and Wu, Jianping and Shan, Ying and Qie, Xiaohu and Shou, Mike Zheng}, title = {All in One: Exploring Unified Video-Language Pre-Training}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6598-6608} }

Parametric Implicit Face Representation for Audio-Driven Facial Reenactment

Ricong Huang,

Peiwen Lai,

Yipeng Qin,

Guanbin Li

[pdf] [supp]

[bibtex]

@InProceedings{Huang_2023_CVPR, author = {Huang, Ricong and Lai, Peiwen and Qin, Yipeng and Li, Guanbin}, title = {Parametric Implicit Face Representation for Audio-Driven Facial Reenactment}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12759-12768} }

Semantic Human Parsing via Scalable Semantic Transfer Over Multiple Label Domains

Jie Yang,

Chaoqun Wang,

Zhen Li,

Junle Wang,

Ruimao Zhang

[pdf] [arXiv]

[bibtex]

@InProceedings{Yang_2023_CVPR, author = {Yang, Jie and Wang, Chaoqun and Li, Zhen and Wang, Junle and Zhang, Ruimao}, title = {Semantic Human Parsing via Scalable Semantic Transfer Over Multiple Label Domains}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {19424-19433} }

Making Vision Transformers Efficient From a Token Sparsification View

Shuning Chang,

Pichao Wang,

Ming Lin,

Fan Wang,

David Junhao Zhang,

Rong Jin,

Mike Zheng Shou

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Chang_2023_CVPR, author = {Chang, Shuning and Wang, Pichao and Lin, Ming and Wang, Fan and Zhang, David Junhao and Jin, Rong and Shou, Mike Zheng}, title = {Making Vision Transformers Efficient From a Token Sparsification View}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6195-6205} }

GEN: Pushing the Limits of Softmax-Based Out-of-Distribution Detection

Xixi Liu,

Yaroslava Lochman,

Christopher Zach

[pdf] [supp]

[bibtex]

@InProceedings{Liu_2023_CVPR, author = {Liu, Xixi and Lochman, Yaroslava and Zach, Christopher}, title = {GEN: Pushing the Limits of Softmax-Based Out-of-Distribution Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {23946-23955} }

RefCLIP: A Universal Teacher for Weakly Supervised Referring Expression Comprehension

Lei Jin,

Gen Luo,

Yiyi Zhou,

Xiaoshuai Sun,

Guannan Jiang,

Annan Shu,

Rongrong Ji

[pdf]

[bibtex]

@InProceedings{Jin_2023_CVPR, author = {Jin, Lei and Luo, Gen and Zhou, Yiyi and Sun, Xiaoshuai and Jiang, Guannan and Shu, Annan and Ji, Rongrong}, title = {RefCLIP: A Universal Teacher for Weakly Supervised Referring Expression Comprehension}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2681-2690} }

VILA: Learning Image Aesthetics From User Comments With Vision-Language Pretraining

Junjie Ke,

Keren Ye,

Jiahui Yu,

Yonghui Wu,

Peyman Milanfar,

Feng Yang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Ke_2023_CVPR, author = {Ke, Junjie and Ye, Keren and Yu, Jiahui and Wu, Yonghui and Milanfar, Peyman and Yang, Feng}, title = {VILA: Learning Image Aesthetics From User Comments With Vision-Language Pretraining}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10041-10051} }

Learnable Skeleton-Aware 3D Point Cloud Sampling

Cheng Wen,

Baosheng Yu,

Dacheng Tao

[pdf] [supp]

[bibtex]

@InProceedings{Wen_2023_CVPR, author = {Wen, Cheng and Yu, Baosheng and Tao, Dacheng}, title = {Learnable Skeleton-Aware 3D Point Cloud Sampling}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {17671-17681} }

Boundary-Enhanced Co-Training for Weakly Supervised Semantic Segmentation

Shenghai Rong,

Bohai Tu,

Zilei Wang,

Junjie Li

[pdf] [supp]

[bibtex]

@InProceedings{Rong_2023_CVPR, author = {Rong, Shenghai and Tu, Bohai and Wang, Zilei and Li, Junjie}, title = {Boundary-Enhanced Co-Training for Weakly Supervised Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {19574-19584} }

Re-IQA: Unsupervised Learning for Image Quality Assessment in the Wild

Avinab Saha,

Sandeep Mishra,

Alan C. Bovik

[pdf] [supp]

[bibtex]

@InProceedings{Saha_2023_CVPR, author = {Saha, Avinab and Mishra, Sandeep and Bovik, Alan C.}, title = {Re-IQA: Unsupervised Learning for Image Quality Assessment in the Wild}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5846-5855} }

Procedure-Aware Pretraining for Instructional Video Understanding

Honglu Zhou,

Roberto Martín-Martín,

Mubbasir Kapadia,

Silvio Savarese,

Juan Carlos Niebles

[pdf] [supp]

[bibtex]

@InProceedings{Zhou_2023_CVPR, author = {Zhou, Honglu and Mart{\'\i}n-Mart{\'\i}n, Roberto and Kapadia, Mubbasir and Savarese, Silvio and Niebles, Juan Carlos}, title = {Procedure-Aware Pretraining for Instructional Video Understanding}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10727-10738} }

Sample-Level Multi-View Graph Clustering

Yuze Tan,

Yixi Liu,

Shudong Huang,

Wentao Feng,

Jiancheng Lv

[pdf]

[bibtex]

@InProceedings{Tan_2023_CVPR, author = {Tan, Yuze and Liu, Yixi and Huang, Shudong and Feng, Wentao and Lv, Jiancheng}, title = {Sample-Level Multi-View Graph Clustering}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {23966-23975} }

Fine-Grained Audible Video Description

Xuyang Shen,

Dong Li,

Jinxing Zhou,

Zhen Qin,

Bowen He,

Xiaodong Han,

Aixuan Li,

Yuchao Dai,

Lingpeng Kong,

Meng Wang,

Yu Qiao,

Yiran Zhong

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Shen_2023_CVPR, author = {Shen, Xuyang and Li, Dong and Zhou, Jinxing and Qin, Zhen and He, Bowen and Han, Xiaodong and Li, Aixuan and Dai, Yuchao and Kong, Lingpeng and Wang, Meng and Qiao, Yu and Zhong, Yiran}, title = {Fine-Grained Audible Video Description}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10585-10596} }

3D Semantic Segmentation in the Wild: Learning Generalized Models for Adverse-Condition Point Clouds

Aoran Xiao,

Jiaxing Huang,

Weihao Xuan,

Ruijie Ren,

Kangcheng Liu,

Dayan Guan,

Abdulmotaleb El Saddik,

Shijian Lu,

Eric P. Xing

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Xiao_2023_CVPR, author = {Xiao, Aoran and Huang, Jiaxing and Xuan, Weihao and Ren, Ruijie and Liu, Kangcheng and Guan, Dayan and El Saddik, Abdulmotaleb and Lu, Shijian and Xing, Eric P.}, title = {3D Semantic Segmentation in the Wild: Learning Generalized Models for Adverse-Condition Point Clouds}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9382-9392} }

Catch Missing Details: Image Reconstruction With Frequency Augmented Variational Autoencoder

Xinmiao Lin,

Yikang Li,

Jenhao Hsiao,

Chiuman Ho,

Yu Kong

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Lin_2023_CVPR, author = {Lin, Xinmiao and Li, Yikang and Hsiao, Jenhao and Ho, Chiuman and Kong, Yu}, title = {Catch Missing Details: Image Reconstruction With Frequency Augmented Variational Autoencoder}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1736-1745} }

RaBit: Parametric Modeling of 3D Biped Cartoon Characters With a Topological-Consistent Dataset

Zhongjin Luo,

Shengcai Cai,

Jinguo Dong,

Ruibo Ming,

Liangdong Qiu,

Xiaohang Zhan,

Xiaoguang Han

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Luo_2023_CVPR, author = {Luo, Zhongjin and Cai, Shengcai and Dong, Jinguo and Ming, Ruibo and Qiu, Liangdong and Zhan, Xiaohang and Han, Xiaoguang}, title = {RaBit: Parametric Modeling of 3D Biped Cartoon Characters With a Topological-Consistent Dataset}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12825-12835} }

Next3D: Generative Neural Texture Rasterization for 3D-Aware Head Avatars

Jingxiang Sun,

Xuan Wang,

Lizhen Wang,

Xiaoyu Li,

Yong Zhang,

Hongwen Zhang,

Yebin Liu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Sun_2023_CVPR, author = {Sun, Jingxiang and Wang, Xuan and Wang, Lizhen and Li, Xiaoyu and Zhang, Yong and Zhang, Hongwen and Liu, Yebin}, title = {Next3D: Generative Neural Texture Rasterization for 3D-Aware Head Avatars}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {20991-21002} }

Uni3D: A Unified Baseline for Multi-Dataset 3D Object Detection

Bo Zhang,

Jiakang Yuan,

Botian Shi,

Tao Chen,

Yikang Li,

Yu Qiao

[pdf] [arXiv]

[bibtex]

@InProceedings{Zhang_2023_CVPR, author = {Zhang, Bo and Yuan, Jiakang and Shi, Botian and Chen, Tao and Li, Yikang and Qiao, Yu}, title = {Uni3D: A Unified Baseline for Multi-Dataset 3D Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9253-9262} }

Linking Garment With Person via Semantically Associated Landmarks for Virtual Try-On

Keyu Yan,

Tingwei Gao,

Hui Zhang,

Chengjun Xie

[pdf] [supp]

[bibtex]

@InProceedings{Yan_2023_CVPR, author = {Yan, Keyu and Gao, Tingwei and Zhang, Hui and Xie, Chengjun}, title = {Linking Garment With Person via Semantically Associated Landmarks for Virtual Try-On}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {17194-17204} }

ACR: Attention Collaboration-Based Regressor for Arbitrary Two-Hand Reconstruction

Zhengdi Yu,

Shaoli Huang,

Chen Fang,

Toby P. Breckon,

Jue Wang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Yu_2023_CVPR, author = {Yu, Zhengdi and Huang, Shaoli and Fang, Chen and Breckon, Toby P. and Wang, Jue}, title = {ACR: Attention Collaboration-Based Regressor for Arbitrary Two-Hand Reconstruction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12955-12964} }

Rotation-Invariant Transformer for Point Cloud Matching

Hao Yu,

Zheng Qin,

Ji Hou,

Mahdi Saleh,

Dongsheng Li,

Benjamin Busam,

Slobodan Ilic

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Yu_2023_CVPR, author = {Yu, Hao and Qin, Zheng and Hou, Ji and Saleh, Mahdi and Li, Dongsheng and Busam, Benjamin and Ilic, Slobodan}, title = {Rotation-Invariant Transformer for Point Cloud Matching}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5384-5393} }

Devil's on the Edges: Selective Quad Attention for Scene Graph Generation

Deunsol Jung,

Sanghyun Kim,

Won Hwa Kim,

Minsu Cho

[pdf] [supp]

[bibtex]

@InProceedings{Jung_2023_CVPR, author = {Jung, Deunsol and Kim, Sanghyun and Kim, Won Hwa and Cho, Minsu}, title = {Devil's on the Edges: Selective Quad Attention for Scene Graph Generation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {18664-18674} }

NIFF: Alleviating Forgetting in Generalized Few-Shot Object Detection via Neural Instance Feature Forging

Karim Guirguis,

Johannes Meier,

George Eskandar,

Matthias Kayser,

Bin Yang,

Jürgen Beyerer

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Guirguis_2023_CVPR, author = {Guirguis, Karim and Meier, Johannes and Eskandar, George and Kayser, Matthias and Yang, Bin and Beyerer, J\"urgen}, title = {NIFF: Alleviating Forgetting in Generalized Few-Shot Object Detection via Neural Instance Feature Forging}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {24193-24202} }

Habitat-Matterport 3D Semantics Dataset

Karmesh Yadav,

Ram Ramrakhya,

Santhosh Kumar Ramakrishnan,

Theo Gervet,

John Turner,

Aaron Gokaslan,

Noah Maestre,

Angel Xuan Chang,

Dhruv Batra,

Manolis Savva,

Alexander William Clegg,

Devendra Singh Chaplot

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Yadav_2023_CVPR, author = {Yadav, Karmesh and Ramrakhya, Ram and Ramakrishnan, Santhosh Kumar and Gervet, Theo and Turner, John and Gokaslan, Aaron and Maestre, Noah and Chang, Angel Xuan and Batra, Dhruv and Savva, Manolis and Clegg, Alexander William and Chaplot, Devendra Singh}, title = {Habitat-Matterport 3D Semantics Dataset}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4927-4936} }

Post-Processing Temporal Action Detection

Sauradip Nag,

Xiatian Zhu,

Yi-Zhe Song,

Tao Xiang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Nag_2023_CVPR, author = {Nag, Sauradip and Zhu, Xiatian and Song, Yi-Zhe and Xiang, Tao}, title = {Post-Processing Temporal Action Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {18837-18845} }

ConZIC: Controllable Zero-Shot Image Captioning by Sampling-Based Polishing

Zequn Zeng,

Hao Zhang,

Ruiying Lu,

Dongsheng Wang,

Bo Chen,

Zhengjue Wang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Zeng_2023_CVPR, author = {Zeng, Zequn and Zhang, Hao and Lu, Ruiying and Wang, Dongsheng and Chen, Bo and Wang, Zhengjue}, title = {ConZIC: Controllable Zero-Shot Image Captioning by Sampling-Based Polishing}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {23465-23476} }

EDGE: Editable Dance Generation From Music

Jonathan Tseng,

Rodrigo Castellon,

Karen Liu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Tseng_2023_CVPR, author = {Tseng, Jonathan and Castellon, Rodrigo and Liu, Karen}, title = {EDGE: Editable Dance Generation From Music}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {448-458} }

Curricular Contrastive Regularization for Physics-Aware Single Image Dehazing

Yu Zheng,

Jiahui Zhan,

Shengfeng He,

Junyu Dong,

Yong Du

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Zheng_2023_CVPR, author = {Zheng, Yu and Zhan, Jiahui and He, Shengfeng and Dong, Junyu and Du, Yong}, title = {Curricular Contrastive Regularization for Physics-Aware Single Image Dehazing}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5785-5794} }

Learning From Noisy Labels With Decoupled Meta Label Purifier

Yuanpeng Tu,

Boshen Zhang,

Yuxi Li,

Liang Liu,

Jian Li,

Yabiao Wang,

Chengjie Wang,

Cai Rong Zhao

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Tu_2023_CVPR, author = {Tu, Yuanpeng and Zhang, Boshen and Li, Yuxi and Liu, Liang and Li, Jian and Wang, Yabiao and Wang, Chengjie and Zhao, Cai Rong}, title = {Learning From Noisy Labels With Decoupled Meta Label Purifier}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {19934-19943} }

Language in a Bottle: Language Model Guided Concept Bottlenecks for Interpretable Image Classification

Yue Yang,

Artemis Panagopoulou,

Shenghao Zhou,

Daniel Jin,

Chris Callison-Burch,

Mark Yatskar

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Yang_2023_CVPR, author = {Yang, Yue and Panagopoulou, Artemis and Zhou, Shenghao and Jin, Daniel and Callison-Burch, Chris and Yatskar, Mark}, title = {Language in a Bottle: Language Model Guided Concept Bottlenecks for Interpretable Image Classification}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {19187-19197} }

Sharpness-Aware Gradient Matching for Domain Generalization

Pengfei Wang,

Zhaoxiang Zhang,

Zhen Lei,

Lei Zhang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Pengfei and Zhang, Zhaoxiang and Lei, Zhen and Zhang, Lei}, title = {Sharpness-Aware Gradient Matching for Domain Generalization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3769-3778} }

ViPLO: Vision Transformer Based Pose-Conditioned Self-Loop Graph for Human-Object Interaction Detection

Jeeseung Park,

Jin-Woo Park,

Jong-Seok Lee

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Park_2023_CVPR, author = {Park, Jeeseung and Park, Jin-Woo and Lee, Jong-Seok}, title = {ViPLO: Vision Transformer Based Pose-Conditioned Self-Loop Graph for Human-Object Interaction Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {17152-17162} }

Improving Table Structure Recognition With Visual-Alignment Sequential Coordinate Modeling

Yongshuai Huang,

Ning Lu,

Dapeng Chen,

Yibo Li,

Zecheng Xie,

Shenggao Zhu,

Liangcai Gao,

Wei Peng

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Huang_2023_CVPR, author = {Huang, Yongshuai and Lu, Ning and Chen, Dapeng and Li, Yibo and Xie, Zecheng and Zhu, Shenggao and Gao, Liangcai and Peng, Wei}, title = {Improving Table Structure Recognition With Visual-Alignment Sequential Coordinate Modeling}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11134-11143} }

MSINet: Twins Contrastive Search of Multi-Scale Interaction for Object ReID

Jianyang Gu,

Kai Wang,

Hao Luo,

Chen Chen,

Wei Jiang,

Yuqiang Fang,

Shanghang Zhang,

Yang You,

Jian Zhao

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Gu_2023_CVPR, author = {Gu, Jianyang and Wang, Kai and Luo, Hao and Chen, Chen and Jiang, Wei and Fang, Yuqiang and Zhang, Shanghang and You, Yang and Zhao, Jian}, title = {MSINet: Twins Contrastive Search of Multi-Scale Interaction for Object ReID}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {19243-19253} }

WIRE: Wavelet Implicit Neural Representations

Vishwanath Saragadam,

Daniel LeJeune,

Jasper Tan,

Guha Balakrishnan,

Ashok Veeraraghavan,

Richard G. Baraniuk

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Saragadam_2023_CVPR, author = {Saragadam, Vishwanath and LeJeune, Daniel and Tan, Jasper and Balakrishnan, Guha and Veeraraghavan, Ashok and Baraniuk, Richard G.}, title = {WIRE: Wavelet Implicit Neural Representations}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {18507-18516} }

Bi-Directional Feature Fusion Generative Adversarial Network for Ultra-High Resolution Pathological Image Virtual Re-Staining

Kexin Sun,

Zhineng Chen,

Gongwei Wang,

Jun Liu,

Xiongjun Ye,

Yu-Gang Jiang

[pdf] [supp]

[bibtex]

@InProceedings{Sun_2023_CVPR, author = {Sun, Kexin and Chen, Zhineng and Wang, Gongwei and Liu, Jun and Ye, Xiongjun and Jiang, Yu-Gang}, title = {Bi-Directional Feature Fusion Generative Adversarial Network for Ultra-High Resolution Pathological Image Virtual Re-Staining}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3904-3913} }

HumanGen: Generating Human Radiance Fields With Explicit Priors

Suyi Jiang,

Haoran Jiang,

Ziyu Wang,

Haimin Luo,

Wenzheng Chen,

Lan Xu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Jiang_2023_CVPR, author = {Jiang, Suyi and Jiang, Haoran and Wang, Ziyu and Luo, Haimin and Chen, Wenzheng and Xu, Lan}, title = {HumanGen: Generating Human Radiance Fields With Explicit Priors}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12543-12554} }

Bringing Inputs to Shared Domains for 3D Interacting Hands Recovery in the Wild

Gyeongsik Moon

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Moon_2023_CVPR, author = {Moon, Gyeongsik}, title = {Bringing Inputs to Shared Domains for 3D Interacting Hands Recovery in the Wild}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {17028-17037} }

Local Connectivity-Based Density Estimation for Face Clustering

Junho Shin,

Hyo-Jun Lee,

Hyunseop Kim,

Jong-Hyeon Baek,

Daehyun Kim,

Yeong Jun Koh

[pdf] [supp]

[bibtex]

@InProceedings{Shin_2023_CVPR, author = {Shin, Junho and Lee, Hyo-Jun and Kim, Hyunseop and Baek, Jong-Hyeon and Kim, Daehyun and Koh, Yeong Jun}, title = {Local Connectivity-Based Density Estimation for Face Clustering}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13621-13629} }

Adaptive Zone-Aware Hierarchical Planner for Vision-Language Navigation

Chen Gao,

Xingyu Peng,

Mi Yan,

He Wang,

Lirong Yang,

Haibing Ren,

Hongsheng Li,

Si Liu

[pdf]

[bibtex]

@InProceedings{Gao_2023_CVPR, author = {Gao, Chen and Peng, Xingyu and Yan, Mi and Wang, He and Yang, Lirong and Ren, Haibing and Li, Hongsheng and Liu, Si}, title = {Adaptive Zone-Aware Hierarchical Planner for Vision-Language Navigation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14911-14920} }

Towards Practical Plug-and-Play Diffusion Models

Hyojun Go,

Yunsung Lee,

Jin-Young Kim,

Seunghyun Lee,

Myeongho Jeong,

Hyun Seung Lee,

Seungtaek Choi

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Go_2023_CVPR, author = {Go, Hyojun and Lee, Yunsung and Kim, Jin-Young and Lee, Seunghyun and Jeong, Myeongho and Lee, Hyun Seung and Choi, Seungtaek}, title = {Towards Practical Plug-and-Play Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1962-1971} }

Memory-Friendly Scalable Super-Resolution via Rewinding Lottery Ticket Hypothesis

Jin Lin,

Xiaotong Luo,

Ming Hong,

Yanyun Qu,

Yuan Xie,

Zongze Wu

[pdf] [supp]

[bibtex]

@InProceedings{Lin_2023_CVPR, author = {Lin, Jin and Luo, Xiaotong and Hong, Ming and Qu, Yanyun and Xie, Yuan and Wu, Zongze}, title = {Memory-Friendly Scalable Super-Resolution via Rewinding Lottery Ticket Hypothesis}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14398-14407} }

YOLOv7: Trainable Bag-of-Freebies Sets New State-of-the-Art for Real-Time Object Detectors

Chien-Yao Wang,

Alexey Bochkovskiy,

Hong-Yuan Mark Liao

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Chien-Yao and Bochkovskiy, Alexey and Liao, Hong-Yuan Mark}, title = {YOLOv7: Trainable Bag-of-Freebies Sets New State-of-the-Art for Real-Time Object Detectors}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7464-7475} }

Deep Deterministic Uncertainty: A New Simple Baseline

Jishnu Mukhoti,

Andreas Kirsch,

Joost van Amersfoort,

Philip H.S. Torr,

Yarin Gal

[pdf] [supp]

[bibtex]

@InProceedings{Mukhoti_2023_CVPR, author = {Mukhoti, Jishnu and Kirsch, Andreas and van Amersfoort, Joost and Torr, Philip H.S. and Gal, Yarin}, title = {Deep Deterministic Uncertainty: A New Simple Baseline}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {24384-24394} }

PartDistillation: Learning Parts From Instance Segmentation

Jang Hyun Cho,

Philipp Krähenbühl,

Vignesh Ramanathan

[pdf] [supp]

[bibtex]

@InProceedings{Cho_2023_CVPR, author = {Cho, Jang Hyun and Kr\"ahenb\"uhl, Philipp and Ramanathan, Vignesh}, title = {PartDistillation: Learning Parts From Instance Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7152-7161} }

Boosting Video Object Segmentation via Space-Time Correspondence Learning

Yurong Zhang,

Liulei Li,

Wenguan Wang,

Rong Xie,

Li Song,

Wenjun Zhang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Zhang_2023_CVPR, author = {Zhang, Yurong and Li, Liulei and Wang, Wenguan and Xie, Rong and Song, Li and Zhang, Wenjun}, title = {Boosting Video Object Segmentation via Space-Time Correspondence Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2246-2256} }

Towards Realistic Long-Tailed Semi-Supervised Learning: Consistency Is All You Need

Tong Wei,

Kai Gan

[pdf] [supp]

[bibtex]

@InProceedings{Wei_2023_CVPR, author = {Wei, Tong and Gan, Kai}, title = {Towards Realistic Long-Tailed Semi-Supervised Learning: Consistency Is All You Need}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3469-3478} }

GAPartNet: Cross-Category Domain-Generalizable Object Perception and Manipulation via Generalizable and Actionable Parts

Haoran Geng,

Helin Xu,

Chengyang Zhao,

Chao Xu,

Li Yi,

Siyuan Huang,

He Wang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Geng_2023_CVPR, author = {Geng, Haoran and Xu, Helin and Zhao, Chengyang and Xu, Chao and Yi, Li and Huang, Siyuan and Wang, He}, title = {GAPartNet: Cross-Category Domain-Generalizable Object Perception and Manipulation via Generalizable and Actionable Parts}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7081-7091} }

NeRDi: Single-View NeRF Synthesis With Language-Guided Diffusion As General Image Priors

Congyue Deng,

Chiyu “Max” Jiang,

Charles R. Qi,

Xinchen Yan,

Yin Zhou,

Leonidas Guibas,

Dragomir Anguelov

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Deng_2023_CVPR, author = {Deng, Congyue and Jiang, Chiyu {\textquotedblleft}Max{\textquotedblright} and Qi, Charles R. and Yan, Xinchen and Zhou, Yin and Guibas, Leonidas and Anguelov, Dragomir}, title = {NeRDi: Single-View NeRF Synthesis With Language-Guided Diffusion As General Image Priors}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {20637-20647} }

Therbligs in Action: Video Understanding Through Motion Primitives

Eadom Dessalene,

Michael Maynord,

Cornelia Fermüller,

Yiannis Aloimonos

[pdf]

[bibtex]

@InProceedings{Dessalene_2023_CVPR, author = {Dessalene, Eadom and Maynord, Michael and Ferm\"uller, Cornelia and Aloimonos, Yiannis}, title = {Therbligs in Action: Video Understanding Through Motion Primitives}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10618-10626} }

InstantAvatar: Learning Avatars From Monocular Video in 60 Seconds

Tianjian Jiang,

Xu Chen,

Jie Song,

Otmar Hilliges

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Jiang_2023_CVPR, author = {Jiang, Tianjian and Chen, Xu and Song, Jie and Hilliges, Otmar}, title = {InstantAvatar: Learning Avatars From Monocular Video in 60 Seconds}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16922-16932} }

You Only Segment Once: Towards Real-Time Panoptic Segmentation

Jie Hu,

Linyan Huang,

Tianhe Ren,

Shengchuan Zhang,

Rongrong Ji,

Liujuan Cao

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Hu_2023_CVPR, author = {Hu, Jie and Huang, Linyan and Ren, Tianhe and Zhang, Shengchuan and Ji, Rongrong and Cao, Liujuan}, title = {You Only Segment Once: Towards Real-Time Panoptic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {17819-17829} }

Robust Single Image Reflection Removal Against Adversarial Attacks

Zhenbo Song,

Zhenyuan Zhang,

Kaihao Zhang,

Wenhan Luo,

Zhaoxin Fan,

Wenqi Ren,

Jianfeng Lu

[pdf]

[bibtex]

@InProceedings{Song_2023_CVPR, author = {Song, Zhenbo and Zhang, Zhenyuan and Zhang, Kaihao and Luo, Wenhan and Fan, Zhaoxin and Ren, Wenqi and Lu, Jianfeng}, title = {Robust Single Image Reflection Removal Against Adversarial Attacks}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {24688-24698} }

OmniObject3D: Large-Vocabulary 3D Object Dataset for Realistic Perception, Reconstruction and Generation

Tong Wu,

Jiarui Zhang,

Xiao Fu,

Yuxin Wang,

Jiawei Ren,

Liang Pan,

Wayne Wu,

Lei Yang,

Jiaqi Wang,

Chen Qian,

Dahua Lin,

Ziwei Liu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Wu_2023_CVPR, author = {Wu, Tong and Zhang, Jiarui and Fu, Xiao and Wang, Yuxin and Ren, Jiawei and Pan, Liang and Wu, Wayne and Yang, Lei and Wang, Jiaqi and Qian, Chen and Lin, Dahua and Liu, Ziwei}, title = {OmniObject3D: Large-Vocabulary 3D Object Dataset for Realistic Perception, Reconstruction and Generation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {803-814} }

PartMix: Regularization Strategy To Learn Part Discovery for Visible-Infrared Person Re-Identification

Minsu Kim,

Seungryong Kim,

Jungin Park,

Seongheon Park,

Kwanghoon Sohn

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Kim_2023_CVPR, author = {Kim, Minsu and Kim, Seungryong and Park, Jungin and Park, Seongheon and Sohn, Kwanghoon}, title = {PartMix: Regularization Strategy To Learn Part Discovery for Visible-Infrared Person Re-Identification}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {18621-18632} }

Uncovering the Disentanglement Capability in Text-to-Image Diffusion Models

Qiucheng Wu,

Yujian Liu,

Handong Zhao,

Ajinkya Kale,

Trung Bui,

Tong Yu,

Zhe Lin,

Yang Zhang,

Shiyu Chang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Wu_2023_CVPR, author = {Wu, Qiucheng and Liu, Yujian and Zhao, Handong and Kale, Ajinkya and Bui, Trung and Yu, Tong and Lin, Zhe and Zhang, Yang and Chang, Shiyu}, title = {Uncovering the Disentanglement Capability in Text-to-Image Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1900-1910} }

Feature Representation Learning With Adaptive Displacement Generation and Transformer Fusion for Micro-Expression Recognition

Zhijun Zhai,

Jianhui Zhao,

Chengjiang Long,

Wenju Xu,

Shuangjiang He,

Huijuan Zhao

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Zhai_2023_CVPR, author = {Zhai, Zhijun and Zhao, Jianhui and Long, Chengjiang and Xu, Wenju and He, Shuangjiang and Zhao, Huijuan}, title = {Feature Representation Learning With Adaptive Displacement Generation and Transformer Fusion for Micro-Expression Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {22086-22095} }

ViewNet: A Novel Projection-Based Backbone With View Pooling for Few-Shot Point Cloud Classification

Jiajing Chen,

Minmin Yang,

Senem Velipasalar

[pdf]

[bibtex]

@InProceedings{Chen_2023_CVPR, author = {Chen, Jiajing and Yang, Minmin and Velipasalar, Senem}, title = {ViewNet: A Novel Projection-Based Backbone With View Pooling for Few-Shot Point Cloud Classification}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {17652-17660} }

EXIF As Language: Learning Cross-Modal Associations Between Images and Camera Metadata

Chenhao Zheng,

Ayush Shrivastava,

Andrew Owens

[pdf] [arXiv]

[bibtex]

@InProceedings{Zheng_2023_CVPR, author = {Zheng, Chenhao and Shrivastava, Ayush and Owens, Andrew}, title = {EXIF As Language: Learning Cross-Modal Associations Between Images and Camera Metadata}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6945-6956} }

ANetQA: A Large-Scale Benchmark for Fine-Grained Compositional Reasoning Over Untrimmed Videos

Zhou Yu,

Lixiang Zheng,

Zhou Zhao,

Fei Wu,

Jianping Fan,

Kui Ren,

Jun Yu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Yu_2023_CVPR, author = {Yu, Zhou and Zheng, Lixiang and Zhao, Zhou and Wu, Fei and Fan, Jianping and Ren, Kui and Yu, Jun}, title = {ANetQA: A Large-Scale Benchmark for Fine-Grained Compositional Reasoning Over Untrimmed Videos}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {23191-23200} }

SadTalker: Learning Realistic 3D Motion Coefficients for Stylized Audio-Driven Single Image Talking Face Animation

Wenxuan Zhang,

Xiaodong Cun,

Xuan Wang,

Yong Zhang,

Xi Shen,

Yu Guo,

Ying Shan,

Fei Wang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Zhang_2023_CVPR, author = {Zhang, Wenxuan and Cun, Xiaodong and Wang, Xuan and Zhang, Yong and Shen, Xi and Guo, Yu and Shan, Ying and Wang, Fei}, title = {SadTalker: Learning Realistic 3D Motion Coefficients for Stylized Audio-Driven Single Image Talking Face Animation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8652-8661} }

HAAV: Hierarchical Aggregation of Augmented Views for Image Captioning

Chia-Wen Kuo,

Zsolt Kira

[pdf] [supp]

[bibtex]

@InProceedings{Kuo_2023_CVPR, author = {Kuo, Chia-Wen and Kira, Zsolt}, title = {HAAV: Hierarchical Aggregation of Augmented Views for Image Captioning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11039-11049} }

CLAMP: Prompt-Based Contrastive Learning for Connecting Language and Animal Pose

Xu Zhang,

Wen Wang,

Zhe Chen,

Yufei Xu,

Jing Zhang,

Dacheng Tao

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Zhang_2023_CVPR, author = {Zhang, Xu and Wang, Wen and Chen, Zhe and Xu, Yufei and Zhang, Jing and Tao, Dacheng}, title = {CLAMP: Prompt-Based Contrastive Learning for Connecting Language and Animal Pose}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {23272-23281} }

Standing Between Past and Future: Spatio-Temporal Modeling for Multi-Camera 3D Multi-Object Tracking

Ziqi Pang,

Jie Li,

Pavel Tokmakov,

Dian Chen,

Sergey Zagoruyko,

Yu-Xiong Wang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Pang_2023_CVPR, author = {Pang, Ziqi and Li, Jie and Tokmakov, Pavel and Chen, Dian and Zagoruyko, Sergey and Wang, Yu-Xiong}, title = {Standing Between Past and Future: Spatio-Temporal Modeling for Multi-Camera 3D Multi-Object Tracking}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {17928-17938} }

Learning Sample Relationship for Exposure Correction

Jie Huang,

Feng Zhao,

Man Zhou,

Jie Xiao,

Naishan Zheng,

Kaiwen Zheng,

Zhiwei Xiong

[pdf]

[bibtex]

@InProceedings{Huang_2023_CVPR, author = {Huang, Jie and Zhao, Feng and Zhou, Man and Xiao, Jie and Zheng, Naishan and Zheng, Kaiwen and Xiong, Zhiwei}, title = {Learning Sample Relationship for Exposure Correction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9904-9913} }

TRACE: 5D Temporal Regression of Avatars With Dynamic Cameras in 3D Environments

Yu Sun,

Qian Bao,

Wu Liu,

Tao Mei,

Michael J. Black

[pdf] [supp]

[bibtex]

@InProceedings{Sun_2023_CVPR, author = {Sun, Yu and Bao, Qian and Liu, Wu and Mei, Tao and Black, Michael J.}, title = {TRACE: 5D Temporal Regression of Avatars With Dynamic Cameras in 3D Environments}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8856-8866} }

TTA-COPE: Test-Time Adaptation for Category-Level Object Pose Estimation

Taeyeop Lee,

Jonathan Tremblay,

Valts Blukis,

Bowen Wen,

Byeong-Uk Lee,

Inkyu Shin,

Stan Birchfield,

In So Kweon,

Kuk-Jin Yoon

[pdf] [supp]

[bibtex]

@InProceedings{Lee_2023_CVPR, author = {Lee, Taeyeop and Tremblay, Jonathan and Blukis, Valts and Wen, Bowen and Lee, Byeong-Uk and Shin, Inkyu and Birchfield, Stan and Kweon, In So and Yoon, Kuk-Jin}, title = {TTA-COPE: Test-Time Adaptation for Category-Level Object Pose Estimation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {21285-21295} }

TrojDiff: Trojan Attacks on Diffusion Models With Diverse Targets

Weixin Chen,

Dawn Song,

Bo Li

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Chen_2023_CVPR, author = {Chen, Weixin and Song, Dawn and Li, Bo}, title = {TrojDiff: Trojan Attacks on Diffusion Models With Diverse Targets}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4035-4044} }

End-to-End 3D Dense Captioning With Vote2Cap-DETR

Sijin Chen,

Hongyuan Zhu,

Xin Chen,

Yinjie Lei,

Gang Yu,

Tao Chen

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Chen_2023_CVPR, author = {Chen, Sijin and Zhu, Hongyuan and Chen, Xin and Lei, Yinjie and Yu, Gang and Chen, Tao}, title = {End-to-End 3D Dense Captioning With Vote2Cap-DETR}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11124-11133} }

Mitigating Task Interference in Multi-Task Learning via Explicit Task Routing With Non-Learnable Primitives

Chuntao Ding,

Zhichao Lu,

Shangguang Wang,

Ran Cheng,

Vishnu Naresh Boddeti

[pdf] [supp]

[bibtex]

@InProceedings{Ding_2023_CVPR, author = {Ding, Chuntao and Lu, Zhichao and Wang, Shangguang and Cheng, Ran and Boddeti, Vishnu Naresh}, title = {Mitigating Task Interference in Multi-Task Learning via Explicit Task Routing With Non-Learnable Primitives}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7756-7765} }

Learned Two-Plane Perspective Prior Based Image Resampling for Efficient Object Detection

Anurag Ghosh,

N. Dinesh Reddy,

Christoph Mertz,

Srinivasa G. Narasimhan

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Ghosh_2023_CVPR, author = {Ghosh, Anurag and Reddy, N. Dinesh and Mertz, Christoph and Narasimhan, Srinivasa G.}, title = {Learned Two-Plane Perspective Prior Based Image Resampling for Efficient Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13364-13373} }

Tell Me What Happened: Unifying Text-Guided Video Completion via Multimodal Masked Video Generation

Tsu-Jui Fu,

Licheng Yu,

Ning Zhang,

Cheng-Yang Fu,

Jong-Chyi Su,

William Yang Wang,

Sean Bell

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Fu_2023_CVPR, author = {Fu, Tsu-Jui and Yu, Licheng and Zhang, Ning and Fu, Cheng-Yang and Su, Jong-Chyi and Wang, William Yang and Bell, Sean}, title = {Tell Me What Happened: Unifying Text-Guided Video Completion via Multimodal Masked Video Generation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10681-10692} }

Tracking Through Containers and Occluders in the Wild

Basile Van Hoorick,

Pavel Tokmakov,

Simon Stent,

Jie Li,

Carl Vondrick

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Van_Hoorick_2023_CVPR, author = {Van Hoorick, Basile and Tokmakov, Pavel and Stent, Simon and Li, Jie and Vondrick, Carl}, title = {Tracking Through Containers and Occluders in the Wild}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13802-13812} }

Geometry and Uncertainty-Aware 3D Point Cloud Class-Incremental Semantic Segmentation

Yuwei Yang,

Munawar Hayat,

Zhao Jin,

Chao Ren,

Yinjie Lei

[pdf] [supp]

[bibtex]

@InProceedings{Yang_2023_CVPR, author = {Yang, Yuwei and Hayat, Munawar and Jin, Zhao and Ren, Chao and Lei, Yinjie}, title = {Geometry and Uncertainty-Aware 3D Point Cloud Class-Incremental Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {21759-21768} }

Neural Kernel Surface Reconstruction

Jiahui Huang,

Zan Gojcic,

Matan Atzmon,

Or Litany,

Sanja Fidler,

Francis Williams

[pdf] [supp]

[bibtex]

@InProceedings{Huang_2023_CVPR, author = {Huang, Jiahui and Gojcic, Zan and Atzmon, Matan and Litany, Or and Fidler, Sanja and Williams, Francis}, title = {Neural Kernel Surface Reconstruction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4369-4379} }

Cooperation or Competition: Avoiding Player Domination for Multi-Target Robustness via Adaptive Budgets

Yimu Wang,

Dinghuai Zhang,

Yihan Wu,

Heng Huang,

Hongyang Zhang

[pdf] [supp]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Yimu and Zhang, Dinghuai and Wu, Yihan and Huang, Heng and Zhang, Hongyang}, title = {Cooperation or Competition: Avoiding Player Domination for Multi-Target Robustness via Adaptive Budgets}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {20564-20574} }

Decompose, Adjust, Compose: Effective Normalization by Playing With Frequency for Domain Generalization

Sangrok Lee,

Jongseong Bae,

Ha Young Kim

[pdf] [arXiv]

[bibtex]

@InProceedings{Lee_2023_CVPR, author = {Lee, Sangrok and Bae, Jongseong and Kim, Ha Young}, title = {Decompose, Adjust, Compose: Effective Normalization by Playing With Frequency for Domain Generalization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11776-11785} }

Multilateral Semantic Relations Modeling for Image Text Retrieval

Zheng Wang,

Zhenwei Gao,

Kangshuai Guo,

Yang Yang,

Xiaoming Wang,

Heng Tao Shen

[pdf]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Zheng and Gao, Zhenwei and Guo, Kangshuai and Yang, Yang and Wang, Xiaoming and Shen, Heng Tao}, title = {Multilateral Semantic Relations Modeling for Image Text Retrieval}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2830-2839} }

Optimization-Inspired Cross-Attention Transformer for Compressive Sensing

Jiechong Song,

Chong Mou,

Shiqi Wang,

Siwei Ma,

Jian Zhang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Song_2023_CVPR, author = {Song, Jiechong and Mou, Chong and Wang, Shiqi and Ma, Siwei and Zhang, Jian}, title = {Optimization-Inspired Cross-Attention Transformer for Compressive Sensing}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6174-6184} }

Novel Class Discovery for 3D Point Cloud Semantic Segmentation

Luigi Riz,

Cristiano Saltori,

Elisa Ricci,

Fabio Poiesi

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Riz_2023_CVPR, author = {Riz, Luigi and Saltori, Cristiano and Ricci, Elisa and Poiesi, Fabio}, title = {Novel Class Discovery for 3D Point Cloud Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9393-9402} }

CAT: LoCalization and IdentificAtion Cascade Detection Transformer for Open-World Object Detection

Shuailei Ma,

Yuefeng Wang,

Ying Wei,

Jiaqi Fan,

Thomas H. Li,

Hongli Liu,

Fanbing Lv

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Ma_2023_CVPR, author = {Ma, Shuailei and Wang, Yuefeng and Wei, Ying and Fan, Jiaqi and Li, Thomas H. and Liu, Hongli and Lv, Fanbing}, title = {CAT: LoCalization and IdentificAtion Cascade Detection Transformer for Open-World Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {19681-19690} }

TruFor: Leveraging All-Round Clues for Trustworthy Image Forgery Detection and Localization

Fabrizio Guillaro,

Davide Cozzolino,

Avneesh Sud,

Nicholas Dufour,

Luisa Verdoliva

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Guillaro_2023_CVPR, author = {Guillaro, Fabrizio and Cozzolino, Davide and Sud, Avneesh and Dufour, Nicholas and Verdoliva, Luisa}, title = {TruFor: Leveraging All-Round Clues for Trustworthy Image Forgery Detection and Localization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {20606-20615} }

LANA: A Language-Capable Navigator for Instruction Following and Generation

Xiaohan Wang,

Wenguan Wang,

Jiayi Shao,

Yi Yang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Xiaohan and Wang, Wenguan and Shao, Jiayi and Yang, Yi}, title = {LANA: A Language-Capable Navigator for Instruction Following and Generation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {19048-19058} }

Learning 3D-Aware Image Synthesis With Unknown Pose Distribution

Zifan Shi,

Yujun Shen,

Yinghao Xu,

Sida Peng,

Yiyi Liao,

Sheng Guo,

Qifeng Chen,

Dit-Yan Yeung

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Shi_2023_CVPR, author = {Shi, Zifan and Shen, Yujun and Xu, Yinghao and Peng, Sida and Liao, Yiyi and Guo, Sheng and Chen, Qifeng and Yeung, Dit-Yan}, title = {Learning 3D-Aware Image Synthesis With Unknown Pose Distribution}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13062-13071} }

Normalizing Flow Based Feature Synthesis for Outlier-Aware Object Detection

Nishant Kumar,

Siniša Šegvić,

Abouzar Eslami,

Stefan Gumhold

[pdf] [supp]

[bibtex]

@InProceedings{Kumar_2023_CVPR, author = {Kumar, Nishant and \v{S}egvi\'c, Sini\v{s}a and Eslami, Abouzar and Gumhold, Stefan}, title = {Normalizing Flow Based Feature Synthesis for Outlier-Aware Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5156-5165} }

DivClust: Controlling Diversity in Deep Clustering

Ioannis Maniadis Metaxas,

Georgios Tzimiropoulos,

Ioannis Patras

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Metaxas_2023_CVPR, author = {Metaxas, Ioannis Maniadis and Tzimiropoulos, Georgios and Patras, Ioannis}, title = {DivClust: Controlling Diversity in Deep Clustering}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3418-3428} }

CAPE: Camera View Position Embedding for Multi-View 3D Object Detection

Kaixin Xiong,

Shi Gong,

Xiaoqing Ye,

Xiao Tan,

Ji Wan,

Errui Ding,

Jingdong Wang,

Xiang Bai

[pdf] [arXiv]

[bibtex]

@InProceedings{Xiong_2023_CVPR, author = {Xiong, Kaixin and Gong, Shi and Ye, Xiaoqing and Tan, Xiao and Wan, Ji and Ding, Errui and Wang, Jingdong and Bai, Xiang}, title = {CAPE: Camera View Position Embedding for Multi-View 3D Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {21570-21579} }

Train-Once-for-All Personalization

Hong-You Chen,

Yandong Li,

Yin Cui,

Mingda Zhang,

Wei-Lun Chao,

Li Zhang

[pdf] [supp]

[bibtex]

@InProceedings{Chen_2023_CVPR, author = {Chen, Hong-You and Li, Yandong and Cui, Yin and Zhang, Mingda and Chao, Wei-Lun and Zhang, Li}, title = {Train-Once-for-All Personalization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11818-11827} }

Bi-Directional Distribution Alignment for Transductive Zero-Shot Learning

Zhicai Wang,

Yanbin Hao,

Tingting Mu,

Ouxiang Li,

Shuo Wang,

Xiangnan He

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Zhicai and Hao, Yanbin and Mu, Tingting and Li, Ouxiang and Wang, Shuo and He, Xiangnan}, title = {Bi-Directional Distribution Alignment for Transductive Zero-Shot Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {19893-19902} }

FlexNeRF: Photorealistic Free-Viewpoint Rendering of Moving Humans From Sparse Views

Vinoj Jayasundara,

Amit Agrawal,

Nicolas Heron,

Abhinav Shrivastava,

Larry S. Davis

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Jayasundara_2023_CVPR, author = {Jayasundara, Vinoj and Agrawal, Amit and Heron, Nicolas and Shrivastava, Abhinav and Davis, Larry S.}, title = {FlexNeRF: Photorealistic Free-Viewpoint Rendering of Moving Humans From Sparse Views}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {21118-21127} }

DIFu: Depth-Guided Implicit Function for Clothed Human Reconstruction

Dae-Young Song,

HeeKyung Lee,

Jeongil Seo,

Donghyeon Cho

[pdf] [supp]

[bibtex]

@InProceedings{Song_2023_CVPR, author = {Song, Dae-Young and Lee, HeeKyung and Seo, Jeongil and Cho, Donghyeon}, title = {DIFu: Depth-Guided Implicit Function for Clothed Human Reconstruction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8738-8747} }

Towards Better Gradient Consistency for Neural Signed Distance Functions via Level Set Alignment

Baorui Ma,

Junsheng Zhou,

Yu-Shen Liu,

Zhizhong Han

[pdf] [supp]

[bibtex]

@InProceedings{Ma_2023_CVPR, author = {Ma, Baorui and Zhou, Junsheng and Liu, Yu-Shen and Han, Zhizhong}, title = {Towards Better Gradient Consistency for Neural Signed Distance Functions via Level Set Alignment}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {17724-17734} }

Zero-Shot Everything Sketch-Based Image Retrieval, and in Explainable Style

Fengyin Lin,

Mingkang Li,

Da Li,

Timothy Hospedales,

Yi-Zhe Song,

Yonggang Qi

[pdf] [arXiv]

[bibtex]

@InProceedings{Lin_2023_CVPR, author = {Lin, Fengyin and Li, Mingkang and Li, Da and Hospedales, Timothy and Song, Yi-Zhe and Qi, Yonggang}, title = {Zero-Shot Everything Sketch-Based Image Retrieval, and in Explainable Style}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {23349-23358} }

Graph Representation for Order-Aware Visual Transformation

Yue Qiu,

Yanjun Sun,

Fumiya Matsuzawa,

Kenji Iwata,

Hirokatsu Kataoka

[pdf] [supp]

[bibtex]

@InProceedings{Qiu_2023_CVPR, author = {Qiu, Yue and Sun, Yanjun and Matsuzawa, Fumiya and Iwata, Kenji and Kataoka, Hirokatsu}, title = {Graph Representation for Order-Aware Visual Transformation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {22793-22802} }

StarCraftImage: A Dataset for Prototyping Spatial Reasoning Methods for Multi-Agent Environments

Sean Kulinski,

Nicholas R. Waytowich,

James Z. Hare,

David I. Inouye

[pdf] [supp]

[bibtex]

@InProceedings{Kulinski_2023_CVPR, author = {Kulinski, Sean and Waytowich, Nicholas R. and Hare, James Z. and Inouye, David I.}, title = {StarCraftImage: A Dataset for Prototyping Spatial Reasoning Methods for Multi-Agent Environments}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {22004-22013} }

Quality-Aware Pre-Trained Models for Blind Image Quality Assessment

Kai Zhao,

Kun Yuan,

Ming Sun,

Mading Li,

Xing Wen

[pdf] [arXiv]

[bibtex]

@InProceedings{Zhao_2023_CVPR, author = {Zhao, Kai and Yuan, Kun and Sun, Ming and Li, Mading and Wen, Xing}, title = {Quality-Aware Pre-Trained Models for Blind Image Quality Assessment}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {22302-22313} }

Topology-Guided Multi-Class Cell Context Generation for Digital Pathology

Shahira Abousamra,

Rajarsi Gupta,

Tahsin Kurc,

Dimitris Samaras,

Joel Saltz,

Chao Chen

[pdf] [arXiv]

[bibtex]

@InProceedings{Abousamra_2023_CVPR, author = {Abousamra, Shahira and Gupta, Rajarsi and Kurc, Tahsin and Samaras, Dimitris and Saltz, Joel and Chen, Chao}, title = {Topology-Guided Multi-Class Cell Context Generation for Digital Pathology}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3323-3333} }

Bi-LRFusion: Bi-Directional LiDAR-Radar Fusion for 3D Dynamic Object Detection

Yingjie Wang,

Jiajun Deng,

Yao Li,

Jinshui Hu,

Cong Liu,

Yu Zhang,

Jianmin Ji,

Wanli Ouyang,

Yanyong Zhang

[pdf] [supp]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Yingjie and Deng, Jiajun and Li, Yao and Hu, Jinshui and Liu, Cong and Zhang, Yu and Ji, Jianmin and Ouyang, Wanli and Zhang, Yanyong}, title = {Bi-LRFusion: Bi-Directional LiDAR-Radar Fusion for 3D Dynamic Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13394-13403} }

Adaptive Graph Convolutional Subspace Clustering

Lai Wei,

Zhengwei Chen,

Jun Yin,

Changming Zhu,

Rigui Zhou,

Jin Liu

[pdf] [arXiv]

[bibtex]

@InProceedings{Wei_2023_CVPR, author = {Wei, Lai and Chen, Zhengwei and Yin, Jun and Zhu, Changming and Zhou, Rigui and Liu, Jin}, title = {Adaptive Graph Convolutional Subspace Clustering}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6262-6271} }

LOCATE: Localize and Transfer Object Parts for Weakly Supervised Affordance Grounding

Gen Li,

Varun Jampani,

Deqing Sun,

Laura Sevilla-Lara

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Li_2023_CVPR, author = {Li, Gen and Jampani, Varun and Sun, Deqing and Sevilla-Lara, Laura}, title = {LOCATE: Localize and Transfer Object Parts for Weakly Supervised Affordance Grounding}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10922-10931} }

Learning Steerable Function for Efficient Image Resampling

Jiacheng Li,

Chang Chen,

Wei Huang,

Zhiqiang Lang,

Fenglong Song,

Youliang Yan,

Zhiwei Xiong

[pdf] [supp]

[bibtex]

@InProceedings{Li_2023_CVPR, author = {Li, Jiacheng and Chen, Chang and Huang, Wei and Lang, Zhiqiang and Song, Fenglong and Yan, Youliang and Xiong, Zhiwei}, title = {Learning Steerable Function for Efficient Image Resampling}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5866-5875} }

TokenHPE: Learning Orientation Tokens for Efficient Head Pose Estimation via Transformers

Cheng Zhang,

Hai Liu,

Yongjian Deng,

Bochen Xie,

Youfu Li

[pdf] [supp]

[bibtex]

@InProceedings{Zhang_2023_CVPR, author = {Zhang, Cheng and Liu, Hai and Deng, Yongjian and Xie, Bochen and Li, Youfu}, title = {TokenHPE: Learning Orientation Tokens for Efficient Head Pose Estimation via Transformers}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8897-8906} }

BioNet: A Biologically-Inspired Network for Face Recognition

Pengyu Li

[pdf] [supp]

[bibtex]

@InProceedings{Li_2023_CVPR, author = {Li, Pengyu}, title = {BioNet: A Biologically-Inspired Network for Face Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10344-10354} }

Scaling Up GANs for Text-to-Image Synthesis

Minguk Kang,

Jun-Yan Zhu,

Richard Zhang,

Jaesik Park,

Eli Shechtman,

Sylvain Paris,

Taesung Park

[pdf] [arXiv]

[bibtex]

@InProceedings{Kang_2023_CVPR, author = {Kang, Minguk and Zhu, Jun-Yan and Zhang, Richard and Park, Jaesik and Shechtman, Eli and Paris, Sylvain and Park, Taesung}, title = {Scaling Up GANs for Text-to-Image Synthesis}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10124-10134} }

DepGraph: Towards Any Structural Pruning

Gongfan Fang,

Xinyin Ma,

Mingli Song,

Michael Bi Mi,

Xinchao Wang

[pdf] [arXiv]

[bibtex]

@InProceedings{Fang_2023_CVPR, author = {Fang, Gongfan and Ma, Xinyin and Song, Mingli and Mi, Michael Bi and Wang, Xinchao}, title = {DepGraph: Towards Any Structural Pruning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16091-16101} }

Exploring Discontinuity for Video Frame Interpolation

Sangjin Lee,

Hyeongmin Lee,

Chajin Shin,

Hanbin Son,

Sangyoun Lee

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Lee_2023_CVPR, author = {Lee, Sangjin and Lee, Hyeongmin and Shin, Chajin and Son, Hanbin and Lee, Sangyoun}, title = {Exploring Discontinuity for Video Frame Interpolation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9791-9800} }

DynamicStereo: Consistent Dynamic Depth From Stereo Videos

Nikita Karaev,

Ignacio Rocco,

Benjamin Graham,

Natalia Neverova,

Andrea Vedaldi,

Christian Rupprecht

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Karaev_2023_CVPR, author = {Karaev, Nikita and Rocco, Ignacio and Graham, Benjamin and Neverova, Natalia and Vedaldi, Andrea and Rupprecht, Christian}, title = {DynamicStereo: Consistent Dynamic Depth From Stereo Videos}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13229-13239} }

Cut and Learn for Unsupervised Object Detection and Instance Segmentation

Xudong Wang,

Rohit Girdhar,

Stella X. Yu,

Ishan Misra

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Xudong and Girdhar, Rohit and Yu, Stella X. and Misra, Ishan}, title = {Cut and Learn for Unsupervised Object Detection and Instance Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3124-3134} }

Privacy-Preserving Adversarial Facial Features

Zhibo Wang,

He Wang,

Shuaifan Jin,

Wenwen Zhang,

Jiahui Hu,

Yan Wang,

Peng Sun,

Wei Yuan,

Kaixin Liu,

Kui Ren

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Zhibo and Wang, He and Jin, Shuaifan and Zhang, Wenwen and Hu, Jiahui and Wang, Yan and Sun, Peng and Yuan, Wei and Liu, Kaixin and Ren, Kui}, title = {Privacy-Preserving Adversarial Facial Features}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8212-8221} }

Exploring the Relationship Between Architectural Design and Adversarially Robust Generalization

Aishan Liu,

Shiyu Tang,

Siyuan Liang,

Ruihao Gong,

Boxi Wu,

Xianglong Liu,

Dacheng Tao

[pdf] [supp]

[bibtex]

@InProceedings{Liu_2023_CVPR, author = {Liu, Aishan and Tang, Shiyu and Liang, Siyuan and Gong, Ruihao and Wu, Boxi and Liu, Xianglong and Tao, Dacheng}, title = {Exploring the Relationship Between Architectural Design and Adversarially Robust Generalization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4096-4107} }

Vid2Avatar: 3D Avatar Reconstruction From Videos in the Wild via Self-Supervised Scene Decomposition

Chen Guo,

Tianjian Jiang,

Xu Chen,

Jie Song,

Otmar Hilliges

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Guo_2023_CVPR, author = {Guo, Chen and Jiang, Tianjian and Chen, Xu and Song, Jie and Hilliges, Otmar}, title = {Vid2Avatar: 3D Avatar Reconstruction From Videos in the Wild via Self-Supervised Scene Decomposition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12858-12868} }

Task Residual for Tuning Vision-Language Models

Tao Yu,

Zhihe Lu,

Xin Jin,

Zhibo Chen,

Xinchao Wang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Yu_2023_CVPR, author = {Yu, Tao and Lu, Zhihe and Jin, Xin and Chen, Zhibo and Wang, Xinchao}, title = {Task Residual for Tuning Vision-Language Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10899-10909} }

Side Adapter Network for Open-Vocabulary Semantic Segmentation

Mengde Xu,

Zheng Zhang,

Fangyun Wei,

Han Hu,

Xiang Bai

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Xu_2023_CVPR, author = {Xu, Mengde and Zhang, Zheng and Wei, Fangyun and Hu, Han and Bai, Xiang}, title = {Side Adapter Network for Open-Vocabulary Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2945-2954} }

Network Expansion for Practical Training Acceleration

Ning Ding,

Yehui Tang,

Kai Han,

Chao Xu,

Yunhe Wang

[pdf]

[bibtex]

@InProceedings{Ding_2023_CVPR, author = {Ding, Ning and Tang, Yehui and Han, Kai and Xu, Chao and Wang, Yunhe}, title = {Network Expansion for Practical Training Acceleration}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {20269-20279} }

FCC: Feature Clusters Compression for Long-Tailed Visual Recognition

Jian Li,

Ziyao Meng,

Daqian Shi,

Rui Song,

Xiaolei Diao,

Jingwen Wang,

Hao Xu

[pdf] [supp]

[bibtex]

@InProceedings{Li_2023_CVPR, author = {Li, Jian and Meng, Ziyao and Shi, Daqian and Song, Rui and Diao, Xiaolei and Wang, Jingwen and Xu, Hao}, title = {FCC: Feature Clusters Compression for Long-Tailed Visual Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {24080-24089} }

Rethinking the Learning Paradigm for Dynamic Facial Expression Recognition

Hanyang Wang,

Bo Li,

Shuang Wu,

Siyuan Shen,

Feng Liu,

Shouhong Ding,

Aimin Zhou

[pdf]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Hanyang and Li, Bo and Wu, Shuang and Shen, Siyuan and Liu, Feng and Ding, Shouhong and Zhou, Aimin}, title = {Rethinking the Learning Paradigm for Dynamic Facial Expression Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {17958-17968} }

Multi-Centroid Task Descriptor for Dynamic Class Incremental Inference

Tenghao Cai,

Zhizhong Zhang,

Xin Tan,

Yanyun Qu,

Guannan Jiang,

Chengjie Wang,

Yuan Xie

[pdf] [supp]

[bibtex]

@InProceedings{Cai_2023_CVPR, author = {Cai, Tenghao and Zhang, Zhizhong and Tan, Xin and Qu, Yanyun and Jiang, Guannan and Wang, Chengjie and Xie, Yuan}, title = {Multi-Centroid Task Descriptor for Dynamic Class Incremental Inference}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7298-7307} }

Hierarchical Prompt Learning for Multi-Task Learning

Yajing Liu,

Yuning Lu,

Hao Liu,

Yaozu An,

Zhuoran Xu,

Zhuokun Yao,

Baofeng Zhang,

Zhiwei Xiong,

Chenguang Gui

[pdf] [supp]

[bibtex]

@InProceedings{Liu_2023_CVPR, author = {Liu, Yajing and Lu, Yuning and Liu, Hao and An, Yaozu and Xu, Zhuoran and Yao, Zhuokun and Zhang, Baofeng and Xiong, Zhiwei and Gui, Chenguang}, title = {Hierarchical Prompt Learning for Multi-Task Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10888-10898} }

Physics-Guided ISO-Dependent Sensor Noise Modeling for Extreme Low-Light Photography

Yue Cao,

Ming Liu,

Shuai Liu,

Xiaotao Wang,

Lei Lei,

Wangmeng Zuo

[pdf] [supp]

[bibtex]

@InProceedings{Cao_2023_CVPR, author = {Cao, Yue and Liu, Ming and Liu, Shuai and Wang, Xiaotao and Lei, Lei and Zuo, Wangmeng}, title = {Physics-Guided ISO-Dependent Sensor Noise Modeling for Extreme Low-Light Photography}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5744-5753} }

RIFormer: Keep Your Vision Backbone Effective but Removing Token Mixer

Jiahao Wang,

Songyang Zhang,

Yong Liu,

Taiqiang Wu,

Yujiu Yang,

Xihui Liu,

Kai Chen,

Ping Luo,

Dahua Lin

[pdf] [supp]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Jiahao and Zhang, Songyang and Liu, Yong and Wu, Taiqiang and Yang, Yujiu and Liu, Xihui and Chen, Kai and Luo, Ping and Lin, Dahua}, title = {RIFormer: Keep Your Vision Backbone Effective but Removing Token Mixer}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14443-14452} }

Context-Based Trit-Plane Coding for Progressive Image Compression

Seungmin Jeon,

Kwang Pyo Choi,

Youngo Park,

Chang-Su Kim

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Jeon_2023_CVPR, author = {Jeon, Seungmin and Choi, Kwang Pyo and Park, Youngo and Kim, Chang-Su}, title = {Context-Based Trit-Plane Coding for Progressive Image Compression}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14348-14357} }

Self-Supervised Learning for Multimodal Non-Rigid 3D Shape Matching

Dongliang Cao,

Florian Bernard

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Cao_2023_CVPR, author = {Cao, Dongliang and Bernard, Florian}, title = {Self-Supervised Learning for Multimodal Non-Rigid 3D Shape Matching}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {17735-17744} }

Recurrent Vision Transformers for Object Detection With Event Cameras

Mathias Gehrig,

Davide Scaramuzza

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Gehrig_2023_CVPR, author = {Gehrig, Mathias and Scaramuzza, Davide}, title = {Recurrent Vision Transformers for Object Detection With Event Cameras}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13884-13893} }

Ham2Pose: Animating Sign Language Notation Into Pose Sequences

Rotem Shalev Arkushin,

Amit Moryossef,

Ohad Fried

[pdf] [supp]

[bibtex]

@InProceedings{Arkushin_2023_CVPR, author = {Arkushin, Rotem Shalev and Moryossef, Amit and Fried, Ohad}, title = {Ham2Pose: Animating Sign Language Notation Into Pose Sequences}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {21046-21056} }

Open-Set Likelihood Maximization for Few-Shot Learning

Malik Boudiaf,

Etienne Bennequin,

Myriam Tami,

Antoine Toubhans,

Pablo Piantanida,

Celine Hudelot,

Ismail Ben Ayed

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Boudiaf_2023_CVPR, author = {Boudiaf, Malik and Bennequin, Etienne and Tami, Myriam and Toubhans, Antoine and Piantanida, Pablo and Hudelot, Celine and Ben Ayed, Ismail}, title = {Open-Set Likelihood Maximization for Few-Shot Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {24007-24016} }

DiGeo: Discriminative Geometry-Aware Learning for Generalized Few-Shot Object Detection

Jiawei Ma,

Yulei Niu,

Jincheng Xu,

Shiyuan Huang,

Guangxing Han,

Shih-Fu Chang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Ma_2023_CVPR, author = {Ma, Jiawei and Niu, Yulei and Xu, Jincheng and Huang, Shiyuan and Han, Guangxing and Chang, Shih-Fu}, title = {DiGeo: Discriminative Geometry-Aware Learning for Generalized Few-Shot Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3208-3218} }

Boosting Accuracy and Robustness of Student Models via Adaptive Adversarial Distillation

Bo Huang,

Mingyang Chen,

Yi Wang,

Junda Lu,

Minhao Cheng,

Wei Wang

[pdf]

[bibtex]

@InProceedings{Huang_2023_CVPR, author = {Huang, Bo and Chen, Mingyang and Wang, Yi and Lu, Junda and Cheng, Minhao and Wang, Wei}, title = {Boosting Accuracy and Robustness of Student Models via Adaptive Adversarial Distillation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {24668-24677} }

METransformer: Radiology Report Generation by Transformer With Multiple Learnable Expert Tokens

Zhanyu Wang,

Lingqiao Liu,

Lei Wang,

Luping Zhou

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Zhanyu and Liu, Lingqiao and Wang, Lei and Zhou, Luping}, title = {METransformer: Radiology Report Generation by Transformer With Multiple Learnable Expert Tokens}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11558-11567} }

PixHt-Lab: Pixel Height Based Light Effect Generation for Image Compositing

Yichen Sheng,

Jianming Zhang,

Julien Philip,

Yannick Hold-Geoffroy,

Xin Sun,

He Zhang,

Lu Ling,

Bedrich Benes

[pdf] [supp]

[bibtex]

@InProceedings{Sheng_2023_CVPR, author = {Sheng, Yichen and Zhang, Jianming and Philip, Julien and Hold-Geoffroy, Yannick and Sun, Xin and Zhang, He and Ling, Lu and Benes, Bedrich}, title = {PixHt-Lab: Pixel Height Based Light Effect Generation for Image Compositing}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16643-16653} }

A Soma Segmentation Benchmark in Full Adult Fly Brain

Xiaoyu Liu,

Bo Hu,

Mingxing Li,

Wei Huang,

Yueyi Zhang,

Zhiwei Xiong

[pdf] [supp]

[bibtex]

@InProceedings{Liu_2023_CVPR, author = {Liu, Xiaoyu and Hu, Bo and Li, Mingxing and Huang, Wei and Zhang, Yueyi and Xiong, Zhiwei}, title = {A Soma Segmentation Benchmark in Full Adult Fly Brain}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7402-7411} }

RGB No More: Minimally-Decoded JPEG Vision Transformers

Jeongsoo Park,

Justin Johnson

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Park_2023_CVPR, author = {Park, Jeongsoo and Johnson, Justin}, title = {RGB No More: Minimally-Decoded JPEG Vision Transformers}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {22334-22346} }

Revealing the Dark Secrets of Masked Image Modeling

Zhenda Xie,

Zigang Geng,

Jingcheng Hu,

Zheng Zhang,

Han Hu,

Yue Cao

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Xie_2023_CVPR, author = {Xie, Zhenda and Geng, Zigang and Hu, Jingcheng and Zhang, Zheng and Hu, Han and Cao, Yue}, title = {Revealing the Dark Secrets of Masked Image Modeling}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14475-14485} }

Fine-Grained Classification With Noisy Labels

Qi Wei,

Lei Feng,

Haoliang Sun,

Ren Wang,

Chenhui Guo,

Yilong Yin

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Wei_2023_CVPR, author = {Wei, Qi and Feng, Lei and Sun, Haoliang and Wang, Ren and Guo, Chenhui and Yin, Yilong}, title = {Fine-Grained Classification With Noisy Labels}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11651-11660} }

CaPriDe Learning: Confidential and Private Decentralized Learning Based on Encryption-Friendly Distillation Loss

Nurbek Tastan,

Karthik Nandakumar

[pdf] [supp]

[bibtex]

@InProceedings{Tastan_2023_CVPR, author = {Tastan, Nurbek and Nandakumar, Karthik}, title = {CaPriDe Learning: Confidential and Private Decentralized Learning Based on Encryption-Friendly Distillation Loss}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8084-8092} }

Hybrid Active Learning via Deep Clustering for Video Action Detection

Aayush J. Rana,

Yogesh S. Rawat

[pdf] [supp]

[bibtex]

@InProceedings{Rana_2023_CVPR, author = {Rana, Aayush J. and Rawat, Yogesh S.}, title = {Hybrid Active Learning via Deep Clustering for Video Action Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {18867-18877} }

Fine-Grained Image-Text Matching by Cross-Modal Hard Aligning Network

Zhengxin Pan,

Fangyu Wu,

Bailing Zhang

[pdf]

[bibtex]

@InProceedings{Pan_2023_CVPR, author = {Pan, Zhengxin and Wu, Fangyu and Zhang, Bailing}, title = {Fine-Grained Image-Text Matching by Cross-Modal Hard Aligning Network}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {19275-19284} }

Sparsifiner: Learning Sparse Instance-Dependent Attention for Efficient Vision Transformers

Cong Wei,

Brendan Duke,

Ruowei Jiang,

Parham Aarabi,

Graham W. Taylor,

Florian Shkurti

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Wei_2023_CVPR, author = {Wei, Cong and Duke, Brendan and Jiang, Ruowei and Aarabi, Parham and Taylor, Graham W. and Shkurti, Florian}, title = {Sparsifiner: Learning Sparse Instance-Dependent Attention for Efficient Vision Transformers}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {22680-22689} }

Structured Sparsity Learning for Efficient Video Super-Resolution

Bin Xia,

Jingwen He,

Yulun Zhang,

Yitong Wang,

Yapeng Tian,

Wenming Yang,

Luc Van Gool

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Xia_2023_CVPR, author = {Xia, Bin and He, Jingwen and Zhang, Yulun and Wang, Yitong and Tian, Yapeng and Yang, Wenming and Van Gool, Luc}, title = {Structured Sparsity Learning for Efficient Video Super-Resolution}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {22638-22647} }

CAP: Robust Point Cloud Classification via Semantic and Structural Modeling

Daizong Ding,

Erling Jiang,

Yuanmin Huang,

Mi Zhang,

Wenxuan Li,

Min Yang

[pdf] [supp]

[bibtex]

@InProceedings{Ding_2023_CVPR, author = {Ding, Daizong and Jiang, Erling and Huang, Yuanmin and Zhang, Mi and Li, Wenxuan and Yang, Min}, title = {CAP: Robust Point Cloud Classification via Semantic and Structural Modeling}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12260-12270} }

"Seeing" Electric Network Frequency From Events

Lexuan Xu,

Guang Hua,

Haijian Zhang,

Lei Yu,

Ning Qiao

[pdf] [arXiv]

[bibtex]

@InProceedings{Xu_2023_CVPR, author = {Xu, Lexuan and Hua, Guang and Zhang, Haijian and Yu, Lei and Qiao, Ning}, title = {''Seeing'' Electric Network Frequency From Events}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {18022-18031} }

MMVC: Learned Multi-Mode Video Compression With Block-Based Prediction Mode Selection and Density-Adaptive Entropy Coding

Bowen Liu,

Yu Chen,

Rakesh Chowdary Machineni,

Shiyu Liu,

Hun-Seok Kim

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Liu_2023_CVPR, author = {Liu, Bowen and Chen, Yu and Machineni, Rakesh Chowdary and Liu, Shiyu and Kim, Hun-Seok}, title = {MMVC: Learned Multi-Mode Video Compression With Block-Based Prediction Mode Selection and Density-Adaptive Entropy Coding}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {18487-18496} }

Visual-Tactile Sensing for In-Hand Object Reconstruction

Wenqiang Xu,

Zhenjun Yu,

Han Xue,

Ruolin Ye,

Siqiong Yao,

Cewu Lu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Xu_2023_CVPR, author = {Xu, Wenqiang and Yu, Zhenjun and Xue, Han and Ye, Ruolin and Yao, Siqiong and Lu, Cewu}, title = {Visual-Tactile Sensing for In-Hand Object Reconstruction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8803-8812} }

vMAP: Vectorised Object Mapping for Neural Field SLAM

Xin Kong,

Shikun Liu,

Marwan Taher,

Andrew J. Davison

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Kong_2023_CVPR, author = {Kong, Xin and Liu, Shikun and Taher, Marwan and Davison, Andrew J.}, title = {vMAP: Vectorised Object Mapping for Neural Field SLAM}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {952-961} }

Images Speak in Images: A Generalist Painter for In-Context Visual Learning

Xinlong Wang,

Wen Wang,

Yue Cao,

Chunhua Shen,

Tiejun Huang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Xinlong and Wang, Wen and Cao, Yue and Shen, Chunhua and Huang, Tiejun}, title = {Images Speak in Images: A Generalist Painter for In-Context Visual Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6830-6839} }

Omni Aggregation Networks for Lightweight Image Super-Resolution

Hang Wang,

Xuanhong Chen,

Bingbing Ni,

Yutian Liu,

Jinfan Liu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Hang and Chen, Xuanhong and Ni, Bingbing and Liu, Yutian and Liu, Jinfan}, title = {Omni Aggregation Networks for Lightweight Image Super-Resolution}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {22378-22387} }

StyLess: Boosting the Transferability of Adversarial Examples

Kaisheng Liang,

Bin Xiao

[pdf] [arXiv]

[bibtex]

@InProceedings{Liang_2023_CVPR, author = {Liang, Kaisheng and Xiao, Bin}, title = {StyLess: Boosting the Transferability of Adversarial Examples}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8163-8172} }

Local-to-Global Registration for Bundle-Adjusting Neural Radiance Fields

Yue Chen,

Xingyu Chen,

Xuan Wang,

Qi Zhang,

Yu Guo,

Ying Shan,

Fei Wang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Chen_2023_CVPR, author = {Chen, Yue and Chen, Xingyu and Wang, Xuan and Zhang, Qi and Guo, Yu and Shan, Ying and Wang, Fei}, title = {Local-to-Global Registration for Bundle-Adjusting Neural Radiance Fields}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8264-8273} }

Uncertainty-Aware Optimal Transport for Semantically Coherent Out-of-Distribution Detection

Fan Lu,

Kai Zhu,

Wei Zhai,

Kecheng Zheng,

Yang Cao

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Lu_2023_CVPR, author = {Lu, Fan and Zhu, Kai and Zhai, Wei and Zheng, Kecheng and Cao, Yang}, title = {Uncertainty-Aware Optimal Transport for Semantically Coherent Out-of-Distribution Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3282-3291} }

FJMP: Factorized Joint Multi-Agent Motion Prediction Over Learned Directed Acyclic Interaction Graphs

Luke Rowe,

Martin Ethier,

Eli-Henry Dykhne,

Krzysztof Czarnecki

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Rowe_2023_CVPR, author = {Rowe, Luke and Ethier, Martin and Dykhne, Eli-Henry and Czarnecki, Krzysztof}, title = {FJMP: Factorized Joint Multi-Agent Motion Prediction Over Learned Directed Acyclic Interaction Graphs}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13745-13755} }

Exploring the Effect of Primitives for Compositional Generalization in Vision-and-Language

Chuanhao Li,

Zhen Li,

Chenchen Jing,

Yunde Jia,

Yuwei Wu

[pdf] [supp]

[bibtex]

@InProceedings{Li_2023_CVPR, author = {Li, Chuanhao and Li, Zhen and Jing, Chenchen and Jia, Yunde and Wu, Yuwei}, title = {Exploring the Effect of Primitives for Compositional Generalization in Vision-and-Language}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {19092-19101} }

Correlational Image Modeling for Self-Supervised Visual Pre-Training

Wei Li,

Jiahao Xie,

Chen Change Loy

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Li_2023_CVPR, author = {Li, Wei and Xie, Jiahao and Loy, Chen Change}, title = {Correlational Image Modeling for Self-Supervised Visual Pre-Training}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15105-15115} }

DC2: Dual-Camera Defocus Control by Learning To Refocus

Hadi Alzayer,

Abdullah Abuolaim,

Leung Chun Chan,

Yang Yang,

Ying Chen Lou,

Jia-Bin Huang,

Abhishek Kar

[pdf] [supp]

[bibtex]

@InProceedings{Alzayer_2023_CVPR, author = {Alzayer, Hadi and Abuolaim, Abdullah and Chan, Leung Chun and Yang, Yang and Lou, Ying Chen and Huang, Jia-Bin and Kar, Abhishek}, title = {DC2: Dual-Camera Defocus Control by Learning To Refocus}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {21488-21497} }

MISC210K: A Large-Scale Dataset for Multi-Instance Semantic Correspondence

Yixuan Sun,

Yiwen Huang,

Haijing Guo,

Yuzhou Zhao,

Runmin Wu,

Yizhou Yu,

Weifeng Ge,

Wenqiang Zhang

[pdf] [supp]

[bibtex]

@InProceedings{Sun_2023_CVPR, author = {Sun, Yixuan and Huang, Yiwen and Guo, Haijing and Zhao, Yuzhou and Wu, Runmin and Yu, Yizhou and Ge, Weifeng and Zhang, Wenqiang}, title = {MISC210K: A Large-Scale Dataset for Multi-Instance Semantic Correspondence}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7121-7130} }

Self-Supervised Implicit Glyph Attention for Text Recognition

Tongkun Guan,

Chaochen Gu,

Jingzheng Tu,

Xue Yang,

Qi Feng,

Yudi Zhao,

Wei Shen

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Guan_2023_CVPR, author = {Guan, Tongkun and Gu, Chaochen and Tu, Jingzheng and Yang, Xue and Feng, Qi and Zhao, Yudi and Shen, Wei}, title = {Self-Supervised Implicit Glyph Attention for Text Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15285-15294} }

ACL-SPC: Adaptive Closed-Loop System for Self-Supervised Point Cloud Completion

Sangmin Hong,

Mohsen Yavartanoo,

Reyhaneh Neshatavar,

Kyoung Mu Lee

[pdf] [supp]

[bibtex]

@InProceedings{Hong_2023_CVPR, author = {Hong, Sangmin and Yavartanoo, Mohsen and Neshatavar, Reyhaneh and Lee, Kyoung Mu}, title = {ACL-SPC: Adaptive Closed-Loop System for Self-Supervised Point Cloud Completion}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9435-9444} }

MAGE: MAsked Generative Encoder To Unify Representation Learning and Image Synthesis

Tianhong Li,

Huiwen Chang,

Shlok Mishra,

Han Zhang,

Dina Katabi,

Dilip Krishnan

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Li_2023_CVPR, author = {Li, Tianhong and Chang, Huiwen and Mishra, Shlok and Zhang, Han and Katabi, Dina and Krishnan, Dilip}, title = {MAGE: MAsked Generative Encoder To Unify Representation Learning and Image Synthesis}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2142-2152} }

Focus on Details: Online Multi-Object Tracking With Diverse Fine-Grained Representation

Hao Ren,

Shoudong Han,

Huilin Ding,

Ziwen Zhang,

Hongwei Wang,

Faquan Wang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Ren_2023_CVPR, author = {Ren, Hao and Han, Shoudong and Ding, Huilin and Zhang, Ziwen and Wang, Hongwei and Wang, Faquan}, title = {Focus on Details: Online Multi-Object Tracking With Diverse Fine-Grained Representation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11289-11298} }

DiffPose: Toward More Reliable 3D Pose Estimation

Jia Gong,

Lin Geng Foo,

Zhipeng Fan,

Qiuhong Ke,

Hossein Rahmani,

Jun Liu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Gong_2023_CVPR, author = {Gong, Jia and Foo, Lin Geng and Fan, Zhipeng and Ke, Qiuhong and Rahmani, Hossein and Liu, Jun}, title = {DiffPose: Toward More Reliable 3D Pose Estimation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13041-13051} }

Lift3D: Synthesize 3D Training Data by Lifting 2D GAN to 3D Generative Radiance Field

Leheng Li,

Qing Lian,

Luozhou Wang,

Ningning Ma,

Ying-Cong Chen

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Li_2023_CVPR, author = {Li, Leheng and Lian, Qing and Wang, Luozhou and Ma, Ningning and Chen, Ying-Cong}, title = {Lift3D: Synthesize 3D Training Data by Lifting 2D GAN to 3D Generative Radiance Field}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {332-341} }

Hunting Sparsity: Density-Guided Contrastive Learning for Semi-Supervised Semantic Segmentation

Xiaoyang Wang,

Bingfeng Zhang,

Limin Yu,

Jimin Xiao

[pdf] [supp]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Xiaoyang and Zhang, Bingfeng and Yu, Limin and Xiao, Jimin}, title = {Hunting Sparsity: Density-Guided Contrastive Learning for Semi-Supervised Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3114-3123} }

Learning Analytical Posterior Probability for Human Mesh Recovery

Qi Fang,

Kang Chen,

Yinghui Fan,

Qing Shuai,

Jiefeng Li,

Weidong Zhang

[pdf] [supp]

[bibtex]

@InProceedings{Fang_2023_CVPR, author = {Fang, Qi and Chen, Kang and Fan, Yinghui and Shuai, Qing and Li, Jiefeng and Zhang, Weidong}, title = {Learning Analytical Posterior Probability for Human Mesh Recovery}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8781-8791} }

Looking Through the Glass: Neural Surface Reconstruction Against High Specular Reflections

Jiaxiong Qiu,

Peng-Tao Jiang,

Yifan Zhu,

Ze-Xin Yin,

Ming-Ming Cheng,

Bo Ren

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Qiu_2023_CVPR, author = {Qiu, Jiaxiong and Jiang, Peng-Tao and Zhu, Yifan and Yin, Ze-Xin and Cheng, Ming-Ming and Ren, Bo}, title = {Looking Through the Glass: Neural Surface Reconstruction Against High Specular Reflections}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {20823-20833} }

Non-Contrastive Unsupervised Learning of Physiological Signals From Video

Jeremy Speth,

Nathan Vance,

Patrick Flynn,

Adam Czajka

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Speth_2023_CVPR, author = {Speth, Jeremy and Vance, Nathan and Flynn, Patrick and Czajka, Adam}, title = {Non-Contrastive Unsupervised Learning of Physiological Signals From Video}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14464-14474} }

FashionSAP: Symbols and Attributes Prompt for Fine-Grained Fashion Vision-Language Pre-Training

Yunpeng Han,

Lisai Zhang,

Qingcai Chen,

Zhijian Chen,

Zhonghua Li,

Jianxin Yang,

Zhao Cao

[pdf] [arXiv]

[bibtex]

@InProceedings{Han_2023_CVPR, author = {Han, Yunpeng and Zhang, Lisai and Chen, Qingcai and Chen, Zhijian and Li, Zhonghua and Yang, Jianxin and Cao, Zhao}, title = {FashionSAP: Symbols and Attributes Prompt for Fine-Grained Fashion Vision-Language Pre-Training}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15028-15038} }

PartSLIP: Low-Shot Part Segmentation for 3D Point Clouds via Pretrained Image-Language Models

Minghua Liu,

Yinhao Zhu,

Hong Cai,

Shizhong Han,

Zhan Ling,

Fatih Porikli,

Hao Su

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Liu_2023_CVPR, author = {Liu, Minghua and Zhu, Yinhao and Cai, Hong and Han, Shizhong and Ling, Zhan and Porikli, Fatih and Su, Hao}, title = {PartSLIP: Low-Shot Part Segmentation for 3D Point Clouds via Pretrained Image-Language Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {21736-21746} }

An Erudite Fine-Grained Visual Classification Model

Dongliang Chang,

Yujun Tong,

Ruoyi Du,

Timothy Hospedales,

Yi-Zhe Song,

Zhanyu Ma

[pdf]

[bibtex]

@InProceedings{Chang_2023_CVPR, author = {Chang, Dongliang and Tong, Yujun and Du, Ruoyi and Hospedales, Timothy and Song, Yi-Zhe and Ma, Zhanyu}, title = {An Erudite Fine-Grained Visual Classification Model}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7268-7277} }

MAGVLT: Masked Generative Vision-and-Language Transformer

Sungwoong Kim,

Daejin Jo,

Donghoon Lee,

Jongmin Kim

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Kim_2023_CVPR, author = {Kim, Sungwoong and Jo, Daejin and Lee, Donghoon and Kim, Jongmin}, title = {MAGVLT: Masked Generative Vision-and-Language Transformer}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {23338-23348} }

Structure Aggregation for Cross-Spectral Stereo Image Guided Denoising

Zehua Sheng,

Zhu Yu,

Xiongwei Liu,

Si-Yuan Cao,

Yuqi Liu,

Hui-Liang Shen,

Huaqi Zhang

[pdf] [supp]

[bibtex]

@InProceedings{Sheng_2023_CVPR, author = {Sheng, Zehua and Yu, Zhu and Liu, Xiongwei and Cao, Si-Yuan and Liu, Yuqi and Shen, Hui-Liang and Zhang, Huaqi}, title = {Structure Aggregation for Cross-Spectral Stereo Image Guided Denoising}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13997-14006} }

Decoupling Human and Camera Motion From Videos in the Wild

Vickie Ye,

Georgios Pavlakos,

Jitendra Malik,

Angjoo Kanazawa

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Ye_2023_CVPR, author = {Ye, Vickie and Pavlakos, Georgios and Malik, Jitendra and Kanazawa, Angjoo}, title = {Decoupling Human and Camera Motion From Videos in the Wild}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {21222-21232} }

DetCLIPv2: Scalable Open-Vocabulary Object Detection Pre-Training via Word-Region Alignment

Lewei Yao,

Jianhua Han,

Xiaodan Liang,

Dan Xu,

Wei Zhang,

Zhenguo Li,

Hang Xu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Yao_2023_CVPR, author = {Yao, Lewei and Han, Jianhua and Liang, Xiaodan and Xu, Dan and Zhang, Wei and Li, Zhenguo and Xu, Hang}, title = {DetCLIPv2: Scalable Open-Vocabulary Object Detection Pre-Training via Word-Region Alignment}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {23497-23506} }

Adversarially Robust Neural Architecture Search for Graph Neural Networks

Beini Xie,

Heng Chang,

Ziwei Zhang,

Xin Wang,

Daixin Wang,

Zhiqiang Zhang,

Rex Ying,

Wenwu Zhu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Xie_2023_CVPR, author = {Xie, Beini and Chang, Heng and Zhang, Ziwei and Wang, Xin and Wang, Daixin and Zhang, Zhiqiang and Ying, Rex and Zhu, Wenwu}, title = {Adversarially Robust Neural Architecture Search for Graph Neural Networks}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8143-8152} }

Affordance Grounding From Demonstration Video To Target Image

Joya Chen,

Difei Gao,

Kevin Qinghong Lin,

Mike Zheng Shou

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Chen_2023_CVPR, author = {Chen, Joya and Gao, Difei and Lin, Kevin Qinghong and Shou, Mike Zheng}, title = {Affordance Grounding From Demonstration Video To Target Image}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6799-6808} }

GrowSP: Unsupervised Semantic Segmentation of 3D Point Clouds

Zihui Zhang,

Bo Yang,

Bing Wang,

Bo Li

[pdf] [supp]

[bibtex]

@InProceedings{Zhang_2023_CVPR, author = {Zhang, Zihui and Yang, Bo and Wang, Bing and Li, Bo}, title = {GrowSP: Unsupervised Semantic Segmentation of 3D Point Clouds}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {17619-17629} }

RONO: Robust Discriminative Learning With Noisy Labels for 2D-3D Cross-Modal Retrieval

Yanglin Feng,

Hongyuan Zhu,

Dezhong Peng,

Xi Peng,

Peng Hu

[pdf] [supp]

[bibtex]

@InProceedings{Feng_2023_CVPR, author = {Feng, Yanglin and Zhu, Hongyuan and Peng, Dezhong and Peng, Xi and Hu, Peng}, title = {RONO: Robust Discriminative Learning With Noisy Labels for 2D-3D Cross-Modal Retrieval}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11610-11619} }

One-Stage 3D Whole-Body Mesh Recovery With Component Aware Transformer

Jing Lin,

Ailing Zeng,

Haoqian Wang,

Lei Zhang,

Yu Li

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Lin_2023_CVPR, author = {Lin, Jing and Zeng, Ailing and Wang, Haoqian and Zhang, Lei and Li, Yu}, title = {One-Stage 3D Whole-Body Mesh Recovery With Component Aware Transformer}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {21159-21168} }

Masked Jigsaw Puzzle: A Versatile Position Embedding for Vision Transformers

Bin Ren,

Yahui Liu,

Yue Song,

Wei Bi,

Rita Cucchiara,

Nicu Sebe,

Wei Wang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Ren_2023_CVPR, author = {Ren, Bin and Liu, Yahui and Song, Yue and Bi, Wei and Cucchiara, Rita and Sebe, Nicu and Wang, Wei}, title = {Masked Jigsaw Puzzle: A Versatile Position Embedding for Vision Transformers}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {20382-20391} }

LayoutDiffusion: Controllable Diffusion Model for Layout-to-Image Generation

Guangcong Zheng,

Xianpan Zhou,

Xuewei Li,

Zhongang Qi,

Ying Shan,

Xi Li

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Zheng_2023_CVPR, author = {Zheng, Guangcong and Zhou, Xianpan and Li, Xuewei and Qi, Zhongang and Shan, Ying and Li, Xi}, title = {LayoutDiffusion: Controllable Diffusion Model for Layout-to-Image Generation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {22490-22499} }

DeepMAD: Mathematical Architecture Design for Deep Convolutional Neural Network

Xuan Shen,

Yaohua Wang,

Ming Lin,

Yilun Huang,

Hao Tang,

Xiuyu Sun,

Yanzhi Wang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Shen_2023_CVPR, author = {Shen, Xuan and Wang, Yaohua and Lin, Ming and Huang, Yilun and Tang, Hao and Sun, Xiuyu and Wang, Yanzhi}, title = {DeepMAD: Mathematical Architecture Design for Deep Convolutional Neural Network}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6163-6173} }

DISC: Learning From Noisy Labels via Dynamic Instance-Specific Selection and Correction

Yifan Li,

Hu Han,

Shiguang Shan,

Xilin Chen

[pdf] [supp]

[bibtex]

@InProceedings{Li_2023_CVPR, author = {Li, Yifan and Han, Hu and Shan, Shiguang and Chen, Xilin}, title = {DISC: Learning From Noisy Labels via Dynamic Instance-Specific Selection and Correction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {24070-24079} }

BBDM: Image-to-Image Translation With Brownian Bridge Diffusion Models

Bo Li,

Kaitao Xue,

Bin Liu,

Yu-Kun Lai

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Li_2023_CVPR, author = {Li, Bo and Xue, Kaitao and Liu, Bin and Lai, Yu-Kun}, title = {BBDM: Image-to-Image Translation With Brownian Bridge Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1952-1961} }

ConQueR: Query Contrast Voxel-DETR for 3D Object Detection

Benjin Zhu,

Zhe Wang,

Shaoshuai Shi,

Hang Xu,

Lanqing Hong,

Hongsheng Li

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Zhu_2023_CVPR, author = {Zhu, Benjin and Wang, Zhe and Shi, Shaoshuai and Xu, Hang and Hong, Lanqing and Li, Hongsheng}, title = {ConQueR: Query Contrast Voxel-DETR for 3D Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9296-9305} }

Probing Neural Representations of Scene Perception in a Hippocampally Dependent Task Using Artificial Neural Networks

Markus Frey,

Christian F. Doeller,

Caswell Barry

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Frey_2023_CVPR, author = {Frey, Markus and Doeller, Christian F. and Barry, Caswell}, title = {Probing Neural Representations of Scene Perception in a Hippocampally Dependent Task Using Artificial Neural Networks}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2113-2121} }

Imagen Editor and EditBench: Advancing and Evaluating Text-Guided Image Inpainting

Su Wang,

Chitwan Saharia,

Ceslee Montgomery,

Jordi Pont-Tuset,

Shai Noy,

Stefano Pellegrini,

Yasumasa Onoe,

Sarah Laszlo,

David J. Fleet,

Radu Soricut,

Jason Baldridge,

Mohammad Norouzi,

Peter Anderson,

William Chan

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Su and Saharia, Chitwan and Montgomery, Ceslee and Pont-Tuset, Jordi and Noy, Shai and Pellegrini, Stefano and Onoe, Yasumasa and Laszlo, Sarah and Fleet, David J. and Soricut, Radu and Baldridge, Jason and Norouzi, Mohammad and Anderson, Peter and Chan, William}, title = {Imagen Editor and EditBench: Advancing and Evaluating Text-Guided Image Inpainting}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {18359-18369} }

Robust Multiview Point Cloud Registration With Reliable Pose Graph Initialization and History Reweighting

Haiping Wang,

Yuan Liu,

Zhen Dong,

Yulan Guo,

Yu-Shen Liu,

Wenping Wang,

Bisheng Yang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Haiping and Liu, Yuan and Dong, Zhen and Guo, Yulan and Liu, Yu-Shen and Wang, Wenping and Yang, Bisheng}, title = {Robust Multiview Point Cloud Registration With Reliable Pose Graph Initialization and History Reweighting}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9506-9515} }

A Probabilistic Framework for Lifelong Test-Time Adaptation

Dhanajit Brahma,

Piyush Rai

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Brahma_2023_CVPR, author = {Brahma, Dhanajit and Rai, Piyush}, title = {A Probabilistic Framework for Lifelong Test-Time Adaptation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3582-3591} }

Sound to Visual Scene Generation by Audio-to-Visual Latent Alignment

Kim Sung-Bin,

Arda Senocak,

Hyunwoo Ha,

Andrew Owens,

Tae-Hyun Oh

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Sung-Bin_2023_CVPR, author = {Sung-Bin, Kim and Senocak, Arda and Ha, Hyunwoo and Owens, Andrew and Oh, Tae-Hyun}, title = {Sound to Visual Scene Generation by Audio-to-Visual Latent Alignment}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6430-6440} }

OSRT: Omnidirectional Image Super-Resolution With Distortion-Aware Transformer

Fanghua Yu,

Xintao Wang,

Mingdeng Cao,

Gen Li,

Ying Shan,

Chao Dong

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Yu_2023_CVPR, author = {Yu, Fanghua and Wang, Xintao and Cao, Mingdeng and Li, Gen and Shan, Ying and Dong, Chao}, title = {OSRT: Omnidirectional Image Super-Resolution With Distortion-Aware Transformer}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13283-13292} }

Text With Knowledge Graph Augmented Transformer for Video Captioning

Xin Gu,

Guang Chen,

Yufei Wang,

Libo Zhang,

Tiejian Luo,

Longyin Wen

[pdf] [arXiv]

[bibtex]

@InProceedings{Gu_2023_CVPR, author = {Gu, Xin and Chen, Guang and Wang, Yufei and Zhang, Libo and Luo, Tiejian and Wen, Longyin}, title = {Text With Knowledge Graph Augmented Transformer for Video Captioning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {18941-18951} }

Filtering, Distillation, and Hard Negatives for Vision-Language Pre-Training

Filip Radenovic,

Abhimanyu Dubey,

Abhishek Kadian,

Todor Mihaylov,

Simon Vandenhende,

Yash Patel,

Yi Wen,

Vignesh Ramanathan,

Dhruv Mahajan

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Radenovic_2023_CVPR, author = {Radenovic, Filip and Dubey, Abhimanyu and Kadian, Abhishek and Mihaylov, Todor and Vandenhende, Simon and Patel, Yash and Wen, Yi and Ramanathan, Vignesh and Mahajan, Dhruv}, title = {Filtering, Distillation, and Hard Negatives for Vision-Language Pre-Training}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6967-6977} }

PointCMP: Contrastive Mask Prediction for Self-Supervised Learning on Point Cloud Videos

Zhiqiang Shen,

Xiaoxiao Sheng,

Longguang Wang,

Yulan Guo,

Qiong Liu,

Xi Zhou

[pdf] [arXiv]

[bibtex]

@InProceedings{Shen_2023_CVPR, author = {Shen, Zhiqiang and Sheng, Xiaoxiao and Wang, Longguang and Guo, Yulan and Liu, Qiong and Zhou, Xi}, title = {PointCMP: Contrastive Mask Prediction for Self-Supervised Learning on Point Cloud Videos}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1212-1222} }

IS-GGT: Iterative Scene Graph Generation With Generative Transformers

Sanjoy Kundu,

Sathyanarayanan N. Aakur

[pdf] [supp]

[bibtex]

@InProceedings{Kundu_2023_CVPR, author = {Kundu, Sanjoy and Aakur, Sathyanarayanan N.}, title = {IS-GGT: Iterative Scene Graph Generation With Generative Transformers}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6292-6301} }

Meta Omnium: A Benchmark for General-Purpose Learning-To-Learn

Ondrej Bohdal,

Yinbing Tian,

Yongshuo Zong,

Ruchika Chavhan,

Da Li,

Henry Gouk,

Li Guo,

Timothy Hospedales

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Bohdal_2023_CVPR, author = {Bohdal, Ondrej and Tian, Yinbing and Zong, Yongshuo and Chavhan, Ruchika and Li, Da and Gouk, Henry and Guo, Li and Hospedales, Timothy}, title = {Meta Omnium: A Benchmark for General-Purpose Learning-To-Learn}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7693-7703} }

Multimodal Industrial Anomaly Detection via Hybrid Fusion

Yue Wang,

Jinlong Peng,

Jiangning Zhang,

Ran Yi,

Yabiao Wang,

Chengjie Wang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Yue and Peng, Jinlong and Zhang, Jiangning and Yi, Ran and Wang, Yabiao and Wang, Chengjie}, title = {Multimodal Industrial Anomaly Detection via Hybrid Fusion}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8032-8041} }

BEV@DC: Bird's-Eye View Assisted Training for Depth Completion

Wending Zhou,

Xu Yan,

Yinghong Liao,

Yuankai Lin,

Jin Huang,

Gangming Zhao,

Shuguang Cui,

Zhen Li

[pdf] [supp]

[bibtex]

@InProceedings{Zhou_2023_CVPR, author = {Zhou, Wending and Yan, Xu and Liao, Yinghong and Lin, Yuankai and Huang, Jin and Zhao, Gangming and Cui, Shuguang and Li, Zhen}, title = {BEV@DC: Bird's-Eye View Assisted Training for Depth Completion}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9233-9242} }

BoxTeacher: Exploring High-Quality Pseudo Labels for Weakly Supervised Instance Segmentation

Tianheng Cheng,

Xinggang Wang,

Shaoyu Chen,

Qian Zhang,

Wenyu Liu

[pdf] [arXiv]

[bibtex]

@InProceedings{Cheng_2023_CVPR, author = {Cheng, Tianheng and Wang, Xinggang and Chen, Shaoyu and Zhang, Qian and Liu, Wenyu}, title = {BoxTeacher: Exploring High-Quality Pseudo Labels for Weakly Supervised Instance Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3145-3154} }

Change-Aware Sampling and Contrastive Learning for Satellite Images

Utkarsh Mall,

Bharath Hariharan,

Kavita Bala

[pdf] [supp]

[bibtex]

@InProceedings{Mall_2023_CVPR, author = {Mall, Utkarsh and Hariharan, Bharath and Bala, Kavita}, title = {Change-Aware Sampling and Contrastive Learning for Satellite Images}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5261-5270} }

Large-Scale Training Data Search for Object Re-Identification

Yue Yao,

Tom Gedeon,

Liang Zheng

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Yao_2023_CVPR, author = {Yao, Yue and Gedeon, Tom and Zheng, Liang}, title = {Large-Scale Training Data Search for Object Re-Identification}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15568-15578} }

Devil Is in the Queries: Advancing Mask Transformers for Real-World Medical Image Segmentation and Out-of-Distribution Localization

Mingze Yuan,

Yingda Xia,

Hexin Dong,

Zifan Chen,

Jiawen Yao,

Mingyan Qiu,

Ke Yan,

Xiaoli Yin,

Yu Shi,

Xin Chen,

Zaiyi Liu,

Bin Dong,

Jingren Zhou,

Le Lu,

Ling Zhang,

Li Zhang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Yuan_2023_CVPR, author = {Yuan, Mingze and Xia, Yingda and Dong, Hexin and Chen, Zifan and Yao, Jiawen and Qiu, Mingyan and Yan, Ke and Yin, Xiaoli and Shi, Yu and Chen, Xin and Liu, Zaiyi and Dong, Bin and Zhou, Jingren and Lu, Le and Zhang, Ling and Zhang, Li}, title = {Devil Is in the Queries: Advancing Mask Transformers for Real-World Medical Image Segmentation and Out-of-Distribution Localization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {23879-23889} }

KD-DLGAN: Data Limited Image Generation via Knowledge Distillation

Kaiwen Cui,

Yingchen Yu,

Fangneng Zhan,

Shengcai Liao,

Shijian Lu,

Eric P. Xing

[pdf] [supp]

[bibtex]

@InProceedings{Cui_2023_CVPR, author = {Cui, Kaiwen and Yu, Yingchen and Zhan, Fangneng and Liao, Shengcai and Lu, Shijian and Xing, Eric P.}, title = {KD-DLGAN: Data Limited Image Generation via Knowledge Distillation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3872-3882} }

Batch Model Consolidation: A Multi-Task Model Consolidation Framework

Iordanis Fostiropoulos,

Jiaye Zhu,

Laurent Itti

[pdf] [supp]

[bibtex]

@InProceedings{Fostiropoulos_2023_CVPR, author = {Fostiropoulos, Iordanis and Zhu, Jiaye and Itti, Laurent}, title = {Batch Model Consolidation: A Multi-Task Model Consolidation Framework}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3664-3676} }

SelfME: Self-Supervised Motion Learning for Micro-Expression Recognition

Xinqi Fan,

Xueli Chen,

Mingjie Jiang,

Ali Raza Shahid,

Hong Yan

[pdf]

[bibtex]

@InProceedings{Fan_2023_CVPR, author = {Fan, Xinqi and Chen, Xueli and Jiang, Mingjie and Shahid, Ali Raza and Yan, Hong}, title = {SelfME: Self-Supervised Motion Learning for Micro-Expression Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13834-13843} }

DR2: Diffusion-Based Robust Degradation Remover for Blind Face Restoration

Zhixin Wang,

Ziying Zhang,

Xiaoyun Zhang,

Huangjie Zheng,

Mingyuan Zhou,

Ya Zhang,

Yanfeng Wang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Zhixin and Zhang, Ziying and Zhang, Xiaoyun and Zheng, Huangjie and Zhou, Mingyuan and Zhang, Ya and Wang, Yanfeng}, title = {DR2: Diffusion-Based Robust Degradation Remover for Blind Face Restoration}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1704-1713} }

T-SEA: Transfer-Based Self-Ensemble Attack on Object Detection

Hao Huang,

Ziyan Chen,

Huanran Chen,

Yongtao Wang,

Kevin Zhang

[pdf]

[bibtex]

@InProceedings{Huang_2023_CVPR, author = {Huang, Hao and Chen, Ziyan and Chen, Huanran and Wang, Yongtao and Zhang, Kevin}, title = {T-SEA: Transfer-Based Self-Ensemble Attack on Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {20514-20523} }

LiDAR2Map: In Defense of LiDAR-Based Semantic Map Construction Using Online Camera Distillation

Song Wang,

Wentong Li,

Wenyu Liu,

Xiaolu Liu,

Jianke Zhu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Song and Li, Wentong and Liu, Wenyu and Liu, Xiaolu and Zhu, Jianke}, title = {LiDAR2Map: In Defense of LiDAR-Based Semantic Map Construction Using Online Camera Distillation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5186-5195} }

NewsNet: A Novel Dataset for Hierarchical Temporal Segmentation

Haoqian Wu,

Keyu Chen,

Haozhe Liu,

Mingchen Zhuge,

Bing Li,

Ruizhi Qiao,

Xiujun Shu,

Bei Gan,

Liangsheng Xu,

Bo Ren,

Mengmeng Xu,

Wentian Zhang,

Raghavendra Ramachandra,

Chia-Wen Lin,

Bernard Ghanem

[pdf] [supp]

[bibtex]

@InProceedings{Wu_2023_CVPR, author = {Wu, Haoqian and Chen, Keyu and Liu, Haozhe and Zhuge, Mingchen and Li, Bing and Qiao, Ruizhi and Shu, Xiujun and Gan, Bei and Xu, Liangsheng and Ren, Bo and Xu, Mengmeng and Zhang, Wentian and Ramachandra, Raghavendra and Lin, Chia-Wen and Ghanem, Bernard}, title = {NewsNet: A Novel Dataset for Hierarchical Temporal Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10669-10680} }

Token Contrast for Weakly-Supervised Semantic Segmentation

Lixiang Ru,

Heliang Zheng,

Yibing Zhan,

Bo Du

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Ru_2023_CVPR, author = {Ru, Lixiang and Zheng, Heliang and Zhan, Yibing and Du, Bo}, title = {Token Contrast for Weakly-Supervised Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3093-3102} }

LightedDepth: Video Depth Estimation in Light of Limited Inference View Angles

Shengjie Zhu,

Xiaoming Liu

[pdf] [supp]

[bibtex]

@InProceedings{Zhu_2023_CVPR, author = {Zhu, Shengjie and Liu, Xiaoming}, title = {LightedDepth: Video Depth Estimation in Light of Limited Inference View Angles}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5003-5012} }

Uncertainty-Aware Unsupervised Image Deblurring With Deep Residual Prior

Xiaole Tang,

Xile Zhao,

Jun Liu,

Jianli Wang,

Yuchun Miao,

Tieyong Zeng

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Tang_2023_CVPR, author = {Tang, Xiaole and Zhao, Xile and Liu, Jun and Wang, Jianli and Miao, Yuchun and Zeng, Tieyong}, title = {Uncertainty-Aware Unsupervised Image Deblurring With Deep Residual Prior}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9883-9892} }

HouseDiffusion: Vector Floorplan Generation via a Diffusion Model With Discrete and Continuous Denoising

Mohammad Amin Shabani,

Sepidehsadat Hosseini,

Yasutaka Furukawa

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Shabani_2023_CVPR, author = {Shabani, Mohammad Amin and Hosseini, Sepidehsadat and Furukawa, Yasutaka}, title = {HouseDiffusion: Vector Floorplan Generation via a Diffusion Model With Discrete and Continuous Denoising}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5466-5475} }

FedDM: Iterative Distribution Matching for Communication-Efficient Federated Learning

Yuanhao Xiong,

Ruochen Wang,

Minhao Cheng,

Felix Yu,

Cho-Jui Hsieh

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Xiong_2023_CVPR, author = {Xiong, Yuanhao and Wang, Ruochen and Cheng, Minhao and Yu, Felix and Hsieh, Cho-Jui}, title = {FedDM: Iterative Distribution Matching for Communication-Efficient Federated Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16323-16332} }

V2X-Seq: A Large-Scale Sequential Dataset for Vehicle-Infrastructure Cooperative Perception and Forecasting

Haibao Yu,

Wenxian Yang,

Hongzhi Ruan,

Zhenwei Yang,

Yingjuan Tang,

Xu Gao,

Xin Hao,

Yifeng Shi,

Yifeng Pan,

Ning Sun,

Juan Song,

Jirui Yuan,

Ping Luo,

Zaiqing Nie

[pdf] [supp]

[bibtex]

@InProceedings{Yu_2023_CVPR, author = {Yu, Haibao and Yang, Wenxian and Ruan, Hongzhi and Yang, Zhenwei and Tang, Yingjuan and Gao, Xu and Hao, Xin and Shi, Yifeng and Pan, Yifeng and Sun, Ning and Song, Juan and Yuan, Jirui and Luo, Ping and Nie, Zaiqing}, title = {V2X-Seq: A Large-Scale Sequential Dataset for Vehicle-Infrastructure Cooperative Perception and Forecasting}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5486-5495} }

PSVT: End-to-End Multi-Person 3D Pose and Shape Estimation With Progressive Video Transformers

Zhongwei Qiu,

Qiansheng Yang,

Jian Wang,

Haocheng Feng,

Junyu Han,

Errui Ding,

Chang Xu,

Dongmei Fu,

Jingdong Wang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Qiu_2023_CVPR, author = {Qiu, Zhongwei and Yang, Qiansheng and Wang, Jian and Feng, Haocheng and Han, Junyu and Ding, Errui and Xu, Chang and Fu, Dongmei and Wang, Jingdong}, title = {PSVT: End-to-End Multi-Person 3D Pose and Shape Estimation With Progressive Video Transformers}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {21254-21263} }

Bit-Shrinking: Limiting Instantaneous Sharpness for Improving Post-Training Quantization

Chen Lin,

Bo Peng,

Zheyang Li,

Wenming Tan,

Ye Ren,

Jun Xiao,

Shiliang Pu

[pdf]

[bibtex]

@InProceedings{Lin_2023_CVPR, author = {Lin, Chen and Peng, Bo and Li, Zheyang and Tan, Wenming and Ren, Ye and Xiao, Jun and Pu, Shiliang}, title = {Bit-Shrinking: Limiting Instantaneous Sharpness for Improving Post-Training Quantization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16196-16205} }

LSTFE-Net:Long Short-Term Feature Enhancement Network for Video Small Object Detection

Jinsheng Xiao,

Yuanxu Wu,

Yunhua Chen,

Shurui Wang,

Zhongyuan Wang,

Jiayi Ma

[pdf]

[bibtex]

@InProceedings{Xiao_2023_CVPR, author = {Xiao, Jinsheng and Wu, Yuanxu and Chen, Yunhua and Wang, Shurui and Wang, Zhongyuan and Ma, Jiayi}, title = {LSTFE-Net:Long Short-Term Feature Enhancement Network for Video Small Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14613-14622} }

MIC: Masked Image Consistency for Context-Enhanced Domain Adaptation

Lukas Hoyer,

Dengxin Dai,

Haoran Wang,

Luc Van Gool

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Hoyer_2023_CVPR, author = {Hoyer, Lukas and Dai, Dengxin and Wang, Haoran and Van Gool, Luc}, title = {MIC: Masked Image Consistency for Context-Enhanced Domain Adaptation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11721-11732} }

Bridging the Gap Between Model Explanations in Partially Annotated Multi-Label Classification

Youngwook Kim,

Jae Myung Kim,

Jieun Jeong,

Cordelia Schmid,

Zeynep Akata,

Jungwoo Lee

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Kim_2023_CVPR, author = {Kim, Youngwook and Kim, Jae Myung and Jeong, Jieun and Schmid, Cordelia and Akata, Zeynep and Lee, Jungwoo}, title = {Bridging the Gap Between Model Explanations in Partially Annotated Multi-Label Classification}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3408-3417} }

SkyEye: Self-Supervised Bird's-Eye-View Semantic Mapping Using Monocular Frontal View Images

Nikhil Gosala,

Kürsat Petek,

Paulo L. J. Drews-Jr,

Wolfram Burgard,

Abhinav Valada

[pdf] [supp]

[bibtex]

@InProceedings{Gosala_2023_CVPR, author = {Gosala, Nikhil and Petek, K\"ursat and Drews-Jr, Paulo L. J. and Burgard, Wolfram and Valada, Abhinav}, title = {SkyEye: Self-Supervised Bird's-Eye-View Semantic Mapping Using Monocular Frontal View Images}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14901-14910} }

Unifying Vision, Text, and Layout for Universal Document Processing

Zineng Tang,

Ziyi Yang,

Guoxin Wang,

Yuwei Fang,

Yang Liu,

Chenguang Zhu,

Michael Zeng,

Cha Zhang,

Mohit Bansal

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Tang_2023_CVPR, author = {Tang, Zineng and Yang, Ziyi and Wang, Guoxin and Fang, Yuwei and Liu, Yang and Zhu, Chenguang and Zeng, Michael and Zhang, Cha and Bansal, Mohit}, title = {Unifying Vision, Text, and Layout for Universal Document Processing}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {19254-19264} }

SparsePose: Sparse-View Camera Pose Regression and Refinement

Samarth Sinha,

Jason Y. Zhang,

Andrea Tagliasacchi,

Igor Gilitschenski,

David B. Lindell

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Sinha_2023_CVPR, author = {Sinha, Samarth and Zhang, Jason Y. and Tagliasacchi, Andrea and Gilitschenski, Igor and Lindell, David B.}, title = {SparsePose: Sparse-View Camera Pose Regression and Refinement}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {21349-21359} }

Learning Audio-Visual Source Localization via False Negative Aware Contrastive Learning

Weixuan Sun,

Jiayi Zhang,

Jianyuan Wang,

Zheyuan Liu,

Yiran Zhong,

Tianpeng Feng,

Yandong Guo,

Yanhao Zhang,

Nick Barnes

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Sun_2023_CVPR, author = {Sun, Weixuan and Zhang, Jiayi and Wang, Jianyuan and Liu, Zheyuan and Zhong, Yiran and Feng, Tianpeng and Guo, Yandong and Zhang, Yanhao and Barnes, Nick}, title = {Learning Audio-Visual Source Localization via False Negative Aware Contrastive Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6420-6429} }

VoxFormer: Sparse Voxel Transformer for Camera-Based 3D Semantic Scene Completion

Yiming Li,

Zhiding Yu,

Christopher Choy,

Chaowei Xiao,

Jose M. Alvarez,

Sanja Fidler,

Chen Feng,

Anima Anandkumar

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Li_2023_CVPR, author = {Li, Yiming and Yu, Zhiding and Choy, Christopher and Xiao, Chaowei and Alvarez, Jose M. and Fidler, Sanja and Feng, Chen and Anandkumar, Anima}, title = {VoxFormer: Sparse Voxel Transformer for Camera-Based 3D Semantic Scene Completion}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9087-9098} }

Joint Video Multi-Frame Interpolation and Deblurring Under Unknown Exposure Time

Wei Shang,

Dongwei Ren,

Yi Yang,

Hongzhi Zhang,

Kede Ma,

Wangmeng Zuo

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Shang_2023_CVPR, author = {Shang, Wei and Ren, Dongwei and Yang, Yi and Zhang, Hongzhi and Ma, Kede and Zuo, Wangmeng}, title = {Joint Video Multi-Frame Interpolation and Deblurring Under Unknown Exposure Time}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13935-13944} }

Flow Supervision for Deformable NeRF

Chaoyang Wang,

Lachlan Ewen MacDonald,

László A. Jeni,

Simon Lucey

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Chaoyang and MacDonald, Lachlan Ewen and Jeni, L\'aszl\'o A. and Lucey, Simon}, title = {Flow Supervision for Deformable NeRF}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {21128-21137} }

MMG-Ego4D: Multimodal Generalization in Egocentric Action Recognition

Xinyu Gong,

Sreyas Mohan,

Naina Dhingra,

Jean-Charles Bazin,

Yilei Li,

Zhangyang Wang,

Rakesh Ranjan

[pdf] [supp]

[bibtex]

@InProceedings{Gong_2023_CVPR, author = {Gong, Xinyu and Mohan, Sreyas and Dhingra, Naina and Bazin, Jean-Charles and Li, Yilei and Wang, Zhangyang and Ranjan, Rakesh}, title = {MMG-Ego4D: Multimodal Generalization in Egocentric Action Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6481-6491} }

Zero-Shot Text-to-Parameter Translation for Game Character Auto-Creation

Rui Zhao,

Wei Li,

Zhipeng Hu,

Lincheng Li,

Zhengxia Zou,

Zhenwei Shi,

Changjie Fan

[pdf] [arXiv]

[bibtex]

@InProceedings{Zhao_2023_CVPR, author = {Zhao, Rui and Li, Wei and Hu, Zhipeng and Li, Lincheng and Zou, Zhengxia and Shi, Zhenwei and Fan, Changjie}, title = {Zero-Shot Text-to-Parameter Translation for Game Character Auto-Creation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {21013-21023} }

PIVOT: Prompting for Video Continual Learning

Andrés Villa,

Juan León Alcázar,

Motasem Alfarra,

Kumail Alhamoud,

Julio Hurtado,

Fabian Caba Heilbron,

Alvaro Soto,

Bernard Ghanem

[pdf] [supp]

[bibtex]

@InProceedings{Villa_2023_CVPR, author = {Villa, Andr\'es and Alc\'azar, Juan Le\'on and Alfarra, Motasem and Alhamoud, Kumail and Hurtado, Julio and Heilbron, Fabian Caba and Soto, Alvaro and Ghanem, Bernard}, title = {PIVOT: Prompting for Video Continual Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {24214-24223} }

Dual-Bridging With Adversarial Noise Generation for Domain Adaptive rPPG Estimation

Jingda Du,

Si-Qi Liu,

Bochao Zhang,

Pong C. Yuen

[pdf]

[bibtex]

@InProceedings{Du_2023_CVPR, author = {Du, Jingda and Liu, Si-Qi and Zhang, Bochao and Yuen, Pong C.}, title = {Dual-Bridging With Adversarial Noise Generation for Domain Adaptive rPPG Estimation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10355-10364} }

Panoptic Video Scene Graph Generation

Jingkang Yang,

Wenxuan Peng,

Xiangtai Li,

Zujin Guo,

Liangyu Chen,

Bo Li,

Zheng Ma,

Kaiyang Zhou,

Wayne Zhang,

Chen Change Loy,

Ziwei Liu

[pdf]

[bibtex]

@InProceedings{Yang_2023_CVPR, author = {Yang, Jingkang and Peng, Wenxuan and Li, Xiangtai and Guo, Zujin and Chen, Liangyu and Li, Bo and Ma, Zheng and Zhou, Kaiyang and Zhang, Wayne and Loy, Chen Change and Liu, Ziwei}, title = {Panoptic Video Scene Graph Generation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {18675-18685} }

3D Video Object Detection With Learnable Object-Centric Global Optimization

Jiawei He,

Yuntao Chen,

Naiyan Wang,

Zhaoxiang Zhang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{He_2023_CVPR, author = {He, Jiawei and Chen, Yuntao and Wang, Naiyan and Zhang, Zhaoxiang}, title = {3D Video Object Detection With Learnable Object-Centric Global Optimization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5106-5115} }

Improving the Transferability of Adversarial Samples by Path-Augmented Method

Jianping Zhang,

Jen-tse Huang,

Wenxuan Wang,

Yichen Li,

Weibin Wu,

Xiaosen Wang,

Yuxin Su,

Michael R. Lyu

[pdf] [arXiv]

[bibtex]

@InProceedings{Zhang_2023_CVPR, author = {Zhang, Jianping and Huang, Jen-tse and Wang, Wenxuan and Li, Yichen and Wu, Weibin and Wang, Xiaosen and Su, Yuxin and Lyu, Michael R.}, title = {Improving the Transferability of Adversarial Samples by Path-Augmented Method}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8173-8182} }

Robust Mean Teacher for Continual and Gradual Test-Time Adaptation

Mario Döbler,

Robert A. Marsden,

Bin Yang

[pdf] [supp]

[bibtex]

@InProceedings{Dobler_2023_CVPR, author = {D\"obler, Mario and Marsden, Robert A. and Yang, Bin}, title = {Robust Mean Teacher for Continual and Gradual Test-Time Adaptation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7704-7714} }

Understanding Imbalanced Semantic Segmentation Through Neural Collapse

Zhisheng Zhong,

Jiequan Cui,

Yibo Yang,

Xiaoyang Wu,

Xiaojuan Qi,

Xiangyu Zhang,

Jiaya Jia

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Zhong_2023_CVPR, author = {Zhong, Zhisheng and Cui, Jiequan and Yang, Yibo and Wu, Xiaoyang and Qi, Xiaojuan and Zhang, Xiangyu and Jia, Jiaya}, title = {Understanding Imbalanced Semantic Segmentation Through Neural Collapse}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {19550-19560} }

MOVES: Manipulated Objects in Video Enable Segmentation

Richard E. L. Higgins,

David F. Fouhey

[pdf]

[bibtex]

@InProceedings{Higgins_2023_CVPR, author = {Higgins, Richard E. L. and Fouhey, David F.}, title = {MOVES: Manipulated Objects in Video Enable Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6334-6343} }

Generating Holistic 3D Human Motion From Speech

Hongwei Yi,

Hualin Liang,

Yifei Liu,

Qiong Cao,

Yandong Wen,

Timo Bolkart,

Dacheng Tao,

Michael J. Black

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Yi_2023_CVPR, author = {Yi, Hongwei and Liang, Hualin and Liu, Yifei and Cao, Qiong and Wen, Yandong and Bolkart, Timo and Tao, Dacheng and Black, Michael J.}, title = {Generating Holistic 3D Human Motion From Speech}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {469-480} }

NeuDA: Neural Deformable Anchor for High-Fidelity Implicit Surface Reconstruction

Bowen Cai,

Jinchi Huang,

Rongfei Jia,

Chengfei Lv,

Huan Fu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Cai_2023_CVPR, author = {Cai, Bowen and Huang, Jinchi and Jia, Rongfei and Lv, Chengfei and Fu, Huan}, title = {NeuDA: Neural Deformable Anchor for High-Fidelity Implicit Surface Reconstruction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8476-8485} }

HOICLIP: Efficient Knowledge Transfer for HOI Detection With Vision-Language Models

Shan Ning,

Longtian Qiu,

Yongfei Liu,

Xuming He

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Ning_2023_CVPR, author = {Ning, Shan and Qiu, Longtian and Liu, Yongfei and He, Xuming}, title = {HOICLIP: Efficient Knowledge Transfer for HOI Detection With Vision-Language Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {23507-23517} }

ShadowNeuS: Neural SDF Reconstruction by Shadow Ray Supervision

Jingwang Ling,

Zhibo Wang,

Feng Xu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Ling_2023_CVPR, author = {Ling, Jingwang and Wang, Zhibo and Xu, Feng}, title = {ShadowNeuS: Neural SDF Reconstruction by Shadow Ray Supervision}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {175-185} }

Generalized UAV Object Detection via Frequency Domain Disentanglement

Kunyu Wang,

Xueyang Fu,

Yukun Huang,

Chengzhi Cao,

Gege Shi,

Zheng-Jun Zha

[pdf] [supp]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Kunyu and Fu, Xueyang and Huang, Yukun and Cao, Chengzhi and Shi, Gege and Zha, Zheng-Jun}, title = {Generalized UAV Object Detection via Frequency Domain Disentanglement}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1064-1073} }

Boosting Weakly-Supervised Temporal Action Localization With Text Information

Guozhang Li,

De Cheng,

Xinpeng Ding,

Nannan Wang,

Xiaoyu Wang,

Xinbo Gao

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Li_2023_CVPR, author = {Li, Guozhang and Cheng, De and Ding, Xinpeng and Wang, Nannan and Wang, Xiaoyu and Gao, Xinbo}, title = {Boosting Weakly-Supervised Temporal Action Localization With Text Information}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10648-10657} }

DINER: Disorder-Invariant Implicit Neural Representation

Shaowen Xie,

Hao Zhu,

Zhen Liu,

Qi Zhang,

You Zhou,

Xun Cao,

Zhan Ma

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Xie_2023_CVPR, author = {Xie, Shaowen and Zhu, Hao and Liu, Zhen and Zhang, Qi and Zhou, You and Cao, Xun and Ma, Zhan}, title = {DINER: Disorder-Invariant Implicit Neural Representation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6143-6152} }

A Light Touch Approach to Teaching Transformers Multi-View Geometry

Yash Bhalgat,

João F. Henriques,

Andrew Zisserman

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Bhalgat_2023_CVPR, author = {Bhalgat, Yash and Henriques, Jo\~ao F. and Zisserman, Andrew}, title = {A Light Touch Approach to Teaching Transformers Multi-View Geometry}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4958-4969} }

Trade-Off Between Robustness and Accuracy of Vision Transformers

Yanxi Li,

Chang Xu

[pdf] [supp]

[bibtex]

@InProceedings{Li_2023_CVPR, author = {Li, Yanxi and Xu, Chang}, title = {Trade-Off Between Robustness and Accuracy of Vision Transformers}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7558-7568} }

Focused and Collaborative Feedback Integration for Interactive Image Segmentation

Qiaoqiao Wei,

Hui Zhang,

Jun-Hai Yong

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Wei_2023_CVPR, author = {Wei, Qiaoqiao and Zhang, Hui and Yong, Jun-Hai}, title = {Focused and Collaborative Feedback Integration for Interactive Image Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {18643-18652} }

Class Prototypes Based Contrastive Learning for Classifying Multi-Label and Fine-Grained Educational Videos

Rohit Gupta,

Anirban Roy,

Claire Christensen,

Sujeong Kim,

Sarah Gerard,

Madeline Cincebeaux,

Ajay Divakaran,

Todd Grindal,

Mubarak Shah

[pdf] [supp]

[bibtex]

@InProceedings{Gupta_2023_CVPR, author = {Gupta, Rohit and Roy, Anirban and Christensen, Claire and Kim, Sujeong and Gerard, Sarah and Cincebeaux, Madeline and Divakaran, Ajay and Grindal, Todd and Shah, Mubarak}, title = {Class Prototypes Based Contrastive Learning for Classifying Multi-Label and Fine-Grained Educational Videos}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {19923-19933} }

Deep Graph-Based Spatial Consistency for Robust Non-Rigid Point Cloud Registration

Zheng Qin,

Hao Yu,

Changjian Wang,

Yuxing Peng,

Kai Xu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Qin_2023_CVPR, author = {Qin, Zheng and Yu, Hao and Wang, Changjian and Peng, Yuxing and Xu, Kai}, title = {Deep Graph-Based Spatial Consistency for Robust Non-Rigid Point Cloud Registration}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5394-5403} }

Source-Free Adaptive Gaze Estimation by Uncertainty Reduction

Xin Cai,

Jiabei Zeng,

Shiguang Shan,

Xilin Chen

[pdf] [supp]

[bibtex]

@InProceedings{Cai_2023_CVPR, author = {Cai, Xin and Zeng, Jiabei and Shan, Shiguang and Chen, Xilin}, title = {Source-Free Adaptive Gaze Estimation by Uncertainty Reduction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {22035-22045} }

Slide-Transformer: Hierarchical Vision Transformer With Local Self-Attention

Xuran Pan,

Tianzhu Ye,

Zhuofan Xia,

Shiji Song,

Gao Huang

[pdf] [supp]

[bibtex]

@InProceedings{Pan_2023_CVPR, author = {Pan, Xuran and Ye, Tianzhu and Xia, Zhuofan and Song, Shiji and Huang, Gao}, title = {Slide-Transformer: Hierarchical Vision Transformer With Local Self-Attention}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2082-2091} }

NeRF-Supervised Deep Stereo

Fabio Tosi,

Alessio Tonioni,

Daniele De Gregorio,

Matteo Poggi

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Tosi_2023_CVPR, author = {Tosi, Fabio and Tonioni, Alessio and De Gregorio, Daniele and Poggi, Matteo}, title = {NeRF-Supervised Deep Stereo}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {855-866} }

Decoupled Multimodal Distilling for Emotion Recognition

Yong Li,

Yuanzhi Wang,

Zhen Cui

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Li_2023_CVPR, author = {Li, Yong and Wang, Yuanzhi and Cui, Zhen}, title = {Decoupled Multimodal Distilling for Emotion Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6631-6640} }

SuperDisco: Super-Class Discovery Improves Visual Recognition for the Long-Tail

Yingjun Du,

Jiayi Shen,

Xiantong Zhen,

Cees G. M. Snoek

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Du_2023_CVPR, author = {Du, Yingjun and Shen, Jiayi and Zhen, Xiantong and Snoek, Cees G. M.}, title = {SuperDisco: Super-Class Discovery Improves Visual Recognition for the Long-Tail}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {19944-19954} }

DualRefine: Self-Supervised Depth and Pose Estimation Through Iterative Epipolar Sampling and Refinement Toward Equilibrium

Antyanta Bangunharcana,

Ahmed Magd,

Kyung-Soo Kim

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Bangunharcana_2023_CVPR, author = {Bangunharcana, Antyanta and Magd, Ahmed and Kim, Kyung-Soo}, title = {DualRefine: Self-Supervised Depth and Pose Estimation Through Iterative Epipolar Sampling and Refinement Toward Equilibrium}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {726-738} }

Improving Generalization of Meta-Learning With Inverted Regularization at Inner-Level

Lianzhe Wang,

Shiji Zhou,

Shanghang Zhang,

Xu Chu,

Heng Chang,

Wenwu Zhu

[pdf] [supp]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Lianzhe and Zhou, Shiji and Zhang, Shanghang and Chu, Xu and Chang, Heng and Zhu, Wenwu}, title = {Improving Generalization of Meta-Learning With Inverted Regularization at Inner-Level}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7826-7835} }

SmallCap: Lightweight Image Captioning Prompted With Retrieval Augmentation

Rita Ramos,

Bruno Martins,

Desmond Elliott,

Yova Kementchedjhieva

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Ramos_2023_CVPR, author = {Ramos, Rita and Martins, Bruno and Elliott, Desmond and Kementchedjhieva, Yova}, title = {SmallCap: Lightweight Image Captioning Prompted With Retrieval Augmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2840-2849} }

Unifying Layout Generation With a Decoupled Diffusion Model

Mude Hui,

Zhizheng Zhang,

Xiaoyi Zhang,

Wenxuan Xie,

Yuwang Wang,

Yan Lu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Hui_2023_CVPR, author = {Hui, Mude and Zhang, Zhizheng and Zhang, Xiaoyi and Xie, Wenxuan and Wang, Yuwang and Lu, Yan}, title = {Unifying Layout Generation With a Decoupled Diffusion Model}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1942-1951} }

Im2Hands: Learning Attentive Implicit Representation of Interacting Two-Hand Shapes

Jihyun Lee,

Minhyuk Sung,

Honggyu Choi,

Tae-Kyun Kim

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Lee_2023_CVPR, author = {Lee, Jihyun and Sung, Minhyuk and Choi, Honggyu and Kim, Tae-Kyun}, title = {Im2Hands: Learning Attentive Implicit Representation of Interacting Two-Hand Shapes}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {21169-21178} }

Long-Term Visual Localization With Mobile Sensors

Shen Yan,

Yu Liu,

Long Wang,

Zehong Shen,

Zhen Peng,

Haomin Liu,

Maojun Zhang,

Guofeng Zhang,

Xiaowei Zhou

[pdf] [arXiv]

[bibtex]

@InProceedings{Yan_2023_CVPR, author = {Yan, Shen and Liu, Yu and Wang, Long and Shen, Zehong and Peng, Zhen and Liu, Haomin and Zhang, Maojun and Zhang, Guofeng and Zhou, Xiaowei}, title = {Long-Term Visual Localization With Mobile Sensors}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {17245-17255} }

Data-Efficient Large Scale Place Recognition With Graded Similarity Supervision

María Leyva-Vallina,

Nicola Strisciuglio,

Nicolai Petkov

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Leyva-Vallina_2023_CVPR, author = {Leyva-Vallina, Mar{\'\i}a and Strisciuglio, Nicola and Petkov, Nicolai}, title = {Data-Efficient Large Scale Place Recognition With Graded Similarity Supervision}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {23487-23496} }

Dynamic Neural Network for Multi-Task Learning Searching Across Diverse Network Topologies

Wonhyeok Choi,

Sunghoon Im

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Choi_2023_CVPR, author = {Choi, Wonhyeok and Im, Sunghoon}, title = {Dynamic Neural Network for Multi-Task Learning Searching Across Diverse Network Topologies}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3779-3788} }

Relightable Neural Human Assets From Multi-View Gradient Illuminations

Taotao Zhou,

Kai He,

Di Wu,

Teng Xu,

Qixuan Zhang,

Kuixiang Shao,

Wenzheng Chen,

Lan Xu,

Jingyi Yu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Zhou_2023_CVPR, author = {Zhou, Taotao and He, Kai and Wu, Di and Xu, Teng and Zhang, Qixuan and Shao, Kuixiang and Chen, Wenzheng and Xu, Lan and Yu, Jingyi}, title = {Relightable Neural Human Assets From Multi-View Gradient Illuminations}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4315-4327} }

Probing Sentiment-Oriented Pre-Training Inspired by Human Sentiment Perception Mechanism

Tinglei Feng,

Jiaxuan Liu,

Jufeng Yang

[pdf]

[bibtex]

@InProceedings{Feng_2023_CVPR, author = {Feng, Tinglei and Liu, Jiaxuan and Yang, Jufeng}, title = {Probing Sentiment-Oriented Pre-Training Inspired by Human Sentiment Perception Mechanism}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2850-2860} }

Imitation Learning As State Matching via Differentiable Physics

Siwei Chen,

Xiao Ma,

Zhongwen Xu

[pdf] [supp]

[bibtex]

@InProceedings{Chen_2023_CVPR, author = {Chen, Siwei and Ma, Xiao and Xu, Zhongwen}, title = {Imitation Learning As State Matching via Differentiable Physics}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7846-7855} }

OpenMix: Exploring Outlier Samples for Misclassification Detection

Fei Zhu,

Zhen Cheng,

Xu-Yao Zhang,

Cheng-Lin Liu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Zhu_2023_CVPR, author = {Zhu, Fei and Cheng, Zhen and Zhang, Xu-Yao and Liu, Cheng-Lin}, title = {OpenMix: Exploring Outlier Samples for Misclassification Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12074-12083} }

Multivariate, Multi-Frequency and Multimodal: Rethinking Graph Neural Networks for Emotion Recognition in Conversation

Feiyu Chen,

Jie Shao,

Shuyuan Zhu,

Heng Tao Shen

[pdf] [supp]

[bibtex]

@InProceedings{Chen_2023_CVPR, author = {Chen, Feiyu and Shao, Jie and Zhu, Shuyuan and Shen, Heng Tao}, title = {Multivariate, Multi-Frequency and Multimodal: Rethinking Graph Neural Networks for Emotion Recognition in Conversation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10761-10770} }

Weakly Supervised Class-Agnostic Motion Prediction for Autonomous Driving

Ruibo Li,

Hanyu Shi,

Ziang Fu,

Zhe Wang,

Guosheng Lin

[pdf] [supp]

[bibtex]

@InProceedings{Li_2023_CVPR, author = {Li, Ruibo and Shi, Hanyu and Fu, Ziang and Wang, Zhe and Lin, Guosheng}, title = {Weakly Supervised Class-Agnostic Motion Prediction for Autonomous Driving}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {17599-17608} }

TOPLight: Lightweight Neural Networks With Task-Oriented Pretraining for Visible-Infrared Recognition

Hao Yu,

Xu Cheng,

Wei Peng

[pdf] [supp]

[bibtex]

@InProceedings{Yu_2023_CVPR, author = {Yu, Hao and Cheng, Xu and Peng, Wei}, title = {TOPLight: Lightweight Neural Networks With Task-Oriented Pretraining for Visible-Infrared Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3541-3550} }

DeFeeNet: Consecutive 3D Human Motion Prediction With Deviation Feedback

Xiaoning Sun,

Huaijiang Sun,

Bin Li,

Dong Wei,

Weiqing Li,

Jianfeng Lu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Sun_2023_CVPR, author = {Sun, Xiaoning and Sun, Huaijiang and Li, Bin and Wei, Dong and Li, Weiqing and Lu, Jianfeng}, title = {DeFeeNet: Consecutive 3D Human Motion Prediction With Deviation Feedback}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5527-5536} }

Where We Are and What We're Looking At: Query Based Worldwide Image Geo-Localization Using Hierarchies and Scenes

Brandon Clark,

Alec Kerrigan,

Parth Parag Kulkarni,

Vicente Vivanco Cepeda,

Mubarak Shah

[pdf] [supp]

[bibtex]

@InProceedings{Clark_2023_CVPR, author = {Clark, Brandon and Kerrigan, Alec and Kulkarni, Parth Parag and Cepeda, Vicente Vivanco and Shah, Mubarak}, title = {Where We Are and What We're Looking At: Query Based Worldwide Image Geo-Localization Using Hierarchies and Scenes}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {23182-23190} }

Bridging Precision and Confidence: A Train-Time Loss for Calibrating Object Detection

Muhammad Akhtar Munir,

Muhammad Haris Khan,

Salman Khan,

Fahad Shahbaz Khan

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Munir_2023_CVPR, author = {Munir, Muhammad Akhtar and Khan, Muhammad Haris and Khan, Salman and Khan, Fahad Shahbaz}, title = {Bridging Precision and Confidence: A Train-Time Loss for Calibrating Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11474-11483} }

DyLiN: Making Light Field Networks Dynamic

Heng Yu,

Joel Julin,

Zoltán Á. Milacski,

Koichiro Niinuma,

László A. Jeni

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Yu_2023_CVPR, author = {Yu, Heng and Julin, Joel and Milacski, Zolt\'an \'A. and Niinuma, Koichiro and Jeni, L\'aszl\'o A.}, title = {DyLiN: Making Light Field Networks Dynamic}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12397-12406} }

Critical Learning Periods for Multisensory Integration in Deep Networks

Michael Kleinman,

Alessandro Achille,

Stefano Soatto

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Kleinman_2023_CVPR, author = {Kleinman, Michael and Achille, Alessandro and Soatto, Stefano}, title = {Critical Learning Periods for Multisensory Integration in Deep Networks}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {24296-24305} }

Human Guided Ground-Truth Generation for Realistic Image Super-Resolution

Du Chen,

Jie Liang,

Xindong Zhang,

Ming Liu,

Hui Zeng,

Lei Zhang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Chen_2023_CVPR, author = {Chen, Du and Liang, Jie and Zhang, Xindong and Liu, Ming and Zeng, Hui and Zhang, Lei}, title = {Human Guided Ground-Truth Generation for Realistic Image Super-Resolution}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14082-14091} }

GarmentTracking: Category-Level Garment Pose Tracking

Han Xue,

Wenqiang Xu,

Jieyi Zhang,

Tutian Tang,

Yutong Li,

Wenxin Du,

Ruolin Ye,

Cewu Lu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Xue_2023_CVPR, author = {Xue, Han and Xu, Wenqiang and Zhang, Jieyi and Tang, Tutian and Li, Yutong and Du, Wenxin and Ye, Ruolin and Lu, Cewu}, title = {GarmentTracking: Category-Level Garment Pose Tracking}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {21233-21242} }

Mask DINO: Towards a Unified Transformer-Based Framework for Object Detection and Segmentation

Feng Li,

Hao Zhang,

Huaizhe Xu,

Shilong Liu,

Lei Zhang,

Lionel M. Ni,

Heung-Yeung Shum

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Li_2023_CVPR, author = {Li, Feng and Zhang, Hao and Xu, Huaizhe and Liu, Shilong and Zhang, Lei and Ni, Lionel M. and Shum, Heung-Yeung}, title = {Mask DINO: Towards a Unified Transformer-Based Framework for Object Detection and Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3041-3050} }

Align and Attend: Multimodal Summarization With Dual Contrastive Losses

Bo He,

Jun Wang,

Jielin Qiu,

Trung Bui,

Abhinav Shrivastava,

Zhaowen Wang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{He_2023_CVPR, author = {He, Bo and Wang, Jun and Qiu, Jielin and Bui, Trung and Shrivastava, Abhinav and Wang, Zhaowen}, title = {Align and Attend: Multimodal Summarization With Dual Contrastive Losses}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14867-14878} }

SinGRAF: Learning a 3D Generative Radiance Field for a Single Scene

Minjung Son,

Jeong Joon Park,

Leonidas Guibas,

Gordon Wetzstein

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Son_2023_CVPR, author = {Son, Minjung and Park, Jeong Joon and Guibas, Leonidas and Wetzstein, Gordon}, title = {SinGRAF: Learning a 3D Generative Radiance Field for a Single Scene}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8507-8517} }

Self-Supervised AutoFlow

Hsin-Ping Huang,

Charles Herrmann,

Junhwa Hur,

Erika Lu,

Kyle Sargent,

Austin Stone,

Ming-Hsuan Yang,

Deqing Sun

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Huang_2023_CVPR, author = {Huang, Hsin-Ping and Herrmann, Charles and Hur, Junhwa and Lu, Erika and Sargent, Kyle and Stone, Austin and Yang, Ming-Hsuan and Sun, Deqing}, title = {Self-Supervised AutoFlow}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11412-11421} }

MagicNet: Semi-Supervised Multi-Organ Segmentation via Magic-Cube Partition and Recovery

Duowen Chen,

Yunhao Bai,

Wei Shen,

Qingli Li,

Lequan Yu,

Yan Wang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Chen_2023_CVPR, author = {Chen, Duowen and Bai, Yunhao and Shen, Wei and Li, Qingli and Yu, Lequan and Wang, Yan}, title = {MagicNet: Semi-Supervised Multi-Organ Segmentation via Magic-Cube Partition and Recovery}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {23869-23878} }

Neuralangelo: High-Fidelity Neural Surface Reconstruction

Zhaoshuo Li,

Thomas Müller,

Alex Evans,

Russell H. Taylor,

Mathias Unberath,

Ming-Yu Liu,

Chen-Hsuan Lin

[pdf] [supp]

[bibtex]

@InProceedings{Li_2023_CVPR, author = {Li, Zhaoshuo and M\"uller, Thomas and Evans, Alex and Taylor, Russell H. and Unberath, Mathias and Liu, Ming-Yu and Lin, Chen-Hsuan}, title = {Neuralangelo: High-Fidelity Neural Surface Reconstruction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8456-8465} }

Re-GAN: Data-Efficient GANs Training via Architectural Reconfiguration

Divya Saxena,

Jiannong Cao,

Jiahao Xu,

Tarun Kulshrestha

[pdf] [supp]

[bibtex]

@InProceedings{Saxena_2023_CVPR, author = {Saxena, Divya and Cao, Jiannong and Xu, Jiahao and Kulshrestha, Tarun}, title = {Re-GAN: Data-Efficient GANs Training via Architectural Reconfiguration}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16230-16240} }

Dimensionality-Varying Diffusion Process

Han Zhang,

Ruili Feng,

Zhantao Yang,

Lianghua Huang,

Yu Liu,

Yifei Zhang,

Yujun Shen,

Deli Zhao,

Jingren Zhou,

Fan Cheng

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Zhang_2023_CVPR, author = {Zhang, Han and Feng, Ruili and Yang, Zhantao and Huang, Lianghua and Liu, Yu and Zhang, Yifei and Shen, Yujun and Zhao, Deli and Zhou, Jingren and Cheng, Fan}, title = {Dimensionality-Varying Diffusion Process}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14307-14316} }

FAME-ViL: Multi-Tasking Vision-Language Model for Heterogeneous Fashion Tasks

Xiao Han,

Xiatian Zhu,

Licheng Yu,

Li Zhang,

Yi-Zhe Song,

Tao Xiang

[pdf] [supp]

[bibtex]

@InProceedings{Han_2023_CVPR, author = {Han, Xiao and Zhu, Xiatian and Yu, Licheng and Zhang, Li and Song, Yi-Zhe and Xiang, Tao}, title = {FAME-ViL: Multi-Tasking Vision-Language Model for Heterogeneous Fashion Tasks}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2669-2680} }

Neural Intrinsic Embedding for Non-Rigid Point Cloud Matching

Puhua Jiang,

Mingze Sun,

Ruqi Huang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Jiang_2023_CVPR, author = {Jiang, Puhua and Sun, Mingze and Huang, Ruqi}, title = {Neural Intrinsic Embedding for Non-Rigid Point Cloud Matching}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {21835-21845} }

Rate Gradient Approximation Attack Threats Deep Spiking Neural Networks

Tong Bu,

Jianhao Ding,

Zecheng Hao,

Zhaofei Yu

[pdf] [supp]

[bibtex]

@InProceedings{Bu_2023_CVPR, author = {Bu, Tong and Ding, Jianhao and Hao, Zecheng and Yu, Zhaofei}, title = {Rate Gradient Approximation Attack Threats Deep Spiking Neural Networks}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7896-7906} }

Few-Shot Geometry-Aware Keypoint Localization

Xingzhe He,

Gaurav Bharaj,

David Ferman,

Helge Rhodin,

Pablo Garrido

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{He_2023_CVPR, author = {He, Xingzhe and Bharaj, Gaurav and Ferman, David and Rhodin, Helge and Garrido, Pablo}, title = {Few-Shot Geometry-Aware Keypoint Localization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {21337-21348} }

RenderDiffusion: Image Diffusion for 3D Reconstruction, Inpainting and Generation

Titas Anciukevičius,

Zexiang Xu,

Matthew Fisher,

Paul Henderson,

Hakan Bilen,

Niloy J. Mitra,

Paul Guerrero

[pdf] [supp]

[bibtex]

@InProceedings{Anciukevicius_2023_CVPR, author = {Anciukevi\v{c}ius, Titas and Xu, Zexiang and Fisher, Matthew and Henderson, Paul and Bilen, Hakan and Mitra, Niloy J. and Guerrero, Paul}, title = {RenderDiffusion: Image Diffusion for 3D Reconstruction, Inpainting and Generation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12608-12618} }

Adaptive Data-Free Quantization

Biao Qian,

Yang Wang,

Richang Hong,

Meng Wang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Qian_2023_CVPR, author = {Qian, Biao and Wang, Yang and Hong, Richang and Wang, Meng}, title = {Adaptive Data-Free Quantization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7960-7968} }

Neural Vector Fields: Implicit Representation by Explicit Learning

Xianghui Yang,

Guosheng Lin,

Zhenghao Chen,

Luping Zhou

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Yang_2023_CVPR, author = {Yang, Xianghui and Lin, Guosheng and Chen, Zhenghao and Zhou, Luping}, title = {Neural Vector Fields: Implicit Representation by Explicit Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16727-16738} }

Latent-NeRF for Shape-Guided Generation of 3D Shapes and Textures

Gal Metzer,

Elad Richardson,

Or Patashnik,

Raja Giryes,

Daniel Cohen-Or

[pdf] [arXiv]

[bibtex]

@InProceedings{Metzer_2023_CVPR, author = {Metzer, Gal and Richardson, Elad and Patashnik, Or and Giryes, Raja and Cohen-Or, Daniel}, title = {Latent-NeRF for Shape-Guided Generation of 3D Shapes and Textures}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12663-12673} }

Learning Generative Structure Prior for Blind Text Image Super-Resolution

Xiaoming Li,

Wangmeng Zuo,

Chen Change Loy

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Li_2023_CVPR, author = {Li, Xiaoming and Zuo, Wangmeng and Loy, Chen Change}, title = {Learning Generative Structure Prior for Blind Text Image Super-Resolution}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10103-10113} }

Overcoming the Trade-Off Between Accuracy and Plausibility in 3D Hand Shape Reconstruction

Ziwei Yu,

Chen Li,

Linlin Yang,

Xiaoxu Zheng,

Michael Bi Mi,

Gim Hee Lee,

Angela Yao

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Yu_2023_CVPR, author = {Yu, Ziwei and Li, Chen and Yang, Linlin and Zheng, Xiaoxu and Mi, Michael Bi and Lee, Gim Hee and Yao, Angela}, title = {Overcoming the Trade-Off Between Accuracy and Plausibility in 3D Hand Shape Reconstruction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {544-553} }

Open-Vocabulary Attribute Detection

María A. Bravo,

Sudhanshu Mittal,

Simon Ging,

Thomas Brox

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Bravo_2023_CVPR, author = {Bravo, Mar{\'\i}a A. and Mittal, Sudhanshu and Ging, Simon and Brox, Thomas}, title = {Open-Vocabulary Attribute Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7041-7050} }

PEFAT: Boosting Semi-Supervised Medical Image Classification via Pseudo-Loss Estimation and Feature Adversarial Training

Qingjie Zeng,

Yutong Xie,

Zilin Lu,

Yong Xia

[pdf] [supp]

[bibtex]

@InProceedings{Zeng_2023_CVPR, author = {Zeng, Qingjie and Xie, Yutong and Lu, Zilin and Xia, Yong}, title = {PEFAT: Boosting Semi-Supervised Medical Image Classification via Pseudo-Loss Estimation and Feature Adversarial Training}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15671-15680} }

TBP-Former: Learning Temporal Bird's-Eye-View Pyramid for Joint Perception and Prediction in Vision-Centric Autonomous Driving

Shaoheng Fang,

Zi Wang,

Yiqi Zhong,

Junhao Ge,

Siheng Chen

[pdf] [supp]

[bibtex]

@InProceedings{Fang_2023_CVPR, author = {Fang, Shaoheng and Wang, Zi and Zhong, Yiqi and Ge, Junhao and Chen, Siheng}, title = {TBP-Former: Learning Temporal Bird's-Eye-View Pyramid for Joint Perception and Prediction in Vision-Centric Autonomous Driving}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1368-1378} }

Ground-Truth Free Meta-Learning for Deep Compressive Sampling

Xinran Qin,

Yuhui Quan,

Tongyao Pang,

Hui Ji

[pdf] [supp]

[bibtex]

@InProceedings{Qin_2023_CVPR, author = {Qin, Xinran and Quan, Yuhui and Pang, Tongyao and Ji, Hui}, title = {Ground-Truth Free Meta-Learning for Deep Compressive Sampling}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9947-9956} }

SHS-Net: Learning Signed Hyper Surfaces for Oriented Normal Estimation of Point Clouds

Qing Li,

Huifang Feng,

Kanle Shi,

Yue Gao,

Yi Fang,

Yu-Shen Liu,

Zhizhong Han

[pdf] [supp]

[bibtex]

@InProceedings{Li_2023_CVPR, author = {Li, Qing and Feng, Huifang and Shi, Kanle and Gao, Yue and Fang, Yi and Liu, Yu-Shen and Han, Zhizhong}, title = {SHS-Net: Learning Signed Hyper Surfaces for Oriented Normal Estimation of Point Clouds}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13591-13600} }

DistractFlow: Improving Optical Flow Estimation via Realistic Distractions and Pseudo-Labeling

Jisoo Jeong,

Hong Cai,

Risheek Garrepalli,

Fatih Porikli

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Jeong_2023_CVPR, author = {Jeong, Jisoo and Cai, Hong and Garrepalli, Risheek and Porikli, Fatih}, title = {DistractFlow: Improving Optical Flow Estimation via Realistic Distractions and Pseudo-Labeling}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13691-13700} }

Test of Time: Instilling Video-Language Models With a Sense of Time

Piyush Bagad,

Makarand Tapaswi,

Cees G. M. Snoek

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Bagad_2023_CVPR, author = {Bagad, Piyush and Tapaswi, Makarand and Snoek, Cees G. M.}, title = {Test of Time: Instilling Video-Language Models With a Sense of Time}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2503-2516} }

Learning To Segment Every Referring Object Point by Point

Mengxue Qu,

Yu Wu,

Yunchao Wei,

Wu Liu,

Xiaodan Liang,

Yao Zhao

[pdf] [supp]

[bibtex]

@InProceedings{Qu_2023_CVPR, author = {Qu, Mengxue and Wu, Yu and Wei, Yunchao and Liu, Wu and Liang, Xiaodan and Zhao, Yao}, title = {Learning To Segment Every Referring Object Point by Point}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3021-3030} }

Seeing With Sound: Long-range Acoustic Beamforming for Multimodal Scene Understanding

Praneeth Chakravarthula,

Jim Aldon D’Souza,

Ethan Tseng,

Joe Bartusek,

Felix Heide

[pdf] [supp]

[bibtex]

@InProceedings{Chakravarthula_2023_CVPR, author = {Chakravarthula, Praneeth and D{\textquoteright}Souza, Jim Aldon and Tseng, Ethan and Bartusek, Joe and Heide, Felix}, title = {Seeing With Sound: Long-range Acoustic Beamforming for Multimodal Scene Understanding}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {982-991} }

OpenScene: 3D Scene Understanding With Open Vocabularies

Songyou Peng,

Kyle Genova,

Chiyu “Max” Jiang,

Andrea Tagliasacchi,

Marc Pollefeys,

Thomas Funkhouser

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Peng_2023_CVPR, author = {Peng, Songyou and Genova, Kyle and Jiang, Chiyu {\textquotedblleft}Max{\textquotedblright} and Tagliasacchi, Andrea and Pollefeys, Marc and Funkhouser, Thomas}, title = {OpenScene: 3D Scene Understanding With Open Vocabularies}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {815-824} }

Movies2Scenes: Using Movie Metadata To Learn Scene Representation

Shixing Chen,

Chun-Hao Liu,

Xiang Hao,

Xiaohan Nie,

Maxim Arap,

Raffay Hamid

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Chen_2023_CVPR, author = {Chen, Shixing and Liu, Chun-Hao and Hao, Xiang and Nie, Xiaohan and Arap, Maxim and Hamid, Raffay}, title = {Movies2Scenes: Using Movie Metadata To Learn Scene Representation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6535-6544} }

Think Twice Before Driving: Towards Scalable Decoders for End-to-End Autonomous Driving

Xiaosong Jia,

Penghao Wu,

Li Chen,

Jiangwei Xie,

Conghui He,

Junchi Yan,

Hongyang Li

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Jia_2023_CVPR, author = {Jia, Xiaosong and Wu, Penghao and Chen, Li and Xie, Jiangwei and He, Conghui and Yan, Junchi and Li, Hongyang}, title = {Think Twice Before Driving: Towards Scalable Decoders for End-to-End Autonomous Driving}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {21983-21994} }

DSVT: Dynamic Sparse Voxel Transformer With Rotated Sets

Haiyang Wang,

Chen Shi,

Shaoshuai Shi,

Meng Lei,

Sen Wang,

Di He,

Bernt Schiele,

Liwei Wang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Haiyang and Shi, Chen and Shi, Shaoshuai and Lei, Meng and Wang, Sen and He, Di and Schiele, Bernt and Wang, Liwei}, title = {DSVT: Dynamic Sparse Voxel Transformer With Rotated Sets}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13520-13529} }

Joint Token Pruning and Squeezing Towards More Aggressive Compression of Vision Transformers

Siyuan Wei,

Tianzhu Ye,

Shen Zhang,

Yao Tang,

Jiajun Liang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Wei_2023_CVPR, author = {Wei, Siyuan and Ye, Tianzhu and Zhang, Shen and Tang, Yao and Liang, Jiajun}, title = {Joint Token Pruning and Squeezing Towards More Aggressive Compression of Vision Transformers}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2092-2101} }

Enhancing the Self-Universality for Transferable Targeted Attacks

Zhipeng Wei,

Jingjing Chen,

Zuxuan Wu,

Yu-Gang Jiang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Wei_2023_CVPR, author = {Wei, Zhipeng and Chen, Jingjing and Wu, Zuxuan and Jiang, Yu-Gang}, title = {Enhancing the Self-Universality for Transferable Targeted Attacks}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12281-12290} }

Disentangling Orthogonal Planes for Indoor Panoramic Room Layout Estimation With Cross-Scale Distortion Awareness

Zhijie Shen,

Zishuo Zheng,

Chunyu Lin,

Lang Nie,

Kang Liao,

Shuai Zheng,

Yao Zhao

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Shen_2023_CVPR, author = {Shen, Zhijie and Zheng, Zishuo and Lin, Chunyu and Nie, Lang and Liao, Kang and Zheng, Shuai and Zhao, Yao}, title = {Disentangling Orthogonal Planes for Indoor Panoramic Room Layout Estimation With Cross-Scale Distortion Awareness}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {17337-17345} }

EditableNeRF: Editing Topologically Varying Neural Radiance Fields by Key Points

Chengwei Zheng,

Wenbin Lin,

Feng Xu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Zheng_2023_CVPR, author = {Zheng, Chengwei and Lin, Wenbin and Xu, Feng}, title = {EditableNeRF: Editing Topologically Varying Neural Radiance Fields by Key Points}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8317-8327} }

Neural Map Prior for Autonomous Driving

Xuan Xiong,

Yicheng Liu,

Tianyuan Yuan,

Yue Wang,

Yilun Wang,

Hang Zhao

[pdf] [arXiv]

[bibtex]

@InProceedings{Xiong_2023_CVPR, author = {Xiong, Xuan and Liu, Yicheng and Yuan, Tianyuan and Wang, Yue and Wang, Yilun and Zhao, Hang}, title = {Neural Map Prior for Autonomous Driving}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {17535-17544} }

Solving Oscillation Problem in Post-Training Quantization Through a Theoretical Perspective

Yuexiao Ma,

Huixia Li,

Xiawu Zheng,

Xuefeng Xiao,

Rui Wang,

Shilei Wen,

Xin Pan,

Fei Chao,

Rongrong Ji

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Ma_2023_CVPR, author = {Ma, Yuexiao and Li, Huixia and Zheng, Xiawu and Xiao, Xuefeng and Wang, Rui and Wen, Shilei and Pan, Xin and Chao, Fei and Ji, Rongrong}, title = {Solving Oscillation Problem in Post-Training Quantization Through a Theoretical Perspective}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7950-7959} }

PEAL: Prior-Embedded Explicit Attention Learning for Low-Overlap Point Cloud Registration

Junle Yu,

Luwei Ren,

Yu Zhang,

Wenhui Zhou,

Lili Lin,

Guojun Dai

[pdf]

[bibtex]

@InProceedings{Yu_2023_CVPR, author = {Yu, Junle and Ren, Luwei and Zhang, Yu and Zhou, Wenhui and Lin, Lili and Dai, Guojun}, title = {PEAL: Prior-Embedded Explicit Attention Learning for Low-Overlap Point Cloud Registration}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {17702-17711} }

NeuralEditor: Editing Neural Radiance Fields via Manipulating Point Clouds

Jun-Kun Chen,

Jipeng Lyu,

Yu-Xiong Wang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Chen_2023_CVPR, author = {Chen, Jun-Kun and Lyu, Jipeng and Wang, Yu-Xiong}, title = {NeuralEditor: Editing Neural Radiance Fields via Manipulating Point Clouds}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12439-12448} }

NIKI: Neural Inverse Kinematics With Invertible Neural Networks for 3D Human Pose and Shape Estimation

Jiefeng Li,

Siyuan Bian,

Qi Liu,

Jiasheng Tang,

Fan Wang,

Cewu Lu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Li_2023_CVPR, author = {Li, Jiefeng and Bian, Siyuan and Liu, Qi and Tang, Jiasheng and Wang, Fan and Lu, Cewu}, title = {NIKI: Neural Inverse Kinematics With Invertible Neural Networks for 3D Human Pose and Shape Estimation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12933-12942} }

Masked Image Modeling With Local Multi-Scale Reconstruction

Haoqing Wang,

Yehui Tang,

Yunhe Wang,

Jianyuan Guo,

Zhi-Hong Deng,

Kai Han

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Haoqing and Tang, Yehui and Wang, Yunhe and Guo, Jianyuan and Deng, Zhi-Hong and Han, Kai}, title = {Masked Image Modeling With Local Multi-Scale Reconstruction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2122-2131} }

Transfer4D: A Framework for Frugal Motion Capture and Deformation Transfer

Shubh Maheshwari,

Rahul Narain,

Ramya Hebbalaguppe

[pdf] [supp]

[bibtex]

@InProceedings{Maheshwari_2023_CVPR, author = {Maheshwari, Shubh and Narain, Rahul and Hebbalaguppe, Ramya}, title = {Transfer4D: A Framework for Frugal Motion Capture and Deformation Transfer}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12836-12846} }

GeoVLN: Learning Geometry-Enhanced Visual Representation With Slot Attention for Vision-and-Language Navigation

Jingyang Huo,

Qiang Sun,

Boyan Jiang,

Haitao Lin,

Yanwei Fu

[pdf] [supp]

[bibtex]

@InProceedings{Huo_2023_CVPR, author = {Huo, Jingyang and Sun, Qiang and Jiang, Boyan and Lin, Haitao and Fu, Yanwei}, title = {GeoVLN: Learning Geometry-Enhanced Visual Representation With Slot Attention for Vision-and-Language Navigation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {23212-23221} }

KiUT: Knowledge-Injected U-Transformer for Radiology Report Generation

Zhongzhen Huang,

Xiaofan Zhang,

Shaoting Zhang

[pdf]

[bibtex]

@InProceedings{Huang_2023_CVPR, author = {Huang, Zhongzhen and Zhang, Xiaofan and Zhang, Shaoting}, title = {KiUT: Knowledge-Injected U-Transformer for Radiology Report Generation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {19809-19818} }

Flexible-Cm GAN: Towards Precise 3D Dose Prediction in Radiotherapy

Riqiang Gao,

Bin Lou,

Zhoubing Xu,

Dorin Comaniciu,

Ali Kamen

[pdf] [supp]

[bibtex]

@InProceedings{Gao_2023_CVPR, author = {Gao, Riqiang and Lou, Bin and Xu, Zhoubing and Comaniciu, Dorin and Kamen, Ali}, title = {Flexible-Cm GAN: Towards Precise 3D Dose Prediction in Radiotherapy}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {715-725} }

Randomized Adversarial Training via Taylor Expansion

Gaojie Jin,

Xinping Yi,

Dengyu Wu,

Ronghui Mu,

Xiaowei Huang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Jin_2023_CVPR, author = {Jin, Gaojie and Yi, Xinping and Wu, Dengyu and Mu, Ronghui and Huang, Xiaowei}, title = {Randomized Adversarial Training via Taylor Expansion}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16447-16457} }

Handy: Towards a High Fidelity 3D Hand Shape and Appearance Model

Rolandos Alexandros Potamias,

Stylianos Ploumpis,

Stylianos Moschoglou,

Vasileios Triantafyllou,

Stefanos Zafeiriou

[pdf] [supp]

[bibtex]

@InProceedings{Potamias_2023_CVPR, author = {Potamias, Rolandos Alexandros and Ploumpis, Stylianos and Moschoglou, Stylianos and Triantafyllou, Vasileios and Zafeiriou, Stefanos}, title = {Handy: Towards a High Fidelity 3D Hand Shape and Appearance Model}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4670-4680} }

Learning To Measure the Point Cloud Reconstruction Loss in a Representation Space

Tianxin Huang,

Zhonggan Ding,

Jiangning Zhang,

Ying Tai,

Zhenyu Zhang,

Mingang Chen,

Chengjie Wang,

Yong Liu

[pdf] [supp]

[bibtex]

@InProceedings{Huang_2023_CVPR, author = {Huang, Tianxin and Ding, Zhonggan and Zhang, Jiangning and Tai, Ying and Zhang, Zhenyu and Chen, Mingang and Wang, Chengjie and Liu, Yong}, title = {Learning To Measure the Point Cloud Reconstruction Loss in a Representation Space}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12208-12217} }

Progressive Neighbor Consistency Mining for Correspondence Pruning

Xin Liu,

Jufeng Yang

[pdf]

[bibtex]

@InProceedings{Liu_2023_CVPR, author = {Liu, Xin and Yang, Jufeng}, title = {Progressive Neighbor Consistency Mining for Correspondence Pruning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9527-9537} }

Learning To Zoom and Unzoom

Chittesh Thavamani,

Mengtian Li,

Francesco Ferroni,

Deva Ramanan

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Thavamani_2023_CVPR, author = {Thavamani, Chittesh and Li, Mengtian and Ferroni, Francesco and Ramanan, Deva}, title = {Learning To Zoom and Unzoom}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5086-5095} }

Task Difficulty Aware Parameter Allocation & Regularization for Lifelong Learning

Wenjin Wang,

Yunqing Hu,

Qianglong Chen,

Yin Zhang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Wenjin and Hu, Yunqing and Chen, Qianglong and Zhang, Yin}, title = {Task Difficulty Aware Parameter Allocation \& Regularization for Lifelong Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7776-7785} }

Bootstrapping Objectness From Videos by Relaxed Common Fate and Visual Grouping

Long Lian,

Zhirong Wu,

Stella X. Yu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Lian_2023_CVPR, author = {Lian, Long and Wu, Zhirong and Yu, Stella X.}, title = {Bootstrapping Objectness From Videos by Relaxed Common Fate and Visual Grouping}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14582-14591} }

From Node Interaction To Hop Interaction: New Effective and Scalable Graph Learning Paradigm

Jie Chen,

Zilong Li,

Yin Zhu,

Junping Zhang,

Jian Pu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Chen_2023_CVPR, author = {Chen, Jie and Li, Zilong and Zhu, Yin and Zhang, Junping and Pu, Jian}, title = {From Node Interaction To Hop Interaction: New Effective and Scalable Graph Learning Paradigm}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7876-7885} }

Semi-Supervised Hand Appearance Recovery via Structure Disentanglement and Dual Adversarial Discrimination

Zimeng Zhao,

Binghui Zuo,

Zhiyu Long,

Yangang Wang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Zhao_2023_CVPR, author = {Zhao, Zimeng and Zuo, Binghui and Long, Zhiyu and Wang, Yangang}, title = {Semi-Supervised Hand Appearance Recovery via Structure Disentanglement and Dual Adversarial Discrimination}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12125-12136} }

Understanding and Improving Features Learned in Deep Functional Maps

Souhaib Attaiki,

Maks Ovsjanikov

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Attaiki_2023_CVPR, author = {Attaiki, Souhaib and Ovsjanikov, Maks}, title = {Understanding and Improving Features Learned in Deep Functional Maps}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1316-1326} }

Back to the Source: Diffusion-Driven Adaptation To Test-Time Corruption

Jin Gao,

Jialing Zhang,

Xihui Liu,

Trevor Darrell,

Evan Shelhamer,

Dequan Wang

[pdf] [supp]

[bibtex]

@InProceedings{Gao_2023_CVPR, author = {Gao, Jin and Zhang, Jialing and Liu, Xihui and Darrell, Trevor and Shelhamer, Evan and Wang, Dequan}, title = {Back to the Source: Diffusion-Driven Adaptation To Test-Time Corruption}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11786-11796} }

PartManip: Learning Cross-Category Generalizable Part Manipulation Policy From Point Cloud Observations

Haoran Geng,

Ziming Li,

Yiran Geng,

Jiayi Chen,

Hao Dong,

He Wang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Geng_2023_CVPR, author = {Geng, Haoran and Li, Ziming and Geng, Yiran and Chen, Jiayi and Dong, Hao and Wang, He}, title = {PartManip: Learning Cross-Category Generalizable Part Manipulation Policy From Point Cloud Observations}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2978-2988} }

Polynomial Implicit Neural Representations for Large Diverse Datasets

Rajhans Singh,

Ankita Shukla,

Pavan Turaga

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Singh_2023_CVPR, author = {Singh, Rajhans and Shukla, Ankita and Turaga, Pavan}, title = {Polynomial Implicit Neural Representations for Large Diverse Datasets}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2041-2051} }

Neural Video Compression With Diverse Contexts

Jiahao Li,

Bin Li,

Yan Lu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Li_2023_CVPR, author = {Li, Jiahao and Li, Bin and Lu, Yan}, title = {Neural Video Compression With Diverse Contexts}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {22616-22626} }

High-Frequency Stereo Matching Network

Haoliang Zhao,

Huizhou Zhou,

Yongjun Zhang,

Jie Chen,

Yitong Yang,

Yong Zhao

[pdf]

[bibtex]

@InProceedings{Zhao_2023_CVPR, author = {Zhao, Haoliang and Zhou, Huizhou and Zhang, Yongjun and Chen, Jie and Yang, Yitong and Zhao, Yong}, title = {High-Frequency Stereo Matching Network}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1327-1336} }

LayoutDM: Discrete Diffusion Model for Controllable Layout Generation

Naoto Inoue,

Kotaro Kikuchi,

Edgar Simo-Serra,

Mayu Otani,

Kota Yamaguchi

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Inoue_2023_CVPR, author = {Inoue, Naoto and Kikuchi, Kotaro and Simo-Serra, Edgar and Otani, Mayu and Yamaguchi, Kota}, title = {LayoutDM: Discrete Diffusion Model for Controllable Layout Generation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10167-10176} }

Markerless Camera-to-Robot Pose Estimation via Self-Supervised Sim-to-Real Transfer

Jingpei Lu,

Florian Richter,

Michael C. Yip

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Lu_2023_CVPR, author = {Lu, Jingpei and Richter, Florian and Yip, Michael C.}, title = {Markerless Camera-to-Robot Pose Estimation via Self-Supervised Sim-to-Real Transfer}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {21296-21306} }

CARTO: Category and Joint Agnostic Reconstruction of ARTiculated Objects

Nick Heppert,

Muhammad Zubair Irshad,

Sergey Zakharov,

Katherine Liu,

Rares Andrei Ambrus,

Jeannette Bohg,

Abhinav Valada,

Thomas Kollar

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Heppert_2023_CVPR, author = {Heppert, Nick and Irshad, Muhammad Zubair and Zakharov, Sergey and Liu, Katherine and Ambrus, Rares Andrei and Bohg, Jeannette and Valada, Abhinav and Kollar, Thomas}, title = {CARTO: Category and Joint Agnostic Reconstruction of ARTiculated Objects}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {21201-21210} }

ShapeTalk: A Language Dataset and Framework for 3D Shape Edits and Deformations

Panos Achlioptas,

Ian Huang,

Minhyuk Sung,

Sergey Tulyakov,

Leonidas Guibas

[pdf]

[bibtex]

@InProceedings{Achlioptas_2023_CVPR, author = {Achlioptas, Panos and Huang, Ian and Sung, Minhyuk and Tulyakov, Sergey and Guibas, Leonidas}, title = {ShapeTalk: A Language Dataset and Framework for 3D Shape Edits and Deformations}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12685-12694} }

Event-Guided Person Re-Identification via Sparse-Dense Complementary Learning

Chengzhi Cao,

Xueyang Fu,

Hongjian Liu,

Yukun Huang,

Kunyu Wang,

Jiebo Luo,

Zheng-Jun Zha

[pdf] [supp]

[bibtex]

@InProceedings{Cao_2023_CVPR, author = {Cao, Chengzhi and Fu, Xueyang and Liu, Hongjian and Huang, Yukun and Wang, Kunyu and Luo, Jiebo and Zha, Zheng-Jun}, title = {Event-Guided Person Re-Identification via Sparse-Dense Complementary Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {17990-17999} }

Regularizing Second-Order Influences for Continual Learning

Zhicheng Sun,

Yadong Mu,

Gang Hua

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Sun_2023_CVPR, author = {Sun, Zhicheng and Mu, Yadong and Hua, Gang}, title = {Regularizing Second-Order Influences for Continual Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {20166-20175} }

Spatial-Then-Temporal Self-Supervised Learning for Video Correspondence

Rui Li,

Dong Liu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Li_2023_CVPR, author = {Li, Rui and Liu, Dong}, title = {Spatial-Then-Temporal Self-Supervised Learning for Video Correspondence}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2279-2288} }

Super-Resolution Neural Operator

Min Wei,

Xuesong Zhang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Wei_2023_CVPR, author = {Wei, Min and Zhang, Xuesong}, title = {Super-Resolution Neural Operator}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {18247-18256} }

GradICON: Approximate Diffeomorphisms via Gradient Inverse Consistency

Lin Tian,

Hastings Greer,

François-Xavier Vialard,

Roland Kwitt,

Raúl San José Estépar,

Richard Jarrett Rushmore,

Nikolaos Makris,

Sylvain Bouix,

Marc Niethammer

[pdf] [supp]

[bibtex]

@InProceedings{Tian_2023_CVPR, author = {Tian, Lin and Greer, Hastings and Vialard, Fran\c{c}ois-Xavier and Kwitt, Roland and Est\'epar, Ra\'ul San Jos\'e and Rushmore, Richard Jarrett and Makris, Nikolaos and Bouix, Sylvain and Niethammer, Marc}, title = {GradICON: Approximate Diffeomorphisms via Gradient Inverse Consistency}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {18084-18094} }

LP-DIF: Learning Local Pattern-Specific Deep Implicit Function for 3D Objects and Scenes

Meng Wang,

Yu-Shen Liu,

Yue Gao,

Kanle Shi,

Yi Fang,

Zhizhong Han

[pdf]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Meng and Liu, Yu-Shen and Gao, Yue and Shi, Kanle and Fang, Yi and Han, Zhizhong}, title = {LP-DIF: Learning Local Pattern-Specific Deep Implicit Function for 3D Objects and Scenes}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {21856-21865} }

PeakConv: Learning Peak Receptive Field for Radar Semantic Segmentation

Liwen Zhang,

Xinyan Zhang,

Youcheng Zhang,

Yufei Guo,

Yuanpei Chen,

Xuhui Huang,

Zhe Ma

[pdf] [supp]

[bibtex]

@InProceedings{Zhang_2023_CVPR, author = {Zhang, Liwen and Zhang, Xinyan and Zhang, Youcheng and Guo, Yufei and Chen, Yuanpei and Huang, Xuhui and Ma, Zhe}, title = {PeakConv: Learning Peak Receptive Field for Radar Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {17577-17586} }

Unsupervised Contour Tracking of Live Cells by Mechanical and Cycle Consistency Losses

Junbong Jang,

Kwonmoo Lee,

Tae-Kyun Kim

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Jang_2023_CVPR, author = {Jang, Junbong and Lee, Kwonmoo and Kim, Tae-Kyun}, title = {Unsupervised Contour Tracking of Live Cells by Mechanical and Cycle Consistency Losses}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {227-236} }

Explaining Image Classifiers With Multiscale Directional Image Representation

Stefan Kolek,

Robert Windesheim,

Hector Andrade-Loarca,

Gitta Kutyniok,

Ron Levie

[pdf] [supp]

[bibtex]

@InProceedings{Kolek_2023_CVPR, author = {Kolek, Stefan and Windesheim, Robert and Andrade-Loarca, Hector and Kutyniok, Gitta and Levie, Ron}, title = {Explaining Image Classifiers With Multiscale Directional Image Representation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {18600-18609} }

RGBD2: Generative Scene Synthesis via Incremental View Inpainting Using RGBD Diffusion Models

Jiabao Lei,

Jiapeng Tang,

Kui Jia

[pdf] [arXiv]

[bibtex]

@InProceedings{Lei_2023_CVPR, author = {Lei, Jiabao and Tang, Jiapeng and Jia, Kui}, title = {RGBD2: Generative Scene Synthesis via Incremental View Inpainting Using RGBD Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8422-8434} }

Distribution Shift Inversion for Out-of-Distribution Prediction

Runpeng Yu,

Songhua Liu,

Xingyi Yang,

Xinchao Wang

[pdf] [supp]

[bibtex]

@InProceedings{Yu_2023_CVPR, author = {Yu, Runpeng and Liu, Songhua and Yang, Xingyi and Wang, Xinchao}, title = {Distribution Shift Inversion for Out-of-Distribution Prediction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3592-3602} }

Deep Polarization Reconstruction With PDAVIS Events

Haiyang Mei,

Zuowen Wang,

Xin Yang,

Xiaopeng Wei,

Tobi Delbruck

[pdf] [supp]

[bibtex]

@InProceedings{Mei_2023_CVPR, author = {Mei, Haiyang and Wang, Zuowen and Yang, Xin and Wei, Xiaopeng and Delbruck, Tobi}, title = {Deep Polarization Reconstruction With PDAVIS Events}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {22149-22158} }

VideoTrack: Learning To Track Objects via Video Transformer

Fei Xie,

Lei Chu,

Jiahao Li,

Yan Lu,

Chao Ma

[pdf] [supp]

[bibtex]

@InProceedings{Xie_2023_CVPR, author = {Xie, Fei and Chu, Lei and Li, Jiahao and Lu, Yan and Ma, Chao}, title = {VideoTrack: Learning To Track Objects via Video Transformer}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {22826-22835} }

System-Status-Aware Adaptive Network for Online Streaming Video Understanding

Lin Geng Foo,

Jia Gong,

Zhipeng Fan,

Jun Liu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Foo_2023_CVPR, author = {Foo, Lin Geng and Gong, Jia and Fan, Zhipeng and Liu, Jun}, title = {System-Status-Aware Adaptive Network for Online Streaming Video Understanding}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10514-10523} }

Parallel Diffusion Models of Operator and Image for Blind Inverse Problems

Hyungjin Chung,

Jeongsol Kim,

Sehui Kim,

Jong Chul Ye

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Chung_2023_CVPR, author = {Chung, Hyungjin and Kim, Jeongsol and Kim, Sehui and Ye, Jong Chul}, title = {Parallel Diffusion Models of Operator and Image for Blind Inverse Problems}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6059-6069} }

Local-Guided Global: Paired Similarity Representation for Visual Reinforcement Learning

Hyesong Choi,

Hunsang Lee,

Wonil Song,

Sangryul Jeon,

Kwanghoon Sohn,

Dongbo Min

[pdf] [supp]

[bibtex]

@InProceedings{Choi_2023_CVPR, author = {Choi, Hyesong and Lee, Hunsang and Song, Wonil and Jeon, Sangryul and Sohn, Kwanghoon and Min, Dongbo}, title = {Local-Guided Global: Paired Similarity Representation for Visual Reinforcement Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15072-15082} }

Semidefinite Relaxations for Robust Multiview Triangulation

Linus Härenstam-Nielsen,

Niclas Zeller,

Daniel Cremers

[pdf] [supp]

[bibtex]

@InProceedings{Harenstam-Nielsen_2023_CVPR, author = {H\"arenstam-Nielsen, Linus and Zeller, Niclas and Cremers, Daniel}, title = {Semidefinite Relaxations for Robust Multiview Triangulation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {749-757} }

Distilling Self-Supervised Vision Transformers for Weakly-Supervised Few-Shot Classification & Segmentation

Dahyun Kang,

Piotr Koniusz,

Minsu Cho,

Naila Murray

[pdf] [supp]

[bibtex]

@InProceedings{Kang_2023_CVPR, author = {Kang, Dahyun and Koniusz, Piotr and Cho, Minsu and Murray, Naila}, title = {Distilling Self-Supervised Vision Transformers for Weakly-Supervised Few-Shot Classification \& Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {19627-19638} }

FFCV: Accelerating Training by Removing Data Bottlenecks

Guillaume Leclerc,

Andrew Ilyas,

Logan Engstrom,

Sung Min Park,

Hadi Salman,

Aleksander Mądry

[pdf] [supp]

[bibtex]

@InProceedings{Leclerc_2023_CVPR, author = {Leclerc, Guillaume and Ilyas, Andrew and Engstrom, Logan and Park, Sung Min and Salman, Hadi and M\k{a}dry, Aleksander}, title = {FFCV: Accelerating Training by Removing Data Bottlenecks}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12011-12020} }

Collaborative Noisy Label Cleaner: Learning Scene-Aware Trailers for Multi-Modal Highlight Detection in Movies

Bei Gan,

Xiujun Shu,

Ruizhi Qiao,

Haoqian Wu,

Keyu Chen,

Hanjun Li,

Bo Ren

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Gan_2023_CVPR, author = {Gan, Bei and Shu, Xiujun and Qiao, Ruizhi and Wu, Haoqian and Chen, Keyu and Li, Hanjun and Ren, Bo}, title = {Collaborative Noisy Label Cleaner: Learning Scene-Aware Trailers for Multi-Modal Highlight Detection in Movies}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {18898-18907} }

Modeling Video As Stochastic Processes for Fine-Grained Video Representation Learning

Heng Zhang,

Daqing Liu,

Qi Zheng,

Bing Su

[pdf] [supp]

[bibtex]

@InProceedings{Zhang_2023_CVPR, author = {Zhang, Heng and Liu, Daqing and Zheng, Qi and Su, Bing}, title = {Modeling Video As Stochastic Processes for Fine-Grained Video Representation Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2225-2234} }

ContraNeRF: Generalizable Neural Radiance Fields for Synthetic-to-Real Novel View Synthesis via Contrastive Learning

Hao Yang,

Lanqing Hong,

Aoxue Li,

Tianyang Hu,

Zhenguo Li,

Gim Hee Lee,

Liwei Wang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Yang_2023_CVPR, author = {Yang, Hao and Hong, Lanqing and Li, Aoxue and Hu, Tianyang and Li, Zhenguo and Lee, Gim Hee and Wang, Liwei}, title = {ContraNeRF: Generalizable Neural Radiance Fields for Synthetic-to-Real Novel View Synthesis via Contrastive Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16508-16517} }

Region-Aware Pretraining for Open-Vocabulary Object Detection With Vision Transformers

Dahun Kim,

Anelia Angelova,

Weicheng Kuo

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Kim_2023_CVPR, author = {Kim, Dahun and Angelova, Anelia and Kuo, Weicheng}, title = {Region-Aware Pretraining for Open-Vocabulary Object Detection With Vision Transformers}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11144-11154} }

PaletteNeRF: Palette-Based Appearance Editing of Neural Radiance Fields

Zhengfei Kuang,

Fujun Luan,

Sai Bi,

Zhixin Shu,

Gordon Wetzstein,

Kalyan Sunkavalli

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Kuang_2023_CVPR, author = {Kuang, Zhengfei and Luan, Fujun and Bi, Sai and Shu, Zhixin and Wetzstein, Gordon and Sunkavalli, Kalyan}, title = {PaletteNeRF: Palette-Based Appearance Editing of Neural Radiance Fields}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {20691-20700} }

Towards Unsupervised Object Detection From LiDAR Point Clouds

Lunjun Zhang,

Anqi Joyce Yang,

Yuwen Xiong,

Sergio Casas,

Bin Yang,

Mengye Ren,

Raquel Urtasun

[pdf] [supp]

[bibtex]

@InProceedings{Zhang_2023_CVPR, author = {Zhang, Lunjun and Yang, Anqi Joyce and Xiong, Yuwen and Casas, Sergio and Yang, Bin and Ren, Mengye and Urtasun, Raquel}, title = {Towards Unsupervised Object Detection From LiDAR Point Clouds}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9317-9328} }

Contrastive Mean Teacher for Domain Adaptive Object Detectors

Shengcao Cao,

Dhiraj Joshi,

Liang-Yan Gui,

Yu-Xiong Wang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Cao_2023_CVPR, author = {Cao, Shengcao and Joshi, Dhiraj and Gui, Liang-Yan and Wang, Yu-Xiong}, title = {Contrastive Mean Teacher for Domain Adaptive Object Detectors}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {23839-23848} }

Learning Transferable Spatiotemporal Representations From Natural Script Knowledge

Ziyun Zeng,

Yuying Ge,

Xihui Liu,

Bin Chen,

Ping Luo,

Shu-Tao Xia,

Yixiao Ge

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Zeng_2023_CVPR, author = {Zeng, Ziyun and Ge, Yuying and Liu, Xihui and Chen, Bin and Luo, Ping and Xia, Shu-Tao and Ge, Yixiao}, title = {Learning Transferable Spatiotemporal Representations From Natural Script Knowledge}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {23079-23089} }

NeRF-DS: Neural Radiance Fields for Dynamic Specular Objects

Zhiwen Yan,

Chen Li,

Gim Hee Lee

[pdf] [supp]

[bibtex]

@InProceedings{Yan_2023_CVPR, author = {Yan, Zhiwen and Li, Chen and Lee, Gim Hee}, title = {NeRF-DS: Neural Radiance Fields for Dynamic Specular Objects}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8285-8295} }

M6Doc: A Large-Scale Multi-Format, Multi-Type, Multi-Layout, Multi-Language, Multi-Annotation Category Dataset for Modern Document Layout Analysis

Hiuyi Cheng,

Peirong Zhang,

Sihang Wu,

Jiaxin Zhang,

Qiyuan Zhu,

Zecheng Xie,

Jing Li,

Kai Ding,

Lianwen Jin

[pdf] [supp]

[bibtex]

@InProceedings{Cheng_2023_CVPR, author = {Cheng, Hiuyi and Zhang, Peirong and Wu, Sihang and Zhang, Jiaxin and Zhu, Qiyuan and Xie, Zecheng and Li, Jing and Ding, Kai and Jin, Lianwen}, title = {M6Doc: A Large-Scale Multi-Format, Multi-Type, Multi-Layout, Multi-Language, Multi-Annotation Category Dataset for Modern Document Layout Analysis}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15138-15147} }

RealFusion: 360deg Reconstruction of Any Object From a Single Image

Luke Melas-Kyriazi,

Iro Laina,

Christian Rupprecht,

Andrea Vedaldi

[pdf] [supp]

[bibtex]

@InProceedings{Melas-Kyriazi_2023_CVPR, author = {Melas-Kyriazi, Luke and Laina, Iro and Rupprecht, Christian and Vedaldi, Andrea}, title = {RealFusion: 360deg Reconstruction of Any Object From a Single Image}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8446-8455} }

CiCo: Domain-Aware Sign Language Retrieval via Cross-Lingual Contrastive Learning

Yiting Cheng,

Fangyun Wei,

Jianmin Bao,

Dong Chen,

Wenqiang Zhang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Cheng_2023_CVPR, author = {Cheng, Yiting and Wei, Fangyun and Bao, Jianmin and Chen, Dong and Zhang, Wenqiang}, title = {CiCo: Domain-Aware Sign Language Retrieval via Cross-Lingual Contrastive Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {19016-19026} }

Relational Space-Time Query in Long-Form Videos

Xitong Yang,

Fu-Jen Chu,

Matt Feiszli,

Raghav Goyal,

Lorenzo Torresani,

Du Tran

[pdf] [supp]

[bibtex]

@InProceedings{Yang_2023_CVPR, author = {Yang, Xitong and Chu, Fu-Jen and Feiszli, Matt and Goyal, Raghav and Torresani, Lorenzo and Tran, Du}, title = {Relational Space-Time Query in Long-Form Videos}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6398-6408} }

LargeKernel3D: Scaling Up Kernels in 3D Sparse CNNs

Yukang Chen,

Jianhui Liu,

Xiangyu Zhang,

Xiaojuan Qi,

Jiaya Jia

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Chen_2023_CVPR, author = {Chen, Yukang and Liu, Jianhui and Zhang, Xiangyu and Qi, Xiaojuan and Jia, Jiaya}, title = {LargeKernel3D: Scaling Up Kernels in 3D Sparse CNNs}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13488-13498} }

Video Dehazing via a Multi-Range Temporal Alignment Network With Physical Prior

Jiaqi Xu,

Xiaowei Hu,

Lei Zhu,

Qi Dou,

Jifeng Dai,

Yu Qiao,

Pheng-Ann Heng

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Xu_2023_CVPR, author = {Xu, Jiaqi and Hu, Xiaowei and Zhu, Lei and Dou, Qi and Dai, Jifeng and Qiao, Yu and Heng, Pheng-Ann}, title = {Video Dehazing via a Multi-Range Temporal Alignment Network With Physical Prior}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {18053-18062} }

3D Concept Learning and Reasoning From Multi-View Images

Yining Hong,

Chunru Lin,

Yilun Du,

Zhenfang Chen,

Joshua B. Tenenbaum,

Chuang Gan

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Hong_2023_CVPR, author = {Hong, Yining and Lin, Chunru and Du, Yilun and Chen, Zhenfang and Tenenbaum, Joshua B. and Gan, Chuang}, title = {3D Concept Learning and Reasoning From Multi-View Images}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9202-9212} }

BiFormer: Learning Bilateral Motion Estimation via Bilateral Transformer for 4K Video Frame Interpolation

Junheum Park,

Jintae Kim,

Chang-Su Kim

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Park_2023_CVPR, author = {Park, Junheum and Kim, Jintae and Kim, Chang-Su}, title = {BiFormer: Learning Bilateral Motion Estimation via Bilateral Transformer for 4K Video Frame Interpolation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1568-1577} }

Integrally Pre-Trained Transformer Pyramid Networks

Yunjie Tian,

Lingxi Xie,

Zhaozhi Wang,

Longhui Wei,

Xiaopeng Zhang,

Jianbin Jiao,

Yaowei Wang,

Qi Tian,

Qixiang Ye

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Tian_2023_CVPR, author = {Tian, Yunjie and Xie, Lingxi and Wang, Zhaozhi and Wei, Longhui and Zhang, Xiaopeng and Jiao, Jianbin and Wang, Yaowei and Tian, Qi and Ye, Qixiang}, title = {Integrally Pre-Trained Transformer Pyramid Networks}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {18610-18620} }

Soft Augmentation for Image Classification

Yang Liu,

Shen Yan,

Laura Leal-Taixé,

James Hays,

Deva Ramanan

[pdf] [supp]

[bibtex]

@InProceedings{Liu_2023_CVPR, author = {Liu, Yang and Yan, Shen and Leal-Taix\'e, Laura and Hays, James and Ramanan, Deva}, title = {Soft Augmentation for Image Classification}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16241-16250} }

Learning From Unique Perspectives: User-Aware Saliency Modeling

Shi Chen,

Nachiappan Valliappan,

Shaolei Shen,

Xinyu Ye,

Kai Kohlhoff,

Junfeng He

[pdf] [supp]

[bibtex]

@InProceedings{Chen_2023_CVPR, author = {Chen, Shi and Valliappan, Nachiappan and Shen, Shaolei and Ye, Xinyu and Kohlhoff, Kai and He, Junfeng}, title = {Learning From Unique Perspectives: User-Aware Saliency Modeling}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2701-2710} }

PREIM3D: 3D Consistent Precise Image Attribute Editing From a Single Image

Jianhui Li,

Jianmin Li,

Haoji Zhang,

Shilong Liu,

Zhengyi Wang,

Zihao Xiao,

Kaiwen Zheng,

Jun Zhu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Li_2023_CVPR, author = {Li, Jianhui and Li, Jianmin and Zhang, Haoji and Liu, Shilong and Wang, Zhengyi and Xiao, Zihao and Zheng, Kaiwen and Zhu, Jun}, title = {PREIM3D: 3D Consistent Precise Image Attribute Editing From a Single Image}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8549-8558} }

MaskSketch: Unpaired Structure-Guided Masked Image Generation

Dina Bashkirova,

José Lezama,

Kihyuk Sohn,

Kate Saenko,

Irfan Essa

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Bashkirova_2023_CVPR, author = {Bashkirova, Dina and Lezama, Jos\'e and Sohn, Kihyuk and Saenko, Kate and Essa, Irfan}, title = {MaskSketch: Unpaired Structure-Guided Masked Image Generation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1879-1889} }

Open-Vocabulary Point-Cloud Object Detection Without 3D Annotation

Yuheng Lu,

Chenfeng Xu,

Xiaobao Wei,

Xiaodong Xie,

Masayoshi Tomizuka,

Kurt Keutzer,

Shanghang Zhang

[pdf] [arXiv]

[bibtex]

@InProceedings{Lu_2023_CVPR, author = {Lu, Yuheng and Xu, Chenfeng and Wei, Xiaobao and Xie, Xiaodong and Tomizuka, Masayoshi and Keutzer, Kurt and Zhang, Shanghang}, title = {Open-Vocabulary Point-Cloud Object Detection Without 3D Annotation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1190-1199} }

Adaptive Channel Sparsity for Federated Learning Under System Heterogeneity

Dongping Liao,

Xitong Gao,

Yiren Zhao,

Cheng-Zhong Xu

[pdf] [supp]

[bibtex]

@InProceedings{Liao_2023_CVPR, author = {Liao, Dongping and Gao, Xitong and Zhao, Yiren and Xu, Cheng-Zhong}, title = {Adaptive Channel Sparsity for Federated Learning Under System Heterogeneity}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {20432-20441} }

Detecting Backdoors in Pre-Trained Encoders

Shiwei Feng,

Guanhong Tao,

Siyuan Cheng,

Guangyu Shen,

Xiangzhe Xu,

Yingqi Liu,

Kaiyuan Zhang,

Shiqing Ma,

Xiangyu Zhang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Feng_2023_CVPR, author = {Feng, Shiwei and Tao, Guanhong and Cheng, Siyuan and Shen, Guangyu and Xu, Xiangzhe and Liu, Yingqi and Zhang, Kaiyuan and Ma, Shiqing and Zhang, Xiangyu}, title = {Detecting Backdoors in Pre-Trained Encoders}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16352-16362} }

Sequential Training of GANs Against GAN-Classifiers Reveals Correlated "Knowledge Gaps" Present Among Independently Trained GAN Instances

Arkanath Pathak,

Nicholas Dufour

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Pathak_2023_CVPR, author = {Pathak, Arkanath and Dufour, Nicholas}, title = {Sequential Training of GANs Against GAN-Classifiers Reveals Correlated ''Knowledge Gaps'' Present Among Independently Trained GAN Instances}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {24460-24469} }

Lookahead Diffusion Probabilistic Models for Refining Mean Estimation

Guoqiang Zhang,

Kenta Niwa,

W. Bastiaan Kleijn

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Zhang_2023_CVPR, author = {Zhang, Guoqiang and Niwa, Kenta and Kleijn, W. Bastiaan}, title = {Lookahead Diffusion Probabilistic Models for Refining Mean Estimation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1421-1429} }

TensoIR: Tensorial Inverse Rendering

Haian Jin,

Isabella Liu,

Peijia Xu,

Xiaoshuai Zhang,

Songfang Han,

Sai Bi,

Xiaowei Zhou,

Zexiang Xu,

Hao Su

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Jin_2023_CVPR, author = {Jin, Haian and Liu, Isabella and Xu, Peijia and Zhang, Xiaoshuai and Han, Songfang and Bi, Sai and Zhou, Xiaowei and Xu, Zexiang and Su, Hao}, title = {TensoIR: Tensorial Inverse Rendering}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {165-174} }

NIPQ: Noise Proxy-Based Integrated Pseudo-Quantization

Juncheol Shin,

Junhyuk So,

Sein Park,

Seungyeop Kang,

Sungjoo Yoo,

Eunhyeok Park

[pdf] [supp]

[bibtex]

@InProceedings{Shin_2023_CVPR, author = {Shin, Juncheol and So, Junhyuk and Park, Sein and Kang, Seungyeop and Yoo, Sungjoo and Park, Eunhyeok}, title = {NIPQ: Noise Proxy-Based Integrated Pseudo-Quantization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3852-3861} }

Primitive Generation and Semantic-Related Alignment for Universal Zero-Shot Segmentation

Shuting He,

Henghui Ding,

Wei Jiang

[pdf] [supp]

[bibtex]

@InProceedings{He_2023_CVPR, author = {He, Shuting and Ding, Henghui and Jiang, Wei}, title = {Primitive Generation and Semantic-Related Alignment for Universal Zero-Shot Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11238-11247} }

Long Range Pooling for 3D Large-Scale Scene Understanding

Xiang-Li Li,

Meng-Hao Guo,

Tai-Jiang Mu,

Ralph R. Martin,

Shi-Min Hu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Li_2023_CVPR, author = {Li, Xiang-Li and Guo, Meng-Hao and Mu, Tai-Jiang and Martin, Ralph R. and Hu, Shi-Min}, title = {Long Range Pooling for 3D Large-Scale Scene Understanding}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10300-10311} }

Object-Goal Visual Navigation via Effective Exploration of Relations Among Historical Navigation States

Heming Du,

Lincheng Li,

Zi Huang,

Xin Yu

[pdf]

[bibtex]

@InProceedings{Du_2023_CVPR, author = {Du, Heming and Li, Lincheng and Huang, Zi and Yu, Xin}, title = {Object-Goal Visual Navigation via Effective Exploration of Relations Among Historical Navigation States}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2563-2573} }

Causally-Aware Intraoperative Imputation for Overall Survival Time Prediction

Xiang Li,

Xuelin Qian,

Litian Liang,

Lingjie Kong,

Qiaole Dong,

Jiejun Chen,

Dingxia Liu,

Xiuzhong Yao,

Yanwei Fu

[pdf] [supp]

[bibtex]

@InProceedings{Li_2023_CVPR, author = {Li, Xiang and Qian, Xuelin and Liang, Litian and Kong, Lingjie and Dong, Qiaole and Chen, Jiejun and Liu, Dingxia and Yao, Xiuzhong and Fu, Yanwei}, title = {Causally-Aware Intraoperative Imputation for Overall Survival Time Prediction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15681-15690} }

Probabilistic Knowledge Distillation of Face Ensembles

Jianqing Xu,

Shen Li,

Ailin Deng,

Miao Xiong,

Jiaying Wu,

Jiaxiang Wu,

Shouhong Ding,

Bryan Hooi

[pdf] [supp]

[bibtex]

@InProceedings{Xu_2023_CVPR, author = {Xu, Jianqing and Li, Shen and Deng, Ailin and Xiong, Miao and Wu, Jiaying and Wu, Jiaxiang and Ding, Shouhong and Hooi, Bryan}, title = {Probabilistic Knowledge Distillation of Face Ensembles}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3489-3498} }

Twin Contrastive Learning With Noisy Labels

Zhizhong Huang,

Junping Zhang,

Hongming Shan

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Huang_2023_CVPR, author = {Huang, Zhizhong and Zhang, Junping and Shan, Hongming}, title = {Twin Contrastive Learning With Noisy Labels}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11661-11670} }

TriVol: Point Cloud Rendering via Triple Volumes

Tao Hu,

Xiaogang Xu,

Ruihang Chu,

Jiaya Jia

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Hu_2023_CVPR, author = {Hu, Tao and Xu, Xiaogang and Chu, Ruihang and Jia, Jiaya}, title = {TriVol: Point Cloud Rendering via Triple Volumes}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {20732-20741} }

(ML)$^2$P-Encoder: On Exploration of Channel-Class Correlation for Multi-Label Zero-Shot Learning

Ziming Liu,

Song Guo,

Xiaocheng Lu,

Jingcai Guo,

Jiewei Zhang,

Yue Zeng,

Fushuo Huo

[pdf] [supp]

[bibtex]

@InProceedings{Liu_2023_CVPR, author = {Liu, Ziming and Guo, Song and Lu, Xiaocheng and Guo, Jingcai and Zhang, Jiewei and Zeng, Yue and Huo, Fushuo}, title = {(ML)\${\textasciicircum}2\$P-Encoder: On Exploration of Channel-Class Correlation for Multi-Label Zero-Shot Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {23859-23868} }

MeMaHand: Exploiting Mesh-Mano Interaction for Single Image Two-Hand Reconstruction

Congyi Wang,

Feida Zhu,

Shilei Wen

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Congyi and Zhu, Feida and Wen, Shilei}, title = {MeMaHand: Exploiting Mesh-Mano Interaction for Single Image Two-Hand Reconstruction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {564-573} }

Asymmetric Feature Fusion for Image Retrieval

Hui Wu,

Min Wang,

Wengang Zhou,

Zhenbo Lu,

Houqiang Li

[pdf] [supp]

[bibtex]

@InProceedings{Wu_2023_CVPR, author = {Wu, Hui and Wang, Min and Zhou, Wengang and Lu, Zhenbo and Li, Houqiang}, title = {Asymmetric Feature Fusion for Image Retrieval}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11082-11092} }

CREPE: Can Vision-Language Foundation Models Reason Compositionally?

Zixian Ma,

Jerry Hong,

Mustafa Omer Gul,

Mona Gandhi,

Irena Gao,

Ranjay Krishna

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Ma_2023_CVPR, author = {Ma, Zixian and Hong, Jerry and Gul, Mustafa Omer and Gandhi, Mona and Gao, Irena and Krishna, Ranjay}, title = {CREPE: Can Vision-Language Foundation Models Reason Compositionally?}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10910-10921} }

DSFNet: Dual Space Fusion Network for Occlusion-Robust 3D Dense Face Alignment

Heyuan Li,

Bo Wang,

Yu Cheng,

Mohan Kankanhalli,

Robby T. Tan

[pdf] [supp]

[bibtex]

@InProceedings{Li_2023_CVPR, author = {Li, Heyuan and Wang, Bo and Cheng, Yu and Kankanhalli, Mohan and Tan, Robby T.}, title = {DSFNet: Dual Space Fusion Network for Occlusion-Robust 3D Dense Face Alignment}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4531-4540} }

MoStGAN-V: Video Generation With Temporal Motion Styles

Xiaoqian Shen,

Xiang Li,

Mohamed Elhoseiny

[pdf] [supp]

[bibtex]

@InProceedings{Shen_2023_CVPR, author = {Shen, Xiaoqian and Li, Xiang and Elhoseiny, Mohamed}, title = {MoStGAN-V: Video Generation With Temporal Motion Styles}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5652-5661} }

Poly-PC: A Polyhedral Network for Multiple Point Cloud Tasks at Once

Tao Xie,

Shiguang Wang,

Ke Wang,

Linqi Yang,

Zhiqiang Jiang,

Xingcheng Zhang,

Kun Dai,

Ruifeng Li,

Jian Cheng

[pdf] [supp]

[bibtex]

@InProceedings{Xie_2023_CVPR, author = {Xie, Tao and Wang, Shiguang and Wang, Ke and Yang, Linqi and Jiang, Zhiqiang and Zhang, Xingcheng and Dai, Kun and Li, Ruifeng and Cheng, Jian}, title = {Poly-PC: A Polyhedral Network for Multiple Point Cloud Tasks at Once}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1233-1243} }

HandsOff: Labeled Dataset Generation With No Additional Human Annotations

Austin Xu,

Mariya I. Vasileva,

Achal Dave,

Arjun Seshadri

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Xu_2023_CVPR, author = {Xu, Austin and Vasileva, Mariya I. and Dave, Achal and Seshadri, Arjun}, title = {HandsOff: Labeled Dataset Generation With No Additional Human Annotations}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7991-8000} }

Semi-Supervised 2D Human Pose Estimation Driven by Position Inconsistency Pseudo Label Correction Module

Linzhi Huang,

Yulong Li,

Hongbo Tian,

Yue Yang,

Xiangang Li,

Weihong Deng,

Jieping Ye

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Huang_2023_CVPR, author = {Huang, Linzhi and Li, Yulong and Tian, Hongbo and Yang, Yue and Li, Xiangang and Deng, Weihong and Ye, Jieping}, title = {Semi-Supervised 2D Human Pose Estimation Driven by Position Inconsistency Pseudo Label Correction Module}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {693-703} }

ARKitTrack: A New Diverse Dataset for Tracking Using Mobile RGB-D Data

Haojie Zhao,

Junsong Chen,

Lijun Wang,

Huchuan Lu

[pdf] [supp]

[bibtex]

@InProceedings{Zhao_2023_CVPR, author = {Zhao, Haojie and Chen, Junsong and Wang, Lijun and Lu, Huchuan}, title = {ARKitTrack: A New Diverse Dataset for Tracking Using Mobile RGB-D Data}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5126-5135} }

Image as a Foreign Language: BEiT Pretraining for Vision and Vision-Language Tasks

Wenhui Wang,

Hangbo Bao,

Li Dong,

Johan Bjorck,

Zhiliang Peng,

Qiang Liu,

Kriti Aggarwal,

Owais Khan Mohammed,

Saksham Singhal,

Subhojit Som,

Furu Wei

[pdf] [supp]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Wenhui and Bao, Hangbo and Dong, Li and Bjorck, Johan and Peng, Zhiliang and Liu, Qiang and Aggarwal, Kriti and Mohammed, Owais Khan and Singhal, Saksham and Som, Subhojit and Wei, Furu}, title = {Image as a Foreign Language: BEiT Pretraining for Vision and Vision-Language Tasks}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {19175-19186} }

Density-Insensitive Unsupervised Domain Adaption on 3D Object Detection

Qianjiang Hu,

Daizong Liu,

Wei Hu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Hu_2023_CVPR, author = {Hu, Qianjiang and Liu, Daizong and Hu, Wei}, title = {Density-Insensitive Unsupervised Domain Adaption on 3D Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {17556-17566} }

Efficient Verification of Neural Networks Against LVM-Based Specifications

Harleen Hanspal,

Alessio Lomuscio

[pdf] [supp]

[bibtex]

@InProceedings{Hanspal_2023_CVPR, author = {Hanspal, Harleen and Lomuscio, Alessio}, title = {Efficient Verification of Neural Networks Against LVM-Based Specifications}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3894-3903} }

Learning Action Changes by Measuring Verb-Adverb Textual Relationships

Davide Moltisanti,

Frank Keller,

Hakan Bilen,

Laura Sevilla-Lara

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Moltisanti_2023_CVPR, author = {Moltisanti, Davide and Keller, Frank and Bilen, Hakan and Sevilla-Lara, Laura}, title = {Learning Action Changes by Measuring Verb-Adverb Textual Relationships}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {23110-23118} }

Feature Aggregated Queries for Transformer-Based Video Object Detectors

Yiming Cui

[pdf] [arXiv]

[bibtex]

@InProceedings{Cui_2023_CVPR, author = {Cui, Yiming}, title = {Feature Aggregated Queries for Transformer-Based Video Object Detectors}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6365-6376} }

Context-Aware Pretraining for Efficient Blind Image Decomposition

Chao Wang,

Zhedong Zheng,

Ruijie Quan,

Yifan Sun,

Yi Yang

[pdf] [supp]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Chao and Zheng, Zhedong and Quan, Ruijie and Sun, Yifan and Yang, Yi}, title = {Context-Aware Pretraining for Efficient Blind Image Decomposition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {18186-18195} }

Weakly Supervised Posture Mining for Fine-Grained Classification

Zhenchao Tang,

Hualin Yang,

Calvin Yu-Chian Chen

[pdf] [supp]

[bibtex]

@InProceedings{Tang_2023_CVPR, author = {Tang, Zhenchao and Yang, Hualin and Chen, Calvin Yu-Chian}, title = {Weakly Supervised Posture Mining for Fine-Grained Classification}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {23735-23744} }

LAVENDER: Unifying Video-Language Understanding As Masked Language Modeling

Linjie Li,

Zhe Gan,

Kevin Lin,

Chung-Ching Lin,

Zicheng Liu,

Ce Liu,

Lijuan Wang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Li_2023_CVPR, author = {Li, Linjie and Gan, Zhe and Lin, Kevin and Lin, Chung-Ching and Liu, Zicheng and Liu, Ce and Wang, Lijuan}, title = {LAVENDER: Unifying Video-Language Understanding As Masked Language Modeling}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {23119-23129} }

Decomposed Cross-Modal Distillation for RGB-Based Temporal Action Detection

Pilhyeon Lee,

Taeoh Kim,

Minho Shim,

Dongyoon Wee,

Hyeran Byun

[pdf] [arXiv]

[bibtex]

@InProceedings{Lee_2023_CVPR, author = {Lee, Pilhyeon and Kim, Taeoh and Shim, Minho and Wee, Dongyoon and Byun, Hyeran}, title = {Decomposed Cross-Modal Distillation for RGB-Based Temporal Action Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2373-2383} }

PyramidFlow: High-Resolution Defect Contrastive Localization Using Pyramid Normalizing Flow

Jiarui Lei,

Xiaobo Hu,

Yue Wang,

Dong Liu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Lei_2023_CVPR, author = {Lei, Jiarui and Hu, Xiaobo and Wang, Yue and Liu, Dong}, title = {PyramidFlow: High-Resolution Defect Contrastive Localization Using Pyramid Normalizing Flow}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14143-14152} }

On-the-Fly Category Discovery

Ruoyi Du,

Dongliang Chang,

Kongming Liang,

Timothy Hospedales,

Yi-Zhe Song,

Zhanyu Ma

[pdf]

[bibtex]

@InProceedings{Du_2023_CVPR, author = {Du, Ruoyi and Chang, Dongliang and Liang, Kongming and Hospedales, Timothy and Song, Yi-Zhe and Ma, Zhanyu}, title = {On-the-Fly Category Discovery}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11691-11700} }

A Unified Knowledge Distillation Framework for Deep Directed Graphical Models

Yizhuo Chen,

Kaizhao Liang,

Zhe Zeng,

Shuochao Yao,

Huajie Shao

[pdf] [supp]

[bibtex]

@InProceedings{Chen_2023_CVPR, author = {Chen, Yizhuo and Liang, Kaizhao and Zeng, Zhe and Yao, Shuochao and Shao, Huajie}, title = {A Unified Knowledge Distillation Framework for Deep Directed Graphical Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7795-7804} }

MAIR: Multi-View Attention Inverse Rendering With 3D Spatially-Varying Lighting Estimation

JunYong Choi,

SeokYeong Lee,

Haesol Park,

Seung-Won Jung,

Ig-Jae Kim,

Junghyun Cho

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Choi_2023_CVPR, author = {Choi, JunYong and Lee, SeokYeong and Park, Haesol and Jung, Seung-Won and Kim, Ig-Jae and Cho, Junghyun}, title = {MAIR: Multi-View Attention Inverse Rendering With 3D Spatially-Varying Lighting Estimation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8392-8401} }

DF-Platter: Multi-Face Heterogeneous Deepfake Dataset

Kartik Narayan,

Harsh Agarwal,

Kartik Thakral,

Surbhi Mittal,

Mayank Vatsa,

Richa Singh

[pdf] [supp]

[bibtex]

@InProceedings{Narayan_2023_CVPR, author = {Narayan, Kartik and Agarwal, Harsh and Thakral, Kartik and Mittal, Surbhi and Vatsa, Mayank and Singh, Richa}, title = {DF-Platter: Multi-Face Heterogeneous Deepfake Dataset}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9739-9748} }

Shifted Diffusion for Text-to-Image Generation

Yufan Zhou,

Bingchen Liu,

Yizhe Zhu,

Xiao Yang,

Changyou Chen,

Jinhui Xu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Zhou_2023_CVPR, author = {Zhou, Yufan and Liu, Bingchen and Zhu, Yizhe and Yang, Xiao and Chen, Changyou and Xu, Jinhui}, title = {Shifted Diffusion for Text-to-Image Generation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10157-10166} }

Robust Unsupervised StyleGAN Image Restoration

Yohan Poirier-Ginter,

Jean-François Lalonde

[pdf] [arXiv]

[bibtex]

@InProceedings{Poirier-Ginter_2023_CVPR, author = {Poirier-Ginter, Yohan and Lalonde, Jean-Fran\c{c}ois}, title = {Robust Unsupervised StyleGAN Image Restoration}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {22292-22301} }

Blemish-Aware and Progressive Face Retouching With Limited Paired Data

Lianxin Xie,

Wen Xue,

Zhen Xu,

Si Wu,

Zhiwen Yu,

Hau San Wong

[pdf]

[bibtex]

@InProceedings{Xie_2023_CVPR, author = {Xie, Lianxin and Xue, Wen and Xu, Zhen and Wu, Si and Yu, Zhiwen and Wong, Hau San}, title = {Blemish-Aware and Progressive Face Retouching With Limited Paired Data}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5599-5608} }

Event-Based Frame Interpolation With Ad-Hoc Deblurring

Lei Sun,

Christos Sakaridis,

Jingyun Liang,

Peng Sun,

Jiezhang Cao,

Kai Zhang,

Qi Jiang,

Kaiwei Wang,

Luc Van Gool

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Sun_2023_CVPR, author = {Sun, Lei and Sakaridis, Christos and Liang, Jingyun and Sun, Peng and Cao, Jiezhang and Zhang, Kai and Jiang, Qi and Wang, Kaiwei and Van Gool, Luc}, title = {Event-Based Frame Interpolation With Ad-Hoc Deblurring}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {18043-18052} }

OvarNet: Towards Open-Vocabulary Object Attribute Recognition

Keyan Chen,

Xiaolong Jiang,

Yao Hu,

Xu Tang,

Yan Gao,

Jianqi Chen,

Weidi Xie

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Chen_2023_CVPR, author = {Chen, Keyan and Jiang, Xiaolong and Hu, Yao and Tang, Xu and Gao, Yan and Chen, Jianqi and Xie, Weidi}, title = {OvarNet: Towards Open-Vocabulary Object Attribute Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {23518-23527} }

Detecting and Grounding Multi-Modal Media Manipulation

Rui Shao,

Tianxing Wu,

Ziwei Liu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Shao_2023_CVPR, author = {Shao, Rui and Wu, Tianxing and Liu, Ziwei}, title = {Detecting and Grounding Multi-Modal Media Manipulation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6904-6913} }

Boosting Detection in Crowd Analysis via Underutilized Output Features

Shaokai Wu,

Fengyu Yang

[pdf] [supp]

[bibtex]

@InProceedings{Wu_2023_CVPR, author = {Wu, Shaokai and Yang, Fengyu}, title = {Boosting Detection in Crowd Analysis via Underutilized Output Features}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15609-15618} }

Human Pose As Compositional Tokens

Zigang Geng,

Chunyu Wang,

Yixuan Wei,

Ze Liu,

Houqiang Li,

Han Hu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Geng_2023_CVPR, author = {Geng, Zigang and Wang, Chunyu and Wei, Yixuan and Liu, Ze and Li, Houqiang and Hu, Han}, title = {Human Pose As Compositional Tokens}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {660-671} }

K3DN: Disparity-Aware Kernel Estimation for Dual-Pixel Defocus Deblurring

Yan Yang,

Liyuan Pan,

Liu Liu,

Miaomiao Liu

[pdf] [supp]

[bibtex]

@InProceedings{Yang_2023_CVPR, author = {Yang, Yan and Pan, Liyuan and Liu, Liu and Liu, Miaomiao}, title = {K3DN: Disparity-Aware Kernel Estimation for Dual-Pixel Defocus Deblurring}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13263-13272} }

3D Line Mapping Revisited

Shaohui Liu,

Yifan Yu,

Rémi Pautrat,

Marc Pollefeys,

Viktor Larsson

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Liu_2023_CVPR, author = {Liu, Shaohui and Yu, Yifan and Pautrat, R\'emi and Pollefeys, Marc and Larsson, Viktor}, title = {3D Line Mapping Revisited}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {21445-21455} }

DartBlur: Privacy Preservation With Detection Artifact Suppression

Baowei Jiang,

Bing Bai,

Haozhe Lin,

Yu Wang,

Yuchen Guo,

Lu Fang

[pdf] [supp]

[bibtex]

@InProceedings{Jiang_2023_CVPR, author = {Jiang, Baowei and Bai, Bing and Lin, Haozhe and Wang, Yu and Guo, Yuchen and Fang, Lu}, title = {DartBlur: Privacy Preservation With Detection Artifact Suppression}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16479-16488} }

Synthesizing Photorealistic Virtual Humans Through Cross-Modal Disentanglement

Siddarth Ravichandran,

Ondřej Texler,

Dimitar Dinev,

Hyun Jae Kang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Ravichandran_2023_CVPR, author = {Ravichandran, Siddarth and Texler, Ond\v{r}ej and Dinev, Dimitar and Kang, Hyun Jae}, title = {Synthesizing Photorealistic Virtual Humans Through Cross-Modal Disentanglement}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4585-4594} }

Test Time Adaptation With Regularized Loss for Weakly Supervised Salient Object Detection

Olga Veksler

[pdf] [supp]

[bibtex]

@InProceedings{Veksler_2023_CVPR, author = {Veksler, Olga}, title = {Test Time Adaptation With Regularized Loss for Weakly Supervised Salient Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7360-7369} }

Self-Supervised Pre-Training With Masked Shape Prediction for 3D Scene Understanding

Li Jiang,

Zetong Yang,

Shaoshuai Shi,

Vladislav Golyanik,

Dengxin Dai,

Bernt Schiele

[pdf] [arXiv]

[bibtex]

@InProceedings{Jiang_2023_CVPR, author = {Jiang, Li and Yang, Zetong and Shi, Shaoshuai and Golyanik, Vladislav and Dai, Dengxin and Schiele, Bernt}, title = {Self-Supervised Pre-Training With Masked Shape Prediction for 3D Scene Understanding}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1168-1178} }

Efficient and Explicit Modelling of Image Hierarchies for Image Restoration

Yawei Li,

Yuchen Fan,

Xiaoyu Xiang,

Denis Demandolx,

Rakesh Ranjan,

Radu Timofte,

Luc Van Gool

[pdf] [arXiv]

[bibtex]

@InProceedings{Li_2023_CVPR, author = {Li, Yawei and Fan, Yuchen and Xiang, Xiaoyu and Demandolx, Denis and Ranjan, Rakesh and Timofte, Radu and Van Gool, Luc}, title = {Efficient and Explicit Modelling of Image Hierarchies for Image Restoration}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {18278-18289} }

Guiding Pseudo-Labels With Uncertainty Estimation for Source-Free Unsupervised Domain Adaptation

Mattia Litrico,

Alessio Del Bue,

Pietro Morerio

[pdf] [arXiv]

[bibtex]

@InProceedings{Litrico_2023_CVPR, author = {Litrico, Mattia and Del Bue, Alessio and Morerio, Pietro}, title = {Guiding Pseudo-Labels With Uncertainty Estimation for Source-Free Unsupervised Domain Adaptation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7640-7650} }

HuManiFlow: Ancestor-Conditioned Normalising Flows on SO(3) Manifolds for Human Pose and Shape Distribution Estimation

Akash Sengupta,

Ignas Budvytis,

Roberto Cipolla

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Sengupta_2023_CVPR, author = {Sengupta, Akash and Budvytis, Ignas and Cipolla, Roberto}, title = {HuManiFlow: Ancestor-Conditioned Normalising Flows on SO(3) Manifolds for Human Pose and Shape Distribution Estimation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4779-4789} }

DKT: Diverse Knowledge Transfer Transformer for Class Incremental Learning

Xinyuan Gao,

Yuhang He,

Songlin Dong,

Jie Cheng,

Xing Wei,

Yihong Gong

[pdf] [supp]

[bibtex]

@InProceedings{Gao_2023_CVPR, author = {Gao, Xinyuan and He, Yuhang and Dong, Songlin and Cheng, Jie and Wei, Xing and Gong, Yihong}, title = {DKT: Diverse Knowledge Transfer Transformer for Class Incremental Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {24236-24245} }

LipFormer: High-Fidelity and Generalizable Talking Face Generation With a Pre-Learned Facial Codebook

Jiayu Wang,

Kang Zhao,

Shiwei Zhang,

Yingya Zhang,

Yujun Shen,

Deli Zhao,

Jingren Zhou

[pdf] [supp]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Jiayu and Zhao, Kang and Zhang, Shiwei and Zhang, Yingya and Shen, Yujun and Zhao, Deli and Zhou, Jingren}, title = {LipFormer: High-Fidelity and Generalizable Talking Face Generation With a Pre-Learned Facial Codebook}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13844-13853} }

Generalizable Local Feature Pre-Training for Deformable Shape Analysis

Souhaib Attaiki,

Lei Li,

Maks Ovsjanikov

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Attaiki_2023_CVPR, author = {Attaiki, Souhaib and Li, Lei and Ovsjanikov, Maks}, title = {Generalizable Local Feature Pre-Training for Deformable Shape Analysis}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13650-13661} }

TarViS: A Unified Approach for Target-Based Video Segmentation

Ali Athar,

Alexander Hermans,

Jonathon Luiten,

Deva Ramanan,

Bastian Leibe

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Athar_2023_CVPR, author = {Athar, Ali and Hermans, Alexander and Luiten, Jonathon and Ramanan, Deva and Leibe, Bastian}, title = {TarViS: A Unified Approach for Target-Based Video Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {18738-18748} }

Progressive Random Convolutions for Single Domain Generalization

Seokeon Choi,

Debasmit Das,

Sungha Choi,

Seunghan Yang,

Hyunsin Park,

Sungrack Yun

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Choi_2023_CVPR, author = {Choi, Seokeon and Das, Debasmit and Choi, Sungha and Yang, Seunghan and Park, Hyunsin and Yun, Sungrack}, title = {Progressive Random Convolutions for Single Domain Generalization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10312-10322} }

IDGI: A Framework To Eliminate Explanation Noise From Integrated Gradients

Ruo Yang,

Binghui Wang,

Mustafa Bilgic

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Yang_2023_CVPR, author = {Yang, Ruo and Wang, Binghui and Bilgic, Mustafa}, title = {IDGI: A Framework To Eliminate Explanation Noise From Integrated Gradients}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {23725-23734} }

OPE-SR: Orthogonal Position Encoding for Designing a Parameter-Free Upsampling Module in Arbitrary-Scale Image Super-Resolution

Gaochao Song,

Qian Sun,

Luo Zhang,

Ran Su,

Jianfeng Shi,

Ying He

[pdf] [supp]

[bibtex]

@InProceedings{Song_2023_CVPR, author = {Song, Gaochao and Sun, Qian and Zhang, Luo and Su, Ran and Shi, Jianfeng and He, Ying}, title = {OPE-SR: Orthogonal Position Encoding for Designing a Parameter-Free Upsampling Module in Arbitrary-Scale Image Super-Resolution}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10009-10020} }

Implicit Surface Contrastive Clustering for LiDAR Point Clouds

Zaiwei Zhang,

Min Bai,

Erran Li

[pdf] [supp]

[bibtex]

@InProceedings{Zhang_2023_CVPR, author = {Zhang, Zaiwei and Bai, Min and Li, Erran}, title = {Implicit Surface Contrastive Clustering for LiDAR Point Clouds}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {21716-21725} }

EC2: Emergent Communication for Embodied Control

Yao Mu,

Shunyu Yao,

Mingyu Ding,

Ping Luo,

Chuang Gan

[pdf] [supp]

[bibtex]

@InProceedings{Mu_2023_CVPR, author = {Mu, Yao and Yao, Shunyu and Ding, Mingyu and Luo, Ping and Gan, Chuang}, title = {EC2: Emergent Communication for Embodied Control}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6704-6714} }

Semantic Ray: Learning a Generalizable Semantic Field With Cross-Reprojection Attention

Fangfu Liu,

Chubin Zhang,

Yu Zheng,

Yueqi Duan

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Liu_2023_CVPR, author = {Liu, Fangfu and Zhang, Chubin and Zheng, Yu and Duan, Yueqi}, title = {Semantic Ray: Learning a Generalizable Semantic Field With Cross-Reprojection Attention}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {17386-17396} }

DynamicDet: A Unified Dynamic Architecture for Object Detection

Zhihao Lin,

Yongtao Wang,

Jinhe Zhang,

Xiaojie Chu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Lin_2023_CVPR, author = {Lin, Zhihao and Wang, Yongtao and Zhang, Jinhe and Chu, Xiaojie}, title = {DynamicDet: A Unified Dynamic Architecture for Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6282-6291} }

I2MVFormer: Large Language Model Generated Multi-View Document Supervision for Zero-Shot Image Classification

Muhammad Ferjad Naeem,

Muhammad Gul Zain Ali Khan,

Yongqin Xian,

Muhammad Zeshan Afzal,

Didier Stricker,

Luc Van Gool,

Federico Tombari

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Naeem_2023_CVPR, author = {Naeem, Muhammad Ferjad and Khan, Muhammad Gul Zain Ali and Xian, Yongqin and Afzal, Muhammad Zeshan and Stricker, Didier and Van Gool, Luc and Tombari, Federico}, title = {I2MVFormer: Large Language Model Generated Multi-View Document Supervision for Zero-Shot Image Classification}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15169-15179} }

MixSim: A Hierarchical Framework for Mixed Reality Traffic Simulation

Simon Suo,

Kelvin Wong,

Justin Xu,

James Tu,

Alexander Cui,

Sergio Casas,

Raquel Urtasun

[pdf] [supp]

[bibtex]

@InProceedings{Suo_2023_CVPR, author = {Suo, Simon and Wong, Kelvin and Xu, Justin and Tu, James and Cui, Alexander and Casas, Sergio and Urtasun, Raquel}, title = {MixSim: A Hierarchical Framework for Mixed Reality Traffic Simulation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9622-9631} }

ORCa: Glossy Objects As Radiance-Field Cameras

Kushagra Tiwary,

Akshat Dave,

Nikhil Behari,

Tzofi Klinghoffer,

Ashok Veeraraghavan,

Ramesh Raskar

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Tiwary_2023_CVPR, author = {Tiwary, Kushagra and Dave, Akshat and Behari, Nikhil and Klinghoffer, Tzofi and Veeraraghavan, Ashok and Raskar, Ramesh}, title = {ORCa: Glossy Objects As Radiance-Field Cameras}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {20773-20782} }

SECAD-Net: Self-Supervised CAD Reconstruction by Learning Sketch-Extrude Operations

Pu Li,

Jianwei Guo,

Xiaopeng Zhang,

Dong-Ming Yan

[pdf] [supp]

[bibtex]

@InProceedings{Li_2023_CVPR, author = {Li, Pu and Guo, Jianwei and Zhang, Xiaopeng and Yan, Dong-Ming}, title = {SECAD-Net: Self-Supervised CAD Reconstruction by Learning Sketch-Extrude Operations}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16816-16826} }

Context-Aware Alignment and Mutual Masking for 3D-Language Pre-Training

Zhao Jin,

Munawar Hayat,

Yuwei Yang,

Yulan Guo,

Yinjie Lei

[pdf] [supp]

[bibtex]

@InProceedings{Jin_2023_CVPR, author = {Jin, Zhao and Hayat, Munawar and Yang, Yuwei and Guo, Yulan and Lei, Yinjie}, title = {Context-Aware Alignment and Mutual Masking for 3D-Language Pre-Training}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10984-10994} }

MDL-NAS: A Joint Multi-Domain Learning Framework for Vision Transformer

Shiguang Wang,

Tao Xie,

Jian Cheng,

Xingcheng Zhang,

Haijun Liu

[pdf] [supp]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Shiguang and Xie, Tao and Cheng, Jian and Zhang, Xingcheng and Liu, Haijun}, title = {MDL-NAS: A Joint Multi-Domain Learning Framework for Vision Transformer}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {20094-20104} }

Dual Alignment Unsupervised Domain Adaptation for Video-Text Retrieval

Xiaoshuai Hao,

Wanqian Zhang,

Dayan Wu,

Fei Zhu,

Bo Li

[pdf]

[bibtex]

@InProceedings{Hao_2023_CVPR, author = {Hao, Xiaoshuai and Zhang, Wanqian and Wu, Dayan and Zhu, Fei and Li, Bo}, title = {Dual Alignment Unsupervised Domain Adaptation for Video-Text Retrieval}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {18962-18972} }

Common Pets in 3D: Dynamic New-View Synthesis of Real-Life Deformable Categories

Samarth Sinha,

Roman Shapovalov,

Jeremy Reizenstein,

Ignacio Rocco,

Natalia Neverova,

Andrea Vedaldi,

David Novotny

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Sinha_2023_CVPR, author = {Sinha, Samarth and Shapovalov, Roman and Reizenstein, Jeremy and Rocco, Ignacio and Neverova, Natalia and Vedaldi, Andrea and Novotny, David}, title = {Common Pets in 3D: Dynamic New-View Synthesis of Real-Life Deformable Categories}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4881-4891} }

Generalized Decoding for Pixel, Image, and Language

Xueyan Zou,

Zi-Yi Dou,

Jianwei Yang,

Zhe Gan,

Linjie Li,

Chunyuan Li,

Xiyang Dai,

Harkirat Behl,

Jianfeng Wang,

Lu Yuan,

Nanyun Peng,

Lijuan Wang,

Yong Jae Lee,

Jianfeng Gao

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Zou_2023_CVPR, author = {Zou, Xueyan and Dou, Zi-Yi and Yang, Jianwei and Gan, Zhe and Li, Linjie and Li, Chunyuan and Dai, Xiyang and Behl, Harkirat and Wang, Jianfeng and Yuan, Lu and Peng, Nanyun and Wang, Lijuan and Lee, Yong Jae and Gao, Jianfeng}, title = {Generalized Decoding for Pixel, Image, and Language}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15116-15127} }

Towards Unified Scene Text Spotting Based on Sequence Generation

Taeho Kil,

Seonghyeon Kim,

Sukmin Seo,

Yoonsik Kim,

Daehee Kim

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Kil_2023_CVPR, author = {Kil, Taeho and Kim, Seonghyeon and Seo, Sukmin and Kim, Yoonsik and Kim, Daehee}, title = {Towards Unified Scene Text Spotting Based on Sequence Generation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15223-15232} }

Normal-Guided Garment UV Prediction for Human Re-Texturing

Yasamin Jafarian,

Tuanfeng Y. Wang,

Duygu Ceylan,

Jimei Yang,

Nathan Carr,

Yi Zhou,

Hyun Soo Park

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Jafarian_2023_CVPR, author = {Jafarian, Yasamin and Wang, Tuanfeng Y. and Ceylan, Duygu and Yang, Jimei and Carr, Nathan and Zhou, Yi and Park, Hyun Soo}, title = {Normal-Guided Garment UV Prediction for Human Re-Texturing}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4627-4636} }

Learning Compact Representations for LiDAR Completion and Generation

Yuwen Xiong,

Wei-Chiu Ma,

Jingkang Wang,

Raquel Urtasun

[pdf] [supp]

[bibtex]

@InProceedings{Xiong_2023_CVPR, author = {Xiong, Yuwen and Ma, Wei-Chiu and Wang, Jingkang and Urtasun, Raquel}, title = {Learning Compact Representations for LiDAR Completion and Generation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1074-1083} }

Computational Flash Photography Through Intrinsics

Sepideh Sarajian Maralan,

Chris Careaga,

Yagiz Aksoy

[pdf] [supp]

[bibtex]

@InProceedings{Maralan_2023_CVPR, author = {Maralan, Sepideh Sarajian and Careaga, Chris and Aksoy, Yagiz}, title = {Computational Flash Photography Through Intrinsics}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16654-16662} }

Hubs and Hyperspheres: Reducing Hubness and Improving Transductive Few-Shot Learning With Hyperspherical Embeddings

Daniel J. Trosten,

Rwiddhi Chakraborty,

Sigurd Løkse,

Kristoffer Knutsen Wickstrøm,

Robert Jenssen,

Michael C. Kampffmeyer

[pdf] [supp]

[bibtex]

@InProceedings{Trosten_2023_CVPR, author = {Trosten, Daniel J. and Chakraborty, Rwiddhi and L{\o}kse, Sigurd and Wickstr{\o}m, Kristoffer Knutsen and Jenssen, Robert and Kampffmeyer, Michael C.}, title = {Hubs and Hyperspheres: Reducing Hubness and Improving Transductive Few-Shot Learning With Hyperspherical Embeddings}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7527-7536} }

Improving Graph Representation for Point Cloud Segmentation via Attentive Filtering

Nan Zhang,

Zhiyi Pan,

Thomas H. Li,

Wei Gao,

Ge Li

[pdf] [supp]

[bibtex]

@InProceedings{Zhang_2023_CVPR, author = {Zhang, Nan and Pan, Zhiyi and Li, Thomas H. and Gao, Wei and Li, Ge}, title = {Improving Graph Representation for Point Cloud Segmentation via Attentive Filtering}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1244-1254} }

SpaText: Spatio-Textual Representation for Controllable Image Generation

Omri Avrahami,

Thomas Hayes,

Oran Gafni,

Sonal Gupta,

Yaniv Taigman,

Devi Parikh,

Dani Lischinski,

Ohad Fried,

Xi Yin

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Avrahami_2023_CVPR, author = {Avrahami, Omri and Hayes, Thomas and Gafni, Oran and Gupta, Sonal and Taigman, Yaniv and Parikh, Devi and Lischinski, Dani and Fried, Ohad and Yin, Xi}, title = {SpaText: Spatio-Textual Representation for Controllable Image Generation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {18370-18380} }

The ObjectFolder Benchmark: Multisensory Learning With Neural and Real Objects

Ruohan Gao,

Yiming Dou,

Hao Li,

Tanmay Agarwal,

Jeannette Bohg,

Yunzhu Li,

Li Fei-Fei,

Jiajun Wu

[pdf]

[bibtex]

@InProceedings{Gao_2023_CVPR, author = {Gao, Ruohan and Dou, Yiming and Li, Hao and Agarwal, Tanmay and Bohg, Jeannette and Li, Yunzhu and Fei-Fei, Li and Wu, Jiajun}, title = {The ObjectFolder Benchmark: Multisensory Learning With Neural and Real Objects}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {17276-17286} }

ScaleFL: Resource-Adaptive Federated Learning With Heterogeneous Clients

Fatih Ilhan,

Gong Su,

Ling Liu

[pdf] [supp]

[bibtex]

@InProceedings{Ilhan_2023_CVPR, author = {Ilhan, Fatih and Su, Gong and Liu, Ling}, title = {ScaleFL: Resource-Adaptive Federated Learning With Heterogeneous Clients}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {24532-24541} }

X3KD: Knowledge Distillation Across Modalities, Tasks and Stages for Multi-Camera 3D Object Detection

Marvin Klingner,

Shubhankar Borse,

Varun Ravi Kumar,

Behnaz Rezaei,

Venkatraman Narayanan,

Senthil Yogamani,

Fatih Porikli

[pdf] [supp]

[bibtex]

@InProceedings{Klingner_2023_CVPR, author = {Klingner, Marvin and Borse, Shubhankar and Kumar, Varun Ravi and Rezaei, Behnaz and Narayanan, Venkatraman and Yogamani, Senthil and Porikli, Fatih}, title = {X3KD: Knowledge Distillation Across Modalities, Tasks and Stages for Multi-Camera 3D Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13343-13353} }

PCT-Net: Full Resolution Image Harmonization Using Pixel-Wise Color Transformations

Julian Jorge Andrade Guerreiro,

Mitsuru Nakazawa,

Björn Stenger

[pdf] [supp]

[bibtex]

@InProceedings{Guerreiro_2023_CVPR, author = {Guerreiro, Julian Jorge Andrade and Nakazawa, Mitsuru and Stenger, Bj\"orn}, title = {PCT-Net: Full Resolution Image Harmonization Using Pixel-Wise Color Transformations}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5917-5926} }

Architecture, Dataset and Model-Scale Agnostic Data-Free Meta-Learning

Zixuan Hu,

Li Shen,

Zhenyi Wang,

Tongliang Liu,

Chun Yuan,

Dacheng Tao

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Hu_2023_CVPR, author = {Hu, Zixuan and Shen, Li and Wang, Zhenyi and Liu, Tongliang and Yuan, Chun and Tao, Dacheng}, title = {Architecture, Dataset and Model-Scale Agnostic Data-Free Meta-Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7736-7745} }

Egocentric Video Task Translation

Zihui Xue,

Yale Song,

Kristen Grauman,

Lorenzo Torresani

[pdf] [supp]

[bibtex]

@InProceedings{Xue_2023_CVPR, author = {Xue, Zihui and Song, Yale and Grauman, Kristen and Torresani, Lorenzo}, title = {Egocentric Video Task Translation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2310-2320} }

Rawgment: Noise-Accounted RAW Augmentation Enables Recognition in a Wide Variety of Environments

Masakazu Yoshimura,

Junji Otsuka,

Atsushi Irie,

Takeshi Ohashi

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Yoshimura_2023_CVPR, author = {Yoshimura, Masakazu and Otsuka, Junji and Irie, Atsushi and Ohashi, Takeshi}, title = {Rawgment: Noise-Accounted RAW Augmentation Enables Recognition in a Wide Variety of Environments}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14007-14017} }

Reliable and Interpretable Personalized Federated Learning

Zixuan Qin,

Liu Yang,

Qilong Wang,

Yahong Han,

Qinghua Hu

[pdf]

[bibtex]

@InProceedings{Qin_2023_CVPR, author = {Qin, Zixuan and Yang, Liu and Wang, Qilong and Han, Yahong and Hu, Qinghua}, title = {Reliable and Interpretable Personalized Federated Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {20422-20431} }

Optimal Transport Minimization: Crowd Localization on Density Maps for Semi-Supervised Counting

Wei Lin,

Antoni B. Chan

[pdf] [supp]

[bibtex]

@InProceedings{Lin_2023_CVPR, author = {Lin, Wei and Chan, Antoni B.}, title = {Optimal Transport Minimization: Crowd Localization on Density Maps for Semi-Supervised Counting}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {21663-21673} }

AdamsFormer for Spatial Action Localization in the Future

Hyung-gun Chi,

Kwonjoon Lee,

Nakul Agarwal,

Yi Xu,

Karthik Ramani,

Chiho Choi

[pdf] [supp]

[bibtex]

@InProceedings{Chi_2023_CVPR, author = {Chi, Hyung-gun and Lee, Kwonjoon and Agarwal, Nakul and Xu, Yi and Ramani, Karthik and Choi, Chiho}, title = {AdamsFormer for Spatial Action Localization in the Future}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {17885-17895} }

Leveraging per Image-Token Consistency for Vision-Language Pre-Training

Yunhao Gou,

Tom Ko,

Hansi Yang,

James Kwok,

Yu Zhang,

Mingxuan Wang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Gou_2023_CVPR, author = {Gou, Yunhao and Ko, Tom and Yang, Hansi and Kwok, James and Zhang, Yu and Wang, Mingxuan}, title = {Leveraging per Image-Token Consistency for Vision-Language Pre-Training}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {19155-19164} }

BITE: Beyond Priors for Improved Three-D Dog Pose Estimation

Nadine Rüegg,

Shashank Tripathi,

Konrad Schindler,

Michael J. Black,

Silvia Zuffi

[pdf] [supp]

[bibtex]

@InProceedings{Ruegg_2023_CVPR, author = {R\"uegg, Nadine and Tripathi, Shashank and Schindler, Konrad and Black, Michael J. and Zuffi, Silvia}, title = {BITE: Beyond Priors for Improved Three-D Dog Pose Estimation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8867-8876} }

Equivalent Transformation and Dual Stream Network Construction for Mobile Image Super-Resolution

Jiahao Chao,

Zhou Zhou,

Hongfan Gao,

Jiali Gong,

Zhengfeng Yang,

Zhenbing Zeng,

Lydia Dehbi

[pdf] [supp]

[bibtex]

@InProceedings{Chao_2023_CVPR, author = {Chao, Jiahao and Zhou, Zhou and Gao, Hongfan and Gong, Jiali and Yang, Zhengfeng and Zeng, Zhenbing and Dehbi, Lydia}, title = {Equivalent Transformation and Dual Stream Network Construction for Mobile Image Super-Resolution}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14102-14111} }

UTM: A Unified Multiple Object Tracking Model With Identity-Aware Feature Enhancement

Sisi You,

Hantao Yao,

Bing-Kun Bao,

Changsheng Xu

[pdf] [supp]

[bibtex]

@InProceedings{You_2023_CVPR, author = {You, Sisi and Yao, Hantao and Bao, Bing-Kun and Xu, Changsheng}, title = {UTM: A Unified Multiple Object Tracking Model With Identity-Aware Feature Enhancement}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {21876-21886} }

On the Stability-Plasticity Dilemma of Class-Incremental Learning

Dongwan Kim,

Bohyung Han

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Kim_2023_CVPR, author = {Kim, Dongwan and Han, Bohyung}, title = {On the Stability-Plasticity Dilemma of Class-Incremental Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {20196-20204} }

Generalization Matters: Loss Minima Flattening via Parameter Hybridization for Efficient Online Knowledge Distillation

Tianli Zhang,

Mengqi Xue,

Jiangtao Zhang,

Haofei Zhang,

Yu Wang,

Lechao Cheng,

Jie Song,

Mingli Song

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Zhang_2023_CVPR, author = {Zhang, Tianli and Xue, Mengqi and Zhang, Jiangtao and Zhang, Haofei and Wang, Yu and Cheng, Lechao and Song, Jie and Song, Mingli}, title = {Generalization Matters: Loss Minima Flattening via Parameter Hybridization for Efficient Online Knowledge Distillation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {20176-20185} }

Gaussian Label Distribution Learning for Spherical Image Object Detection

Hang Xu,

Xinyuan Liu,

Qiang Zhao,

Yike Ma,

Chenggang Yan,

Feng Dai

[pdf] [supp]

[bibtex]

@InProceedings{Xu_2023_CVPR, author = {Xu, Hang and Liu, Xinyuan and Zhao, Qiang and Ma, Yike and Yan, Chenggang and Dai, Feng}, title = {Gaussian Label Distribution Learning for Spherical Image Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1033-1042} }

High-Resolution Image Reconstruction With Latent Diffusion Models From Human Brain Activity

Yu Takagi,

Shinji Nishimoto

[pdf] [supp]

[bibtex]

@InProceedings{Takagi_2023_CVPR, author = {Takagi, Yu and Nishimoto, Shinji}, title = {High-Resolution Image Reconstruction With Latent Diffusion Models From Human Brain Activity}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14453-14463} }

L-CoIns: Language-Based Colorization With Instance Awareness

Zheng Chang,

Shuchen Weng,

Peixuan Zhang,

Yu Li,

Si Li,

Boxin Shi

[pdf] [supp]

[bibtex]

@InProceedings{Chang_2023_CVPR, author = {Chang, Zheng and Weng, Shuchen and Zhang, Peixuan and Li, Yu and Li, Si and Shi, Boxin}, title = {L-CoIns: Language-Based Colorization With Instance Awareness}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {19221-19230} }

On the Effects of Self-Supervision and Contrastive Alignment in Deep Multi-View Clustering

Daniel J. Trosten,

Sigurd Løkse,

Robert Jenssen,

Michael C. Kampffmeyer

[pdf] [supp]

[bibtex]

@InProceedings{Trosten_2023_CVPR, author = {Trosten, Daniel J. and L{\o}kse, Sigurd and Jenssen, Robert and Kampffmeyer, Michael C.}, title = {On the Effects of Self-Supervision and Contrastive Alignment in Deep Multi-View Clustering}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {23976-23985} }

Activating More Pixels in Image Super-Resolution Transformer

Xiangyu Chen,

Xintao Wang,

Jiantao Zhou,

Yu Qiao,

Chao Dong

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Chen_2023_CVPR, author = {Chen, Xiangyu and Wang, Xintao and Zhou, Jiantao and Qiao, Yu and Dong, Chao}, title = {Activating More Pixels in Image Super-Resolution Transformer}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {22367-22377} }

BEV-SAN: Accurate BEV 3D Object Detection via Slice Attention Networks

Xiaowei Chi,

Jiaming Liu,

Ming Lu,

Rongyu Zhang,

Zhaoqing Wang,

Yandong Guo,

Shanghang Zhang

[pdf] [supp]

[bibtex]

@InProceedings{Chi_2023_CVPR, author = {Chi, Xiaowei and Liu, Jiaming and Lu, Ming and Zhang, Rongyu and Wang, Zhaoqing and Guo, Yandong and Zhang, Shanghang}, title = {BEV-SAN: Accurate BEV 3D Object Detection via Slice Attention Networks}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {17461-17470} }

The Dark Side of Dynamic Routing Neural Networks: Towards Efficiency Backdoor Injection

Simin Chen,

Hanlin Chen,

Mirazul Haque,

Cong Liu,

Wei Yang

[pdf] [supp]

[bibtex]

@InProceedings{Chen_2023_CVPR, author = {Chen, Simin and Chen, Hanlin and Haque, Mirazul and Liu, Cong and Yang, Wei}, title = {The Dark Side of Dynamic Routing Neural Networks: Towards Efficiency Backdoor Injection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {24585-24594} }

Better "CMOS" Produces Clearer Images: Learning Space-Variant Blur Estimation for Blind Image Super-Resolution

Xuhai Chen,

Jiangning Zhang,

Chao Xu,

Yabiao Wang,

Chengjie Wang,

Yong Liu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Chen_2023_CVPR, author = {Chen, Xuhai and Zhang, Jiangning and Xu, Chao and Wang, Yabiao and Wang, Chengjie and Liu, Yong}, title = {Better ''CMOS'' Produces Clearer Images: Learning Space-Variant Blur Estimation for Blind Image Super-Resolution}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1651-1661} }

MixTeacher: Mining Promising Labels With Mixed Scale Teacher for Semi-Supervised Object Detection

Liang Liu,

Boshen Zhang,

Jiangning Zhang,

Wuhao Zhang,

Zhenye Gan,

Guanzhong Tian,

Wenbing Zhu,

Yabiao Wang,

Chengjie Wang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Liu_2023_CVPR, author = {Liu, Liang and Zhang, Boshen and Zhang, Jiangning and Zhang, Wuhao and Gan, Zhenye and Tian, Guanzhong and Zhu, Wenbing and Wang, Yabiao and Wang, Chengjie}, title = {MixTeacher: Mining Promising Labels With Mixed Scale Teacher for Semi-Supervised Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7370-7379} }

DARE-GRAM: Unsupervised Domain Adaptation Regression by Aligning Inverse Gram Matrices

Ismail Nejjar,

Qin Wang,

Olga Fink

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Nejjar_2023_CVPR, author = {Nejjar, Ismail and Wang, Qin and Fink, Olga}, title = {DARE-GRAM: Unsupervised Domain Adaptation Regression by Aligning Inverse Gram Matrices}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11744-11754} }

Bidirectional Copy-Paste for Semi-Supervised Medical Image Segmentation

Yunhao Bai,

Duowen Chen,

Qingli Li,

Wei Shen,

Yan Wang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Bai_2023_CVPR, author = {Bai, Yunhao and Chen, Duowen and Li, Qingli and Shen, Wei and Wang, Yan}, title = {Bidirectional Copy-Paste for Semi-Supervised Medical Image Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11514-11524} }

Learning Discriminative Representations for Skeleton Based Action Recognition

Huanyu Zhou,

Qingjie Liu,

Yunhong Wang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Zhou_2023_CVPR, author = {Zhou, Huanyu and Liu, Qingjie and Wang, Yunhong}, title = {Learning Discriminative Representations for Skeleton Based Action Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10608-10617} }

NeRF in the Palm of Your Hand: Corrective Augmentation for Robotics via Novel-View Synthesis

Allan Zhou,

Moo Jin Kim,

Lirui Wang,

Pete Florence,

Chelsea Finn

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Zhou_2023_CVPR, author = {Zhou, Allan and Kim, Moo Jin and Wang, Lirui and Florence, Pete and Finn, Chelsea}, title = {NeRF in the Palm of Your Hand: Corrective Augmentation for Robotics via Novel-View Synthesis}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {17907-17917} }

NeuMap: Neural Coordinate Mapping by Auto-Transdecoder for Camera Localization

Shitao Tang,

Sicong Tang,

Andrea Tagliasacchi,

Ping Tan,

Yasutaka Furukawa

[pdf] [arXiv]

[bibtex]

@InProceedings{Tang_2023_CVPR, author = {Tang, Shitao and Tang, Sicong and Tagliasacchi, Andrea and Tan, Ping and Furukawa, Yasutaka}, title = {NeuMap: Neural Coordinate Mapping by Auto-Transdecoder for Camera Localization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {929-939} }

AShapeFormer: Semantics-Guided Object-Level Active Shape Encoding for 3D Object Detection via Transformers

Zechuan Li,

Hongshan Yu,

Zhengeng Yang,

Tongjia Chen,

Naveed Akhtar

[pdf] [supp]

[bibtex]

@InProceedings{Li_2023_CVPR, author = {Li, Zechuan and Yu, Hongshan and Yang, Zhengeng and Chen, Tongjia and Akhtar, Naveed}, title = {AShapeFormer: Semantics-Guided Object-Level Active Shape Encoding for 3D Object Detection via Transformers}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1012-1021} }

SeSDF: Self-Evolved Signed Distance Field for Implicit 3D Clothed Human Reconstruction

Yukang Cao,

Kai Han,

Kwan-Yee K. Wong

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Cao_2023_CVPR, author = {Cao, Yukang and Han, Kai and Wong, Kwan-Yee K.}, title = {SeSDF: Self-Evolved Signed Distance Field for Implicit 3D Clothed Human Reconstruction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4647-4657} }

Deep Depth Estimation From Thermal Image

Ukcheol Shin,

Jinsun Park,

In So Kweon

[pdf] [supp]

[bibtex]

@InProceedings{Shin_2023_CVPR, author = {Shin, Ukcheol and Park, Jinsun and Kweon, In So}, title = {Deep Depth Estimation From Thermal Image}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1043-1053} }

Cross-GAN Auditing: Unsupervised Identification of Attribute Level Similarities and Differences Between Pretrained Generative Models

Matthew L. Olson,

Shusen Liu,

Rushil Anirudh,

Jayaraman J. Thiagarajan,

Peer-Timo Bremer,

Weng-Keen Wong

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Olson_2023_CVPR, author = {Olson, Matthew L. and Liu, Shusen and Anirudh, Rushil and Thiagarajan, Jayaraman J. and Bremer, Peer-Timo and Wong, Weng-Keen}, title = {Cross-GAN Auditing: Unsupervised Identification of Attribute Level Similarities and Differences Between Pretrained Generative Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7981-7990} }

Building Rearticulable Models for Arbitrary 3D Objects From 4D Point Clouds

Shaowei Liu,

Saurabh Gupta,

Shenlong Wang

[pdf] [supp]

[bibtex]

@InProceedings{Liu_2023_CVPR, author = {Liu, Shaowei and Gupta, Saurabh and Wang, Shenlong}, title = {Building Rearticulable Models for Arbitrary 3D Objects From 4D Point Clouds}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {21138-21147} }

Backdoor Defense via Adaptively Splitting Poisoned Dataset

Kuofeng Gao,

Yang Bai,

Jindong Gu,

Yong Yang,

Shu-Tao Xia

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Gao_2023_CVPR, author = {Gao, Kuofeng and Bai, Yang and Gu, Jindong and Yang, Yong and Xia, Shu-Tao}, title = {Backdoor Defense via Adaptively Splitting Poisoned Dataset}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4005-4014} }

Neural Congealing: Aligning Images to a Joint Semantic Atlas

Dolev Ofri-Amar,

Michal Geyer,

Yoni Kasten,

Tali Dekel

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Ofri-Amar_2023_CVPR, author = {Ofri-Amar, Dolev and Geyer, Michal and Kasten, Yoni and Dekel, Tali}, title = {Neural Congealing: Aligning Images to a Joint Semantic Atlas}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {19403-19412} }

Adaptive Spot-Guided Transformer for Consistent Local Feature Matching

Jiahuan Yu,

Jiahao Chang,

Jianfeng He,

Tianzhu Zhang,

Jiyang Yu,

Feng Wu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Yu_2023_CVPR, author = {Yu, Jiahuan and Chang, Jiahao and He, Jianfeng and Zhang, Tianzhu and Yu, Jiyang and Wu, Feng}, title = {Adaptive Spot-Guided Transformer for Consistent Local Feature Matching}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {21898-21908} }

Wide-Angle Rectification via Content-Aware Conformal Mapping

Qi Zhang,

Hongdong Li,

Qing Wang

[pdf] [supp]

[bibtex]

@InProceedings{Zhang_2023_CVPR, author = {Zhang, Qi and Li, Hongdong and Wang, Qing}, title = {Wide-Angle Rectification via Content-Aware Conformal Mapping}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {17357-17365} }

Towards Stable Human Pose Estimation via Cross-View Fusion and Foot Stabilization

Li’an Zhuo,

Jian Cao,

Qi Wang,

Bang Zhang,

Liefeng Bo

[pdf] [supp]

[bibtex]

@InProceedings{Zhuo_2023_CVPR, author = {Zhuo, Li{\textquoteright}an and Cao, Jian and Wang, Qi and Zhang, Bang and Bo, Liefeng}, title = {Towards Stable Human Pose Estimation via Cross-View Fusion and Foot Stabilization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {650-659} }

Few-Shot Non-Line-of-Sight Imaging With Signal-Surface Collaborative Regularization

Xintong Liu,

Jianyu Wang,

Leping Xiao,

Xing Fu,

Lingyun Qiu,

Zuoqiang Shi

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Liu_2023_CVPR, author = {Liu, Xintong and Wang, Jianyu and Xiao, Leping and Fu, Xing and Qiu, Lingyun and Shi, Zuoqiang}, title = {Few-Shot Non-Line-of-Sight Imaging With Signal-Surface Collaborative Regularization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13303-13312} }

SINE: SINgle Image Editing With Text-to-Image Diffusion Models

Zhixing Zhang,

Ligong Han,

Arnab Ghosh,

Dimitris N. Metaxas,

Jian Ren

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Zhang_2023_CVPR, author = {Zhang, Zhixing and Han, Ligong and Ghosh, Arnab and Metaxas, Dimitris N. and Ren, Jian}, title = {SINE: SINgle Image Editing With Text-to-Image Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6027-6037} }

Probabilistic Debiasing of Scene Graphs

Bashirul Azam Biswas,

Qiang Ji

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Biswas_2023_CVPR, author = {Biswas, Bashirul Azam and Ji, Qiang}, title = {Probabilistic Debiasing of Scene Graphs}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10429-10438} }

OSAN: A One-Stage Alignment Network To Unify Multimodal Alignment and Unsupervised Domain Adaptation

Ye Liu,

Lingfeng Qiao,

Changchong Lu,

Di Yin,

Chen Lin,

Haoyuan Peng,

Bo Ren

[pdf]

[bibtex]

@InProceedings{Liu_2023_CVPR, author = {Liu, Ye and Qiao, Lingfeng and Lu, Changchong and Yin, Di and Lin, Chen and Peng, Haoyuan and Ren, Bo}, title = {OSAN: A One-Stage Alignment Network To Unify Multimodal Alignment and Unsupervised Domain Adaptation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3551-3560} }

Token Turing Machines

Michael S. Ryoo,

Keerthana Gopalakrishnan,

Kumara Kahatapitiya,

Ted Xiao,

Kanishka Rao,

Austin Stone,

Yao Lu,

Julian Ibarz,

Anurag Arnab

[pdf] [arXiv]

[bibtex]

@InProceedings{Ryoo_2023_CVPR, author = {Ryoo, Michael S. and Gopalakrishnan, Keerthana and Kahatapitiya, Kumara and Xiao, Ted and Rao, Kanishka and Stone, Austin and Lu, Yao and Ibarz, Julian and Arnab, Anurag}, title = {Token Turing Machines}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {19070-19081} }

Solving 3D Inverse Problems Using Pre-Trained 2D Diffusion Models

Hyungjin Chung,

Dohoon Ryu,

Michael T. McCann,

Marc L. Klasky,

Jong Chul Ye

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Chung_2023_CVPR, author = {Chung, Hyungjin and Ryu, Dohoon and McCann, Michael T. and Klasky, Marc L. and Ye, Jong Chul}, title = {Solving 3D Inverse Problems Using Pre-Trained 2D Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {22542-22551} }

Heat Diffusion Based Multi-Scale and Geometric Structure-Aware Transformer for Mesh Segmentation

Chi-Chong Wong

[pdf]

[bibtex]

@InProceedings{Wong_2023_CVPR, author = {Wong, Chi-Chong}, title = {Heat Diffusion Based Multi-Scale and Geometric Structure-Aware Transformer for Mesh Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4413-4422} }

DyNCA: Real-Time Dynamic Texture Synthesis Using Neural Cellular Automata

Ehsan Pajouheshgar,

Yitao Xu,

Tong Zhang,

Sabine Süsstrunk

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Pajouheshgar_2023_CVPR, author = {Pajouheshgar, Ehsan and Xu, Yitao and Zhang, Tong and S\"usstrunk, Sabine}, title = {DyNCA: Real-Time Dynamic Texture Synthesis Using Neural Cellular Automata}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {20742-20751} }

Semantic-Promoted Debiasing and Background Disambiguation for Zero-Shot Instance Segmentation

Shuting He,

Henghui Ding,

Wei Jiang

[pdf] [supp]

[bibtex]

@InProceedings{He_2023_CVPR, author = {He, Shuting and Ding, Henghui and Jiang, Wei}, title = {Semantic-Promoted Debiasing and Background Disambiguation for Zero-Shot Instance Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {19498-19507} }

RelightableHands: Efficient Neural Relighting of Articulated Hand Models

Shun Iwase,

Shunsuke Saito,

Tomas Simon,

Stephen Lombardi,

Timur Bagautdinov,

Rohan Joshi,

Fabian Prada,

Takaaki Shiratori,

Yaser Sheikh,

Jason Saragih

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Iwase_2023_CVPR, author = {Iwase, Shun and Saito, Shunsuke and Simon, Tomas and Lombardi, Stephen and Bagautdinov, Timur and Joshi, Rohan and Prada, Fabian and Shiratori, Takaaki and Sheikh, Yaser and Saragih, Jason}, title = {RelightableHands: Efficient Neural Relighting of Articulated Hand Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16663-16673} }

Paired-Point Lifting for Enhanced Privacy-Preserving Visual Localization

Chunghwan Lee,

Jaihoon Kim,

Chanhyuk Yun,

Je Hyeong Hong

[pdf]

[bibtex]

@InProceedings{Lee_2023_CVPR, author = {Lee, Chunghwan and Kim, Jaihoon and Yun, Chanhyuk and Hong, Je Hyeong}, title = {Paired-Point Lifting for Enhanced Privacy-Preserving Visual Localization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {17266-17275} }

Depth Estimation From Camera Image and mmWave Radar Point Cloud

Akash Deep Singh,

Yunhao Ba,

Ankur Sarker,

Howard Zhang,

Achuta Kadambi,

Stefano Soatto,

Mani Srivastava,

Alex Wong

[pdf] [supp]

[bibtex]

@InProceedings{Singh_2023_CVPR, author = {Singh, Akash Deep and Ba, Yunhao and Sarker, Ankur and Zhang, Howard and Kadambi, Achuta and Soatto, Stefano and Srivastava, Mani and Wong, Alex}, title = {Depth Estimation From Camera Image and mmWave Radar Point Cloud}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9275-9285} }

Learning Event Guided High Dynamic Range Video Reconstruction

Yixin Yang,

Jin Han,

Jinxiu Liang,

Imari Sato,

Boxin Shi

[pdf] [supp]

[bibtex]

@InProceedings{Yang_2023_CVPR, author = {Yang, Yixin and Han, Jin and Liang, Jinxiu and Sato, Imari and Shi, Boxin}, title = {Learning Event Guided High Dynamic Range Video Reconstruction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13924-13934} }

Multi-Granularity Archaeological Dating of Chinese Bronze Dings Based on a Knowledge-Guided Relation Graph

Rixin Zhou,

Jiafu Wei,

Qian Zhang,

Ruihua Qi,

Xi Yang,

Chuntao Li

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Zhou_2023_CVPR, author = {Zhou, Rixin and Wei, Jiafu and Zhang, Qian and Qi, Ruihua and Yang, Xi and Li, Chuntao}, title = {Multi-Granularity Archaeological Dating of Chinese Bronze Dings Based on a Knowledge-Guided Relation Graph}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3103-3113} }

CASP-Net: Rethinking Video Saliency Prediction From an Audio-Visual Consistency Perceptual Perspective

Junwen Xiong,

Ganglai Wang,

Peng Zhang,

Wei Huang,

Yufei Zha,

Guangtao Zhai

[pdf]

[bibtex]

@InProceedings{Xiong_2023_CVPR, author = {Xiong, Junwen and Wang, Ganglai and Zhang, Peng and Huang, Wei and Zha, Yufei and Zhai, Guangtao}, title = {CASP-Net: Rethinking Video Saliency Prediction From an Audio-Visual Consistency Perceptual Perspective}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6441-6450} }

Learning Expressive Prompting With Residuals for Vision Transformers

Rajshekhar Das,

Yonatan Dukler,

Avinash Ravichandran,

Ashwin Swaminathan

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Das_2023_CVPR, author = {Das, Rajshekhar and Dukler, Yonatan and Ravichandran, Avinash and Swaminathan, Ashwin}, title = {Learning Expressive Prompting With Residuals for Vision Transformers}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3366-3377} }

Prototypical Residual Networks for Anomaly Detection and Localization

Hui Zhang,

Zuxuan Wu,

Zheng Wang,

Zhineng Chen,

Yu-Gang Jiang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Zhang_2023_CVPR, author = {Zhang, Hui and Wu, Zuxuan and Wang, Zheng and Chen, Zhineng and Jiang, Yu-Gang}, title = {Prototypical Residual Networks for Anomaly Detection and Localization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16281-16291} }

What Happened 3 Seconds Ago? Inferring the Past With Thermal Imaging

Zitian Tang,

Wenjie Ye,

Wei-Chiu Ma,

Hang Zhao

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Tang_2023_CVPR, author = {Tang, Zitian and Ye, Wenjie and Ma, Wei-Chiu and Zhao, Hang}, title = {What Happened 3 Seconds Ago? Inferring the Past With Thermal Imaging}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {17111-17120} }

Ultrahigh Resolution Image/Video Matting With Spatio-Temporal Sparsity

Yanan Sun,

Chi-Keung Tang,

Yu-Wing Tai

[pdf] [supp]

[bibtex]

@InProceedings{Sun_2023_CVPR, author = {Sun, Yanan and Tang, Chi-Keung and Tai, Yu-Wing}, title = {Ultrahigh Resolution Image/Video Matting With Spatio-Temporal Sparsity}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14112-14121} }

AnyFlow: Arbitrary Scale Optical Flow With Implicit Neural Representation

Hyunyoung Jung,

Zhuo Hui,

Lei Luo,

Haitao Yang,

Feng Liu,

Sungjoo Yoo,

Rakesh Ranjan,

Denis Demandolx

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Jung_2023_CVPR, author = {Jung, Hyunyoung and Hui, Zhuo and Luo, Lei and Yang, Haitao and Liu, Feng and Yoo, Sungjoo and Ranjan, Rakesh and Demandolx, Denis}, title = {AnyFlow: Arbitrary Scale Optical Flow With Implicit Neural Representation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5455-5465} }

Zero-Shot Noise2Noise: Efficient Image Denoising Without Any Data

Youssef Mansour,

Reinhard Heckel

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Mansour_2023_CVPR, author = {Mansour, Youssef and Heckel, Reinhard}, title = {Zero-Shot Noise2Noise: Efficient Image Denoising Without Any Data}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14018-14027} }

Vector Quantization With Self-Attention for Quality-Independent Representation Learning

Zhou Yang,

Weisheng Dong,

Xin Li,

Mengluan Huang,

Yulin Sun,

Guangming Shi

[pdf] [supp]

[bibtex]

@InProceedings{Yang_2023_CVPR, author = {Yang, Zhou and Dong, Weisheng and Li, Xin and Huang, Mengluan and Sun, Yulin and Shi, Guangming}, title = {Vector Quantization With Self-Attention for Quality-Independent Representation Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {24438-24448} }

Generating Anomalies for Video Anomaly Detection With Prompt-Based Feature Mapping

Zuhao Liu,

Xiao-Ming Wu,

Dian Zheng,

Kun-Yu Lin,

Wei-Shi Zheng

[pdf]

[bibtex]

@InProceedings{Liu_2023_CVPR, author = {Liu, Zuhao and Wu, Xiao-Ming and Zheng, Dian and Lin, Kun-Yu and Zheng, Wei-Shi}, title = {Generating Anomalies for Video Anomaly Detection With Prompt-Based Feature Mapping}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {24500-24510} }

Diffusion-Based Signed Distance Fields for 3D Shape Generation

Jaehyeok Shim,

Changwoo Kang,

Kyungdon Joo

[pdf] [supp]

[bibtex]

@InProceedings{Shim_2023_CVPR, author = {Shim, Jaehyeok and Kang, Changwoo and Joo, Kyungdon}, title = {Diffusion-Based Signed Distance Fields for 3D Shape Generation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {20887-20897} }

Hierarchical Temporal Transformer for 3D Hand Pose Estimation and Action Recognition From Egocentric RGB Videos

Yilin Wen,

Hao Pan,

Lei Yang,

Jia Pan,

Taku Komura,

Wenping Wang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Wen_2023_CVPR, author = {Wen, Yilin and Pan, Hao and Yang, Lei and Pan, Jia and Komura, Taku and Wang, Wenping}, title = {Hierarchical Temporal Transformer for 3D Hand Pose Estimation and Action Recognition From Egocentric RGB Videos}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {21243-21253} }

CAP-VSTNet: Content Affinity Preserved Versatile Style Transfer

Linfeng Wen,

Chengying Gao,

Changqing Zou

[pdf] [supp]

[bibtex]

@InProceedings{Wen_2023_CVPR, author = {Wen, Linfeng and Gao, Chengying and Zou, Changqing}, title = {CAP-VSTNet: Content Affinity Preserved Versatile Style Transfer}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {18300-18309} }

FIANCEE: Faster Inference of Adversarial Networks via Conditional Early Exits

Polina Karpikova,

Ekaterina Radionova,

Anastasia Yaschenko,

Andrei Spiridonov,

Leonid Kostyushko,

Riccardo Fabbricatore,

Aleksei Ivakhnenko

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Karpikova_2023_CVPR, author = {Karpikova, Polina and Radionova, Ekaterina and Yaschenko, Anastasia and Spiridonov, Andrei and Kostyushko, Leonid and Fabbricatore, Riccardo and Ivakhnenko, Aleksei}, title = {FIANCEE: Faster Inference of Adversarial Networks via Conditional Early Exits}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12032-12043} }

Simultaneously Short- and Long-Term Temporal Modeling for Semi-Supervised Video Semantic Segmentation

Jiangwei Lao,

Weixiang Hong,

Xin Guo,

Yingying Zhang,

Jian Wang,

Jingdong Chen,

Wei Chu

[pdf] [supp]

[bibtex]

@InProceedings{Lao_2023_CVPR, author = {Lao, Jiangwei and Hong, Weixiang and Guo, Xin and Zhang, Yingying and Wang, Jian and Chen, Jingdong and Chu, Wei}, title = {Simultaneously Short- and Long-Term Temporal Modeling for Semi-Supervised Video Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14763-14772} }

Federated Domain Generalization With Generalization Adjustment

Ruipeng Zhang,

Qinwei Xu,

Jiangchao Yao,

Ya Zhang,

Qi Tian,

Yanfeng Wang

[pdf] [supp]

[bibtex]

@InProceedings{Zhang_2023_CVPR, author = {Zhang, Ruipeng and Xu, Qinwei and Yao, Jiangchao and Zhang, Ya and Tian, Qi and Wang, Yanfeng}, title = {Federated Domain Generalization With Generalization Adjustment}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3954-3963} }

Tunable Convolutions With Parametric Multi-Loss Optimization

Matteo Maggioni,

Thomas Tanay,

Francesca Babiloni,

Steven McDonagh,

Aleš Leonardis

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Maggioni_2023_CVPR, author = {Maggioni, Matteo and Tanay, Thomas and Babiloni, Francesca and McDonagh, Steven and Leonardis, Ale\v{s}}, title = {Tunable Convolutions With Parametric Multi-Loss Optimization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {20226-20236} }

Learning To Generate Text-Grounded Mask for Open-World Semantic Segmentation From Only Image-Text Pairs

Junbum Cha,

Jonghwan Mun,

Byungseok Roh

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Cha_2023_CVPR, author = {Cha, Junbum and Mun, Jonghwan and Roh, Byungseok}, title = {Learning To Generate Text-Grounded Mask for Open-World Semantic Segmentation From Only Image-Text Pairs}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11165-11174} }

CoMFormer: Continual Learning in Semantic and Panoptic Segmentation

Fabio Cermelli,

Matthieu Cord,

Arthur Douillard

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Cermelli_2023_CVPR, author = {Cermelli, Fabio and Cord, Matthieu and Douillard, Arthur}, title = {CoMFormer: Continual Learning in Semantic and Panoptic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3010-3020} }

DeepSolo: Let Transformer Decoder With Explicit Points Solo for Text Spotting

Maoyuan Ye,

Jing Zhang,

Shanshan Zhao,

Juhua Liu,

Tongliang Liu,

Bo Du,

Dacheng Tao

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Ye_2023_CVPR, author = {Ye, Maoyuan and Zhang, Jing and Zhao, Shanshan and Liu, Juhua and Liu, Tongliang and Du, Bo and Tao, Dacheng}, title = {DeepSolo: Let Transformer Decoder With Explicit Points Solo for Text Spotting}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {19348-19357} }

Conditional Generation of Audio From Video via Foley Analogies

Yuexi Du,

Ziyang Chen,

Justin Salamon,

Bryan Russell,

Andrew Owens

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Du_2023_CVPR, author = {Du, Yuexi and Chen, Ziyang and Salamon, Justin and Russell, Bryan and Owens, Andrew}, title = {Conditional Generation of Audio From Video via Foley Analogies}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2426-2436} }

Diverse 3D Hand Gesture Prediction From Body Dynamics by Bilateral Hand Disentanglement

Xingqun Qi,

Chen Liu,

Muyi Sun,

Lincheng Li,

Changjie Fan,

Xin Yu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Qi_2023_CVPR, author = {Qi, Xingqun and Liu, Chen and Sun, Muyi and Li, Lincheng and Fan, Changjie and Yu, Xin}, title = {Diverse 3D Hand Gesture Prediction From Body Dynamics by Bilateral Hand Disentanglement}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4616-4626} }

DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation

Nataniel Ruiz,

Yuanzhen Li,

Varun Jampani,

Yael Pritch,

Michael Rubinstein,

Kfir Aberman

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Ruiz_2023_CVPR, author = {Ruiz, Nataniel and Li, Yuanzhen and Jampani, Varun and Pritch, Yael and Rubinstein, Michael and Aberman, Kfir}, title = {DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {22500-22510} }

MOSO: Decomposing MOtion, Scene and Object for Video Prediction

Mingzhen Sun,

Weining Wang,

Xinxin Zhu,

Jing Liu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Sun_2023_CVPR, author = {Sun, Mingzhen and Wang, Weining and Zhu, Xinxin and Liu, Jing}, title = {MOSO: Decomposing MOtion, Scene and Object for Video Prediction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {18727-18737} }

Shakes on a Plane: Unsupervised Depth Estimation From Unstabilized Photography

Ilya Chugunov,

Yuxuan Zhang,

Felix Heide

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Chugunov_2023_CVPR, author = {Chugunov, Ilya and Zhang, Yuxuan and Heide, Felix}, title = {Shakes on a Plane: Unsupervised Depth Estimation From Unstabilized Photography}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13240-13251} }

Learning Video Representations From Large Language Models

Yue Zhao,

Ishan Misra,

Philipp Krähenbühl,

Rohit Girdhar

[pdf] [supp]

[bibtex]

@InProceedings{Zhao_2023_CVPR, author = {Zhao, Yue and Misra, Ishan and Kr\"ahenb\"uhl, Philipp and Girdhar, Rohit}, title = {Learning Video Representations From Large Language Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6586-6597} }

Learning the Distribution of Errors in Stereo Matching for Joint Disparity and Uncertainty Estimation

Liyan Chen,

Weihan Wang,

Philippos Mordohai

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Chen_2023_CVPR, author = {Chen, Liyan and Wang, Weihan and Mordohai, Philippos}, title = {Learning the Distribution of Errors in Stereo Matching for Joint Disparity and Uncertainty Estimation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {17235-17244} }

Learning Correspondence Uncertainty via Differentiable Nonlinear Least Squares

Dominik Muhle,

Lukas Koestler,

Krishna Murthy Jatavallabhula,

Daniel Cremers

[pdf] [supp]

[bibtex]

@InProceedings{Muhle_2023_CVPR, author = {Muhle, Dominik and Koestler, Lukas and Jatavallabhula, Krishna Murthy and Cremers, Daniel}, title = {Learning Correspondence Uncertainty via Differentiable Nonlinear Least Squares}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13102-13112} }

Samples With Low Loss Curvature Improve Data Efficiency

Isha Garg,

Kaushik Roy

[pdf] [supp]

[bibtex]

@InProceedings{Garg_2023_CVPR, author = {Garg, Isha and Roy, Kaushik}, title = {Samples With Low Loss Curvature Improve Data Efficiency}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {20290-20300} }

Towards Effective Visual Representations for Partial-Label Learning

Shiyu Xia,

Jiaqi Lv,

Ning Xu,

Gang Niu,

Xin Geng

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Xia_2023_CVPR, author = {Xia, Shiyu and Lv, Jiaqi and Xu, Ning and Niu, Gang and Geng, Xin}, title = {Towards Effective Visual Representations for Partial-Label Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15589-15598} }

MaskCLIP: Masked Self-Distillation Advances Contrastive Language-Image Pretraining

Xiaoyi Dong,

Jianmin Bao,

Yinglin Zheng,

Ting Zhang,

Dongdong Chen,

Hao Yang,

Ming Zeng,

Weiming Zhang,

Lu Yuan,

Dong Chen,

Fang Wen,

Nenghai Yu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Dong_2023_CVPR, author = {Dong, Xiaoyi and Bao, Jianmin and Zheng, Yinglin and Zhang, Ting and Chen, Dongdong and Yang, Hao and Zeng, Ming and Zhang, Weiming and Yuan, Lu and Chen, Dong and Wen, Fang and Yu, Nenghai}, title = {MaskCLIP: Masked Self-Distillation Advances Contrastive Language-Image Pretraining}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10995-11005} }

Open-Vocabulary Semantic Segmentation With Mask-Adapted CLIP

Feng Liang,

Bichen Wu,

Xiaoliang Dai,

Kunpeng Li,

Yinan Zhao,

Hang Zhang,

Peizhao Zhang,

Peter Vajda,

Diana Marculescu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Liang_2023_CVPR, author = {Liang, Feng and Wu, Bichen and Dai, Xiaoliang and Li, Kunpeng and Zhao, Yinan and Zhang, Hang and Zhang, Peizhao and Vajda, Peter and Marculescu, Diana}, title = {Open-Vocabulary Semantic Segmentation With Mask-Adapted CLIP}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7061-7070} }

A Loopback Network for Explainable Microvascular Invasion Classification

Shengxuming Zhang,

Tianqi Shi,

Yang Jiang,

Xiuming Zhang,

Jie Lei,

Zunlei Feng,

Mingli Song

[pdf] [supp]

[bibtex]

@InProceedings{Zhang_2023_CVPR, author = {Zhang, Shengxuming and Shi, Tianqi and Jiang, Yang and Zhang, Xiuming and Lei, Jie and Feng, Zunlei and Song, Mingli}, title = {A Loopback Network for Explainable Microvascular Invasion Classification}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7443-7453} }

TINC: Tree-Structured Implicit Neural Compression

Runzhao Yang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Yang_2023_CVPR, author = {Yang, Runzhao}, title = {TINC: Tree-Structured Implicit Neural Compression}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {18517-18526} }

Unifying Short and Long-Term Tracking With Graph Hierarchies

Orcun Cetintas,

Guillem Brasó,

Laura Leal-Taixé

[pdf] [supp]

[bibtex]

@InProceedings{Cetintas_2023_CVPR, author = {Cetintas, Orcun and Bras\'o, Guillem and Leal-Taix\'e, Laura}, title = {Unifying Short and Long-Term Tracking With Graph Hierarchies}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {22877-22887} }

Inferring and Leveraging Parts From Object Shape for Improving Semantic Image Synthesis

Yuxiang Wei,

Zhilong Ji,

Xiaohe Wu,

Jinfeng Bai,

Lei Zhang,

Wangmeng Zuo

[pdf] [supp]

[bibtex]

@InProceedings{Wei_2023_CVPR, author = {Wei, Yuxiang and Ji, Zhilong and Wu, Xiaohe and Bai, Jinfeng and Zhang, Lei and Zuo, Wangmeng}, title = {Inferring and Leveraging Parts From Object Shape for Improving Semantic Image Synthesis}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11248-11258} }

MIME: Human-Aware 3D Scene Generation

Hongwei Yi,

Chun-Hao P. Huang,

Shashank Tripathi,

Lea Hering,

Justus Thies,

Michael J. Black

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Yi_2023_CVPR, author = {Yi, Hongwei and Huang, Chun-Hao P. and Tripathi, Shashank and Hering, Lea and Thies, Justus and Black, Michael J.}, title = {MIME: Human-Aware 3D Scene Generation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12965-12976} }

Re-Basin via Implicit Sinkhorn Differentiation

Fidel A. Guerrero Peña,

Heitor Rapela Medeiros,

Thomas Dubail,

Masih Aminbeidokhti,

Eric Granger,

Marco Pedersoli

[pdf] [supp]

[bibtex]

@InProceedings{Pena_2023_CVPR, author = {Pe\~na, Fidel A. Guerrero and Medeiros, Heitor Rapela and Dubail, Thomas and Aminbeidokhti, Masih and Granger, Eric and Pedersoli, Marco}, title = {Re-Basin via Implicit Sinkhorn Differentiation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {20237-20246} }

NerVE: Neural Volumetric Edges for Parametric Curve Extraction From Point Cloud

Xiangyu Zhu,

Dong Du,

Weikai Chen,

Zhiyou Zhao,

Yinyu Nie,

Xiaoguang Han

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Zhu_2023_CVPR, author = {Zhu, Xiangyu and Du, Dong and Chen, Weikai and Zhao, Zhiyou and Nie, Yinyu and Han, Xiaoguang}, title = {NerVE: Neural Volumetric Edges for Parametric Curve Extraction From Point Cloud}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13601-13610} }

ShapeClipper: Scalable 3D Shape Learning From Single-View Images via Geometric and CLIP-Based Consistency

Zixuan Huang,

Varun Jampani,

Anh Thai,

Yuanzhen Li,

Stefan Stojanov,

James M. Rehg

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Huang_2023_CVPR, author = {Huang, Zixuan and Jampani, Varun and Thai, Anh and Li, Yuanzhen and Stojanov, Stefan and Rehg, James M.}, title = {ShapeClipper: Scalable 3D Shape Learning From Single-View Images via Geometric and CLIP-Based Consistency}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12912-12922} }

Supervised Masked Knowledge Distillation for Few-Shot Transformers

Han Lin,

Guangxing Han,

Jiawei Ma,

Shiyuan Huang,

Xudong Lin,

Shih-Fu Chang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Lin_2023_CVPR, author = {Lin, Han and Han, Guangxing and Ma, Jiawei and Huang, Shiyuan and Lin, Xudong and Chang, Shih-Fu}, title = {Supervised Masked Knowledge Distillation for Few-Shot Transformers}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {19649-19659} }

RIDCP: Revitalizing Real Image Dehazing via High-Quality Codebook Priors

Rui-Qi Wu,

Zheng-Peng Duan,

Chun-Le Guo,

Zhi Chai,

Chongyi Li

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Wu_2023_CVPR, author = {Wu, Rui-Qi and Duan, Zheng-Peng and Guo, Chun-Le and Chai, Zhi and Li, Chongyi}, title = {RIDCP: Revitalizing Real Image Dehazing via High-Quality Codebook Priors}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {22282-22291} }

Exact-NeRF: An Exploration of a Precise Volumetric Parameterization for Neural Radiance Fields

Brian K. S. Isaac-Medina,

Chris G. Willcocks,

Toby P. Breckon

[pdf] [supp]

[bibtex]

@InProceedings{Isaac-Medina_2023_CVPR, author = {Isaac-Medina, Brian K. S. and Willcocks, Chris G. and Breckon, Toby P.}, title = {Exact-NeRF: An Exploration of a Precise Volumetric Parameterization for Neural Radiance Fields}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {66-75} }

Backdoor Attacks Against Deep Image Compression via Adaptive Frequency Trigger

Yi Yu,

Yufei Wang,

Wenhan Yang,

Shijian Lu,

Yap-Peng Tan,

Alex C. Kot

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Yu_2023_CVPR, author = {Yu, Yi and Wang, Yufei and Yang, Wenhan and Lu, Shijian and Tan, Yap-Peng and Kot, Alex C.}, title = {Backdoor Attacks Against Deep Image Compression via Adaptive Frequency Trigger}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12250-12259} }

Recurrence Without Recurrence: Stable Video Landmark Detection With Deep Equilibrium Models

Paul Micaelli,

Arash Vahdat,

Hongxu Yin,

Jan Kautz,

Pavlo Molchanov

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Micaelli_2023_CVPR, author = {Micaelli, Paul and Vahdat, Arash and Yin, Hongxu and Kautz, Jan and Molchanov, Pavlo}, title = {Recurrence Without Recurrence: Stable Video Landmark Detection With Deep Equilibrium Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {22814-22825} }

Generalized Relation Modeling for Transformer Tracking

Shenyuan Gao,

Chunluan Zhou,

Jun Zhang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Gao_2023_CVPR, author = {Gao, Shenyuan and Zhou, Chunluan and Zhang, Jun}, title = {Generalized Relation Modeling for Transformer Tracking}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {18686-18695} }

Non-Line-of-Sight Imaging With Signal Superresolution Network

Jianyu Wang,

Xintong Liu,

Leping Xiao,

Zuoqiang Shi,

Lingyun Qiu,

Xing Fu

[pdf] [supp]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Jianyu and Liu, Xintong and Xiao, Leping and Shi, Zuoqiang and Qiu, Lingyun and Fu, Xing}, title = {Non-Line-of-Sight Imaging With Signal Superresolution Network}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {17420-17429} }

WildLight: In-the-Wild Inverse Rendering With a Flashlight

Ziang Cheng,

Junxuan Li,

Hongdong Li

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Cheng_2023_CVPR, author = {Cheng, Ziang and Li, Junxuan and Li, Hongdong}, title = {WildLight: In-the-Wild Inverse Rendering With a Flashlight}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4305-4314} }

A Probabilistic Attention Model With Occlusion-Aware Texture Regression for 3D Hand Reconstruction From a Single RGB Image

Zheheng Jiang,

Hossein Rahmani,

Sue Black,

Bryan M. Williams

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Jiang_2023_CVPR, author = {Jiang, Zheheng and Rahmani, Hossein and Black, Sue and Williams, Bryan M.}, title = {A Probabilistic Attention Model With Occlusion-Aware Texture Regression for 3D Hand Reconstruction From a Single RGB Image}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {758-767} }

MixNeRF: Modeling a Ray With Mixture Density for Novel View Synthesis From Sparse Inputs

Seunghyeon Seo,

Donghoon Han,

Yeonjin Chang,

Nojun Kwak

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Seo_2023_CVPR, author = {Seo, Seunghyeon and Han, Donghoon and Chang, Yeonjin and Kwak, Nojun}, title = {MixNeRF: Modeling a Ray With Mixture Density for Novel View Synthesis From Sparse Inputs}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {20659-20668} }

A New Path: Scaling Vision-and-Language Navigation With Synthetic Instructions and Imitation Learning

Aishwarya Kamath,

Peter Anderson,

Su Wang,

Jing Yu Koh,

Alexander Ku,

Austin Waters,

Yinfei Yang,

Jason Baldridge,

Zarana Parekh

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Kamath_2023_CVPR, author = {Kamath, Aishwarya and Anderson, Peter and Wang, Su and Koh, Jing Yu and Ku, Alexander and Waters, Austin and Yang, Yinfei and Baldridge, Jason and Parekh, Zarana}, title = {A New Path: Scaling Vision-and-Language Navigation With Synthetic Instructions and Imitation Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10813-10823} }

Layout-Based Causal Inference for Object Navigation

Sixian Zhang,

Xinhang Song,

Weijie Li,

Yubing Bai,

Xinyao Yu,

Shuqiang Jiang

[pdf] [supp]

[bibtex]

@InProceedings{Zhang_2023_CVPR, author = {Zhang, Sixian and Song, Xinhang and Li, Weijie and Bai, Yubing and Yu, Xinyao and Jiang, Shuqiang}, title = {Layout-Based Causal Inference for Object Navigation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10792-10802} }

Pose-Disentangled Contrastive Learning for Self-Supervised Facial Representation

Yuanyuan Liu,

Wenbin Wang,

Yibing Zhan,

Shaoze Feng,

Kejun Liu,

Zhe Chen

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Liu_2023_CVPR, author = {Liu, Yuanyuan and Wang, Wenbin and Zhan, Yibing and Feng, Shaoze and Liu, Kejun and Chen, Zhe}, title = {Pose-Disentangled Contrastive Learning for Self-Supervised Facial Representation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9717-9728} }

Cross-Domain 3D Hand Pose Estimation With Dual Modalities

Qiuxia Lin,

Linlin Yang,

Angela Yao

[pdf] [supp]

[bibtex]

@InProceedings{Lin_2023_CVPR, author = {Lin, Qiuxia and Yang, Linlin and Yao, Angela}, title = {Cross-Domain 3D Hand Pose Estimation With Dual Modalities}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {17184-17193} }

Attribute-Preserving Face Dataset Anonymization via Latent Code Optimization

Simone Barattin,

Christos Tzelepis,

Ioannis Patras,

Nicu Sebe

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Barattin_2023_CVPR, author = {Barattin, Simone and Tzelepis, Christos and Patras, Ioannis and Sebe, Nicu}, title = {Attribute-Preserving Face Dataset Anonymization via Latent Code Optimization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8001-8010} }

Inverse Rendering of Translucent Objects Using Physical and Neural Renderers

Chenhao Li,

Trung Thanh Ngo,

Hajime Nagahara

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Li_2023_CVPR, author = {Li, Chenhao and Ngo, Trung Thanh and Nagahara, Hajime}, title = {Inverse Rendering of Translucent Objects Using Physical and Neural Renderers}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12510-12520} }

Towards Building Self-Aware Object Detectors via Reliable Uncertainty Quantification and Calibration

Kemal Oksuz,

Tom Joy,

Puneet K. Dokania

[pdf] [supp]

[bibtex]

@InProceedings{Oksuz_2023_CVPR, author = {Oksuz, Kemal and Joy, Tom and Dokania, Puneet K.}, title = {Towards Building Self-Aware Object Detectors via Reliable Uncertainty Quantification and Calibration}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9263-9274} }

Ensemble-Based Blackbox Attacks on Dense Prediction

Zikui Cai,

Yaoteng Tan,

M. Salman Asif

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Cai_2023_CVPR, author = {Cai, Zikui and Tan, Yaoteng and Asif, M. Salman}, title = {Ensemble-Based Blackbox Attacks on Dense Prediction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4045-4055} }

Improving Fairness in Facial Albedo Estimation via Visual-Textual Cues

Xingyu Ren,

Jiankang Deng,

Chao Ma,

Yichao Yan,

Xiaokang Yang

[pdf]

[bibtex]

@InProceedings{Ren_2023_CVPR, author = {Ren, Xingyu and Deng, Jiankang and Ma, Chao and Yan, Yichao and Yang, Xiaokang}, title = {Improving Fairness in Facial Albedo Estimation via Visual-Textual Cues}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4511-4520} }

Source-Free Video Domain Adaptation With Spatial-Temporal-Historical Consistency Learning

Kai Li,

Deep Patel,

Erik Kruus,

Martin Renqiang Min

[pdf] [supp]

[bibtex]

@InProceedings{Li_2023_CVPR, author = {Li, Kai and Patel, Deep and Kruus, Erik and Min, Martin Renqiang}, title = {Source-Free Video Domain Adaptation With Spatial-Temporal-Historical Consistency Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14643-14652} }

SmartAssign: Learning a Smart Knowledge Assignment Strategy for Deraining and Desnowing

Yinglong Wang,

Chao Ma,

Jianzhuang Liu

[pdf]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Yinglong and Ma, Chao and Liu, Jianzhuang}, title = {SmartAssign: Learning a Smart Knowledge Assignment Strategy for Deraining and Desnowing}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3677-3686} }

Delving Into Discrete Normalizing Flows on SO(3) Manifold for Probabilistic Rotation Modeling

Yulin Liu,

Haoran Liu,

Yingda Yin,

Yang Wang,

Baoquan Chen,

He Wang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Liu_2023_CVPR, author = {Liu, Yulin and Liu, Haoran and Yin, Yingda and Wang, Yang and Chen, Baoquan and Wang, He}, title = {Delving Into Discrete Normalizing Flows on SO(3) Manifold for Probabilistic Rotation Modeling}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {21264-21273} }

SfM-TTR: Using Structure From Motion for Test-Time Refinement of Single-View Depth Networks

Sergio Izquierdo,

Javier Civera

[pdf] [supp]

[bibtex]

@InProceedings{Izquierdo_2023_CVPR, author = {Izquierdo, Sergio and Civera, Javier}, title = {SfM-TTR: Using Structure From Motion for Test-Time Refinement of Single-View Depth Networks}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {21466-21476} }

Fusing Pre-Trained Language Models With Multimodal Prompts Through Reinforcement Learning

Youngjae Yu,

Jiwan Chung,

Heeseung Yun,

Jack Hessel,

Jae Sung Park,

Ximing Lu,

Rowan Zellers,

Prithviraj Ammanabrolu,

Ronan Le Bras,

Gunhee Kim,

Yejin Choi

[pdf] [supp]

[bibtex]

@InProceedings{Yu_2023_CVPR, author = {Yu, Youngjae and Chung, Jiwan and Yun, Heeseung and Hessel, Jack and Park, Jae Sung and Lu, Ximing and Zellers, Rowan and Ammanabrolu, Prithviraj and Le Bras, Ronan and Kim, Gunhee and Choi, Yejin}, title = {Fusing Pre-Trained Language Models With Multimodal Prompts Through Reinforcement Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10845-10856} }

MELTR: Meta Loss Transformer for Learning To Fine-Tune Video Foundation Models

Dohwan Ko,

Joonmyung Choi,

Hyeong Kyu Choi,

Kyoung-Woon On,

Byungseok Roh,

Hyunwoo J. Kim

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Ko_2023_CVPR, author = {Ko, Dohwan and Choi, Joonmyung and Choi, Hyeong Kyu and On, Kyoung-Woon and Roh, Byungseok and Kim, Hyunwoo J.}, title = {MELTR: Meta Loss Transformer for Learning To Fine-Tune Video Foundation Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {20105-20115} }

Dense Network Expansion for Class Incremental Learning

Zhiyuan Hu,

Yunsheng Li,

Jiancheng Lyu,

Dashan Gao,

Nuno Vasconcelos

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Hu_2023_CVPR, author = {Hu, Zhiyuan and Li, Yunsheng and Lyu, Jiancheng and Gao, Dashan and Vasconcelos, Nuno}, title = {Dense Network Expansion for Class Incremental Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11858-11867} }

Meta-Personalizing Vision-Language Models To Find Named Instances in Video

Chun-Hsiao Yeh,

Bryan Russell,

Josef Sivic,

Fabian Caba Heilbron,

Simon Jenni

[pdf] [supp]

[bibtex]

@InProceedings{Yeh_2023_CVPR, author = {Yeh, Chun-Hsiao and Russell, Bryan and Sivic, Josef and Heilbron, Fabian Caba and Jenni, Simon}, title = {Meta-Personalizing Vision-Language Models To Find Named Instances in Video}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {19123-19132} }

Regularize Implicit Neural Representation by Itself

Zhemin Li,

Hongxia Wang,

Deyu Meng

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Li_2023_CVPR, author = {Li, Zhemin and Wang, Hongxia and Meng, Deyu}, title = {Regularize Implicit Neural Representation by Itself}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10280-10288} }

Egocentric Audio-Visual Object Localization

Chao Huang,

Yapeng Tian,

Anurag Kumar,

Chenliang Xu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Huang_2023_CVPR, author = {Huang, Chao and Tian, Yapeng and Kumar, Anurag and Xu, Chenliang}, title = {Egocentric Audio-Visual Object Localization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {22910-22921} }

DropKey for Vision Transformer

Bonan Li,

Yinhan Hu,

Xuecheng Nie,

Congying Han,

Xiangjian Jiang,

Tiande Guo,

Luoqi Liu

[pdf] [supp]

[bibtex]

@InProceedings{Li_2023_CVPR, author = {Li, Bonan and Hu, Yinhan and Nie, Xuecheng and Han, Congying and Jiang, Xiangjian and Guo, Tiande and Liu, Luoqi}, title = {DropKey for Vision Transformer}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {22700-22709} }

sRGB Real Noise Synthesizing With Neighboring Correlation-Aware Noise Model

Zixuan Fu,

Lanqing Guo,

Bihan Wen

[pdf] [supp]

[bibtex]

@InProceedings{Fu_2023_CVPR, author = {Fu, Zixuan and Guo, Lanqing and Wen, Bihan}, title = {sRGB Real Noise Synthesizing With Neighboring Correlation-Aware Noise Model}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1683-1691} }

Meta Architecture for Point Cloud Analysis

Haojia Lin,

Xiawu Zheng,

Lijiang Li,

Fei Chao,

Shanshan Wang,

Yan Wang,

Yonghong Tian,

Rongrong Ji

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Lin_2023_CVPR, author = {Lin, Haojia and Zheng, Xiawu and Li, Lijiang and Chao, Fei and Wang, Shanshan and Wang, Yan and Tian, Yonghong and Ji, Rongrong}, title = {Meta Architecture for Point Cloud Analysis}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {17682-17691} }

Ambiguous Medical Image Segmentation Using Diffusion Models

Aimon Rahman,

Jeya Maria Jose Valanarasu,

Ilker Hacihaliloglu,

Vishal M. Patel

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Rahman_2023_CVPR, author = {Rahman, Aimon and Valanarasu, Jeya Maria Jose and Hacihaliloglu, Ilker and Patel, Vishal M.}, title = {Ambiguous Medical Image Segmentation Using Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11536-11546} }

CIRCLE: Capture in Rich Contextual Environments

João Pedro Araújo,

Jiaman Li,

Karthik Vetrivel,

Rishi Agarwal,

Jiajun Wu,

Deepak Gopinath,

Alexander William Clegg,

Karen Liu

[pdf] [supp]

[bibtex]

@InProceedings{Araujo_2023_CVPR, author = {Ara\'ujo, Jo\~ao Pedro and Li, Jiaman and Vetrivel, Karthik and Agarwal, Rishi and Wu, Jiajun and Gopinath, Deepak and Clegg, Alexander William and Liu, Karen}, title = {CIRCLE: Capture in Rich Contextual Environments}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {21211-21221} }

Revisiting Weak-to-Strong Consistency in Semi-Supervised Semantic Segmentation

Lihe Yang,

Lei Qi,

Litong Feng,

Wayne Zhang,

Yinghuan Shi

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Yang_2023_CVPR, author = {Yang, Lihe and Qi, Lei and Feng, Litong and Zhang, Wayne and Shi, Yinghuan}, title = {Revisiting Weak-to-Strong Consistency in Semi-Supervised Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7236-7246} }

Implicit View-Time Interpolation of Stereo Videos Using Multi-Plane Disparities and Non-Uniform Coordinates

Avinash Paliwal,

Andrii Tsarov,

Nima Khademi Kalantari

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Paliwal_2023_CVPR, author = {Paliwal, Avinash and Tsarov, Andrii and Kalantari, Nima Khademi}, title = {Implicit View-Time Interpolation of Stereo Videos Using Multi-Plane Disparities and Non-Uniform Coordinates}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {888-898} }

PyPose: A Library for Robot Learning With Physics-Based Optimization

Chen Wang,

Dasong Gao,

Kuan Xu,

Junyi Geng,

Yaoyu Hu,

Yuheng Qiu,

Bowen Li,

Fan Yang,

Brady Moon,

Abhinav Pandey,

Aryan,

Jiahe Xu,

Tianhao Wu,

Haonan He,

Daning Huang,

Zhongqiang Ren,

Shibo Zhao,

Taimeng Fu,

Pranay Reddy,

Xiao Lin,

Wenshan Wang,

Jingnan Shi,

Rajat Talak,

Kun Cao,

Yi Du,

Han Wang,

Huai Yu,

Shanzhao Wang,

Siyu Chen,

Ananth Kashyap,

Rohan Bandaru,

Karthik Dantu,

Jiajun Wu,

Lihua Xie,

Luca Carlone,

Marco Hutter,

Sebastian Scherer

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Chen and Gao, Dasong and Xu, Kuan and Geng, Junyi and Hu, Yaoyu and Qiu, Yuheng and Li, Bowen and Yang, Fan and Moon, Brady and Pandey, Abhinav and Aryan and Xu, Jiahe and Wu, Tianhao and He, Haonan and Huang, Daning and Ren, Zhongqiang and Zhao, Shibo and Fu, Taimeng and Reddy, Pranay and Lin, Xiao and Wang, Wenshan and Shi, Jingnan and Talak, Rajat and Cao, Kun and Du, Yi and Wang, Han and Yu, Huai and Wang, Shanzhao and Chen, Siyu and Kashyap, Ananth and Bandaru, Rohan and Dantu, Karthik and Wu, Jiajun and Xie, Lihua and Carlone, Luca and Hutter, Marco and Scherer, Sebastian}, title = {PyPose: A Library for Robot Learning With Physics-Based Optimization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {22024-22034} }

Make Landscape Flatter in Differentially Private Federated Learning

Yifan Shi,

Yingqi Liu,

Kang Wei,

Li Shen,

Xueqian Wang,

Dacheng Tao

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Shi_2023_CVPR, author = {Shi, Yifan and Liu, Yingqi and Wei, Kang and Shen, Li and Wang, Xueqian and Tao, Dacheng}, title = {Make Landscape Flatter in Differentially Private Federated Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {24552-24562} }

BlackVIP: Black-Box Visual Prompting for Robust Transfer Learning

Changdae Oh,

Hyeji Hwang,

Hee-young Lee,

YongTaek Lim,

Geunyoung Jung,

Jiyoung Jung,

Hosik Choi,

Kyungwoo Song

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Oh_2023_CVPR, author = {Oh, Changdae and Hwang, Hyeji and Lee, Hee-young and Lim, YongTaek and Jung, Geunyoung and Jung, Jiyoung and Choi, Hosik and Song, Kyungwoo}, title = {BlackVIP: Black-Box Visual Prompting for Robust Transfer Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {24224-24235} }

DeepVecFont-v2: Exploiting Transformers To Synthesize Vector Fonts With Higher Quality

Yuqing Wang,

Yizhi Wang,

Longhui Yu,

Yuesheng Zhu,

Zhouhui Lian

[pdf] [supp]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Yuqing and Wang, Yizhi and Yu, Longhui and Zhu, Yuesheng and Lian, Zhouhui}, title = {DeepVecFont-v2: Exploiting Transformers To Synthesize Vector Fonts With Higher Quality}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {18320-18328} }

pCON: Polarimetric Coordinate Networks for Neural Scene Representations

Henry Peters,

Yunhao Ba,

Achuta Kadambi

[pdf] [supp]

[bibtex]

@InProceedings{Peters_2023_CVPR, author = {Peters, Henry and Ba, Yunhao and Kadambi, Achuta}, title = {pCON: Polarimetric Coordinate Networks for Neural Scene Representations}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16579-16589} }

Soft-Landing Strategy for Alleviating the Task Discrepancy Problem in Temporal Action Localization Tasks

Hyolim Kang,

Hanjung Kim,

Joungbin An,

Minsu Cho,

Seon Joo Kim

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Kang_2023_CVPR, author = {Kang, Hyolim and Kim, Hanjung and An, Joungbin and Cho, Minsu and Kim, Seon Joo}, title = {Soft-Landing Strategy for Alleviating the Task Discrepancy Problem in Temporal Action Localization Tasks}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6514-6523} }

Visibility Aware Human-Object Interaction Tracking From Single RGB Camera

Xianghui Xie,

Bharat Lal Bhatnagar,

Gerard Pons-Moll

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Xie_2023_CVPR, author = {Xie, Xianghui and Bhatnagar, Bharat Lal and Pons-Moll, Gerard}, title = {Visibility Aware Human-Object Interaction Tracking From Single RGB Camera}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4757-4768} }

Uncertainty-Aware Vision-Based Metric Cross-View Geolocalization

Florian Fervers,

Sebastian Bullinger,

Christoph Bodensteiner,

Michael Arens,

Rainer Stiefelhagen

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Fervers_2023_CVPR, author = {Fervers, Florian and Bullinger, Sebastian and Bodensteiner, Christoph and Arens, Michael and Stiefelhagen, Rainer}, title = {Uncertainty-Aware Vision-Based Metric Cross-View Geolocalization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {21621-21631} }

DANI-Net: Uncalibrated Photometric Stereo by Differentiable Shadow Handling, Anisotropic Reflectance Modeling, and Neural Inverse Rendering

Zongrui Li,

Qian Zheng,

Boxin Shi,

Gang Pan,

Xudong Jiang

[pdf] [supp]

[bibtex]

@InProceedings{Li_2023_CVPR, author = {Li, Zongrui and Zheng, Qian and Shi, Boxin and Pan, Gang and Jiang, Xudong}, title = {DANI-Net: Uncalibrated Photometric Stereo by Differentiable Shadow Handling, Anisotropic Reflectance Modeling, and Neural Inverse Rendering}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8381-8391} }

Towards Better Stability and Adaptability: Improve Online Self-Training for Model Adaptation in Semantic Segmentation

Dong Zhao,

Shuang Wang,

Qi Zang,

Dou Quan,

Xiutiao Ye,

Licheng Jiao

[pdf]

[bibtex]

@InProceedings{Zhao_2023_CVPR, author = {Zhao, Dong and Wang, Shuang and Zang, Qi and Quan, Dou and Ye, Xiutiao and Jiao, Licheng}, title = {Towards Better Stability and Adaptability: Improve Online Self-Training for Model Adaptation in Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11733-11743} }

Continuous Landmark Detection With 3D Queries

Prashanth Chandran,

Gaspard Zoss,

Paulo Gotardo,

Derek Bradley

[pdf] [supp]

[bibtex]

@InProceedings{Chandran_2023_CVPR, author = {Chandran, Prashanth and Zoss, Gaspard and Gotardo, Paulo and Bradley, Derek}, title = {Continuous Landmark Detection With 3D Queries}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16858-16867} }

Ranking Regularization for Critical Rare Classes: Minimizing False Positives at a High True Positive Rate

Kiarash Mohammadi,

He Zhao,

Mengyao Zhai,

Frederick Tung

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Mohammadi_2023_CVPR, author = {Mohammadi, Kiarash and Zhao, He and Zhai, Mengyao and Tung, Frederick}, title = {Ranking Regularization for Critical Rare Classes: Minimizing False Positives at a High True Positive Rate}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15783-15792} }

Rethinking Gradient Projection Continual Learning: Stability / Plasticity Feature Space Decoupling

Zhen Zhao,

Zhizhong Zhang,

Xin Tan,

Jun Liu,

Yanyun Qu,

Yuan Xie,

Lizhuang Ma

[pdf] [supp]

[bibtex]

@InProceedings{Zhao_2023_CVPR, author = {Zhao, Zhen and Zhang, Zhizhong and Tan, Xin and Liu, Jun and Qu, Yanyun and Xie, Yuan and Ma, Lizhuang}, title = {Rethinking Gradient Projection Continual Learning: Stability / Plasticity Feature Space Decoupling}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3718-3727} }

Joint HDR Denoising and Fusion: A Real-World Mobile HDR Image Dataset

Shuaizheng Liu,

Xindong Zhang,

Lingchen Sun,

Zhetong Liang,

Hui Zeng,

Lei Zhang

[pdf] [supp]

[bibtex]

@InProceedings{Liu_2023_CVPR, author = {Liu, Shuaizheng and Zhang, Xindong and Sun, Lingchen and Liang, Zhetong and Zeng, Hui and Zhang, Lei}, title = {Joint HDR Denoising and Fusion: A Real-World Mobile HDR Image Dataset}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13966-13975} }

FlatFormer: Flattened Window Attention for Efficient Point Cloud Transformer

Zhijian Liu,

Xinyu Yang,

Haotian Tang,

Shang Yang,

Song Han

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Liu_2023_CVPR, author = {Liu, Zhijian and Yang, Xinyu and Tang, Haotian and Yang, Shang and Han, Song}, title = {FlatFormer: Flattened Window Attention for Efficient Point Cloud Transformer}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1200-1211} }

Unbiased Scene Graph Generation in Videos

Sayak Nag,

Kyle Min,

Subarna Tripathi,

Amit K. Roy-Chowdhury

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Nag_2023_CVPR, author = {Nag, Sayak and Min, Kyle and Tripathi, Subarna and Roy-Chowdhury, Amit K.}, title = {Unbiased Scene Graph Generation in Videos}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {22803-22813} }

Dynamic Graph Learning With Content-Guided Spatial-Frequency Relation Reasoning for Deepfake Detection

Yuan Wang,

Kun Yu,

Chen Chen,

Xiyuan Hu,

Silong Peng

[pdf] [supp]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Yuan and Yu, Kun and Chen, Chen and Hu, Xiyuan and Peng, Silong}, title = {Dynamic Graph Learning With Content-Guided Spatial-Frequency Relation Reasoning for Deepfake Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7278-7287} }

Visual Language Pretrained Multiple Instance Zero-Shot Transfer for Histopathology Images

Ming Y. Lu,

Bowen Chen,

Andrew Zhang,

Drew F. K. Williamson,

Richard J. Chen,

Tong Ding,

Long Phi Le,

Yung-Sung Chuang,

Faisal Mahmood

[pdf] [supp]

[bibtex]

@InProceedings{Lu_2023_CVPR, author = {Lu, Ming Y. and Chen, Bowen and Zhang, Andrew and Williamson, Drew F. K. and Chen, Richard J. and Ding, Tong and Le, Long Phi and Chuang, Yung-Sung and Mahmood, Faisal}, title = {Visual Language Pretrained Multiple Instance Zero-Shot Transfer for Histopathology Images}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {19764-19775} }

MIST: Multi-Modal Iterative Spatial-Temporal Transformer for Long-Form Video Question Answering

Difei Gao,

Luowei Zhou,

Lei Ji,

Linchao Zhu,

Yi Yang,

Mike Zheng Shou

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Gao_2023_CVPR, author = {Gao, Difei and Zhou, Luowei and Ji, Lei and Zhu, Linchao and Yang, Yi and Shou, Mike Zheng}, title = {MIST: Multi-Modal Iterative Spatial-Temporal Transformer for Long-Form Video Question Answering}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14773-14783} }

PMR: Prototypical Modal Rebalance for Multimodal Learning

Yunfeng Fan,

Wenchao Xu,

Haozhao Wang,

Junxiao Wang,

Song Guo

[pdf] [arXiv]

[bibtex]

@InProceedings{Fan_2023_CVPR, author = {Fan, Yunfeng and Xu, Wenchao and Wang, Haozhao and Wang, Junxiao and Guo, Song}, title = {PMR: Prototypical Modal Rebalance for Multimodal Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {20029-20038} }

Two-Stage Co-Segmentation Network Based on Discriminative Representation for Recovering Human Mesh From Videos

Boyang Zhang,

Kehua Ma,

Suping Wu,

Zhixiang Yuan

[pdf] [supp]

[bibtex]

@InProceedings{Zhang_2023_CVPR, author = {Zhang, Boyang and Ma, Kehua and Wu, Suping and Yuan, Zhixiang}, title = {Two-Stage Co-Segmentation Network Based on Discriminative Representation for Recovering Human Mesh From Videos}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5662-5670} }

Multi-Sensor Large-Scale Dataset for Multi-View 3D Reconstruction

Oleg Voynov,

Gleb Bobrovskikh,

Pavel Karpyshev,

Saveliy Galochkin,

Andrei-Timotei Ardelean,

Arseniy Bozhenko,

Ekaterina Karmanova,

Pavel Kopanev,

Yaroslav Labutin-Rymsho,

Ruslan Rakhimov,

Aleksandr Safin,

Valerii Serpiva,

Alexey Artemov,

Evgeny Burnaev,

Dzmitry Tsetserukou,

Denis Zorin

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Voynov_2023_CVPR, author = {Voynov, Oleg and Bobrovskikh, Gleb and Karpyshev, Pavel and Galochkin, Saveliy and Ardelean, Andrei-Timotei and Bozhenko, Arseniy and Karmanova, Ekaterina and Kopanev, Pavel and Labutin-Rymsho, Yaroslav and Rakhimov, Ruslan and Safin, Aleksandr and Serpiva, Valerii and Artemov, Alexey and Burnaev, Evgeny and Tsetserukou, Dzmitry and Zorin, Denis}, title = {Multi-Sensor Large-Scale Dataset for Multi-View 3D Reconstruction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {21392-21403} }

Privacy-Preserving Representations Are Not Enough: Recovering Scene Content From Camera Poses

Kunal Chelani,

Torsten Sattler,

Fredrik Kahl,

Zuzana Kukelova

[pdf] [supp]

[bibtex]

@InProceedings{Chelani_2023_CVPR, author = {Chelani, Kunal and Sattler, Torsten and Kahl, Fredrik and Kukelova, Zuzana}, title = {Privacy-Preserving Representations Are Not Enough: Recovering Scene Content From Camera Poses}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13132-13141} }

Learning Anchor Transformations for 3D Garment Animation

Fang Zhao,

Zekun Li,

Shaoli Huang,

Junwu Weng,

Tianfei Zhou,

Guo-Sen Xie,

Jue Wang,

Ying Shan

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Zhao_2023_CVPR, author = {Zhao, Fang and Li, Zekun and Huang, Shaoli and Weng, Junwu and Zhou, Tianfei and Xie, Guo-Sen and Wang, Jue and Shan, Ying}, title = {Learning Anchor Transformations for 3D Garment Animation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {491-500} }

Actionlet-Dependent Contrastive Learning for Unsupervised Skeleton-Based Action Recognition

Lilang Lin,

Jiahang Zhang,

Jiaying Liu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Lin_2023_CVPR, author = {Lin, Lilang and Zhang, Jiahang and Liu, Jiaying}, title = {Actionlet-Dependent Contrastive Learning for Unsupervised Skeleton-Based Action Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2363-2372} }

Ref-NPR: Reference-Based Non-Photorealistic Radiance Fields for Controllable Scene Stylization

Yuechen Zhang,

Zexin He,

Jinbo Xing,

Xufeng Yao,

Jiaya Jia

[pdf] [supp]

[bibtex]

@InProceedings{Zhang_2023_CVPR, author = {Zhang, Yuechen and He, Zexin and Xing, Jinbo and Yao, Xufeng and Jia, Jiaya}, title = {Ref-NPR: Reference-Based Non-Photorealistic Radiance Fields for Controllable Scene Stylization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4242-4251} }

PanoHead: Geometry-Aware 3D Full-Head Synthesis in 360deg

Sizhe An,

Hongyi Xu,

Yichun Shi,

Guoxian Song,

Umit Y. Ogras,

Linjie Luo

[pdf] [supp]

[bibtex]

@InProceedings{An_2023_CVPR, author = {An, Sizhe and Xu, Hongyi and Shi, Yichun and Song, Guoxian and Ogras, Umit Y. and Luo, Linjie}, title = {PanoHead: Geometry-Aware 3D Full-Head Synthesis in 360deg}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {20950-20959} }

Rethinking Feature-Based Knowledge Distillation for Face Recognition

Jingzhi Li,

Zidong Guo,

Hui Li,

Seungju Han,

Ji-won Baek,

Min Yang,

Ran Yang,

Sungjoo Suh

[pdf] [supp]

[bibtex]

@InProceedings{Li_2023_CVPR, author = {Li, Jingzhi and Guo, Zidong and Li, Hui and Han, Seungju and Baek, Ji-won and Yang, Min and Yang, Ran and Suh, Sungjoo}, title = {Rethinking Feature-Based Knowledge Distillation for Face Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {20156-20165} }

NeurOCS: Neural NOCS Supervision for Monocular 3D Object Localization

Zhixiang Min,

Bingbing Zhuang,

Samuel Schulter,

Buyu Liu,

Enrique Dunn,

Manmohan Chandraker

[pdf] [supp]

[bibtex]

@InProceedings{Min_2023_CVPR, author = {Min, Zhixiang and Zhuang, Bingbing and Schulter, Samuel and Liu, Buyu and Dunn, Enrique and Chandraker, Manmohan}, title = {NeurOCS: Neural NOCS Supervision for Monocular 3D Object Localization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {21404-21414} }

Tree Instance Segmentation With Temporal Contour Graph

Adnan Firoze,

Cameron Wingren,

Raymond A. Yeh,

Bedrich Benes,

Daniel Aliaga

[pdf] [supp]

[bibtex]

@InProceedings{Firoze_2023_CVPR, author = {Firoze, Adnan and Wingren, Cameron and Yeh, Raymond A. and Benes, Bedrich and Aliaga, Daniel}, title = {Tree Instance Segmentation With Temporal Contour Graph}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2193-2202} }

A New Dataset Based on Images Taken by Blind People for Testing the Robustness of Image Classification Models Trained for ImageNet Categories

Reza Akbarian Bafghi,

Danna Gurari

[pdf] [supp]

[bibtex]

@InProceedings{Bafghi_2023_CVPR, author = {Bafghi, Reza Akbarian and Gurari, Danna}, title = {A New Dataset Based on Images Taken by Blind People for Testing the Robustness of Image Classification Models Trained for ImageNet Categories}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16261-16270} }

Detecting Backdoors During the Inference Stage Based on Corruption Robustness Consistency

Xiaogeng Liu,

Minghui Li,

Haoyu Wang,

Shengshan Hu,

Dengpan Ye,

Hai Jin,

Libing Wu,

Chaowei Xiao

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Liu_2023_CVPR, author = {Liu, Xiaogeng and Li, Minghui and Wang, Haoyu and Hu, Shengshan and Ye, Dengpan and Jin, Hai and Wu, Libing and Xiao, Chaowei}, title = {Detecting Backdoors During the Inference Stage Based on Corruption Robustness Consistency}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16363-16372} }

Black-Box Sparse Adversarial Attack via Multi-Objective Optimisation

Phoenix Neale Williams,

Ke Li

[pdf] [supp]

[bibtex]

@InProceedings{Williams_2023_CVPR, author = {Williams, Phoenix Neale and Li, Ke}, title = {Black-Box Sparse Adversarial Attack via Multi-Objective Optimisation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12291-12301} }

Renderable Neural Radiance Map for Visual Navigation

Obin Kwon,

Jeongho Park,

Songhwai Oh

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Kwon_2023_CVPR, author = {Kwon, Obin and Park, Jeongho and Oh, Songhwai}, title = {Renderable Neural Radiance Map for Visual Navigation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9099-9108} }

Revisiting Reverse Distillation for Anomaly Detection

Tran Dinh Tien,

Anh Tuan Nguyen,

Nguyen Hoang Tran,

Ta Duc Huy,

Soan T.M. Duong,

Chanh D. Tr. Nguyen,

Steven Q. H. Truong

[pdf]

[bibtex]

@InProceedings{Tien_2023_CVPR, author = {Tien, Tran Dinh and Nguyen, Anh Tuan and Tran, Nguyen Hoang and Huy, Ta Duc and Duong, Soan T.M. and Nguyen, Chanh D. Tr. and Truong, Steven Q. H.}, title = {Revisiting Reverse Distillation for Anomaly Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {24511-24520} }

Diffusion-Based Generation, Optimization, and Planning in 3D Scenes

Siyuan Huang,

Zan Wang,

Puhao Li,

Baoxiong Jia,

Tengyu Liu,

Yixin Zhu,

Wei Liang,

Song-Chun Zhu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Huang_2023_CVPR, author = {Huang, Siyuan and Wang, Zan and Li, Puhao and Jia, Baoxiong and Liu, Tengyu and Zhu, Yixin and Liang, Wei and Zhu, Song-Chun}, title = {Diffusion-Based Generation, Optimization, and Planning in 3D Scenes}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16750-16761} }

TMO: Textured Mesh Acquisition of Objects With a Mobile Device by Using Differentiable Rendering

Jaehoon Choi,

Dongki Jung,

Taejae Lee,

Sangwook Kim,

Youngdong Jung,

Dinesh Manocha,

Donghwan Lee

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Choi_2023_CVPR, author = {Choi, Jaehoon and Jung, Dongki and Lee, Taejae and Kim, Sangwook and Jung, Youngdong and Manocha, Dinesh and Lee, Donghwan}, title = {TMO: Textured Mesh Acquisition of Objects With a Mobile Device by Using Differentiable Rendering}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16674-16684} }

Meta-Causal Learning for Single Domain Generalization

Jin Chen,

Zhi Gao,

Xinxiao Wu,

Jiebo Luo

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Chen_2023_CVPR, author = {Chen, Jin and Gao, Zhi and Wu, Xinxiao and Luo, Jiebo}, title = {Meta-Causal Learning for Single Domain Generalization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7683-7692} }

Grad-PU: Arbitrary-Scale Point Cloud Upsampling via Gradient Descent With Learned Distance Functions

Yun He,

Danhang Tang,

Yinda Zhang,

Xiangyang Xue,

Yanwei Fu

[pdf] [supp]

[bibtex]

@InProceedings{He_2023_CVPR, author = {He, Yun and Tang, Danhang and Zhang, Yinda and Xue, Xiangyang and Fu, Yanwei}, title = {Grad-PU: Arbitrary-Scale Point Cloud Upsampling via Gradient Descent With Learned Distance Functions}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5354-5363} }

Trainable Projected Gradient Method for Robust Fine-Tuning

Junjiao Tian,

Zecheng He,

Xiaoliang Dai,

Chih-Yao Ma,

Yen-Cheng Liu,

Zsolt Kira

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Tian_2023_CVPR, author = {Tian, Junjiao and He, Zecheng and Dai, Xiaoliang and Ma, Chih-Yao and Liu, Yen-Cheng and Kira, Zsolt}, title = {Trainable Projected Gradient Method for Robust Fine-Tuning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7836-7845} }

Text2Scene: Text-Driven Indoor Scene Stylization With Part-Aware Details

Inwoo Hwang,

Hyeonwoo Kim,

Young Min Kim

[pdf] [supp]

[bibtex]

@InProceedings{Hwang_2023_CVPR, author = {Hwang, Inwoo and Kim, Hyeonwoo and Kim, Young Min}, title = {Text2Scene: Text-Driven Indoor Scene Stylization With Part-Aware Details}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1890-1899} }

FEND: A Future Enhanced Distribution-Aware Contrastive Learning Framework for Long-Tail Trajectory Prediction

Yuning Wang,

Pu Zhang,

Lei Bai,

Jianru Xue

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Yuning and Zhang, Pu and Bai, Lei and Xue, Jianru}, title = {FEND: A Future Enhanced Distribution-Aware Contrastive Learning Framework for Long-Tail Trajectory Prediction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1400-1409} }

MP-Former: Mask-Piloted Transformer for Image Segmentation

Hao Zhang,

Feng Li,

Huaizhe Xu,

Shijia Huang,

Shilong Liu,

Lionel M. Ni,

Lei Zhang

[pdf] [supp]

[bibtex]

@InProceedings{Zhang_2023_CVPR, author = {Zhang, Hao and Li, Feng and Xu, Huaizhe and Huang, Shijia and Liu, Shilong and Ni, Lionel M. and Zhang, Lei}, title = {MP-Former: Mask-Piloted Transformer for Image Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {18074-18083} }

HDR Imaging With Spatially Varying Signal-to-Noise Ratios

Yiheng Chi,

Xingguang Zhang,

Stanley H. Chan

[pdf] [arXiv]

[bibtex]

@InProceedings{Chi_2023_CVPR, author = {Chi, Yiheng and Zhang, Xingguang and Chan, Stanley H.}, title = {HDR Imaging With Spatially Varying Signal-to-Noise Ratios}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5724-5734} }

Learning Orthogonal Prototypes for Generalized Few-Shot Semantic Segmentation

Sun-Ao Liu,

Yiheng Zhang,

Zhaofan Qiu,

Hongtao Xie,

Yongdong Zhang,

Ting Yao

[pdf]

[bibtex]

@InProceedings{Liu_2023_CVPR, author = {Liu, Sun-Ao and Zhang, Yiheng and Qiu, Zhaofan and Xie, Hongtao and Zhang, Yongdong and Yao, Ting}, title = {Learning Orthogonal Prototypes for Generalized Few-Shot Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11319-11328} }

TAPS3D: Text-Guided 3D Textured Shape Generation From Pseudo Supervision

Jiacheng Wei,

Hao Wang,

Jiashi Feng,

Guosheng Lin,

Kim-Hui Yap

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Wei_2023_CVPR, author = {Wei, Jiacheng and Wang, Hao and Feng, Jiashi and Lin, Guosheng and Yap, Kim-Hui}, title = {TAPS3D: Text-Guided 3D Textured Shape Generation From Pseudo Supervision}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16805-16815} }

Are Deep Neural Networks SMARTer Than Second Graders?

Anoop Cherian,

Kuan-Chuan Peng,

Suhas Lohit,

Kevin A. Smith,

Joshua B. Tenenbaum

[pdf] [arXiv]

[bibtex]

@InProceedings{Cherian_2023_CVPR, author = {Cherian, Anoop and Peng, Kuan-Chuan and Lohit, Suhas and Smith, Kevin A. and Tenenbaum, Joshua B.}, title = {Are Deep Neural Networks SMARTer Than Second Graders?}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10834-10844} }

Reliability in Semantic Segmentation: Are We on the Right Track?

Pau de Jorge,

Riccardo Volpi,

Philip H.S. Torr,

Grégory Rogez

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{de_Jorge_2023_CVPR, author = {de Jorge, Pau and Volpi, Riccardo and Torr, Philip H.S. and Rogez, Gr\'egory}, title = {Reliability in Semantic Segmentation: Are We on the Right Track?}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7173-7182} }

Video Test-Time Adaptation for Action Recognition

Wei Lin,

Muhammad Jehanzeb Mirza,

Mateusz Kozinski,

Horst Possegger,

Hilde Kuehne,

Horst Bischof

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Lin_2023_CVPR, author = {Lin, Wei and Mirza, Muhammad Jehanzeb and Kozinski, Mateusz and Possegger, Horst and Kuehne, Hilde and Bischof, Horst}, title = {Video Test-Time Adaptation for Action Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {22952-22961} }

Bi-Level Meta-Learning for Few-Shot Domain Generalization

Xiaorong Qin,

Xinhang Song,

Shuqiang Jiang

[pdf] [supp]

[bibtex]

@InProceedings{Qin_2023_CVPR, author = {Qin, Xiaorong and Song, Xinhang and Jiang, Shuqiang}, title = {Bi-Level Meta-Learning for Few-Shot Domain Generalization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15900-15910} }

Tensor4D: Efficient Neural 4D Decomposition for High-Fidelity Dynamic Reconstruction and Rendering

Ruizhi Shao,

Zerong Zheng,

Hanzhang Tu,

Boning Liu,

Hongwen Zhang,

Yebin Liu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Shao_2023_CVPR, author = {Shao, Ruizhi and Zheng, Zerong and Tu, Hanzhang and Liu, Boning and Zhang, Hongwen and Liu, Yebin}, title = {Tensor4D: Efficient Neural 4D Decomposition for High-Fidelity Dynamic Reconstruction and Rendering}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16632-16642} }

Blowing in the Wind: CycleNet for Human Cinemagraphs From Still Images

Hugo Bertiche,

Niloy J. Mitra,

Kuldeep Kulkarni,

Chun-Hao P. Huang,

Tuanfeng Y. Wang,

Meysam Madadi,

Sergio Escalera,

Duygu Ceylan

[pdf] [arXiv]

[bibtex]

@InProceedings{Bertiche_2023_CVPR, author = {Bertiche, Hugo and Mitra, Niloy J. and Kulkarni, Kuldeep and Huang, Chun-Hao P. and Wang, Tuanfeng Y. and Madadi, Meysam and Escalera, Sergio and Ceylan, Duygu}, title = {Blowing in the Wind: CycleNet for Human Cinemagraphs From Still Images}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {459-468} }

Learning Personalized High Quality Volumetric Head Avatars From Monocular RGB Videos

Ziqian Bai,

Feitong Tan,

Zeng Huang,

Kripasindhu Sarkar,

Danhang Tang,

Di Qiu,

Abhimitra Meka,

Ruofei Du,

Mingsong Dou,

Sergio Orts-Escolano,

Rohit Pandey,

Ping Tan,

Thabo Beeler,

Sean Fanello,

Yinda Zhang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Bai_2023_CVPR, author = {Bai, Ziqian and Tan, Feitong and Huang, Zeng and Sarkar, Kripasindhu and Tang, Danhang and Qiu, Di and Meka, Abhimitra and Du, Ruofei and Dou, Mingsong and Orts-Escolano, Sergio and Pandey, Rohit and Tan, Ping and Beeler, Thabo and Fanello, Sean and Zhang, Yinda}, title = {Learning Personalized High Quality Volumetric Head Avatars From Monocular RGB Videos}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16890-16900} }

Multi-Modal Learning With Missing Modality via Shared-Specific Feature Modelling

Hu Wang,

Yuanhong Chen,

Congbo Ma,

Jodie Avery,

Louise Hull,

Gustavo Carneiro

[pdf]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Hu and Chen, Yuanhong and Ma, Congbo and Avery, Jodie and Hull, Louise and Carneiro, Gustavo}, title = {Multi-Modal Learning With Missing Modality via Shared-Specific Feature Modelling}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15878-15887} }

Panoptic Compositional Feature Field for Editable Scene Rendering With Network-Inferred Labels via Metric Learning

Xinhua Cheng,

Yanmin Wu,

Mengxi Jia,

Qian Wang,

Jian Zhang

[pdf] [supp]

[bibtex]

@InProceedings{Cheng_2023_CVPR, author = {Cheng, Xinhua and Wu, Yanmin and Jia, Mengxi and Wang, Qian and Zhang, Jian}, title = {Panoptic Compositional Feature Field for Editable Scene Rendering With Network-Inferred Labels via Metric Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4947-4957} }

Progressive Backdoor Erasing via Connecting Backdoor and Adversarial Attacks

Bingxu Mu,

Zhenxing Niu,

Le Wang,

Xue Wang,

Qiguang Miao,

Rong Jin,

Gang Hua

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Mu_2023_CVPR, author = {Mu, Bingxu and Niu, Zhenxing and Wang, Le and Wang, Xue and Miao, Qiguang and Jin, Rong and Hua, Gang}, title = {Progressive Backdoor Erasing via Connecting Backdoor and Adversarial Attacks}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {20495-20503} }

LayoutFormer++: Conditional Graphic Layout Generation via Constraint Serialization and Decoding Space Restriction

Zhaoyun Jiang,

Jiaqi Guo,

Shizhao Sun,

Huayu Deng,

Zhongkai Wu,

Vuksan Mijovic,

Zijiang James Yang,

Jian-Guang Lou,

Dongmei Zhang

[pdf] [supp]

[bibtex]

@InProceedings{Jiang_2023_CVPR, author = {Jiang, Zhaoyun and Guo, Jiaqi and Sun, Shizhao and Deng, Huayu and Wu, Zhongkai and Mijovic, Vuksan and Yang, Zijiang James and Lou, Jian-Guang and Zhang, Dongmei}, title = {LayoutFormer++: Conditional Graphic Layout Generation via Constraint Serialization and Decoding Space Restriction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {18403-18412} }

DisWOT: Student Architecture Search for Distillation WithOut Training

Peijie Dong,

Lujun Li,

Zimian Wei

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Dong_2023_CVPR, author = {Dong, Peijie and Li, Lujun and Wei, Zimian}, title = {DisWOT: Student Architecture Search for Distillation WithOut Training}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11898-11908} }

Stare at What You See: Masked Image Modeling Without Reconstruction

Hongwei Xue,

Peng Gao,

Hongyang Li,

Yu Qiao,

Hao Sun,

Houqiang Li,

Jiebo Luo

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Xue_2023_CVPR, author = {Xue, Hongwei and Gao, Peng and Li, Hongyang and Qiao, Yu and Sun, Hao and Li, Houqiang and Luo, Jiebo}, title = {Stare at What You See: Masked Image Modeling Without Reconstruction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {22732-22741} }

Joint Visual Grounding and Tracking With Natural Language Specification

Li Zhou,

Zikun Zhou,

Kaige Mao,

Zhenyu He

[pdf] [arXiv]

[bibtex]

@InProceedings{Zhou_2023_CVPR, author = {Zhou, Li and Zhou, Zikun and Mao, Kaige and He, Zhenyu}, title = {Joint Visual Grounding and Tracking With Natural Language Specification}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {23151-23160} }

Neural Kaleidoscopic Space Sculpting

Byeongjoo Ahn,

Michael De Zeeuw,

Ioannis Gkioulekas,

Aswin C. Sankaranarayanan

[pdf] [supp]

[bibtex]

@InProceedings{Ahn_2023_CVPR, author = {Ahn, Byeongjoo and De Zeeuw, Michael and Gkioulekas, Ioannis and Sankaranarayanan, Aswin C.}, title = {Neural Kaleidoscopic Space Sculpting}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4349-4358} }

Few-Shot Semantic Image Synthesis With Class Affinity Transfer

Marlène Careil,

Jakob Verbeek,

Stéphane Lathuilière

[pdf] [supp]

[bibtex]

@InProceedings{Careil_2023_CVPR, author = {Careil, Marl\`ene and Verbeek, Jakob and Lathuili\`ere, St\'ephane}, title = {Few-Shot Semantic Image Synthesis With Class Affinity Transfer}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {23611-23620} }

Implicit Identity Driven Deepfake Face Swapping Detection

Baojin Huang,

Zhongyuan Wang,

Jifan Yang,

Jiaxin Ai,

Qin Zou,

Qian Wang,

Dengpan Ye

[pdf]

[bibtex]

@InProceedings{Huang_2023_CVPR, author = {Huang, Baojin and Wang, Zhongyuan and Yang, Jifan and Ai, Jiaxin and Zou, Qin and Wang, Qian and Ye, Dengpan}, title = {Implicit Identity Driven Deepfake Face Swapping Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4490-4499} }

Class Relationship Embedded Learning for Source-Free Unsupervised Domain Adaptation

Yixin Zhang,

Zilei Wang,

Weinan He

[pdf] [supp]

[bibtex]

@InProceedings{Zhang_2023_CVPR, author = {Zhang, Yixin and Wang, Zilei and He, Weinan}, title = {Class Relationship Embedded Learning for Source-Free Unsupervised Domain Adaptation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7619-7629} }

Logical Consistency and Greater Descriptive Power for Facial Hair Attribute Learning

Haiyu Wu,

Grace Bezold,

Aman Bhatta,

Kevin W. Bowyer

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Wu_2023_CVPR, author = {Wu, Haiyu and Bezold, Grace and Bhatta, Aman and Bowyer, Kevin W.}, title = {Logical Consistency and Greater Descriptive Power for Facial Hair Attribute Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8588-8597} }

One-to-Few Label Assignment for End-to-End Dense Detection

Shuai Li,

Minghan Li,

Ruihuang Li,

Chenhang He,

Lei Zhang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Li_2023_CVPR, author = {Li, Shuai and Li, Minghan and Li, Ruihuang and He, Chenhang and Zhang, Lei}, title = {One-to-Few Label Assignment for End-to-End Dense Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7350-7359} }

Spatio-Temporal Pixel-Level Contrastive Learning-Based Source-Free Domain Adaptation for Video Semantic Segmentation

Shao-Yuan Lo,

Poojan Oza,

Sumanth Chennupati,

Alejandro Galindo,

Vishal M. Patel

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Lo_2023_CVPR, author = {Lo, Shao-Yuan and Oza, Poojan and Chennupati, Sumanth and Galindo, Alejandro and Patel, Vishal M.}, title = {Spatio-Temporal Pixel-Level Contrastive Learning-Based Source-Free Domain Adaptation for Video Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10534-10543} }

InternImage: Exploring Large-Scale Vision Foundation Models With Deformable Convolutions

Wenhai Wang,

Jifeng Dai,

Zhe Chen,

Zhenhang Huang,

Zhiqi Li,

Xizhou Zhu,

Xiaowei Hu,

Tong Lu,

Lewei Lu,

Hongsheng Li,

Xiaogang Wang,

Yu Qiao

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Wenhai and Dai, Jifeng and Chen, Zhe and Huang, Zhenhang and Li, Zhiqi and Zhu, Xizhou and Hu, Xiaowei and Lu, Tong and Lu, Lewei and Li, Hongsheng and Wang, Xiaogang and Qiao, Yu}, title = {InternImage: Exploring Large-Scale Vision Foundation Models With Deformable Convolutions}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14408-14419} }

DAA: A Delta Age AdaIN Operation for Age Estimation via Binary Code Transformer

Ping Chen,

Xingpeng Zhang,

Ye Li,

Ju Tao,

Bin Xiao,

Bing Wang,

Zongjie Jiang

[pdf] [arXiv]

[bibtex]

@InProceedings{Chen_2023_CVPR, author = {Chen, Ping and Zhang, Xingpeng and Li, Ye and Tao, Ju and Xiao, Bin and Wang, Bing and Jiang, Zongjie}, title = {DAA: A Delta Age AdaIN Operation for Age Estimation via Binary Code Transformer}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15836-15845} }

Fake It Till You Make It: Learning Transferable Representations From Synthetic ImageNet Clones

Mert Bülent Sarıyıldız,

Karteek Alahari,

Diane Larlus,

Yannis Kalantidis

[pdf] [supp]

[bibtex]

@InProceedings{Sariyildiz_2023_CVPR, author = {Sar{\i}y{\i}ld{\i}z, Mert B\"ulent and Alahari, Karteek and Larlus, Diane and Kalantidis, Yannis}, title = {Fake It Till You Make It: Learning Transferable Representations From Synthetic ImageNet Clones}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8011-8021} }

Mind the Label Shift of Augmentation-Based Graph OOD Generalization

Junchi Yu,

Jian Liang,

Ran He

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Yu_2023_CVPR, author = {Yu, Junchi and Liang, Jian and He, Ran}, title = {Mind the Label Shift of Augmentation-Based Graph OOD Generalization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11620-11630} }

Unsupervised Intrinsic Image Decomposition With LiDAR Intensity

Shogo Sato,

Yasuhiro Yao,

Taiga Yoshida,

Takuhiro Kaneko,

Shingo Ando,

Jun Shimamura

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Sato_2023_CVPR, author = {Sato, Shogo and Yao, Yasuhiro and Yoshida, Taiga and Kaneko, Takuhiro and Ando, Shingo and Shimamura, Jun}, title = {Unsupervised Intrinsic Image Decomposition With LiDAR Intensity}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13466-13475} }

HIER: Metric Learning Beyond Class Labels via Hierarchical Regularization

Sungyeon Kim,

Boseung Jeong,

Suha Kwak

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Kim_2023_CVPR, author = {Kim, Sungyeon and Jeong, Boseung and Kwak, Suha}, title = {HIER: Metric Learning Beyond Class Labels via Hierarchical Regularization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {19903-19912} }

Diffusion Probabilistic Model Made Slim

Xingyi Yang,

Daquan Zhou,

Jiashi Feng,

Xinchao Wang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Yang_2023_CVPR, author = {Yang, Xingyi and Zhou, Daquan and Feng, Jiashi and Wang, Xinchao}, title = {Diffusion Probabilistic Model Made Slim}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {22552-22562} }

Confidence-Aware Personalized Federated Learning via Variational Expectation Maximization

Junyi Zhu,

Xingchen Ma,

Matthew B. Blaschko

[pdf] [supp]

[bibtex]

@InProceedings{Zhu_2023_CVPR, author = {Zhu, Junyi and Ma, Xingchen and Blaschko, Matthew B.}, title = {Confidence-Aware Personalized Federated Learning via Variational Expectation Maximization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {24542-24551} }

Hierarchical Supervision and Shuffle Data Augmentation for 3D Semi-Supervised Object Detection

Chuandong Liu,

Chenqiang Gao,

Fangcen Liu,

Pengcheng Li,

Deyu Meng,

Xinbo Gao

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Liu_2023_CVPR, author = {Liu, Chuandong and Gao, Chenqiang and Liu, Fangcen and Li, Pengcheng and Meng, Deyu and Gao, Xinbo}, title = {Hierarchical Supervision and Shuffle Data Augmentation for 3D Semi-Supervised Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {23819-23828} }

Interactive and Explainable Region-Guided Radiology Report Generation

Tim Tanida,

Philip Müller,

Georgios Kaissis,

Daniel Rueckert

[pdf] [supp]

[bibtex]

@InProceedings{Tanida_2023_CVPR, author = {Tanida, Tim and M\"uller, Philip and Kaissis, Georgios and Rueckert, Daniel}, title = {Interactive and Explainable Region-Guided Radiology Report Generation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7433-7442} }

MED-VT: Multiscale Encoder-Decoder Video Transformer With Application To Object Segmentation

Rezaul Karim,

He Zhao,

Richard P. Wildes,

Mennatullah Siam

[pdf] [supp]

[bibtex]

@InProceedings{Karim_2023_CVPR, author = {Karim, Rezaul and Zhao, He and Wildes, Richard P. and Siam, Mennatullah}, title = {MED-VT: Multiscale Encoder-Decoder Video Transformer With Application To Object Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6323-6333} }

PET-NeuS: Positional Encoding Tri-Planes for Neural Surfaces

Yiqun Wang,

Ivan Skorokhodov,

Peter Wonka

[pdf] [supp]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Yiqun and Skorokhodov, Ivan and Wonka, Peter}, title = {PET-NeuS: Positional Encoding Tri-Planes for Neural Surfaces}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12598-12607} }

ZegCLIP: Towards Adapting CLIP for Zero-Shot Semantic Segmentation

Ziqin Zhou,

Yinjie Lei,

Bowen Zhang,

Lingqiao Liu,

Yifan Liu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Zhou_2023_CVPR, author = {Zhou, Ziqin and Lei, Yinjie and Zhang, Bowen and Liu, Lingqiao and Liu, Yifan}, title = {ZegCLIP: Towards Adapting CLIP for Zero-Shot Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11175-11185} }

AdaptiveMix: Improving GAN Training via Feature Space Shrinkage

Haozhe Liu,

Wentian Zhang,

Bing Li,

Haoqian Wu,

Nanjun He,

Yawen Huang,

Yuexiang Li,

Bernard Ghanem,

Yefeng Zheng

[pdf] [supp]

[bibtex]

@InProceedings{Liu_2023_CVPR, author = {Liu, Haozhe and Zhang, Wentian and Li, Bing and Wu, Haoqian and He, Nanjun and Huang, Yawen and Li, Yuexiang and Ghanem, Bernard and Zheng, Yefeng}, title = {AdaptiveMix: Improving GAN Training via Feature Space Shrinkage}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16219-16229} }

Specialist Diffusion: Plug-and-Play Sample-Efficient Fine-Tuning of Text-to-Image Diffusion Models To Learn Any Unseen Style

Haoming Lu,

Hazarapet Tunanyan,

Kai Wang,

Shant Navasardyan,

Zhangyang Wang,

Humphrey Shi

[pdf] [supp]

[bibtex]

@InProceedings{Lu_2023_CVPR, author = {Lu, Haoming and Tunanyan, Hazarapet and Wang, Kai and Navasardyan, Shant and Wang, Zhangyang and Shi, Humphrey}, title = {Specialist Diffusion: Plug-and-Play Sample-Efficient Fine-Tuning of Text-to-Image Diffusion Models To Learn Any Unseen Style}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14267-14276} }

Benchmarking Self-Supervised Learning on Diverse Pathology Datasets

Mingu Kang,

Heon Song,

Seonwook Park,

Donggeun Yoo,

Sérgio Pereira

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Kang_2023_CVPR, author = {Kang, Mingu and Song, Heon and Park, Seonwook and Yoo, Donggeun and Pereira, S\'ergio}, title = {Benchmarking Self-Supervised Learning on Diverse Pathology Datasets}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3344-3354} }

Planning-Oriented Autonomous Driving

Yihan Hu,

Jiazhi Yang,

Li Chen,

Keyu Li,

Chonghao Sima,

Xizhou Zhu,

Siqi Chai,

Senyao Du,

Tianwei Lin,

Wenhai Wang,

Lewei Lu,

Xiaosong Jia,

Qiang Liu,

Jifeng Dai,

Yu Qiao,

Hongyang Li

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Hu_2023_CVPR, author = {Hu, Yihan and Yang, Jiazhi and Chen, Li and Li, Keyu and Sima, Chonghao and Zhu, Xizhou and Chai, Siqi and Du, Senyao and Lin, Tianwei and Wang, Wenhai and Lu, Lewei and Jia, Xiaosong and Liu, Qiang and Dai, Jifeng and Qiao, Yu and Li, Hongyang}, title = {Planning-Oriented Autonomous Driving}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {17853-17862} }

HyperCUT: Video Sequence From a Single Blurry Image Using Unsupervised Ordering

Bang-Dang Pham,

Phong Tran,

Anh Tran,

Cuong Pham,

Rang Nguyen,

Minh Hoai

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Pham_2023_CVPR, author = {Pham, Bang-Dang and Tran, Phong and Tran, Anh and Pham, Cuong and Nguyen, Rang and Hoai, Minh}, title = {HyperCUT: Video Sequence From a Single Blurry Image Using Unsupervised Ordering}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9843-9852} }

Can't Steal? Cont-Steal! Contrastive Stealing Attacks Against Image Encoders

Zeyang Sha,

Xinlei He,

Ning Yu,

Michael Backes,

Yang Zhang

[pdf] [supp]

[bibtex]

@InProceedings{Sha_2023_CVPR, author = {Sha, Zeyang and He, Xinlei and Yu, Ning and Backes, Michael and Zhang, Yang}, title = {Can't Steal? Cont-Steal! Contrastive Stealing Attacks Against Image Encoders}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16373-16383} }

Document Image Shadow Removal Guided by Color-Aware Background

Ling Zhang,

Yinghao He,

Qing Zhang,

Zheng Liu,

Xiaolong Zhang,

Chunxia Xiao

[pdf] [supp]

[bibtex]

@InProceedings{Zhang_2023_CVPR, author = {Zhang, Ling and He, Yinghao and Zhang, Qing and Liu, Zheng and Zhang, Xiaolong and Xiao, Chunxia}, title = {Document Image Shadow Removal Guided by Color-Aware Background}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1818-1827} }

Independent Component Alignment for Multi-Task Learning

Dmitry Senushkin,

Nikolay Patakin,

Arseny Kuznetsov,

Anton Konushin

[pdf] [supp]

[bibtex]

@InProceedings{Senushkin_2023_CVPR, author = {Senushkin, Dmitry and Patakin, Nikolay and Kuznetsov, Arseny and Konushin, Anton}, title = {Independent Component Alignment for Multi-Task Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {20083-20093} }

Edges to Shapes to Concepts: Adversarial Augmentation for Robust Vision

Aditay Tripathi,

Rishubh Singh,

Anirban Chakraborty,

Pradeep Shenoy

[pdf] [supp]

[bibtex]

@InProceedings{Tripathi_2023_CVPR, author = {Tripathi, Aditay and Singh, Rishubh and Chakraborty, Anirban and Shenoy, Pradeep}, title = {Edges to Shapes to Concepts: Adversarial Augmentation for Robust Vision}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {24470-24479} }

ReVISE: Self-Supervised Speech Resynthesis With Visual Input for Universal and Generalized Speech Regeneration

Wei-Ning Hsu,

Tal Remez,

Bowen Shi,

Jacob Donley,

Yossi Adi

[pdf] [supp]

[bibtex]

@InProceedings{Hsu_2023_CVPR, author = {Hsu, Wei-Ning and Remez, Tal and Shi, Bowen and Donley, Jacob and Adi, Yossi}, title = {ReVISE: Self-Supervised Speech Resynthesis With Visual Input for Universal and Generalized Speech Regeneration}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {18795-18805} }

Improved Distribution Matching for Dataset Condensation

Ganlong Zhao,

Guanbin Li,

Yipeng Qin,

Yizhou Yu

[pdf] [supp]

[bibtex]

@InProceedings{Zhao_2023_CVPR, author = {Zhao, Ganlong and Li, Guanbin and Qin, Yipeng and Yu, Yizhou}, title = {Improved Distribution Matching for Dataset Condensation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7856-7865} }

Feature Separation and Recalibration for Adversarial Robustness

Woo Jae Kim,

Yoonki Cho,

Junsik Jung,

Sung-Eui Yoon

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Kim_2023_CVPR, author = {Kim, Woo Jae and Cho, Yoonki and Jung, Junsik and Yoon, Sung-Eui}, title = {Feature Separation and Recalibration for Adversarial Robustness}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8183-8192} }

Nerflets: Local Radiance Fields for Efficient Structure-Aware 3D Scene Representation From 2D Supervision

Xiaoshuai Zhang,

Abhijit Kundu,

Thomas Funkhouser,

Leonidas Guibas,

Hao Su,

Kyle Genova

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Zhang_2023_CVPR, author = {Zhang, Xiaoshuai and Kundu, Abhijit and Funkhouser, Thomas and Guibas, Leonidas and Su, Hao and Genova, Kyle}, title = {Nerflets: Local Radiance Fields for Efficient Structure-Aware 3D Scene Representation From 2D Supervision}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8274-8284} }

CLIP Is Also an Efficient Segmenter: A Text-Driven Approach for Weakly Supervised Semantic Segmentation

Yuqi Lin,

Minghao Chen,

Wenxiao Wang,

Boxi Wu,

Ke Li,

Binbin Lin,

Haifeng Liu,

Xiaofei He

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Lin_2023_CVPR, author = {Lin, Yuqi and Chen, Minghao and Wang, Wenxiao and Wu, Boxi and Li, Ke and Lin, Binbin and Liu, Haifeng and He, Xiaofei}, title = {CLIP Is Also an Efficient Segmenter: A Text-Driven Approach for Weakly Supervised Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15305-15314} }

Slimmable Dataset Condensation

Songhua Liu,

Jingwen Ye,

Runpeng Yu,

Xinchao Wang

[pdf] [supp]

[bibtex]

@InProceedings{Liu_2023_CVPR, author = {Liu, Songhua and Ye, Jingwen and Yu, Runpeng and Wang, Xinchao}, title = {Slimmable Dataset Condensation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3759-3768} }

Spatially Adaptive Self-Supervised Learning for Real-World Image Denoising

Junyi Li,

Zhilu Zhang,

Xiaoyu Liu,

Chaoyu Feng,

Xiaotao Wang,

Lei Lei,

Wangmeng Zuo

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Li_2023_CVPR, author = {Li, Junyi and Zhang, Zhilu and Liu, Xiaoyu and Feng, Chaoyu and Wang, Xiaotao and Lei, Lei and Zuo, Wangmeng}, title = {Spatially Adaptive Self-Supervised Learning for Real-World Image Denoising}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9914-9924} }

Data-Free Knowledge Distillation via Feature Exchange and Activation Region Constraint

Shikang Yu,

Jiachen Chen,

Hu Han,

Shuqiang Jiang

[pdf] [supp]

[bibtex]

@InProceedings{Yu_2023_CVPR, author = {Yu, Shikang and Chen, Jiachen and Han, Hu and Jiang, Shuqiang}, title = {Data-Free Knowledge Distillation via Feature Exchange and Activation Region Constraint}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {24266-24275} }

CLIP-Sculptor: Zero-Shot Generation of High-Fidelity and Diverse Shapes From Natural Language

Aditya Sanghi,

Rao Fu,

Vivian Liu,

Karl D.D. Willis,

Hooman Shayani,

Amir H. Khasahmadi,

Srinath Sridhar,

Daniel Ritchie

[pdf] [supp]

[bibtex]

@InProceedings{Sanghi_2023_CVPR, author = {Sanghi, Aditya and Fu, Rao and Liu, Vivian and Willis, Karl D.D. and Shayani, Hooman and Khasahmadi, Amir H. and Sridhar, Srinath and Ritchie, Daniel}, title = {CLIP-Sculptor: Zero-Shot Generation of High-Fidelity and Diverse Shapes From Natural Language}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {18339-18348} }

Mask-Free Video Instance Segmentation

Lei Ke,

Martin Danelljan,

Henghui Ding,

Yu-Wing Tai,

Chi-Keung Tang,

Fisher Yu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Ke_2023_CVPR, author = {Ke, Lei and Danelljan, Martin and Ding, Henghui and Tai, Yu-Wing and Tang, Chi-Keung and Yu, Fisher}, title = {Mask-Free Video Instance Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {22857-22866} }

Continual Detection Transformer for Incremental Object Detection

Yaoyao Liu,

Bernt Schiele,

Andrea Vedaldi,

Christian Rupprecht

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Liu_2023_CVPR, author = {Liu, Yaoyao and Schiele, Bernt and Vedaldi, Andrea and Rupprecht, Christian}, title = {Continual Detection Transformer for Incremental Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {23799-23808} }

Two-Stream Networks for Weakly-Supervised Temporal Action Localization With Semantic-Aware Mechanisms

Yu Wang,

Yadong Li,

Hongbin Wang

[pdf]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Yu and Li, Yadong and Wang, Hongbin}, title = {Two-Stream Networks for Weakly-Supervised Temporal Action Localization With Semantic-Aware Mechanisms}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {18878-18887} }

HyperMatch: Noise-Tolerant Semi-Supervised Learning via Relaxed Contrastive Constraint

Beitong Zhou,

Jing Lu,

Kerui Liu,

Yunlu Xu,

Zhanzhan Cheng,

Yi Niu

[pdf] [supp]

[bibtex]

@InProceedings{Zhou_2023_CVPR, author = {Zhou, Beitong and Lu, Jing and Liu, Kerui and Xu, Yunlu and Cheng, Zhanzhan and Niu, Yi}, title = {HyperMatch: Noise-Tolerant Semi-Supervised Learning via Relaxed Contrastive Constraint}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {24017-24026} }

From Images to Textual Prompts: Zero-Shot Visual Question Answering With Frozen Large Language Models

Jiaxian Guo,

Junnan Li,

Dongxu Li,

Anthony Meng Huat Tiong,

Boyang Li,

Dacheng Tao,

Steven Hoi

[pdf] [supp]

[bibtex]

@InProceedings{Guo_2023_CVPR, author = {Guo, Jiaxian and Li, Junnan and Li, Dongxu and Tiong, Anthony Meng Huat and Li, Boyang and Tao, Dacheng and Hoi, Steven}, title = {From Images to Textual Prompts: Zero-Shot Visual Question Answering With Frozen Large Language Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10867-10877} }

LEGO-Net: Learning Regular Rearrangements of Objects in Rooms

Qiuhong Anna Wei,

Sijie Ding,

Jeong Joon Park,

Rahul Sajnani,

Adrien Poulenard,

Srinath Sridhar,

Leonidas Guibas

[pdf] [supp]

[bibtex]

@InProceedings{Wei_2023_CVPR, author = {Wei, Qiuhong Anna and Ding, Sijie and Park, Jeong Joon and Sajnani, Rahul and Poulenard, Adrien and Sridhar, Srinath and Guibas, Leonidas}, title = {LEGO-Net: Learning Regular Rearrangements of Objects in Rooms}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {19037-19047} }

FastInst: A Simple Query-Based Model for Real-Time Instance Segmentation

Junjie He,

Pengyu Li,

Yifeng Geng,

Xuansong Xie

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{He_2023_CVPR, author = {He, Junjie and Li, Pengyu and Geng, Yifeng and Xie, Xuansong}, title = {FastInst: A Simple Query-Based Model for Real-Time Instance Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {23663-23672} }

Observation-Centric SORT: Rethinking SORT for Robust Multi-Object Tracking

Jinkun Cao,

Jiangmiao Pang,

Xinshuo Weng,

Rawal Khirodkar,

Kris Kitani

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Cao_2023_CVPR, author = {Cao, Jinkun and Pang, Jiangmiao and Weng, Xinshuo and Khirodkar, Rawal and Kitani, Kris}, title = {Observation-Centric SORT: Rethinking SORT for Robust Multi-Object Tracking}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9686-9696} }

Multi-View Azimuth Stereo via Tangent Space Consistency

Xu Cao,

Hiroaki Santo,

Fumio Okura,

Yasuyuki Matsushita

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Cao_2023_CVPR, author = {Cao, Xu and Santo, Hiroaki and Okura, Fumio and Matsushita, Yasuyuki}, title = {Multi-View Azimuth Stereo via Tangent Space Consistency}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {825-834} }

VectorFusion: Text-to-SVG by Abstracting Pixel-Based Diffusion Models

Ajay Jain,

Amber Xie,

Pieter Abbeel

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Jain_2023_CVPR, author = {Jain, Ajay and Xie, Amber and Abbeel, Pieter}, title = {VectorFusion: Text-to-SVG by Abstracting Pixel-Based Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1911-1920} }

The Dialog Must Go On: Improving Visual Dialog via Generative Self-Training

Gi-Cheon Kang,

Sungdong Kim,

Jin-Hwa Kim,

Donghyun Kwak,

Byoung-Tak Zhang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Kang_2023_CVPR, author = {Kang, Gi-Cheon and Kim, Sungdong and Kim, Jin-Hwa and Kwak, Donghyun and Zhang, Byoung-Tak}, title = {The Dialog Must Go On: Improving Visual Dialog via Generative Self-Training}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6746-6756} }

Binarizing Sparse Convolutional Networks for Efficient Point Cloud Analysis

Xiuwei Xu,

Ziwei Wang,

Jie Zhou,

Jiwen Lu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Xu_2023_CVPR, author = {Xu, Xiuwei and Wang, Ziwei and Zhou, Jie and Lu, Jiwen}, title = {Binarizing Sparse Convolutional Networks for Efficient Point Cloud Analysis}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5313-5322} }

Transformer-Based Learned Optimization

Erik Gärtner,

Luke Metz,

Mykhaylo Andriluka,

C. Daniel Freeman,

Cristian Sminchisescu

[pdf] [supp]

[bibtex]

@InProceedings{Gartner_2023_CVPR, author = {G\"artner, Erik and Metz, Luke and Andriluka, Mykhaylo and Freeman, C. Daniel and Sminchisescu, Cristian}, title = {Transformer-Based Learned Optimization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11970-11979} }

Diffusion Art or Digital Forgery? Investigating Data Replication in Diffusion Models

Gowthami Somepalli,

Vasu Singla,

Micah Goldblum,

Jonas Geiping,

Tom Goldstein

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Somepalli_2023_CVPR, author = {Somepalli, Gowthami and Singla, Vasu and Goldblum, Micah and Geiping, Jonas and Goldstein, Tom}, title = {Diffusion Art or Digital Forgery? Investigating Data Replication in Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6048-6058} }

Neuralizer: General Neuroimage Analysis Without Re-Training

Steffen Czolbe,

Adrian V. Dalca

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Czolbe_2023_CVPR, author = {Czolbe, Steffen and Dalca, Adrian V.}, title = {Neuralizer: General Neuroimage Analysis Without Re-Training}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6217-6230} }

Quantum-Inspired Spectral-Spatial Pyramid Network for Hyperspectral Image Classification

Jie Zhang,

Yongshan Zhang,

Yicong Zhou

[pdf]

[bibtex]

@InProceedings{Zhang_2023_CVPR, author = {Zhang, Jie and Zhang, Yongshan and Zhou, Yicong}, title = {Quantum-Inspired Spectral-Spatial Pyramid Network for Hyperspectral Image Classification}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9925-9934} }

Towards Benchmarking and Assessing Visual Naturalness of Physical World Adversarial Attacks

Simin Li,

Shuning Zhang,

Gujun Chen,

Dong Wang,

Pu Feng,

Jiakai Wang,

Aishan Liu,

Xin Yi,

Xianglong Liu

[pdf] [supp]

[bibtex]

@InProceedings{Li_2023_CVPR, author = {Li, Simin and Zhang, Shuning and Chen, Gujun and Wang, Dong and Feng, Pu and Wang, Jiakai and Liu, Aishan and Yi, Xin and Liu, Xianglong}, title = {Towards Benchmarking and Assessing Visual Naturalness of Physical World Adversarial Attacks}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12324-12333} }

Visual Prompt Multi-Modal Tracking

Jiawen Zhu,

Simiao Lai,

Xin Chen,

Dong Wang,

Huchuan Lu

[pdf] [arXiv]

[bibtex]

@InProceedings{Zhu_2023_CVPR, author = {Zhu, Jiawen and Lai, Simiao and Chen, Xin and Wang, Dong and Lu, Huchuan}, title = {Visual Prompt Multi-Modal Tracking}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9516-9526} }

Self-Supervised Representation Learning for CAD

Benjamin T. Jones,

Michael Hu,

Milin Kodnongbua,

Vladimir G. Kim,

Adriana Schulz

[pdf] [supp]

[bibtex]

@InProceedings{Jones_2023_CVPR, author = {Jones, Benjamin T. and Hu, Michael and Kodnongbua, Milin and Kim, Vladimir G. and Schulz, Adriana}, title = {Self-Supervised Representation Learning for CAD}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {21327-21336} }

DETRs With Hybrid Matching

Ding Jia,

Yuhui Yuan,

Haodi He,

Xiaopei Wu,

Haojun Yu,

Weihong Lin,

Lei Sun,

Chao Zhang,

Han Hu

[pdf] [arXiv]

[bibtex]

@InProceedings{Jia_2023_CVPR, author = {Jia, Ding and Yuan, Yuhui and He, Haodi and Wu, Xiaopei and Yu, Haojun and Lin, Weihong and Sun, Lei and Zhang, Chao and Hu, Han}, title = {DETRs With Hybrid Matching}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {19702-19712} }

Dealing With Cross-Task Class Discrimination in Online Continual Learning

Yiduo Guo,

Bing Liu,

Dongyan Zhao

[pdf] [supp]

[bibtex]

@InProceedings{Guo_2023_CVPR, author = {Guo, Yiduo and Liu, Bing and Zhao, Dongyan}, title = {Dealing With Cross-Task Class Discrimination in Online Continual Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11878-11887} }

Angelic Patches for Improving Third-Party Object Detector Performance

Wenwen Si,

Shuo Li,

Sangdon Park,

Insup Lee,

Osbert Bastani

[pdf] [supp]

[bibtex]

@InProceedings{Si_2023_CVPR, author = {Si, Wenwen and Li, Shuo and Park, Sangdon and Lee, Insup and Bastani, Osbert}, title = {Angelic Patches for Improving Third-Party Object Detector Performance}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {24638-24647} }

UniDexGrasp: Universal Robotic Dexterous Grasping via Learning Diverse Proposal Generation and Goal-Conditioned Policy

Yinzhen Xu,

Weikang Wan,

Jialiang Zhang,

Haoran Liu,

Zikang Shan,

Hao Shen,

Ruicheng Wang,

Haoran Geng,

Yijia Weng,

Jiayi Chen,

Tengyu Liu,

Li Yi,

He Wang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Xu_2023_CVPR, author = {Xu, Yinzhen and Wan, Weikang and Zhang, Jialiang and Liu, Haoran and Shan, Zikang and Shen, Hao and Wang, Ruicheng and Geng, Haoran and Weng, Yijia and Chen, Jiayi and Liu, Tengyu and Yi, Li and Wang, He}, title = {UniDexGrasp: Universal Robotic Dexterous Grasping via Learning Diverse Proposal Generation and Goal-Conditioned Policy}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4737-4746} }

A Rotation-Translation-Decoupled Solution for Robust and Efficient Visual-Inertial Initialization

Yijia He,

Bo Xu,

Zhanpeng Ouyang,

Hongdong Li

[pdf] [supp]

[bibtex]

@InProceedings{He_2023_CVPR, author = {He, Yijia and Xu, Bo and Ouyang, Zhanpeng and Li, Hongdong}, title = {A Rotation-Translation-Decoupled Solution for Robust and Efficient Visual-Inertial Initialization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {739-748} }

GIVL: Improving Geographical Inclusivity of Vision-Language Models With Pre-Training Methods

Da Yin,

Feng Gao,

Govind Thattai,

Michael Johnston,

Kai-Wei Chang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Yin_2023_CVPR, author = {Yin, Da and Gao, Feng and Thattai, Govind and Johnston, Michael and Chang, Kai-Wei}, title = {GIVL: Improving Geographical Inclusivity of Vision-Language Models With Pre-Training Methods}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10951-10961} }

Bi3D: Bi-Domain Active Learning for Cross-Domain 3D Object Detection

Jiakang Yuan,

Bo Zhang,

Xiangchao Yan,

Tao Chen,

Botian Shi,

Yikang Li,

Yu Qiao

[pdf] [arXiv]

[bibtex]

@InProceedings{Yuan_2023_CVPR, author = {Yuan, Jiakang and Zhang, Bo and Yan, Xiangchao and Chen, Tao and Shi, Botian and Li, Yikang and Qiao, Yu}, title = {Bi3D: Bi-Domain Active Learning for Cross-Domain 3D Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15599-15608} }

Towards Fast Adaptation of Pretrained Contrastive Models for Multi-Channel Video-Language Retrieval

Xudong Lin,

Simran Tiwari,

Shiyuan Huang,

Manling Li,

Mike Zheng Shou,

Heng Ji,

Shih-Fu Chang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Lin_2023_CVPR, author = {Lin, Xudong and Tiwari, Simran and Huang, Shiyuan and Li, Manling and Shou, Mike Zheng and Ji, Heng and Chang, Shih-Fu}, title = {Towards Fast Adaptation of Pretrained Contrastive Models for Multi-Channel Video-Language Retrieval}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14846-14855} }

Mask-Free OVIS: Open-Vocabulary Instance Segmentation Without Manual Mask Annotations

Vibashan VS,

Ning Yu,

Chen Xing,

Can Qin,

Mingfei Gao,

Juan Carlos Niebles,

Vishal M. Patel,

Ran Xu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{VS_2023_CVPR, author = {VS, Vibashan and Yu, Ning and Xing, Chen and Qin, Can and Gao, Mingfei and Niebles, Juan Carlos and Patel, Vishal M. and Xu, Ran}, title = {Mask-Free OVIS: Open-Vocabulary Instance Segmentation Without Manual Mask Annotations}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {23539-23549} }

Complete-to-Partial 4D Distillation for Self-Supervised Point Cloud Sequence Representation Learning

Zhuoyang Zhang,

Yuhao Dong,

Yunze Liu,

Li Yi

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Zhang_2023_CVPR, author = {Zhang, Zhuoyang and Dong, Yuhao and Liu, Yunze and Yi, Li}, title = {Complete-to-Partial 4D Distillation for Self-Supervised Point Cloud Sequence Representation Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {17661-17670} }

BundleSDF: Neural 6-DoF Tracking and 3D Reconstruction of Unknown Objects

Bowen Wen,

Jonathan Tremblay,

Valts Blukis,

Stephen Tyree,

Thomas Müller,

Alex Evans,

Dieter Fox,

Jan Kautz,

Stan Birchfield

[pdf] [supp]

[bibtex]

@InProceedings{Wen_2023_CVPR, author = {Wen, Bowen and Tremblay, Jonathan and Blukis, Valts and Tyree, Stephen and M\"uller, Thomas and Evans, Alex and Fox, Dieter and Kautz, Jan and Birchfield, Stan}, title = {BundleSDF: Neural 6-DoF Tracking and 3D Reconstruction of Unknown Objects}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {606-617} }

Multi-Modal Gait Recognition via Effective Spatial-Temporal Feature Fusion

Yufeng Cui,

Yimei Kang

[pdf]

[bibtex]

@InProceedings{Cui_2023_CVPR, author = {Cui, Yufeng and Kang, Yimei}, title = {Multi-Modal Gait Recognition via Effective Spatial-Temporal Feature Fusion}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {17949-17957} }

Crowd3D: Towards Hundreds of People Reconstruction From a Single Image

Hao Wen,

Jing Huang,

Huili Cui,

Haozhe Lin,

Yu-Kun Lai,

Lu Fang,

Kun Li

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Wen_2023_CVPR, author = {Wen, Hao and Huang, Jing and Cui, Huili and Lin, Haozhe and Lai, Yu-Kun and Fang, Lu and Li, Kun}, title = {Crowd3D: Towards Hundreds of People Reconstruction From a Single Image}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8937-8946} }

Highly Confident Local Structure Based Consensus Graph Learning for Incomplete Multi-View Clustering

Jie Wen,

Chengliang Liu,

Gehui Xu,

Zhihao Wu,

Chao Huang,

Lunke Fei,

Yong Xu

[pdf] [supp]

[bibtex]

@InProceedings{Wen_2023_CVPR, author = {Wen, Jie and Liu, Chengliang and Xu, Gehui and Wu, Zhihao and Huang, Chao and Fei, Lunke and Xu, Yong}, title = {Highly Confident Local Structure Based Consensus Graph Learning for Incomplete Multi-View Clustering}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15712-15721} }

Humans As Light Bulbs: 3D Human Reconstruction From Thermal Reflection

Ruoshi Liu,

Carl Vondrick

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Liu_2023_CVPR, author = {Liu, Ruoshi and Vondrick, Carl}, title = {Humans As Light Bulbs: 3D Human Reconstruction From Thermal Reflection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12531-12542} }

Hierarchical Discriminative Learning Improves Visual Representations of Biomedical Microscopy

Cheng Jiang,

Xinhai Hou,

Akhil Kondepudi,

Asadur Chowdury,

Christian W. Freudiger,

Daniel A. Orringer,

Honglak Lee,

Todd C. Hollon

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Jiang_2023_CVPR, author = {Jiang, Cheng and Hou, Xinhai and Kondepudi, Akhil and Chowdury, Asadur and Freudiger, Christian W. and Orringer, Daniel A. and Lee, Honglak and Hollon, Todd C.}, title = {Hierarchical Discriminative Learning Improves Visual Representations of Biomedical Microscopy}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {19798-19808} }

ProD: Prompting-To-Disentangle Domain Knowledge for Cross-Domain Few-Shot Image Classification

Tianyi Ma,

Yifan Sun,

Zongxin Yang,

Yi Yang

[pdf] [supp]

[bibtex]

@InProceedings{Ma_2023_CVPR, author = {Ma, Tianyi and Sun, Yifan and Yang, Zongxin and Yang, Yi}, title = {ProD: Prompting-To-Disentangle Domain Knowledge for Cross-Domain Few-Shot Image Classification}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {19754-19763} }

CafeBoost: Causal Feature Boost To Eliminate Task-Induced Bias for Class Incremental Learning

Benliu Qiu,

Hongliang Li,

Haitao Wen,

Heqian Qiu,

Lanxiao Wang,

Fanman Meng,

Qingbo Wu,

Lili Pan

[pdf] [supp]

[bibtex]

@InProceedings{Qiu_2023_CVPR, author = {Qiu, Benliu and Li, Hongliang and Wen, Haitao and Qiu, Heqian and Wang, Lanxiao and Meng, Fanman and Wu, Qingbo and Pan, Lili}, title = {CafeBoost: Causal Feature Boost To Eliminate Task-Induced Bias for Class Incremental Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16016-16025} }

A-La-Carte Prompt Tuning (APT): Combining Distinct Data via Composable Prompting

Benjamin Bowman,

Alessandro Achille,

Luca Zancato,

Matthew Trager,

Pramuditha Perera,

Giovanni Paolini,

Stefano Soatto

[pdf] [supp]

[bibtex]

@InProceedings{Bowman_2023_CVPR, author = {Bowman, Benjamin and Achille, Alessandro and Zancato, Luca and Trager, Matthew and Perera, Pramuditha and Paolini, Giovanni and Soatto, Stefano}, title = {A-La-Carte Prompt Tuning (APT): Combining Distinct Data via Composable Prompting}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14984-14993} }

ImageNet-E: Benchmarking Neural Network Robustness via Attribute Editing

Xiaodan Li,

Yuefeng Chen,

Yao Zhu,

Shuhui Wang,

Rong Zhang,

Hui Xue

[pdf] [supp]

[bibtex]

@InProceedings{Li_2023_CVPR, author = {Li, Xiaodan and Chen, Yuefeng and Zhu, Yao and Wang, Shuhui and Zhang, Rong and Xue, Hui}, title = {ImageNet-E: Benchmarking Neural Network Robustness via Attribute Editing}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {20371-20381} }

Learning With Fantasy: Semantic-Aware Virtual Contrastive Constraint for Few-Shot Class-Incremental Learning

Zeyin Song,

Yifan Zhao,

Yujun Shi,

Peixi Peng,

Li Yuan,

Yonghong Tian

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Song_2023_CVPR, author = {Song, Zeyin and Zhao, Yifan and Shi, Yujun and Peng, Peixi and Yuan, Li and Tian, Yonghong}, title = {Learning With Fantasy: Semantic-Aware Virtual Contrastive Constraint for Few-Shot Class-Incremental Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {24183-24192} }

ViLEM: Visual-Language Error Modeling for Image-Text Retrieval

Yuxin Chen,

Zongyang Ma,

Ziqi Zhang,

Zhongang Qi,

Chunfeng Yuan,

Ying Shan,

Bing Li,

Weiming Hu,

Xiaohu Qie,

Jianping Wu

[pdf] [supp]

[bibtex]

@InProceedings{Chen_2023_CVPR, author = {Chen, Yuxin and Ma, Zongyang and Zhang, Ziqi and Qi, Zhongang and Yuan, Chunfeng and Shan, Ying and Li, Bing and Hu, Weiming and Qie, Xiaohu and Wu, Jianping}, title = {ViLEM: Visual-Language Error Modeling for Image-Text Retrieval}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11018-11027} }

Egocentric Auditory Attention Localization in Conversations

Fiona Ryan,

Hao Jiang,

Abhinav Shukla,

James M. Rehg,

Vamsi Krishna Ithapu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Ryan_2023_CVPR, author = {Ryan, Fiona and Jiang, Hao and Shukla, Abhinav and Rehg, James M. and Ithapu, Vamsi Krishna}, title = {Egocentric Auditory Attention Localization in Conversations}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14663-14674} }

Texture-Guided Saliency Distilling for Unsupervised Salient Object Detection

Huajun Zhou,

Bo Qiao,

Lingxiao Yang,

Jianhuang Lai,

Xiaohua Xie

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Zhou_2023_CVPR, author = {Zhou, Huajun and Qiao, Bo and Yang, Lingxiao and Lai, Jianhuang and Xie, Xiaohua}, title = {Texture-Guided Saliency Distilling for Unsupervised Salient Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7257-7267} }

AltFreezing for More General Video Face Forgery Detection

Zhendong Wang,

Jianmin Bao,

Wengang Zhou,

Weilun Wang,

Houqiang Li

[pdf] [supp]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Zhendong and Bao, Jianmin and Zhou, Wengang and Wang, Weilun and Li, Houqiang}, title = {AltFreezing for More General Video Face Forgery Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4129-4138} }

Cascaded Local Implicit Transformer for Arbitrary-Scale Super-Resolution

Hao-Wei Chen,

Yu-Syuan Xu,

Min-Fong Hong,

Yi-Min Tsai,

Hsien-Kai Kuo,

Chun-Yi Lee

[pdf] [arXiv]

[bibtex]

@InProceedings{Chen_2023_CVPR, author = {Chen, Hao-Wei and Xu, Yu-Syuan and Hong, Min-Fong and Tsai, Yi-Min and Kuo, Hsien-Kai and Lee, Chun-Yi}, title = {Cascaded Local Implicit Transformer for Arbitrary-Scale Super-Resolution}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {18257-18267} }

Learning Partial Correlation Based Deep Visual Representation for Image Classification

Saimunur Rahman,

Piotr Koniusz,

Lei Wang,

Luping Zhou,

Peyman Moghadam,

Changming Sun

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Rahman_2023_CVPR, author = {Rahman, Saimunur and Koniusz, Piotr and Wang, Lei and Zhou, Luping and Moghadam, Peyman and Sun, Changming}, title = {Learning Partial Correlation Based Deep Visual Representation for Image Classification}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6231-6240} }

Open-World Multi-Task Control Through Goal-Aware Representation Learning and Adaptive Horizon Prediction

Shaofei Cai,

Zihao Wang,

Xiaojian Ma,

Anji Liu,

Yitao Liang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Cai_2023_CVPR, author = {Cai, Shaofei and Wang, Zihao and Ma, Xiaojian and Liu, Anji and Liang, Yitao}, title = {Open-World Multi-Task Control Through Goal-Aware Representation Learning and Adaptive Horizon Prediction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13734-13744} }

MoDi: Unconditional Motion Synthesis From Diverse Data

Sigal Raab,

Inbal Leibovitch,

Peizhuo Li,

Kfir Aberman,

Olga Sorkine-Hornung,

Daniel Cohen-Or

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Raab_2023_CVPR, author = {Raab, Sigal and Leibovitch, Inbal and Li, Peizhuo and Aberman, Kfir and Sorkine-Hornung, Olga and Cohen-Or, Daniel}, title = {MoDi: Unconditional Motion Synthesis From Diverse Data}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13873-13883} }

Visual Localization Using Imperfect 3D Models From the Internet

Vojtech Panek,

Zuzana Kukelova,

Torsten Sattler

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Panek_2023_CVPR, author = {Panek, Vojtech and Kukelova, Zuzana and Sattler, Torsten}, title = {Visual Localization Using Imperfect 3D Models From the Internet}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13175-13186} }

Network-Free, Unsupervised Semantic Segmentation With Synthetic Images

Qianli Feng,

Raghudeep Gadde,

Wentong Liao,

Eduard Ramon,

Aleix Martinez

[pdf] [supp]

[bibtex]

@InProceedings{Feng_2023_CVPR, author = {Feng, Qianli and Gadde, Raghudeep and Liao, Wentong and Ramon, Eduard and Martinez, Aleix}, title = {Network-Free, Unsupervised Semantic Segmentation With Synthetic Images}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {23602-23610} }

Hierarchical Dense Correlation Distillation for Few-Shot Segmentation

Bohao Peng,

Zhuotao Tian,

Xiaoyang Wu,

Chengyao Wang,

Shu Liu,

Jingyong Su,

Jiaya Jia

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Peng_2023_CVPR, author = {Peng, Bohao and Tian, Zhuotao and Wu, Xiaoyang and Wang, Chengyao and Liu, Shu and Su, Jingyong and Jia, Jiaya}, title = {Hierarchical Dense Correlation Distillation for Few-Shot Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {23641-23651} }

PVO: Panoptic Visual Odometry

Weicai Ye,

Xinyue Lan,

Shuo Chen,

Yuhang Ming,

Xingyuan Yu,

Hujun Bao,

Zhaopeng Cui,

Guofeng Zhang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Ye_2023_CVPR, author = {Ye, Weicai and Lan, Xinyue and Chen, Shuo and Ming, Yuhang and Yu, Xingyuan and Bao, Hujun and Cui, Zhaopeng and Zhang, Guofeng}, title = {PVO: Panoptic Visual Odometry}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9579-9589} }

Generative Diffusion Prior for Unified Image Restoration and Enhancement

Ben Fei,

Zhaoyang Lyu,

Liang Pan,

Junzhe Zhang,

Weidong Yang,

Tianyue Luo,

Bo Zhang,

Bo Dai

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Fei_2023_CVPR, author = {Fei, Ben and Lyu, Zhaoyang and Pan, Liang and Zhang, Junzhe and Yang, Weidong and Luo, Tianyue and Zhang, Bo and Dai, Bo}, title = {Generative Diffusion Prior for Unified Image Restoration and Enhancement}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9935-9946} }

Real-Time Controllable Denoising for Image and Video

Zhaoyang Zhang,

Yitong Jiang,

Wenqi Shao,

Xiaogang Wang,

Ping Luo,

Kaimo Lin,

Jinwei Gu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Zhang_2023_CVPR, author = {Zhang, Zhaoyang and Jiang, Yitong and Shao, Wenqi and Wang, Xiaogang and Luo, Ping and Lin, Kaimo and Gu, Jinwei}, title = {Real-Time Controllable Denoising for Image and Video}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14028-14038} }

ISBNet: A 3D Point Cloud Instance Segmentation Network With Instance-Aware Sampling and Box-Aware Dynamic Convolution

Tuan Duc Ngo,

Binh-Son Hua,

Khoi Nguyen

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Ngo_2023_CVPR, author = {Ngo, Tuan Duc and Hua, Binh-Son and Nguyen, Khoi}, title = {ISBNet: A 3D Point Cloud Instance Segmentation Network With Instance-Aware Sampling and Box-Aware Dynamic Convolution}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13550-13559} }

Hi4D: 4D Instance Segmentation of Close Human Interaction

Yifei Yin,

Chen Guo,

Manuel Kaufmann,

Juan Jose Zarate,

Jie Song,

Otmar Hilliges

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Yin_2023_CVPR, author = {Yin, Yifei and Guo, Chen and Kaufmann, Manuel and Zarate, Juan Jose and Song, Jie and Hilliges, Otmar}, title = {Hi4D: 4D Instance Segmentation of Close Human Interaction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {17016-17027} }

Hi-LASSIE: High-Fidelity Articulated Shape and Skeleton Discovery From Sparse Image Ensemble

Chun-Han Yao,

Wei-Chih Hung,

Yuanzhen Li,

Michael Rubinstein,

Ming-Hsuan Yang,

Varun Jampani

[pdf] [supp]

[bibtex]

@InProceedings{Yao_2023_CVPR, author = {Yao, Chun-Han and Hung, Wei-Chih and Li, Yuanzhen and Rubinstein, Michael and Yang, Ming-Hsuan and Jampani, Varun}, title = {Hi-LASSIE: High-Fidelity Articulated Shape and Skeleton Discovery From Sparse Image Ensemble}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4853-4862} }

IterativePFN: True Iterative Point Cloud Filtering

Dasith de Silva Edirimuni,

Xuequan Lu,

Zhiwen Shao,

Gang Li,

Antonio Robles-Kelly,

Ying He

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{de_Silva_Edirimuni_2023_CVPR, author = {de Silva Edirimuni, Dasith and Lu, Xuequan and Shao, Zhiwen and Li, Gang and Robles-Kelly, Antonio and He, Ying}, title = {IterativePFN: True Iterative Point Cloud Filtering}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13530-13539} }

Computationally Budgeted Continual Learning: What Does Matter?

Ameya Prabhu,

Hasan Abed Al Kader Hammoud,

Puneet K. Dokania,

Philip H.S. Torr,

Ser-Nam Lim,

Bernard Ghanem,

Adel Bibi

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Prabhu_2023_CVPR, author = {Prabhu, Ameya and Al Kader Hammoud, Hasan Abed and Dokania, Puneet K. and Torr, Philip H.S. and Lim, Ser-Nam and Ghanem, Bernard and Bibi, Adel}, title = {Computationally Budgeted Continual Learning: What Does Matter?}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3698-3707} }

Decentralized Learning With Multi-Headed Distillation

Andrey Zhmoginov,

Mark Sandler,

Nolan Miller,

Gus Kristiansen,

Max Vladymyrov

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Zhmoginov_2023_CVPR, author = {Zhmoginov, Andrey and Sandler, Mark and Miller, Nolan and Kristiansen, Gus and Vladymyrov, Max}, title = {Decentralized Learning With Multi-Headed Distillation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8053-8063} }

SQUID: Deep Feature In-Painting for Unsupervised Anomaly Detection

Tiange Xiang,

Yixiao Zhang,

Yongyi Lu,

Alan L. Yuille,

Chaoyi Zhang,

Weidong Cai,

Zongwei Zhou

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Xiang_2023_CVPR, author = {Xiang, Tiange and Zhang, Yixiao and Lu, Yongyi and Yuille, Alan L. and Zhang, Chaoyi and Cai, Weidong and Zhou, Zongwei}, title = {SQUID: Deep Feature In-Painting for Unsupervised Anomaly Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {23890-23901} }

CF-Font: Content Fusion for Few-Shot Font Generation

Chi Wang,

Min Zhou,

Tiezheng Ge,

Yuning Jiang,

Hujun Bao,

Weiwei Xu

[pdf] [supp]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Chi and Zhou, Min and Ge, Tiezheng and Jiang, Yuning and Bao, Hujun and Xu, Weiwei}, title = {CF-Font: Content Fusion for Few-Shot Font Generation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1858-1867} }

On the Convergence of IRLS and Its Variants in Outlier-Robust Estimation

Liangzu Peng,

Christian Kümmerle,

René Vidal

[pdf] [supp]

[bibtex]

@InProceedings{Peng_2023_CVPR, author = {Peng, Liangzu and K\"ummerle, Christian and Vidal, Ren\'e}, title = {On the Convergence of IRLS and Its Variants in Outlier-Robust Estimation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {17808-17818} }

CLIP-S4: Language-Guided Self-Supervised Semantic Segmentation

Wenbin He,

Suphanut Jamonnak,

Liang Gou,

Liu Ren

[pdf] [supp]

[bibtex]

@InProceedings{He_2023_CVPR, author = {He, Wenbin and Jamonnak, Suphanut and Gou, Liang and Ren, Liu}, title = {CLIP-S4: Language-Guided Self-Supervised Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11207-11216} }

Deep Incomplete Multi-View Clustering With Cross-View Partial Sample and Prototype Alignment

Jiaqi Jin,

Siwei Wang,

Zhibin Dong,

Xinwang Liu,

En Zhu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Jin_2023_CVPR, author = {Jin, Jiaqi and Wang, Siwei and Dong, Zhibin and Liu, Xinwang and Zhu, En}, title = {Deep Incomplete Multi-View Clustering With Cross-View Partial Sample and Prototype Alignment}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11600-11609} }

A New Comprehensive Benchmark for Semi-Supervised Video Anomaly Detection and Anticipation

Congqi Cao,

Yue Lu,

Peng Wang,

Yanning Zhang

[pdf] [supp]

[bibtex]

@InProceedings{Cao_2023_CVPR, author = {Cao, Congqi and Lu, Yue and Wang, Peng and Zhang, Yanning}, title = {A New Comprehensive Benchmark for Semi-Supervised Video Anomaly Detection and Anticipation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {20392-20401} }

Revisiting Multimodal Representation in Contrastive Learning: From Patch and Token Embeddings to Finite Discrete Tokens

Yuxiao Chen,

Jianbo Yuan,

Yu Tian,

Shijie Geng,

Xinyu Li,

Ding Zhou,

Dimitris N. Metaxas,

Hongxia Yang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Chen_2023_CVPR, author = {Chen, Yuxiao and Yuan, Jianbo and Tian, Yu and Geng, Shijie and Li, Xinyu and Zhou, Ding and Metaxas, Dimitris N. and Yang, Hongxia}, title = {Revisiting Multimodal Representation in Contrastive Learning: From Patch and Token Embeddings to Finite Discrete Tokens}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15095-15104} }

3Mformer: Multi-Order Multi-Mode Transformer for Skeletal Action Recognition

Lei Wang,

Piotr Koniusz

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Lei and Koniusz, Piotr}, title = {3Mformer: Multi-Order Multi-Mode Transformer for Skeletal Action Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5620-5631} }

HumanBench: Towards General Human-Centric Perception With Projector Assisted Pretraining

Shixiang Tang,

Cheng Chen,

Qingsong Xie,

Meilin Chen,

Yizhou Wang,

Yuanzheng Ci,

Lei Bai,

Feng Zhu,

Haiyang Yang,

Li Yi,

Rui Zhao,

Wanli Ouyang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Tang_2023_CVPR, author = {Tang, Shixiang and Chen, Cheng and Xie, Qingsong and Chen, Meilin and Wang, Yizhou and Ci, Yuanzheng and Bai, Lei and Zhu, Feng and Yang, Haiyang and Yi, Li and Zhao, Rui and Ouyang, Wanli}, title = {HumanBench: Towards General Human-Centric Perception With Projector Assisted Pretraining}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {21970-21982} }

Heterogeneous Continual Learning

Divyam Madaan,

Hongxu Yin,

Wonmin Byeon,

Jan Kautz,

Pavlo Molchanov

[pdf] [supp]

[bibtex]

@InProceedings{Madaan_2023_CVPR, author = {Madaan, Divyam and Yin, Hongxu and Byeon, Wonmin and Kautz, Jan and Molchanov, Pavlo}, title = {Heterogeneous Continual Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15985-15995} }

Object Pose Estimation With Statistical Guarantees: Conformal Keypoint Detection and Geometric Uncertainty Propagation

Heng Yang,

Marco Pavone

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Yang_2023_CVPR, author = {Yang, Heng and Pavone, Marco}, title = {Object Pose Estimation With Statistical Guarantees: Conformal Keypoint Detection and Geometric Uncertainty Propagation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8947-8958} }

Transformer Scale Gate for Semantic Segmentation

Hengcan Shi,

Munawar Hayat,

Jianfei Cai

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Shi_2023_CVPR, author = {Shi, Hengcan and Hayat, Munawar and Cai, Jianfei}, title = {Transformer Scale Gate for Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3051-3060} }

Deep Graph Reprogramming

Yongcheng Jing,

Chongbin Yuan,

Li Ju,

Yiding Yang,

Xinchao Wang,

Dacheng Tao

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Jing_2023_CVPR, author = {Jing, Yongcheng and Yuan, Chongbin and Ju, Li and Yang, Yiding and Wang, Xinchao and Tao, Dacheng}, title = {Deep Graph Reprogramming}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {24345-24354} }

Compacting Binary Neural Networks by Sparse Kernel Selection

Yikai Wang,

Wenbing Huang,

Yinpeng Dong,

Fuchun Sun,

Anbang Yao

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Yikai and Huang, Wenbing and Dong, Yinpeng and Sun, Fuchun and Yao, Anbang}, title = {Compacting Binary Neural Networks by Sparse Kernel Selection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {24374-24383} }

EMT-NAS:Transferring Architectural Knowledge Between Tasks From Different Datasets

Peng Liao,

Yaochu Jin,

Wenli Du

[pdf] [supp]

[bibtex]

@InProceedings{Liao_2023_CVPR, author = {Liao, Peng and Jin, Yaochu and Du, Wenli}, title = {EMT-NAS:Transferring Architectural Knowledge Between Tasks From Different Datasets}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3643-3653} }

3D-Aware Multi-Class Image-to-Image Translation With NeRFs

Senmao Li,

Joost van de Weijer,

Yaxing Wang,

Fahad Shahbaz Khan,

Meiqin Liu,

Jian Yang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Li_2023_CVPR, author = {Li, Senmao and van de Weijer, Joost and Wang, Yaxing and Khan, Fahad Shahbaz and Liu, Meiqin and Yang, Jian}, title = {3D-Aware Multi-Class Image-to-Image Translation With NeRFs}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12652-12662} }

Learning Joint Latent Space EBM Prior Model for Multi-Layer Generator

Jiali Cui,

Ying Nian Wu,

Tian Han

[pdf] [supp]

[bibtex]

@InProceedings{Cui_2023_CVPR, author = {Cui, Jiali and Wu, Ying Nian and Han, Tian}, title = {Learning Joint Latent Space EBM Prior Model for Multi-Layer Generator}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3603-3612} }

Unsupervised Visible-Infrared Person Re-Identification via Progressive Graph Matching and Alternate Learning

Zesen Wu,

Mang Ye

[pdf] [supp]

[bibtex]

@InProceedings{Wu_2023_CVPR, author = {Wu, Zesen and Ye, Mang}, title = {Unsupervised Visible-Infrared Person Re-Identification via Progressive Graph Matching and Alternate Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9548-9558} }

Hierarchical B-Frame Video Coding Using Two-Layer CANF Without Motion Coding

David Alexandre,

Hsueh-Ming Hang,

Wen-Hsiao Peng

[pdf] [supp]

[bibtex]

@InProceedings{Alexandre_2023_CVPR, author = {Alexandre, David and Hang, Hsueh-Ming and Peng, Wen-Hsiao}, title = {Hierarchical B-Frame Video Coding Using Two-Layer CANF Without Motion Coding}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10249-10258} }

Benchmarking Robustness of 3D Object Detection to Common Corruptions

Yinpeng Dong,

Caixin Kang,

Jinlai Zhang,

Zijian Zhu,

Yikai Wang,

Xiao Yang,

Hang Su,

Xingxing Wei,

Jun Zhu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Dong_2023_CVPR, author = {Dong, Yinpeng and Kang, Caixin and Zhang, Jinlai and Zhu, Zijian and Wang, Yikai and Yang, Xiao and Su, Hang and Wei, Xingxing and Zhu, Jun}, title = {Benchmarking Robustness of 3D Object Detection to Common Corruptions}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1022-1032} }

Unified Mask Embedding and Correspondence Learning for Self-Supervised Video Segmentation

Liulei Li,

Wenguan Wang,

Tianfei Zhou,

Jianwu Li,

Yi Yang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Li_2023_CVPR, author = {Li, Liulei and Wang, Wenguan and Zhou, Tianfei and Li, Jianwu and Yang, Yi}, title = {Unified Mask Embedding and Correspondence Learning for Self-Supervised Video Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {18706-18716} }

Seeing Beyond the Brain: Conditional Diffusion Model With Sparse Masked Modeling for Vision Decoding

Zijiao Chen,

Jiaxin Qing,

Tiange Xiang,

Wan Lin Yue,

Juan Helen Zhou

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Chen_2023_CVPR, author = {Chen, Zijiao and Qing, Jiaxin and Xiang, Tiange and Yue, Wan Lin and Zhou, Juan Helen}, title = {Seeing Beyond the Brain: Conditional Diffusion Model With Sparse Masked Modeling for Vision Decoding}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {22710-22720} }

PointAvatar: Deformable Point-Based Head Avatars From Videos

Yufeng Zheng,

Wang Yifan,

Gordon Wetzstein,

Michael J. Black,

Otmar Hilliges

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Zheng_2023_CVPR, author = {Zheng, Yufeng and Yifan, Wang and Wetzstein, Gordon and Black, Michael J. and Hilliges, Otmar}, title = {PointAvatar: Deformable Point-Based Head Avatars From Videos}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {21057-21067} }

Seeing Through the Glass: Neural 3D Reconstruction of Object Inside a Transparent Container

Jinguang Tong,

Sundaram Muthu,

Fahira Afzal Maken,

Chuong Nguyen,

Hongdong Li

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Tong_2023_CVPR, author = {Tong, Jinguang and Muthu, Sundaram and Maken, Fahira Afzal and Nguyen, Chuong and Li, Hongdong}, title = {Seeing Through the Glass: Neural 3D Reconstruction of Object Inside a Transparent Container}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12555-12564} }

OrienterNet: Visual Localization in 2D Public Maps With Neural Matching

Paul-Edouard Sarlin,

Daniel DeTone,

Tsun-Yi Yang,

Armen Avetisyan,

Julian Straub,

Tomasz Malisiewicz,

Samuel Rota Bulò,

Richard Newcombe,

Peter Kontschieder,

Vasileios Balntas

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Sarlin_2023_CVPR, author = {Sarlin, Paul-Edouard and DeTone, Daniel and Yang, Tsun-Yi and Avetisyan, Armen and Straub, Julian and Malisiewicz, Tomasz and Bul\`o, Samuel Rota and Newcombe, Richard and Kontschieder, Peter and Balntas, Vasileios}, title = {OrienterNet: Visual Localization in 2D Public Maps With Neural Matching}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {21632-21642} }

PMatch: Paired Masked Image Modeling for Dense Geometric Matching

Shengjie Zhu,

Xiaoming Liu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Zhu_2023_CVPR, author = {Zhu, Shengjie and Liu, Xiaoming}, title = {PMatch: Paired Masked Image Modeling for Dense Geometric Matching}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {21909-21918} }

Neural Voting Field for Camera-Space 3D Hand Pose Estimation

Lin Huang,

Chung-Ching Lin,

Kevin Lin,

Lin Liang,

Lijuan Wang,

Junsong Yuan,

Zicheng Liu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Huang_2023_CVPR, author = {Huang, Lin and Lin, Chung-Ching and Lin, Kevin and Liang, Lin and Wang, Lijuan and Yuan, Junsong and Liu, Zicheng}, title = {Neural Voting Field for Camera-Space 3D Hand Pose Estimation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8969-8978} }

STMT: A Spatial-Temporal Mesh Transformer for MoCap-Based Action Recognition

Xiaoyu Zhu,

Po-Yao Huang,

Junwei Liang,

Celso M. de Melo,

Alexander G. Hauptmann

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Zhu_2023_CVPR, author = {Zhu, Xiaoyu and Huang, Po-Yao and Liang, Junwei and de Melo, Celso M. and Hauptmann, Alexander G.}, title = {STMT: A Spatial-Temporal Mesh Transformer for MoCap-Based Action Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1526-1536} }

Visual Recognition-Driven Image Restoration for Multiple Degradation With Intrinsic Semantics Recovery

Zizheng Yang,

Jie Huang,

Jiahao Chang,

Man Zhou,

Hu Yu,

Jinghao Zhang,

Feng Zhao

[pdf] [supp]

[bibtex]

@InProceedings{Yang_2023_CVPR, author = {Yang, Zizheng and Huang, Jie and Chang, Jiahao and Zhou, Man and Yu, Hu and Zhang, Jinghao and Zhao, Feng}, title = {Visual Recognition-Driven Image Restoration for Multiple Degradation With Intrinsic Semantics Recovery}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14059-14070} }

High-Fidelity Generalized Emotional Talking Face Generation With Multi-Modal Emotion Space Learning

Chao Xu,

Junwei Zhu,

Jiangning Zhang,

Yue Han,

Wenqing Chu,

Ying Tai,

Chengjie Wang,

Zhifeng Xie,

Yong Liu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Xu_2023_CVPR, author = {Xu, Chao and Zhu, Junwei and Zhang, Jiangning and Han, Yue and Chu, Wenqing and Tai, Ying and Wang, Chengjie and Xie, Zhifeng and Liu, Yong}, title = {High-Fidelity Generalized Emotional Talking Face Generation With Multi-Modal Emotion Space Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6609-6619} }

Masked and Adaptive Transformer for Exemplar Based Image Translation

Chang Jiang,

Fei Gao,

Biao Ma,

Yuhao Lin,

Nannan Wang,

Gang Xu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Jiang_2023_CVPR, author = {Jiang, Chang and Gao, Fei and Ma, Biao and Lin, Yuhao and Wang, Nannan and Xu, Gang}, title = {Masked and Adaptive Transformer for Exemplar Based Image Translation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {22418-22427} }

Knowledge Combination To Learn Rotated Detection Without Rotated Annotation

Tianyu Zhu,

Bryce Ferenczi,

Pulak Purkait,

Tom Drummond,

Hamid Rezatofighi,

Anton van den Hengel

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Zhu_2023_CVPR, author = {Zhu, Tianyu and Ferenczi, Bryce and Purkait, Pulak and Drummond, Tom and Rezatofighi, Hamid and van den Hengel, Anton}, title = {Knowledge Combination To Learn Rotated Detection Without Rotated Annotation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15518-15527} }

Teaching Matters: Investigating the Role of Supervision in Vision Transformers

Matthew Walmer,

Saksham Suri,

Kamal Gupta,

Abhinav Shrivastava

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Walmer_2023_CVPR, author = {Walmer, Matthew and Suri, Saksham and Gupta, Kamal and Shrivastava, Abhinav}, title = {Teaching Matters: Investigating the Role of Supervision in Vision Transformers}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7486-7496} }

Imagic: Text-Based Real Image Editing With Diffusion Models

Bahjat Kawar,

Shiran Zada,

Oran Lang,

Omer Tov,

Huiwen Chang,

Tali Dekel,

Inbar Mosseri,

Michal Irani

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Kawar_2023_CVPR, author = {Kawar, Bahjat and Zada, Shiran and Lang, Oran and Tov, Omer and Chang, Huiwen and Dekel, Tali and Mosseri, Inbar and Irani, Michal}, title = {Imagic: Text-Based Real Image Editing With Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6007-6017} }

Pointersect: Neural Rendering With Cloud-Ray Intersection

Jen-Hao Rick Chang,

Wei-Yu Chen,

Anurag Ranjan,

Kwang Moo Yi,

Oncel Tuzel

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Chang_2023_CVPR, author = {Chang, Jen-Hao Rick and Chen, Wei-Yu and Ranjan, Anurag and Yi, Kwang Moo and Tuzel, Oncel}, title = {Pointersect: Neural Rendering With Cloud-Ray Intersection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8359-8369} }

Beyond Attentive Tokens: Incorporating Token Importance and Diversity for Efficient Vision Transformers

Sifan Long,

Zhen Zhao,

Jimin Pi,

Shengsheng Wang,

Jingdong Wang

[pdf] [arXiv]

[bibtex]

@InProceedings{Long_2023_CVPR, author = {Long, Sifan and Zhao, Zhen and Pi, Jimin and Wang, Shengsheng and Wang, Jingdong}, title = {Beyond Attentive Tokens: Incorporating Token Importance and Diversity for Efficient Vision Transformers}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10334-10343} }

You Are Catching My Attention: Are Vision Transformers Bad Learners Under Backdoor Attacks?

Zenghui Yuan,

Pan Zhou,

Kai Zou,

Yu Cheng

[pdf] [supp]

[bibtex]

@InProceedings{Yuan_2023_CVPR, author = {Yuan, Zenghui and Zhou, Pan and Zou, Kai and Cheng, Yu}, title = {You Are Catching My Attention: Are Vision Transformers Bad Learners Under Backdoor Attacks?}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {24605-24615} }

STDLens: Model Hijacking-Resilient Federated Learning for Object Detection

Ka-Ho Chow,

Ling Liu,

Wenqi Wei,

Fatih Ilhan,

Yanzhao Wu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Chow_2023_CVPR, author = {Chow, Ka-Ho and Liu, Ling and Wei, Wenqi and Ilhan, Fatih and Wu, Yanzhao}, title = {STDLens: Model Hijacking-Resilient Federated Learning for Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16343-16351} }

Contrastive Grouping With Transformer for Referring Image Segmentation

Jiajin Tang,

Ge Zheng,

Cheng Shi,

Sibei Yang

[pdf]

[bibtex]

@InProceedings{Tang_2023_CVPR, author = {Tang, Jiajin and Zheng, Ge and Shi, Cheng and Yang, Sibei}, title = {Contrastive Grouping With Transformer for Referring Image Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {23570-23580} }

MagicPony: Learning Articulated 3D Animals in the Wild

Shangzhe Wu,

Ruining Li,

Tomas Jakab,

Christian Rupprecht,

Andrea Vedaldi

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Wu_2023_CVPR, author = {Wu, Shangzhe and Li, Ruining and Jakab, Tomas and Rupprecht, Christian and Vedaldi, Andrea}, title = {MagicPony: Learning Articulated 3D Animals in the Wild}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8792-8802} }

PaCa-ViT: Learning Patch-to-Cluster Attention in Vision Transformers

Ryan Grainger,

Thomas Paniagua,

Xi Song,

Naresh Cuntoor,

Mun Wai Lee,

Tianfu Wu

[pdf] [supp]

[bibtex]

@InProceedings{Grainger_2023_CVPR, author = {Grainger, Ryan and Paniagua, Thomas and Song, Xi and Cuntoor, Naresh and Lee, Mun Wai and Wu, Tianfu}, title = {PaCa-ViT: Learning Patch-to-Cluster Attention in Vision Transformers}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {18568-18578} }

Pix2map: Cross-Modal Retrieval for Inferring Street Maps From Images

Xindi Wu,

KwunFung Lau,

Francesco Ferroni,

Aljoša Ošep,

Deva Ramanan

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Wu_2023_CVPR, author = {Wu, Xindi and Lau, KwunFung and Ferroni, Francesco and O\v{s}ep, Aljo\v{s}a and Ramanan, Deva}, title = {Pix2map: Cross-Modal Retrieval for Inferring Street Maps From Images}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {17514-17523} }

LightPainter: Interactive Portrait Relighting With Freehand Scribble

Yiqun Mei,

He Zhang,

Xuaner Zhang,

Jianming Zhang,

Zhixin Shu,

Yilin Wang,

Zijun Wei,

Shi Yan,

HyunJoon Jung,

Vishal M. Patel

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Mei_2023_CVPR, author = {Mei, Yiqun and Zhang, He and Zhang, Xuaner and Zhang, Jianming and Shu, Zhixin and Wang, Yilin and Wei, Zijun and Yan, Shi and Jung, HyunJoon and Patel, Vishal M.}, title = {LightPainter: Interactive Portrait Relighting With Freehand Scribble}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {195-205} }

Affordances From Human Videos as a Versatile Representation for Robotics

Shikhar Bahl,

Russell Mendonca,

Lili Chen,

Unnat Jain,

Deepak Pathak

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Bahl_2023_CVPR, author = {Bahl, Shikhar and Mendonca, Russell and Chen, Lili and Jain, Unnat and Pathak, Deepak}, title = {Affordances From Human Videos as a Versatile Representation for Robotics}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13778-13790} }

Unsupervised Inference of Signed Distance Functions From Single Sparse Point Clouds Without Learning Priors

Chao Chen,

Yu-Shen Liu,

Zhizhong Han

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Chen_2023_CVPR, author = {Chen, Chao and Liu, Yu-Shen and Han, Zhizhong}, title = {Unsupervised Inference of Signed Distance Functions From Single Sparse Point Clouds Without Learning Priors}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {17712-17723} }

AMT: All-Pairs Multi-Field Transforms for Efficient Frame Interpolation

Zhen Li,

Zuo-Liang Zhu,

Ling-Hao Han,

Qibin Hou,

Chun-Le Guo,

Ming-Ming Cheng

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Li_2023_CVPR, author = {Li, Zhen and Zhu, Zuo-Liang and Han, Ling-Hao and Hou, Qibin and Guo, Chun-Le and Cheng, Ming-Ming}, title = {AMT: All-Pairs Multi-Field Transforms for Efficient Frame Interpolation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9801-9810} }

Vision Transformers Are Parameter-Efficient Audio-Visual Learners

Yan-Bo Lin,

Yi-Lin Sung,

Jie Lei,

Mohit Bansal,

Gedas Bertasius

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Lin_2023_CVPR, author = {Lin, Yan-Bo and Sung, Yi-Lin and Lei, Jie and Bansal, Mohit and Bertasius, Gedas}, title = {Vision Transformers Are Parameter-Efficient Audio-Visual Learners}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2299-2309} }

Deep Discriminative Spatial and Temporal Network for Efficient Video Deblurring

Jinshan Pan,

Boming Xu,

Jiangxin Dong,

Jianjun Ge,

Jinhui Tang

[pdf] [supp]

[bibtex]

@InProceedings{Pan_2023_CVPR, author = {Pan, Jinshan and Xu, Boming and Dong, Jiangxin and Ge, Jianjun and Tang, Jinhui}, title = {Deep Discriminative Spatial and Temporal Network for Efficient Video Deblurring}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {22191-22200} }

Training Debiased Subnetworks With Contrastive Weight Pruning

Geon Yeong Park,

Sangmin Lee,

Sang Wan Lee,

Jong Chul Ye

[pdf] [supp]

[bibtex]

@InProceedings{Park_2023_CVPR, author = {Park, Geon Yeong and Lee, Sangmin and Lee, Sang Wan and Ye, Jong Chul}, title = {Training Debiased Subnetworks With Contrastive Weight Pruning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7929-7938} }

SparseViT: Revisiting Activation Sparsity for Efficient High-Resolution Vision Transformer

Xuanyao Chen,

Zhijian Liu,

Haotian Tang,

Li Yi,

Hang Zhao,

Song Han

[pdf] [arXiv]

[bibtex]

@InProceedings{Chen_2023_CVPR, author = {Chen, Xuanyao and Liu, Zhijian and Tang, Haotian and Yi, Li and Zhao, Hang and Han, Song}, title = {SparseViT: Revisiting Activation Sparsity for Efficient High-Resolution Vision Transformer}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2061-2070} }

Prototype-Based Embedding Network for Scene Graph Generation

Chaofan Zheng,

Xinyu Lyu,

Lianli Gao,

Bo Dai,

Jingkuan Song

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Zheng_2023_CVPR, author = {Zheng, Chaofan and Lyu, Xinyu and Gao, Lianli and Dai, Bo and Song, Jingkuan}, title = {Prototype-Based Embedding Network for Scene Graph Generation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {22783-22792} }

Toward RAW Object Detection: A New Benchmark and a New Model

Ruikang Xu,

Chang Chen,

Jingyang Peng,

Cheng Li,

Yibin Huang,

Fenglong Song,

Youliang Yan,

Zhiwei Xiong

[pdf] [supp]

[bibtex]

@InProceedings{Xu_2023_CVPR, author = {Xu, Ruikang and Chen, Chang and Peng, Jingyang and Li, Cheng and Huang, Yibin and Song, Fenglong and Yan, Youliang and Xiong, Zhiwei}, title = {Toward RAW Object Detection: A New Benchmark and a New Model}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13384-13393} }

Music-Driven Group Choreography

Nhat Le,

Thang Pham,

Tuong Do,

Erman Tjiputra,

Quang D. Tran,

Anh Nguyen

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Le_2023_CVPR, author = {Le, Nhat and Pham, Thang and Do, Tuong and Tjiputra, Erman and Tran, Quang D. and Nguyen, Anh}, title = {Music-Driven Group Choreography}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8673-8682} }

Cascade Evidential Learning for Open-World Weakly-Supervised Temporal Action Localization

Mengyuan Chen,

Junyu Gao,

Changsheng Xu

[pdf]

[bibtex]

@InProceedings{Chen_2023_CVPR, author = {Chen, Mengyuan and Gao, Junyu and Xu, Changsheng}, title = {Cascade Evidential Learning for Open-World Weakly-Supervised Temporal Action Localization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14741-14750} }

Efficient Movie Scene Detection Using State-Space Transformers

Md Mohaiminul Islam,

Mahmudul Hasan,

Kishan Shamsundar Athrey,

Tony Braskich,

Gedas Bertasius

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Islam_2023_CVPR, author = {Islam, Md Mohaiminul and Hasan, Mahmudul and Athrey, Kishan Shamsundar and Braskich, Tony and Bertasius, Gedas}, title = {Efficient Movie Scene Detection Using State-Space Transformers}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {18749-18758} }

Multispectral Video Semantic Segmentation: A Benchmark Dataset and Baseline

Wei Ji,

Jingjing Li,

Cheng Bian,

Zongwei Zhou,

Jiaying Zhao,

Alan L. Yuille,

Li Cheng

[pdf] [supp]

[bibtex]

@InProceedings{Ji_2023_CVPR, author = {Ji, Wei and Li, Jingjing and Bian, Cheng and Zhou, Zongwei and Zhao, Jiaying and Yuille, Alan L. and Cheng, Li}, title = {Multispectral Video Semantic Segmentation: A Benchmark Dataset and Baseline}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1094-1104} }

Reducing the Label Bias for Timestamp Supervised Temporal Action Segmentation

Kaiyuan Liu,

Yunheng Li,

Shenglan Liu,

Chenwei Tan,

Zihang Shao

[pdf] [supp]

[bibtex]

@InProceedings{Liu_2023_CVPR, author = {Liu, Kaiyuan and Li, Yunheng and Liu, Shenglan and Tan, Chenwei and Shao, Zihang}, title = {Reducing the Label Bias for Timestamp Supervised Temporal Action Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6503-6513} }

Efficient Semantic Segmentation by Altering Resolutions for Compressed Videos

Yubin Hu,

Yuze He,

Yanghao Li,

Jisheng Li,

Yuxing Han,

Jiangtao Wen,

Yong-Jin Liu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Hu_2023_CVPR, author = {Hu, Yubin and He, Yuze and Li, Yanghao and Li, Jisheng and Han, Yuxing and Wen, Jiangtao and Liu, Yong-Jin}, title = {Efficient Semantic Segmentation by Altering Resolutions for Compressed Videos}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {22627-22637} }

STAR Loss: Reducing Semantic Ambiguity in Facial Landmark Detection

Zhenglin Zhou,

Huaxia Li,

Hong Liu,

Nanyang Wang,

Gang Yu,

Rongrong Ji

[pdf] [supp]

[bibtex]

@InProceedings{Zhou_2023_CVPR, author = {Zhou, Zhenglin and Li, Huaxia and Liu, Hong and Wang, Nanyang and Yu, Gang and Ji, Rongrong}, title = {STAR Loss: Reducing Semantic Ambiguity in Facial Landmark Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15475-15484} }

A Meta-Learning Approach to Predicting Performance and Data Requirements

Achin Jain,

Gurumurthy Swaminathan,

Paolo Favaro,

Hao Yang,

Avinash Ravichandran,

Hrayr Harutyunyan,

Alessandro Achille,

Onkar Dabeer,

Bernt Schiele,

Ashwin Swaminathan,

Stefano Soatto

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Jain_2023_CVPR, author = {Jain, Achin and Swaminathan, Gurumurthy and Favaro, Paolo and Yang, Hao and Ravichandran, Avinash and Harutyunyan, Hrayr and Achille, Alessandro and Dabeer, Onkar and Schiele, Bernt and Swaminathan, Ashwin and Soatto, Stefano}, title = {A Meta-Learning Approach to Predicting Performance and Data Requirements}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3623-3632} }

Seeing What You Said: Talking Face Generation Guided by a Lip Reading Expert

Jiadong Wang,

Xinyuan Qian,

Malu Zhang,

Robby T. Tan,

Haizhou Li

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Jiadong and Qian, Xinyuan and Zhang, Malu and Tan, Robby T. and Li, Haizhou}, title = {Seeing What You Said: Talking Face Generation Guided by a Lip Reading Expert}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14653-14662} }

Deep Curvilinear Editing: Commutative and Nonlinear Image Manipulation for Pretrained Deep Generative Model

Takehiro Aoshima,

Takashi Matsubara

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Aoshima_2023_CVPR, author = {Aoshima, Takehiro and Matsubara, Takashi}, title = {Deep Curvilinear Editing: Commutative and Nonlinear Image Manipulation for Pretrained Deep Generative Model}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5957-5967} }

Learning Semantic-Aware Knowledge Guidance for Low-Light Image Enhancement

Yuhui Wu,

Chen Pan,

Guoqing Wang,

Yang Yang,

Jiwei Wei,

Chongyi Li,

Heng Tao Shen

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Wu_2023_CVPR, author = {Wu, Yuhui and Pan, Chen and Wang, Guoqing and Yang, Yang and Wei, Jiwei and Li, Chongyi and Shen, Heng Tao}, title = {Learning Semantic-Aware Knowledge Guidance for Low-Light Image Enhancement}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1662-1671} }

SimpSON: Simplifying Photo Cleanup With Single-Click Distracting Object Segmentation Network

Chuong Huynh,

Yuqian Zhou,

Zhe Lin,

Connelly Barnes,

Eli Shechtman,

Sohrab Amirghodsi,

Abhinav Shrivastava

[pdf] [supp]

[bibtex]

@InProceedings{Huynh_2023_CVPR, author = {Huynh, Chuong and Zhou, Yuqian and Lin, Zhe and Barnes, Connelly and Shechtman, Eli and Amirghodsi, Sohrab and Shrivastava, Abhinav}, title = {SimpSON: Simplifying Photo Cleanup With Single-Click Distracting Object Segmentation Network}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14518-14527} }

Learning Neural Duplex Radiance Fields for Real-Time View Synthesis

Ziyu Wan,

Christian Richardt,

Aljaž Božič,

Chao Li,

Vijay Rengarajan,

Seonghyeon Nam,

Xiaoyu Xiang,

Tuotuo Li,

Bo Zhu,

Rakesh Ranjan,

Jing Liao

[pdf] [supp]

[bibtex]

@InProceedings{Wan_2023_CVPR, author = {Wan, Ziyu and Richardt, Christian and Bo\v{z}i\v{c}, Alja\v{z} and Li, Chao and Rengarajan, Vijay and Nam, Seonghyeon and Xiang, Xiaoyu and Li, Tuotuo and Zhu, Bo and Ranjan, Rakesh and Liao, Jing}, title = {Learning Neural Duplex Radiance Fields for Real-Time View Synthesis}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8307-8316} }

Deep Arbitrary-Scale Image Super-Resolution via Scale-Equivariance Pursuit

Xiaohang Wang,

Xuanhong Chen,

Bingbing Ni,

Hang Wang,

Zhengyan Tong,

Yutian Liu

[pdf] [supp]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Xiaohang and Chen, Xuanhong and Ni, Bingbing and Wang, Hang and Tong, Zhengyan and Liu, Yutian}, title = {Deep Arbitrary-Scale Image Super-Resolution via Scale-Equivariance Pursuit}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1786-1795} }

Towards Modality-Agnostic Person Re-Identification With Descriptive Query

Cuiqun Chen,

Mang Ye,

Ding Jiang

[pdf]

[bibtex]

@InProceedings{Chen_2023_CVPR, author = {Chen, Cuiqun and Ye, Mang and Jiang, Ding}, title = {Towards Modality-Agnostic Person Re-Identification With Descriptive Query}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15128-15137} }

Discriminating Known From Unknown Objects via Structure-Enhanced Recurrent Variational AutoEncoder

Aming Wu,

Cheng Deng

[pdf] [supp]

[bibtex]

@InProceedings{Wu_2023_CVPR, author = {Wu, Aming and Deng, Cheng}, title = {Discriminating Known From Unknown Objects via Structure-Enhanced Recurrent Variational AutoEncoder}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {23956-23965} }

Occlusion-Free Scene Recovery via Neural Radiance Fields

Chengxuan Zhu,

Renjie Wan,

Yunkai Tang,

Boxin Shi

[pdf] [supp]

[bibtex]

@InProceedings{Zhu_2023_CVPR, author = {Zhu, Chengxuan and Wan, Renjie and Tang, Yunkai and Shi, Boxin}, title = {Occlusion-Free Scene Recovery via Neural Radiance Fields}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {20722-20731} }

OmniAL: A Unified CNN Framework for Unsupervised Anomaly Localization

Ying Zhao

[pdf] [supp]

[bibtex]

@InProceedings{Zhao_2023_CVPR, author = {Zhao, Ying}, title = {OmniAL: A Unified CNN Framework for Unsupervised Anomaly Localization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3924-3933} }

An In-Depth Exploration of Person Re-Identification and Gait Recognition in Cloth-Changing Conditions

Weijia Li,

Saihui Hou,

Chunjie Zhang,

Chunshui Cao,

Xu Liu,

Yongzhen Huang,

Yao Zhao

[pdf]

[bibtex]

@InProceedings{Li_2023_CVPR, author = {Li, Weijia and Hou, Saihui and Zhang, Chunjie and Cao, Chunshui and Liu, Xu and Huang, Yongzhen and Zhao, Yao}, title = {An In-Depth Exploration of Person Re-Identification and Gait Recognition in Cloth-Changing Conditions}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13824-13833} }

Visual Exemplar Driven Task-Prompting for Unified Perception in Autonomous Driving

Xiwen Liang,

Minzhe Niu,

Jianhua Han,

Hang Xu,

Chunjing Xu,

Xiaodan Liang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Liang_2023_CVPR, author = {Liang, Xiwen and Niu, Minzhe and Han, Jianhua and Xu, Hang and Xu, Chunjing and Liang, Xiaodan}, title = {Visual Exemplar Driven Task-Prompting for Unified Perception in Autonomous Driving}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9611-9621} }

Toward Verifiable and Reproducible Human Evaluation for Text-to-Image Generation

Mayu Otani,

Riku Togashi,

Yu Sawai,

Ryosuke Ishigami,

Yuta Nakashima,

Esa Rahtu,

Janne Heikkilä,

Shin’ichi Satoh

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Otani_2023_CVPR, author = {Otani, Mayu and Togashi, Riku and Sawai, Yu and Ishigami, Ryosuke and Nakashima, Yuta and Rahtu, Esa and Heikkil\"a, Janne and Satoh, Shin{\textquoteright}ichi}, title = {Toward Verifiable and Reproducible Human Evaluation for Text-to-Image Generation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14277-14286} }

Semi-Supervised Domain Adaptation With Source Label Adaptation

Yu-Chu Yu,

Hsuan-Tien Lin

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Yu_2023_CVPR, author = {Yu, Yu-Chu and Lin, Hsuan-Tien}, title = {Semi-Supervised Domain Adaptation With Source Label Adaptation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {24100-24109} }

Range-Nullspace Video Frame Interpolation With Focalized Motion Estimation

Zhiyang Yu,

Yu Zhang,

Dongqing Zou,

Xijun Chen,

Jimmy S. Ren,

Shunqing Ren

[pdf] [supp]

[bibtex]

@InProceedings{Yu_2023_CVPR, author = {Yu, Zhiyang and Zhang, Yu and Zou, Dongqing and Chen, Xijun and Ren, Jimmy S. and Ren, Shunqing}, title = {Range-Nullspace Video Frame Interpolation With Focalized Motion Estimation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {22159-22168} }

FlowGrad: Controlling the Output of Generative ODEs With Gradients

Xingchao Liu,

Lemeng Wu,

Shujian Zhang,

Chengyue Gong,

Wei Ping,

Qiang Liu

[pdf] [supp]

[bibtex]

@InProceedings{Liu_2023_CVPR, author = {Liu, Xingchao and Wu, Lemeng and Zhang, Shujian and Gong, Chengyue and Ping, Wei and Liu, Qiang}, title = {FlowGrad: Controlling the Output of Generative ODEs With Gradients}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {24335-24344} }

Learning Weather-General and Weather-Specific Features for Image Restoration Under Multiple Adverse Weather Conditions

Yurui Zhu,

Tianyu Wang,

Xueyang Fu,

Xuanyu Yang,

Xin Guo,

Jifeng Dai,

Yu Qiao,

Xiaowei Hu

[pdf]

[bibtex]

@InProceedings{Zhu_2023_CVPR, author = {Zhu, Yurui and Wang, Tianyu and Fu, Xueyang and Yang, Xuanyu and Guo, Xin and Dai, Jifeng and Qiao, Yu and Hu, Xiaowei}, title = {Learning Weather-General and Weather-Specific Features for Image Restoration Under Multiple Adverse Weather Conditions}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {21747-21758} }

Generalized Deep 3D Shape Prior via Part-Discretized Diffusion Process

Yuhan Li,

Yishun Dou,

Xuanhong Chen,

Bingbing Ni,

Yilin Sun,

Yutian Liu,

Fuzhen Wang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Li_2023_CVPR, author = {Li, Yuhan and Dou, Yishun and Chen, Xuanhong and Ni, Bingbing and Sun, Yilin and Liu, Yutian and Wang, Fuzhen}, title = {Generalized Deep 3D Shape Prior via Part-Discretized Diffusion Process}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16784-16794} }

Conflict-Based Cross-View Consistency for Semi-Supervised Semantic Segmentation

Zicheng Wang,

Zhen Zhao,

Xiaoxia Xing,

Dong Xu,

Xiangyu Kong,

Luping Zhou

[pdf] [arXiv]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Zicheng and Zhao, Zhen and Xing, Xiaoxia and Xu, Dong and Kong, Xiangyu and Zhou, Luping}, title = {Conflict-Based Cross-View Consistency for Semi-Supervised Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {19585-19595} }

Learning a 3D Morphable Face Reflectance Model From Low-Cost Data

Yuxuan Han,

Zhibo Wang,

Feng Xu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Han_2023_CVPR, author = {Han, Yuxuan and Wang, Zhibo and Xu, Feng}, title = {Learning a 3D Morphable Face Reflectance Model From Low-Cost Data}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8598-8608} }

SCoDA: Domain Adaptive Shape Completion for Real Scans

Yushuang Wu,

Zizheng Yan,

Ce Chen,

Lai Wei,

Xiao Li,

Guanbin Li,

Yihao Li,

Shuguang Cui,

Xiaoguang Han

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Wu_2023_CVPR, author = {Wu, Yushuang and Yan, Zizheng and Chen, Ce and Wei, Lai and Li, Xiao and Li, Guanbin and Li, Yihao and Cui, Shuguang and Han, Xiaoguang}, title = {SCoDA: Domain Adaptive Shape Completion for Real Scans}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {17630-17641} }

Recurrent Homography Estimation Using Homography-Guided Image Warping and Focus Transformer

Si-Yuan Cao,

Runmin Zhang,

Lun Luo,

Beinan Yu,

Zehua Sheng,

Junwei Li,

Hui-Liang Shen

[pdf] [supp]

[bibtex]

@InProceedings{Cao_2023_CVPR, author = {Cao, Si-Yuan and Zhang, Runmin and Luo, Lun and Yu, Beinan and Sheng, Zehua and Li, Junwei and Shen, Hui-Liang}, title = {Recurrent Homography Estimation Using Homography-Guided Image Warping and Focus Transformer}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9833-9842} }

I2-SDF: Intrinsic Indoor Scene Reconstruction and Editing via Raytracing in Neural SDFs

Jingsen Zhu,

Yuchi Huo,

Qi Ye,

Fujun Luan,

Jifan Li,

Dianbing Xi,

Lisha Wang,

Rui Tang,

Wei Hua,

Hujun Bao,

Rui Wang

[pdf] [supp]

[bibtex]

@InProceedings{Zhu_2023_CVPR, author = {Zhu, Jingsen and Huo, Yuchi and Ye, Qi and Luan, Fujun and Li, Jifan and Xi, Dianbing and Wang, Lisha and Tang, Rui and Hua, Wei and Bao, Hujun and Wang, Rui}, title = {I2-SDF: Intrinsic Indoor Scene Reconstruction and Editing via Raytracing in Neural SDFs}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12489-12498} }

DLBD: A Self-Supervised Direct-Learned Binary Descriptor

Bin Xiao,

Yang Hu,

Bo Liu,

Xiuli Bi,

Weisheng Li,

Xinbo Gao

[pdf]

[bibtex]

@InProceedings{Xiao_2023_CVPR, author = {Xiao, Bin and Hu, Yang and Liu, Bo and Bi, Xiuli and Li, Weisheng and Gao, Xinbo}, title = {DLBD: A Self-Supervised Direct-Learned Binary Descriptor}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15846-15855} }

Fuzzy Positive Learning for Semi-Supervised Semantic Segmentation

Pengchong Qiao,

Zhidan Wei,

Yu Wang,

Zhennan Wang,

Guoli Song,

Fan Xu,

Xiangyang Ji,

Chang Liu,

Jie Chen

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Qiao_2023_CVPR, author = {Qiao, Pengchong and Wei, Zhidan and Wang, Yu and Wang, Zhennan and Song, Guoli and Xu, Fan and Ji, Xiangyang and Liu, Chang and Chen, Jie}, title = {Fuzzy Positive Learning for Semi-Supervised Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15465-15474} }

Canonical Fields: Self-Supervised Learning of Pose-Canonicalized Neural Fields

Rohith Agaram,

Shaurya Dewan,

Rahul Sajnani,

Adrien Poulenard,

Madhava Krishna,

Srinath Sridhar

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Agaram_2023_CVPR, author = {Agaram, Rohith and Dewan, Shaurya and Sajnani, Rahul and Poulenard, Adrien and Krishna, Madhava and Sridhar, Srinath}, title = {Canonical Fields: Self-Supervised Learning of Pose-Canonicalized Neural Fields}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4500-4510} }

TransFlow: Transformer As Flow Learner

Yawen Lu,

Qifan Wang,

Siqi Ma,

Tong Geng,

Yingjie Victor Chen,

Huaijin Chen,

Dongfang Liu

[pdf] [arXiv]

[bibtex]

@InProceedings{Lu_2023_CVPR, author = {Lu, Yawen and Wang, Qifan and Ma, Siqi and Geng, Tong and Chen, Yingjie Victor and Chen, Huaijin and Liu, Dongfang}, title = {TransFlow: Transformer As Flow Learner}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {18063-18073} }

Multi-View Inverse Rendering for Large-Scale Real-World Indoor Scenes

Zhen Li,

Lingli Wang,

Mofang Cheng,

Cihui Pan,

Jiaqi Yang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Li_2023_CVPR, author = {Li, Zhen and Wang, Lingli and Cheng, Mofang and Pan, Cihui and Yang, Jiaqi}, title = {Multi-View Inverse Rendering for Large-Scale Real-World Indoor Scenes}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12499-12509} }

AutoFocusFormer: Image Segmentation off the Grid

Chen Ziwen,

Kaushik Patnaik,

Shuangfei Zhai,

Alvin Wan,

Zhile Ren,

Alexander G. Schwing,

Alex Colburn,

Li Fuxin

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Ziwen_2023_CVPR, author = {Ziwen, Chen and Patnaik, Kaushik and Zhai, Shuangfei and Wan, Alvin and Ren, Zhile and Schwing, Alexander G. and Colburn, Alex and Fuxin, Li}, title = {AutoFocusFormer: Image Segmentation off the Grid}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {18227-18236} }

Boosting Transductive Few-Shot Fine-Tuning With Margin-Based Uncertainty Weighting and Probability Regularization

Ran Tao,

Hao Chen,

Marios Savvides

[pdf] [supp]

[bibtex]

@InProceedings{Tao_2023_CVPR, author = {Tao, Ran and Chen, Hao and Savvides, Marios}, title = {Boosting Transductive Few-Shot Fine-Tuning With Margin-Based Uncertainty Weighting and Probability Regularization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15752-15761} }

SMPConv: Self-Moving Point Representations for Continuous Convolution

Sanghyeon Kim,

Eunbyung Park

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Kim_2023_CVPR, author = {Kim, Sanghyeon and Park, Eunbyung}, title = {SMPConv: Self-Moving Point Representations for Continuous Convolution}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10289-10299} }

CLIP2Protect: Protecting Facial Privacy Using Text-Guided Makeup via Adversarial Latent Search

Fahad Shamshad,

Muzammal Naseer,

Karthik Nandakumar

[pdf] [supp]

[bibtex]

@InProceedings{Shamshad_2023_CVPR, author = {Shamshad, Fahad and Naseer, Muzammal and Nandakumar, Karthik}, title = {CLIP2Protect: Protecting Facial Privacy Using Text-Guided Makeup via Adversarial Latent Search}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {20595-20605} }

Improving Weakly Supervised Temporal Action Localization by Bridging Train-Test Gap in Pseudo Labels

Jingqiu Zhou,

Linjiang Huang,

Liang Wang,

Si Liu,

Hongsheng Li

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Zhou_2023_CVPR, author = {Zhou, Jingqiu and Huang, Linjiang and Wang, Liang and Liu, Si and Li, Hongsheng}, title = {Improving Weakly Supervised Temporal Action Localization by Bridging Train-Test Gap in Pseudo Labels}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {23003-23012} }

PRISE: Demystifying Deep Lucas-Kanade With Strongly Star-Convex Constraints for Multimodel Image Alignment

Yiqing Zhang,

Xinming Huang,

Ziming Zhang

[pdf] [arXiv]

[bibtex]

@InProceedings{Zhang_2023_CVPR, author = {Zhang, Yiqing and Huang, Xinming and Zhang, Ziming}, title = {PRISE: Demystifying Deep Lucas-Kanade With Strongly Star-Convex Constraints for Multimodel Image Alignment}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13187-13197} }

Learning To Exploit Temporal Structure for Biomedical Vision-Language Processing

Shruthi Bannur,

Stephanie Hyland,

Qianchu Liu,

Fernando Pérez-García,

Maximilian Ilse,

Daniel C. Castro,

Benedikt Boecking,

Harshita Sharma,

Kenza Bouzid,

Anja Thieme,

Anton Schwaighofer,

Maria Wetscherek,

Matthew P. Lungren,

Aditya Nori,

Javier Alvarez-Valle,

Ozan Oktay

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Bannur_2023_CVPR, author = {Bannur, Shruthi and Hyland, Stephanie and Liu, Qianchu and P\'erez-Garc{\'\i}a, Fernando and Ilse, Maximilian and Castro, Daniel C. and Boecking, Benedikt and Sharma, Harshita and Bouzid, Kenza and Thieme, Anja and Schwaighofer, Anton and Wetscherek, Maria and Lungren, Matthew P. and Nori, Aditya and Alvarez-Valle, Javier and Oktay, Ozan}, title = {Learning To Exploit Temporal Structure for Biomedical Vision-Language Processing}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15016-15027} }

Simple Cues Lead to a Strong Multi-Object Tracker

Jenny Seidenschwarz,

Guillem Brasó,

Víctor Castro Serrano,

Ismail Elezi,

Laura Leal-Taixé

[pdf] [supp]

[bibtex]

@InProceedings{Seidenschwarz_2023_CVPR, author = {Seidenschwarz, Jenny and Bras\'o, Guillem and Serrano, V{\'\i}ctor Castro and Elezi, Ismail and Leal-Taix\'e, Laura}, title = {Simple Cues Lead to a Strong Multi-Object Tracker}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13813-13823} }

Marching-Primitives: Shape Abstraction From Signed Distance Function

Weixiao Liu,

Yuwei Wu,

Sipu Ruan,

Gregory S. Chirikjian

[pdf] [supp]

[bibtex]

@InProceedings{Liu_2023_CVPR, author = {Liu, Weixiao and Wu, Yuwei and Ruan, Sipu and Chirikjian, Gregory S.}, title = {Marching-Primitives: Shape Abstraction From Signed Distance Function}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8771-8780} }

BiasAdv: Bias-Adversarial Augmentation for Model Debiasing

Jongin Lim,

Youngdong Kim,

Byungjai Kim,

Chanho Ahn,

Jinwoo Shin,

Eunho Yang,

Seungju Han

[pdf] [supp]

[bibtex]

@InProceedings{Lim_2023_CVPR, author = {Lim, Jongin and Kim, Youngdong and Kim, Byungjai and Ahn, Chanho and Shin, Jinwoo and Yang, Eunho and Han, Seungju}, title = {BiasAdv: Bias-Adversarial Augmentation for Model Debiasing}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3832-3841} }

CDDFuse: Correlation-Driven Dual-Branch Feature Decomposition for Multi-Modality Image Fusion

Zixiang Zhao,

Haowen Bai,

Jiangshe Zhang,

Yulun Zhang,

Shuang Xu,

Zudi Lin,

Radu Timofte,

Luc Van Gool

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Zhao_2023_CVPR, author = {Zhao, Zixiang and Bai, Haowen and Zhang, Jiangshe and Zhang, Yulun and Xu, Shuang and Lin, Zudi and Timofte, Radu and Van Gool, Luc}, title = {CDDFuse: Correlation-Driven Dual-Branch Feature Decomposition for Multi-Modality Image Fusion}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5906-5916} }

Cross-Modal Implicit Relation Reasoning and Aligning for Text-to-Image Person Retrieval

Ding Jiang,

Mang Ye

[pdf] [arXiv]

[bibtex]

@InProceedings{Jiang_2023_CVPR, author = {Jiang, Ding and Ye, Mang}, title = {Cross-Modal Implicit Relation Reasoning and Aligning for Text-to-Image Person Retrieval}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2787-2797} }

REVEAL: Retrieval-Augmented Visual-Language Pre-Training With Multi-Source Multimodal Knowledge Memory

Ziniu Hu,

Ahmet Iscen,

Chen Sun,

Zirui Wang,

Kai-Wei Chang,

Yizhou Sun,

Cordelia Schmid,

David A. Ross,

Alireza Fathi

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Hu_2023_CVPR, author = {Hu, Ziniu and Iscen, Ahmet and Sun, Chen and Wang, Zirui and Chang, Kai-Wei and Sun, Yizhou and Schmid, Cordelia and Ross, David A. and Fathi, Alireza}, title = {REVEAL: Retrieval-Augmented Visual-Language Pre-Training With Multi-Source Multimodal Knowledge Memory}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {23369-23379} }

Learning To Retain While Acquiring: Combating Distribution-Shift in Adversarial Data-Free Knowledge Distillation

Gaurav Patel,

Konda Reddy Mopuri,

Qiang Qiu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Patel_2023_CVPR, author = {Patel, Gaurav and Mopuri, Konda Reddy and Qiu, Qiang}, title = {Learning To Retain While Acquiring: Combating Distribution-Shift in Adversarial Data-Free Knowledge Distillation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7786-7794} }

Why Is the Winner the Best?

Matthias Eisenmann,

Annika Reinke,

Vivienn Weru,

Minu D. Tizabi,

Fabian Isensee,

Tim J. Adler,

Sharib Ali,

Vincent Andrearczyk,

Marc Aubreville,

Ujjwal Baid,

Spyridon Bakas,

Niranjan Balu,

Sophia Bano,

Jorge Bernal,

Sebastian Bodenstedt,

Alessandro Casella,

Veronika Cheplygina,

Marie Daum,

Marleen de Bruijne,

Adrien Depeursinge,

Reuben Dorent,

Jan Egger,

David G. Ellis,

Sandy Engelhardt,

Melanie Ganz,

Noha Ghatwary,

Gabriel Girard,

Patrick Godau,

Anubha Gupta,

Lasse Hansen,

Kanako Harada,

Mattias P. Heinrich,

Nicholas Heller,

Alessa Hering,

Arnaud Huaulmé,

Pierre Jannin,

Ali Emre Kavur,

Oldřich Kodym,

Michal Kozubek,

Jianning Li,

Hongwei Li,

Jun Ma,

Carlos Martín-Isla,

Bjoern Menze,

Alison Noble,

Valentin Oreiller,

Nicolas Padoy,

Sarthak Pati,

Kelly Payette,

Tim Rädsch,

Jonathan Rafael-Patiño,

Vivek Singh Bawa,

Stefanie Speidel,

Carole H. Sudre,

Kimberlin van Wijnen,

Martin Wagner,

Donglai Wei,

Amine Yamlahi,

Moi Hoon Yap,

Chun Yuan,

Maximilian Zenk,

Aneeq Zia,

David Zimmerer,

Dogu Baran Aydogan,

Binod Bhattarai,

Louise Bloch,

Raphael Brüngel,

Jihoon Cho,

Chanyeol Choi,

Qi Dou,

Ivan Ezhov,

Christoph M. Friedrich,

Clifton D. Fuller,

Rebati Raman Gaire,

Adrian Galdran,

Álvaro García Faura,

Maria Grammatikopoulou,

SeulGi Hong,

Mostafa Jahanifar,

Ikbeom Jang,

Abdolrahim Kadkhodamohammadi,

Inha Kang,

Florian Kofler,

Satoshi Kondo,

Hugo Kuijf,

Mingxing Li,

Minh Luu,

Tomaž Martinčič,

Pedro Morais,

Mohamed A. Naser,

Bruno Oliveira,

David Owen,

Subeen Pang,

Jinah Park,

Sung-Hong Park,

Szymon Plotka,

Elodie Puybareau,

Nasir Rajpoot,

Kanghyun Ryu,

Numan Saeed,

Adam Shephard,

Pengcheng Shi,

Dejan Štepec,

Ronast Subedi,

Guillaume Tochon,

Helena R. Torres,

Helene Urien,

João L. Vilaça,

Kareem A. Wahid,

Haojie Wang,

Jiacheng Wang,

Liansheng Wang,

Xiyue Wang,

Benedikt Wiestler,

Marek Wodzinski,

Fangfang Xia,

Juanying Xie,

Zhiwei Xiong,

Sen Yang,

Yanwu Yang,

Zixuan Zhao,

Klaus Maier-Hein,

Paul F. Jäger,

Annette Kopp-Schneider,

Lena Maier-Hein

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Eisenmann_2023_CVPR, author = {Eisenmann, Matthias and Reinke, Annika and Weru, Vivienn and Tizabi, Minu D. and Isensee, Fabian and Adler, Tim J. and Ali, Sharib and Andrearczyk, Vincent and Aubreville, Marc and Baid, Ujjwal and Bakas, Spyridon and Balu, Niranjan and Bano, Sophia and Bernal, Jorge and Bodenstedt, Sebastian and Casella, Alessandro and Cheplygina, Veronika and Daum, Marie and de Bruijne, Marleen and Depeursinge, Adrien and Dorent, Reuben and Egger, Jan and Ellis, David G. and Engelhardt, Sandy and Ganz, Melanie and Ghatwary, Noha and Girard, Gabriel and Godau, Patrick and Gupta, Anubha and Hansen, Lasse and Harada, Kanako and Heinrich, Mattias P. and Heller, Nicholas and Hering, Alessa and Huaulm\'e, Arnaud and Jannin, Pierre and Kavur, Ali Emre and Kodym, Old\v{r}ich and Kozubek, Michal and Li, Jianning and Li, Hongwei and Ma, Jun and Mart{\'\i}n-Isla, Carlos and Menze, Bjoern and Noble, Alison and Oreiller, Valentin and Padoy, Nicolas and Pati, Sarthak and Payette, Kelly and R\"adsch, Tim and Rafael-Pati\~no, Jonathan and Bawa, Vivek Singh and Speidel, Stefanie and Sudre, Carole H. and van Wijnen, Kimberlin and Wagner, Martin and Wei, Donglai and Yamlahi, Amine and Yap, Moi Hoon and Yuan, Chun and Zenk, Maximilian and Zia, Aneeq and Zimmerer, David and Aydogan, Dogu Baran and Bhattarai, Binod and Bloch, Louise and Br\"ungel, Raphael and Cho, Jihoon and Choi, Chanyeol and Dou, Qi and Ezhov, Ivan and Friedrich, Christoph M. and Fuller, Clifton D. and Gaire, Rebati Raman and Galdran, Adrian and Faura, \'Alvaro Garc{\'\i}a and Grammatikopoulou, Maria and Hong, SeulGi and Jahanifar, Mostafa and Jang, Ikbeom and Kadkhodamohammadi, Abdolrahim and Kang, Inha and Kofler, Florian and Kondo, Satoshi and Kuijf, Hugo and Li, Mingxing and Luu, Minh and Martin\v{c}i\v{c}, Toma\v{z} and Morais, Pedro and Naser, Mohamed A. and Oliveira, Bruno and Owen, David and Pang, Subeen and Park, Jinah and Park, Sung-Hong and Plotka, Szymon and Puybareau, Elodie and Rajpoot, Nasir and Ryu, Kanghyun and Saeed, Numan and Shephard, Adam and Shi, Pengcheng and \v{S}tepec, Dejan and Subedi, Ronast and Tochon, Guillaume and Torres, Helena R. and Urien, Helene and Vila\c{c}a, Jo\~ao L. and Wahid, Kareem A. and Wang, Haojie and Wang, Jiacheng and Wang, Liansheng and Wang, Xiyue and Wiestler, Benedikt and Wodzinski, Marek and Xia, Fangfang and Xie, Juanying and Xiong, Zhiwei and Yang, Sen and Yang, Yanwu and Zhao, Zixuan and Maier-Hein, Klaus and J\"ager, Paul F. and Kopp-Schneider, Annette and Maier-Hein, Lena}, title = {Why Is the Winner the Best?}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {19955-19966} }

HGNet: Learning Hierarchical Geometry From Points, Edges, and Surfaces

Ting Yao,

Yehao Li,

Yingwei Pan,

Tao Mei

[pdf] [supp]

[bibtex]

@InProceedings{Yao_2023_CVPR, author = {Yao, Ting and Li, Yehao and Pan, Yingwei and Mei, Tao}, title = {HGNet: Learning Hierarchical Geometry From Points, Edges, and Surfaces}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {21846-21855} }

PointVector: A Vector Representation in Point Cloud Analysis

Xin Deng,

WenYu Zhang,

Qing Ding,

XinMing Zhang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Deng_2023_CVPR, author = {Deng, Xin and Zhang, WenYu and Ding, Qing and Zhang, XinMing}, title = {PointVector: A Vector Representation in Point Cloud Analysis}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9455-9465} }

BAEFormer: Bi-Directional and Early Interaction Transformers for Bird's Eye View Semantic Segmentation

Cong Pan,

Yonghao He,

Junran Peng,

Qian Zhang,

Wei Sui,

Zhaoxiang Zhang

[pdf]

[bibtex]

@InProceedings{Pan_2023_CVPR, author = {Pan, Cong and He, Yonghao and Peng, Junran and Zhang, Qian and Sui, Wei and Zhang, Zhaoxiang}, title = {BAEFormer: Bi-Directional and Early Interaction Transformers for Bird's Eye View Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9590-9599} }

Good Is Bad: Causality Inspired Cloth-Debiasing for Cloth-Changing Person Re-Identification

Zhengwei Yang,

Meng Lin,

Xian Zhong,

Yu Wu,

Zheng Wang

[pdf] [supp]

[bibtex]

@InProceedings{Yang_2023_CVPR, author = {Yang, Zhengwei and Lin, Meng and Zhong, Xian and Wu, Yu and Wang, Zheng}, title = {Good Is Bad: Causality Inspired Cloth-Debiasing for Cloth-Changing Person Re-Identification}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1472-1481} }

Use Your Head: Improving Long-Tail Video Recognition

Toby Perrett,

Saptarshi Sinha,

Tilo Burghardt,

Majid Mirmehdi,

Dima Damen

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Perrett_2023_CVPR, author = {Perrett, Toby and Sinha, Saptarshi and Burghardt, Tilo and Mirmehdi, Majid and Damen, Dima}, title = {Use Your Head: Improving Long-Tail Video Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2415-2425} }

Revisiting the P3P Problem

Yaqing Ding,

Jian Yang,

Viktor Larsson,

Carl Olsson,

Kalle Åström

[pdf] [supp]

[bibtex]

@InProceedings{Ding_2023_CVPR, author = {Ding, Yaqing and Yang, Jian and Larsson, Viktor and Olsson, Carl and \r{A}str\"om, Kalle}, title = {Revisiting the P3P Problem}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4872-4880} }

Generic-to-Specific Distillation of Masked Autoencoders

Wei Huang,

Zhiliang Peng,

Li Dong,

Furu Wei,

Jianbin Jiao,

Qixiang Ye

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Huang_2023_CVPR, author = {Huang, Wei and Peng, Zhiliang and Dong, Li and Wei, Furu and Jiao, Jianbin and Ye, Qixiang}, title = {Generic-to-Specific Distillation of Masked Autoencoders}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15996-16005} }

PAniC-3D: Stylized Single-View 3D Reconstruction From Portraits of Anime Characters

Shuhong Chen,

Kevin Zhang,

Yichun Shi,

Heng Wang,

Yiheng Zhu,

Guoxian Song,

Sizhe An,

Janus Kristjansson,

Xiao Yang,

Matthias Zwicker

[pdf] [supp]

[bibtex]

@InProceedings{Chen_2023_CVPR, author = {Chen, Shuhong and Zhang, Kevin and Shi, Yichun and Wang, Heng and Zhu, Yiheng and Song, Guoxian and An, Sizhe and Kristjansson, Janus and Yang, Xiao and Zwicker, Matthias}, title = {PAniC-3D: Stylized Single-View 3D Reconstruction From Portraits of Anime Characters}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {21068-21077} }

Combining Implicit-Explicit View Correlation for Light Field Semantic Segmentation

Ruixuan Cong,

Da Yang,

Rongshan Chen,

Sizhe Wang,

Zhenglong Cui,

Hao Sheng

[pdf]

[bibtex]

@InProceedings{Cong_2023_CVPR, author = {Cong, Ruixuan and Yang, Da and Chen, Rongshan and Wang, Sizhe and Cui, Zhenglong and Sheng, Hao}, title = {Combining Implicit-Explicit View Correlation for Light Field Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9172-9181} }

TimeBalance: Temporally-Invariant and Temporally-Distinctive Video Representations for Semi-Supervised Action Recognition

Ishan Rajendrakumar Dave,

Mamshad Nayeem Rizve,

Chen Chen,

Mubarak Shah

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Dave_2023_CVPR, author = {Dave, Ishan Rajendrakumar and Rizve, Mamshad Nayeem and Chen, Chen and Shah, Mubarak}, title = {TimeBalance: Temporally-Invariant and Temporally-Distinctive Video Representations for Semi-Supervised Action Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2341-2352} }

SunStage: Portrait Reconstruction and Relighting Using the Sun as a Light Stage

Yifan Wang,

Aleksander Holynski,

Xiuming Zhang,

Xuaner Zhang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Yifan and Holynski, Aleksander and Zhang, Xiuming and Zhang, Xuaner}, title = {SunStage: Portrait Reconstruction and Relighting Using the Sun as a Light Stage}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {20792-20802} }

Private Image Generation With Dual-Purpose Auxiliary Classifier

Chen Chen,

Daochang Liu,

Siqi Ma,

Surya Nepal,

Chang Xu

[pdf] [supp]

[bibtex]

@InProceedings{Chen_2023_CVPR, author = {Chen, Chen and Liu, Daochang and Ma, Siqi and Nepal, Surya and Xu, Chang}, title = {Private Image Generation With Dual-Purpose Auxiliary Classifier}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {20361-20370} }

3D-POP - An Automated Annotation Approach to Facilitate Markerless 2D-3D Tracking of Freely Moving Birds With Marker-Based Motion Capture

Hemal Naik,

Alex Hoi Hang Chan,

Junran Yang,

Mathilde Delacoux,

Iain D. Couzin,

Fumihiro Kano,

Máté Nagy

[pdf] [supp]

[bibtex]

@InProceedings{Naik_2023_CVPR, author = {Naik, Hemal and Chan, Alex Hoi Hang and Yang, Junran and Delacoux, Mathilde and Couzin, Iain D. and Kano, Fumihiro and Nagy, M\'at\'e}, title = {3D-POP - An Automated Annotation Approach to Facilitate Markerless 2D-3D Tracking of Freely Moving Birds With Marker-Based Motion Capture}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {21274-21284} }

SOOD: Towards Semi-Supervised Oriented Object Detection

Wei Hua,

Dingkang Liang,

Jingyu Li,

Xiaolong Liu,

Zhikang Zou,

Xiaoqing Ye,

Xiang Bai

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Hua_2023_CVPR, author = {Hua, Wei and Liang, Dingkang and Li, Jingyu and Liu, Xiaolong and Zou, Zhikang and Ye, Xiaoqing and Bai, Xiang}, title = {SOOD: Towards Semi-Supervised Oriented Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15558-15567} }

Unified Keypoint-Based Action Recognition Framework via Structured Keypoint Pooling

Ryo Hachiuma,

Fumiaki Sato,

Taiki Sekii

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Hachiuma_2023_CVPR, author = {Hachiuma, Ryo and Sato, Fumiaki and Sekii, Taiki}, title = {Unified Keypoint-Based Action Recognition Framework via Structured Keypoint Pooling}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {22962-22971} }

Multi-View Reconstruction Using Signed Ray Distance Functions (SRDF)

Pierre Zins,

Yuanlu Xu,

Edmond Boyer,

Stefanie Wuhrer,

Tony Tung

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Zins_2023_CVPR, author = {Zins, Pierre and Xu, Yuanlu and Boyer, Edmond and Wuhrer, Stefanie and Tung, Tony}, title = {Multi-View Reconstruction Using Signed Ray Distance Functions (SRDF)}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16696-16706} }

Beyond mAP: Towards Better Evaluation of Instance Segmentation

Rohit Jena,

Lukas Zhornyak,

Nehal Doiphode,

Pratik Chaudhari,

Vivek Buch,

James Gee,

Jianbo Shi

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Jena_2023_CVPR, author = {Jena, Rohit and Zhornyak, Lukas and Doiphode, Nehal and Chaudhari, Pratik and Buch, Vivek and Gee, James and Shi, Jianbo}, title = {Beyond mAP: Towards Better Evaluation of Instance Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11309-11318} }

Generating Aligned Pseudo-Supervision From Non-Aligned Data for Image Restoration in Under-Display Camera

Ruicheng Feng,

Chongyi Li,

Huaijin Chen,

Shuai Li,

Jinwei Gu,

Chen Change Loy

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Feng_2023_CVPR, author = {Feng, Ruicheng and Li, Chongyi and Chen, Huaijin and Li, Shuai and Gu, Jinwei and Loy, Chen Change}, title = {Generating Aligned Pseudo-Supervision From Non-Aligned Data for Image Restoration in Under-Display Camera}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5013-5022} }

Improving Cross-Modal Retrieval With Set of Diverse Embeddings

Dongwon Kim,

Namyup Kim,

Suha Kwak

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Kim_2023_CVPR, author = {Kim, Dongwon and Kim, Namyup and Kwak, Suha}, title = {Improving Cross-Modal Retrieval With Set of Diverse Embeddings}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {23422-23431} }

BASiS: Batch Aligned Spectral Embedding Space

Or Streicher,

Ido Cohen,

Guy Gilboa

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Streicher_2023_CVPR, author = {Streicher, Or and Cohen, Ido and Gilboa, Guy}, title = {BASiS: Batch Aligned Spectral Embedding Space}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10396-10405} }

Neural Pixel Composition for 3D-4D View Synthesis From Multi-Views

Aayush Bansal,

Michael Zollhöfer

[pdf] [supp]

[bibtex]

@InProceedings{Bansal_2023_CVPR, author = {Bansal, Aayush and Zollh\"ofer, Michael}, title = {Neural Pixel Composition for 3D-4D View Synthesis From Multi-Views}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {290-299} }

DCFace: Synthetic Face Generation With Dual Condition Diffusion Model

Minchul Kim,

Feng Liu,

Anil Jain,

Xiaoming Liu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Kim_2023_CVPR, author = {Kim, Minchul and Liu, Feng and Jain, Anil and Liu, Xiaoming}, title = {DCFace: Synthetic Face Generation With Dual Condition Diffusion Model}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12715-12725} }

CRAFT: Concept Recursive Activation FacTorization for Explainability

Thomas Fel,

Agustin Picard,

Louis Béthune,

Thibaut Boissin,

David Vigouroux,

Julien Colin,

Rémi Cadène,

Thomas Serre

[pdf] [supp]

[bibtex]

@InProceedings{Fel_2023_CVPR, author = {Fel, Thomas and Picard, Agustin and B\'ethune, Louis and Boissin, Thibaut and Vigouroux, David and Colin, Julien and Cad\`ene, R\'emi and Serre, Thomas}, title = {CRAFT: Concept Recursive Activation FacTorization for Explainability}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2711-2721} }

Policy Adaptation From Foundation Model Feedback

Yuying Ge,

Annabella Macaluso,

Li Erran Li,

Ping Luo,

Xiaolong Wang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Ge_2023_CVPR, author = {Ge, Yuying and Macaluso, Annabella and Li, Li Erran and Luo, Ping and Wang, Xiaolong}, title = {Policy Adaptation From Foundation Model Feedback}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {19059-19069} }

Recognizing Rigid Patterns of Unlabeled Point Clouds by Complete and Continuous Isometry Invariants With No False Negatives and No False Positives

Daniel Widdowson,

Vitaliy Kurlin

[pdf] [arXiv]

[bibtex]

@InProceedings{Widdowson_2023_CVPR, author = {Widdowson, Daniel and Kurlin, Vitaliy}, title = {Recognizing Rigid Patterns of Unlabeled Point Clouds by Complete and Continuous Isometry Invariants With No False Negatives and No False Positives}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1275-1284} }

N-Gram in Swin Transformers for Efficient Lightweight Image Super-Resolution

Haram Choi,

Jeongmin Lee,

Jihoon Yang

[pdf] [supp]

[bibtex]

@InProceedings{Choi_2023_CVPR, author = {Choi, Haram and Lee, Jeongmin and Yang, Jihoon}, title = {N-Gram in Swin Transformers for Efficient Lightweight Image Super-Resolution}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2071-2081} }

Semi-DETR: Semi-Supervised Object Detection With Detection Transformers

Jiacheng Zhang,

Xiangru Lin,

Wei Zhang,

Kuo Wang,

Xiao Tan,

Junyu Han,

Errui Ding,

Jingdong Wang,

Guanbin Li

[pdf] [supp]

[bibtex]

@InProceedings{Zhang_2023_CVPR, author = {Zhang, Jiacheng and Lin, Xiangru and Zhang, Wei and Wang, Kuo and Tan, Xiao and Han, Junyu and Ding, Errui and Wang, Jingdong and Li, Guanbin}, title = {Semi-DETR: Semi-Supervised Object Detection With Detection Transformers}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {23809-23818} }

Infinite Photorealistic Worlds Using Procedural Generation

Alexander Raistrick,

Lahav Lipson,

Zeyu Ma,

Lingjie Mei,

Mingzhe Wang,

Yiming Zuo,

Karhan Kayan,

Hongyu Wen,

Beining Han,

Yihan Wang,

Alejandro Newell,

Hei Law,

Ankit Goyal,

Kaiyu Yang,

Jia Deng

[pdf] [supp]

[bibtex]

@InProceedings{Raistrick_2023_CVPR, author = {Raistrick, Alexander and Lipson, Lahav and Ma, Zeyu and Mei, Lingjie and Wang, Mingzhe and Zuo, Yiming and Kayan, Karhan and Wen, Hongyu and Han, Beining and Wang, Yihan and Newell, Alejandro and Law, Hei and Goyal, Ankit and Yang, Kaiyu and Deng, Jia}, title = {Infinite Photorealistic Worlds Using Procedural Generation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12630-12641} }

Diversity-Measurable Anomaly Detection

Wenrui Liu,

Hong Chang,

Bingpeng Ma,

Shiguang Shan,

Xilin Chen

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Liu_2023_CVPR, author = {Liu, Wenrui and Chang, Hong and Ma, Bingpeng and Shan, Shiguang and Chen, Xilin}, title = {Diversity-Measurable Anomaly Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12147-12156} }

Hybrid Neural Rendering for Large-Scale Scenes With Motion Blur

Peng Dai,

Yinda Zhang,

Xin Yu,

Xiaoyang Lyu,

Xiaojuan Qi

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Dai_2023_CVPR, author = {Dai, Peng and Zhang, Yinda and Yu, Xin and Lyu, Xiaoyang and Qi, Xiaojuan}, title = {Hybrid Neural Rendering for Large-Scale Scenes With Motion Blur}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {154-164} }

Perception-Oriented Single Image Super-Resolution Using Optimal Objective Estimation

Seung Ho Park,

Young Su Moon,

Nam Ik Cho

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Park_2023_CVPR, author = {Park, Seung Ho and Moon, Young Su and Cho, Nam Ik}, title = {Perception-Oriented Single Image Super-Resolution Using Optimal Objective Estimation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1725-1735} }

GP-VTON: Towards General Purpose Virtual Try-On via Collaborative Local-Flow Global-Parsing Learning

Zhenyu Xie,

Zaiyu Huang,

Xin Dong,

Fuwei Zhao,

Haoye Dong,

Xijin Zhang,

Feida Zhu,

Xiaodan Liang

[pdf] [supp]

[bibtex]

@InProceedings{Xie_2023_CVPR, author = {Xie, Zhenyu and Huang, Zaiyu and Dong, Xin and Zhao, Fuwei and Dong, Haoye and Zhang, Xijin and Zhu, Feida and Liang, Xiaodan}, title = {GP-VTON: Towards General Purpose Virtual Try-On via Collaborative Local-Flow Global-Parsing Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {23550-23559} }

A Large-Scale Robustness Analysis of Video Action Recognition Models

Madeline Chantry Schiappa,

Naman Biyani,

Prudvi Kamtam,

Shruti Vyas,

Hamid Palangi,

Vibhav Vineet,

Yogesh S. Rawat

[pdf] [supp]

[bibtex]

@InProceedings{Schiappa_2023_CVPR, author = {Schiappa, Madeline Chantry and Biyani, Naman and Kamtam, Prudvi and Vyas, Shruti and Palangi, Hamid and Vineet, Vibhav and Rawat, Yogesh S.}, title = {A Large-Scale Robustness Analysis of Video Action Recognition Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14698-14708} }

Decomposed Soft Prompt Guided Fusion Enhancing for Compositional Zero-Shot Learning

Xiaocheng Lu,

Song Guo,

Ziming Liu,

Jingcai Guo

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Lu_2023_CVPR, author = {Lu, Xiaocheng and Guo, Song and Liu, Ziming and Guo, Jingcai}, title = {Decomposed Soft Prompt Guided Fusion Enhancing for Compositional Zero-Shot Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {23560-23569} }

Hierarchical Semantic Contrast for Scene-Aware Video Anomaly Detection

Shengyang Sun,

Xiaojin Gong

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Sun_2023_CVPR, author = {Sun, Shengyang and Gong, Xiaojin}, title = {Hierarchical Semantic Contrast for Scene-Aware Video Anomaly Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {22846-22856} }

All-in-Focus Imaging From Event Focal Stack

Hanyue Lou,

Minggui Teng,

Yixin Yang,

Boxin Shi

[pdf] [supp]

[bibtex]

@InProceedings{Lou_2023_CVPR, author = {Lou, Hanyue and Teng, Minggui and Yang, Yixin and Shi, Boxin}, title = {All-in-Focus Imaging From Event Focal Stack}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {17366-17375} }

Video Probabilistic Diffusion Models in Projected Latent Space

Sihyun Yu,

Kihyuk Sohn,

Subin Kim,

Jinwoo Shin

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Yu_2023_CVPR, author = {Yu, Sihyun and Sohn, Kihyuk and Kim, Subin and Shin, Jinwoo}, title = {Video Probabilistic Diffusion Models in Projected Latent Space}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {18456-18466} }

Learning 3D Scene Priors With 2D Supervision

Yinyu Nie,

Angela Dai,

Xiaoguang Han,

Matthias Nießner

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Nie_2023_CVPR, author = {Nie, Yinyu and Dai, Angela and Han, Xiaoguang and Nie{\ss}ner, Matthias}, title = {Learning 3D Scene Priors With 2D Supervision}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {792-802} }

Blind Video Deflickering by Neural Filtering With a Flawed Atlas

Chenyang Lei,

Xuanchi Ren,

Zhaoxiang Zhang,

Qifeng Chen

[pdf] [arXiv]

[bibtex]

@InProceedings{Lei_2023_CVPR, author = {Lei, Chenyang and Ren, Xuanchi and Zhang, Zhaoxiang and Chen, Qifeng}, title = {Blind Video Deflickering by Neural Filtering With a Flawed Atlas}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10439-10448} }

Label-Free Liver Tumor Segmentation

Qixin Hu,

Yixiong Chen,

Junfei Xiao,

Shuwen Sun,

Jieneng Chen,

Alan L. Yuille,

Zongwei Zhou

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Hu_2023_CVPR, author = {Hu, Qixin and Chen, Yixiong and Xiao, Junfei and Sun, Shuwen and Chen, Jieneng and Yuille, Alan L. and Zhou, Zongwei}, title = {Label-Free Liver Tumor Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7422-7432} }

Grid-Guided Neural Radiance Fields for Large Urban Scenes

Linning Xu,

Yuanbo Xiangli,

Sida Peng,

Xingang Pan,

Nanxuan Zhao,

Christian Theobalt,

Bo Dai,

Dahua Lin

[pdf] [arXiv]

[bibtex]

@InProceedings{Xu_2023_CVPR, author = {Xu, Linning and Xiangli, Yuanbo and Peng, Sida and Pan, Xingang and Zhao, Nanxuan and Theobalt, Christian and Dai, Bo and Lin, Dahua}, title = {Grid-Guided Neural Radiance Fields for Large Urban Scenes}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8296-8306} }

Defining and Quantifying the Emergence of Sparse Concepts in DNNs

Jie Ren,

Mingjie Li,

Qirui Chen,

Huiqi Deng,

Quanshi Zhang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Ren_2023_CVPR, author = {Ren, Jie and Li, Mingjie and Chen, Qirui and Deng, Huiqi and Zhang, Quanshi}, title = {Defining and Quantifying the Emergence of Sparse Concepts in DNNs}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {20280-20289} }

Uncurated Image-Text Datasets: Shedding Light on Demographic Bias

Noa Garcia,

Yusuke Hirota,

Yankun Wu,

Yuta Nakashima

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Garcia_2023_CVPR, author = {Garcia, Noa and Hirota, Yusuke and Wu, Yankun and Nakashima, Yuta}, title = {Uncurated Image-Text Datasets: Shedding Light on Demographic Bias}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6957-6966} }

FreeSeg: Unified, Universal and Open-Vocabulary Image Segmentation

Jie Qin,

Jie Wu,

Pengxiang Yan,

Ming Li,

Ren Yuxi,

Xuefeng Xiao,

Yitong Wang,

Rui Wang,

Shilei Wen,

Xin Pan,

Xingang Wang

[pdf] [arXiv]

[bibtex]

@InProceedings{Qin_2023_CVPR, author = {Qin, Jie and Wu, Jie and Yan, Pengxiang and Li, Ming and Yuxi, Ren and Xiao, Xuefeng and Wang, Yitong and Wang, Rui and Wen, Shilei and Pan, Xin and Wang, Xingang}, title = {FreeSeg: Unified, Universal and Open-Vocabulary Image Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {19446-19455} }

AVFormer: Injecting Vision Into Frozen Speech Models for Zero-Shot AV-ASR

Paul Hongsuck Seo,

Arsha Nagrani,

Cordelia Schmid

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Seo_2023_CVPR, author = {Seo, Paul Hongsuck and Nagrani, Arsha and Schmid, Cordelia}, title = {AVFormer: Injecting Vision Into Frozen Speech Models for Zero-Shot AV-ASR}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {22922-22931} }

FreeNeRF: Improving Few-Shot Neural Rendering With Free Frequency Regularization

Jiawei Yang,

Marco Pavone,

Yue Wang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Yang_2023_CVPR, author = {Yang, Jiawei and Pavone, Marco and Wang, Yue}, title = {FreeNeRF: Improving Few-Shot Neural Rendering With Free Frequency Regularization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8254-8263} }

Adversarial Robustness via Random Projection Filters

Minjing Dong,

Chang Xu

[pdf] [supp]

[bibtex]

@InProceedings{Dong_2023_CVPR, author = {Dong, Minjing and Xu, Chang}, title = {Adversarial Robustness via Random Projection Filters}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4077-4086} }

VNE: An Effective Method for Improving Deep Representation by Manipulating Eigenvalue Distribution

Jaeill Kim,

Suhyun Kang,

Duhun Hwang,

Jungwook Shin,

Wonjong Rhee

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Kim_2023_CVPR, author = {Kim, Jaeill and Kang, Suhyun and Hwang, Duhun and Shin, Jungwook and Rhee, Wonjong}, title = {VNE: An Effective Method for Improving Deep Representation by Manipulating Eigenvalue Distribution}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3799-3810} }

Self-Guided Diffusion Models

Vincent Tao Hu,

David W. Zhang,

Yuki M. Asano,

Gertjan J. Burghouts,

Cees G. M. Snoek

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Hu_2023_CVPR, author = {Hu, Vincent Tao and Zhang, David W. and Asano, Yuki M. and Burghouts, Gertjan J. and Snoek, Cees G. M.}, title = {Self-Guided Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {18413-18422} }

NeuWigs: A Neural Dynamic Model for Volumetric Hair Capture and Animation

Ziyan Wang,

Giljoo Nam,

Tuur Stuyck,

Stephen Lombardi,

Chen Cao,

Jason Saragih,

Michael Zollhöfer,

Jessica Hodgins,

Christoph Lassner

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Ziyan and Nam, Giljoo and Stuyck, Tuur and Lombardi, Stephen and Cao, Chen and Saragih, Jason and Zollh\"ofer, Michael and Hodgins, Jessica and Lassner, Christoph}, title = {NeuWigs: A Neural Dynamic Model for Volumetric Hair Capture and Animation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8641-8651} }

CLIP2: Contrastive Language-Image-Point Pretraining From Real-World Point Cloud Data

Yihan Zeng,

Chenhan Jiang,

Jiageng Mao,

Jianhua Han,

Chaoqiang Ye,

Qingqiu Huang,

Dit-Yan Yeung,

Zhen Yang,

Xiaodan Liang,

Hang Xu

[pdf] [supp]

[bibtex]

@InProceedings{Zeng_2023_CVPR, author = {Zeng, Yihan and Jiang, Chenhan and Mao, Jiageng and Han, Jianhua and Ye, Chaoqiang and Huang, Qingqiu and Yeung, Dit-Yan and Yang, Zhen and Liang, Xiaodan and Xu, Hang}, title = {CLIP2: Contrastive Language-Image-Point Pretraining From Real-World Point Cloud Data}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15244-15253} }

HNeRV: A Hybrid Neural Representation for Videos

Hao Chen,

Matthew Gwilliam,

Ser-Nam Lim,

Abhinav Shrivastava

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Chen_2023_CVPR, author = {Chen, Hao and Gwilliam, Matthew and Lim, Ser-Nam and Shrivastava, Abhinav}, title = {HNeRV: A Hybrid Neural Representation for Videos}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10270-10279} }

Model-Agnostic Gender Debiased Image Captioning

Yusuke Hirota,

Yuta Nakashima,

Noa Garcia

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Hirota_2023_CVPR, author = {Hirota, Yusuke and Nakashima, Yuta and Garcia, Noa}, title = {Model-Agnostic Gender Debiased Image Captioning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15191-15200} }

Local Implicit Ray Function for Generalizable Radiance Field Representation

Xin Huang,

Qi Zhang,

Ying Feng,

Xiaoyu Li,

Xuan Wang,

Qing Wang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Huang_2023_CVPR, author = {Huang, Xin and Zhang, Qi and Feng, Ying and Li, Xiaoyu and Wang, Xuan and Wang, Qing}, title = {Local Implicit Ray Function for Generalizable Radiance Field Representation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {97-107} }

One-Shot High-Fidelity Talking-Head Synthesis With Deformable Neural Radiance Field

Weichuang Li,

Longhao Zhang,

Dong Wang,

Bin Zhao,

Zhigang Wang,

Mulin Chen,

Bang Zhang,

Zhongjian Wang,

Liefeng Bo,

Xuelong Li

[pdf] [arXiv]

[bibtex]

@InProceedings{Li_2023_CVPR, author = {Li, Weichuang and Zhang, Longhao and Wang, Dong and Zhao, Bin and Wang, Zhigang and Chen, Mulin and Zhang, Bang and Wang, Zhongjian and Bo, Liefeng and Li, Xuelong}, title = {One-Shot High-Fidelity Talking-Head Synthesis With Deformable Neural Radiance Field}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {17969-17978} }

FitMe: Deep Photorealistic 3D Morphable Model Avatars

Alexandros Lattas,

Stylianos Moschoglou,

Stylianos Ploumpis,

Baris Gecer,

Jiankang Deng,

Stefanos Zafeiriou

[pdf] [supp]

[bibtex]

@InProceedings{Lattas_2023_CVPR, author = {Lattas, Alexandros and Moschoglou, Stylianos and Ploumpis, Stylianos and Gecer, Baris and Deng, Jiankang and Zafeiriou, Stefanos}, title = {FitMe: Deep Photorealistic 3D Morphable Model Avatars}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8629-8640} }

Dense Distinct Query for End-to-End Object Detection

Shilong Zhang,

Xinjiang Wang,

Jiaqi Wang,

Jiangmiao Pang,

Chengqi Lyu,

Wenwei Zhang,

Ping Luo,

Kai Chen

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Zhang_2023_CVPR, author = {Zhang, Shilong and Wang, Xinjiang and Wang, Jiaqi and Pang, Jiangmiao and Lyu, Chengqi and Zhang, Wenwei and Luo, Ping and Chen, Kai}, title = {Dense Distinct Query for End-to-End Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7329-7338} }

CLIPPO: Image-and-Language Understanding From Pixels Only

Michael Tschannen,

Basil Mustafa,

Neil Houlsby

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Tschannen_2023_CVPR, author = {Tschannen, Michael and Mustafa, Basil and Houlsby, Neil}, title = {CLIPPO: Image-and-Language Understanding From Pixels Only}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11006-11017} }

Trajectory-Aware Body Interaction Transformer for Multi-Person Pose Forecasting

Xiaogang Peng,

Siyuan Mao,

Zizhao Wu

[pdf] [arXiv]

[bibtex]

@InProceedings{Peng_2023_CVPR, author = {Peng, Xiaogang and Mao, Siyuan and Wu, Zizhao}, title = {Trajectory-Aware Body Interaction Transformer for Multi-Person Pose Forecasting}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {17121-17130} }

Conditional Image-to-Video Generation With Latent Flow Diffusion Models

Haomiao Ni,

Changhao Shi,

Kai Li,

Sharon X. Huang,

Martin Renqiang Min

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Ni_2023_CVPR, author = {Ni, Haomiao and Shi, Changhao and Li, Kai and Huang, Sharon X. and Min, Martin Renqiang}, title = {Conditional Image-to-Video Generation With Latent Flow Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {18444-18455} }

Virtual Sparse Convolution for Multimodal 3D Object Detection

Hai Wu,

Chenglu Wen,

Shaoshuai Shi,

Xin Li,

Cheng Wang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Wu_2023_CVPR, author = {Wu, Hai and Wen, Chenglu and Shi, Shaoshuai and Li, Xin and Wang, Cheng}, title = {Virtual Sparse Convolution for Multimodal 3D Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {21653-21662} }

DETR With Additional Global Aggregation for Cross-Domain Weakly Supervised Object Detection

Zongheng Tang,

Yifan Sun,

Si Liu,

Yi Yang

[pdf] [arXiv]

[bibtex]

@InProceedings{Tang_2023_CVPR, author = {Tang, Zongheng and Sun, Yifan and Liu, Si and Yang, Yi}, title = {DETR With Additional Global Aggregation for Cross-Domain Weakly Supervised Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11422-11432} }

Divide and Adapt: Active Domain Adaptation via Customized Learning

Duojun Huang,

Jichang Li,

Weikai Chen,

Junshi Huang,

Zhenhua Chai,

Guanbin Li

[pdf] [supp]

[bibtex]

@InProceedings{Huang_2023_CVPR, author = {Huang, Duojun and Li, Jichang and Chen, Weikai and Huang, Junshi and Chai, Zhenhua and Li, Guanbin}, title = {Divide and Adapt: Active Domain Adaptation via Customized Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7651-7660} }

Towards Universal Fake Image Detectors That Generalize Across Generative Models

Utkarsh Ojha,

Yuheng Li,

Yong Jae Lee

[pdf] [arXiv]

[bibtex]

@InProceedings{Ojha_2023_CVPR, author = {Ojha, Utkarsh and Li, Yuheng and Lee, Yong Jae}, title = {Towards Universal Fake Image Detectors That Generalize Across Generative Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {24480-24489} }

Towards Bridging the Performance Gaps of Joint Energy-Based Models

Xiulong Yang,

Qing Su,

Shihao Ji

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Yang_2023_CVPR, author = {Yang, Xiulong and Su, Qing and Ji, Shihao}, title = {Towards Bridging the Performance Gaps of Joint Energy-Based Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15732-15741} }

Learning Spatial-Temporal Implicit Neural Representations for Event-Guided Video Super-Resolution

Yunfan Lu,

Zipeng Wang,

Minjie Liu,

Hongjian Wang,

Lin Wang

[pdf] [arXiv]

[bibtex]

@InProceedings{Lu_2023_CVPR, author = {Lu, Yunfan and Wang, Zipeng and Liu, Minjie and Wang, Hongjian and Wang, Lin}, title = {Learning Spatial-Temporal Implicit Neural Representations for Event-Guided Video Super-Resolution}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1557-1567} }

Both Style and Distortion Matter: Dual-Path Unsupervised Domain Adaptation for Panoramic Semantic Segmentation

Xu Zheng,

Jinjing Zhu,

Yexin Liu,

Zidong Cao,

Chong Fu,

Lin Wang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Zheng_2023_CVPR, author = {Zheng, Xu and Zhu, Jinjing and Liu, Yexin and Cao, Zidong and Fu, Chong and Wang, Lin}, title = {Both Style and Distortion Matter: Dual-Path Unsupervised Domain Adaptation for Panoramic Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1285-1295} }

expOSE: Accurate Initialization-Free Projective Factorization Using Exponential Regularization

José Pedro Iglesias,

Amanda Nilsson,

Carl Olsson

[pdf] [supp]

[bibtex]

@InProceedings{Iglesias_2023_CVPR, author = {Iglesias, Jos\'e Pedro and Nilsson, Amanda and Olsson, Carl}, title = {expOSE: Accurate Initialization-Free Projective Factorization Using Exponential Regularization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8959-8968} }

OpenGait: Revisiting Gait Recognition Towards Better Practicality

Chao Fan,

Junhao Liang,

Chuanfu Shen,

Saihui Hou,

Yongzhen Huang,

Shiqi Yu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Fan_2023_CVPR, author = {Fan, Chao and Liang, Junhao and Shen, Chuanfu and Hou, Saihui and Huang, Yongzhen and Yu, Shiqi}, title = {OpenGait: Revisiting Gait Recognition Towards Better Practicality}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9707-9716} }

ALTO: Alternating Latent Topologies for Implicit 3D Reconstruction

Zhen Wang,

Shijie Zhou,

Jeong Joon Park,

Despoina Paschalidou,

Suya You,

Gordon Wetzstein,

Leonidas Guibas,

Achuta Kadambi

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Zhen and Zhou, Shijie and Park, Jeong Joon and Paschalidou, Despoina and You, Suya and Wetzstein, Gordon and Guibas, Leonidas and Kadambi, Achuta}, title = {ALTO: Alternating Latent Topologies for Implicit 3D Reconstruction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {259-270} }

Learning Debiased Representations via Conditional Attribute Interpolation

Yi-Kai Zhang,

Qi-Wei Wang,

De-Chuan Zhan,

Han-Jia Ye

[pdf] [supp]

[bibtex]

@InProceedings{Zhang_2023_CVPR, author = {Zhang, Yi-Kai and Wang, Qi-Wei and Zhan, De-Chuan and Ye, Han-Jia}, title = {Learning Debiased Representations via Conditional Attribute Interpolation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7599-7608} }

A Large-Scale Homography Benchmark

Daniel Barath,

Dmytro Mishkin,

Michal Polic,

Wolfgang Förstner,

Jiri Matas

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Barath_2023_CVPR, author = {Barath, Daniel and Mishkin, Dmytro and Polic, Michal and F\"orstner, Wolfgang and Matas, Jiri}, title = {A Large-Scale Homography Benchmark}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {21360-21370} }

Modeling Inter-Class and Intra-Class Constraints in Novel Class Discovery

Wenbin Li,

Zhichen Fan,

Jing Huo,

Yang Gao

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Li_2023_CVPR, author = {Li, Wenbin and Fan, Zhichen and Huo, Jing and Gao, Yang}, title = {Modeling Inter-Class and Intra-Class Constraints in Novel Class Discovery}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3449-3458} }

Weakly Supervised Video Emotion Detection and Prediction via Cross-Modal Temporal Erasing Network

Zhicheng Zhang,

Lijuan Wang,

Jufeng Yang

[pdf]

[bibtex]

@InProceedings{Zhang_2023_CVPR, author = {Zhang, Zhicheng and Wang, Lijuan and Yang, Jufeng}, title = {Weakly Supervised Video Emotion Detection and Prediction via Cross-Modal Temporal Erasing Network}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {18888-18897} }

Multiple Instance Learning via Iterative Self-Paced Supervised Contrastive Learning

Kangning Liu,

Weicheng Zhu,

Yiqiu Shen,

Sheng Liu,

Narges Razavian,

Krzysztof J. Geras,

Carlos Fernandez-Granda

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Liu_2023_CVPR, author = {Liu, Kangning and Zhu, Weicheng and Shen, Yiqiu and Liu, Sheng and Razavian, Narges and Geras, Krzysztof J. and Fernandez-Granda, Carlos}, title = {Multiple Instance Learning via Iterative Self-Paced Supervised Contrastive Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3355-3365} }

Consistent View Synthesis With Pose-Guided Diffusion Models

Hung-Yu Tseng,

Qinbo Li,

Changil Kim,

Suhib Alsisan,

Jia-Bin Huang,

Johannes Kopf

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Tseng_2023_CVPR, author = {Tseng, Hung-Yu and Li, Qinbo and Kim, Changil and Alsisan, Suhib and Huang, Jia-Bin and Kopf, Johannes}, title = {Consistent View Synthesis With Pose-Guided Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16773-16783} }

MSMDFusion: Fusing LiDAR and Camera at Multiple Scales With Multi-Depth Seeds for 3D Object Detection

Yang Jiao,

Zequn Jie,

Shaoxiang Chen,

Jingjing Chen,

Lin Ma,

Yu-Gang Jiang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Jiao_2023_CVPR, author = {Jiao, Yang and Jie, Zequn and Chen, Shaoxiang and Chen, Jingjing and Ma, Lin and Jiang, Yu-Gang}, title = {MSMDFusion: Fusing LiDAR and Camera at Multiple Scales With Multi-Depth Seeds for 3D Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {21643-21652} }

Dense-Localizing Audio-Visual Events in Untrimmed Videos: A Large-Scale Benchmark and Baseline

Tiantian Geng,

Teng Wang,

Jinming Duan,

Runmin Cong,

Feng Zheng

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Geng_2023_CVPR, author = {Geng, Tiantian and Wang, Teng and Duan, Jinming and Cong, Runmin and Zheng, Feng}, title = {Dense-Localizing Audio-Visual Events in Untrimmed Videos: A Large-Scale Benchmark and Baseline}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {22942-22951} }

Weak-Shot Object Detection Through Mutual Knowledge Transfer

Xuanyi Du,

Weitao Wan,

Chong Sun,

Chen Li

[pdf]

[bibtex]

@InProceedings{Du_2023_CVPR, author = {Du, Xuanyi and Wan, Weitao and Sun, Chong and Li, Chen}, title = {Weak-Shot Object Detection Through Mutual Knowledge Transfer}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {19671-19680} }

DATID-3D: Diversity-Preserved Domain Adaptation Using Text-to-Image Diffusion for 3D Generative Model

Gwanghyun Kim,

Se Young Chun

[pdf] [supp]

[bibtex]

@InProceedings{Kim_2023_CVPR, author = {Kim, Gwanghyun and Chun, Se Young}, title = {DATID-3D: Diversity-Preserved Domain Adaptation Using Text-to-Image Diffusion for 3D Generative Model}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14203-14213} }

CrowdCLIP: Unsupervised Crowd Counting via Vision-Language Model

Dingkang Liang,

Jiahao Xie,

Zhikang Zou,

Xiaoqing Ye,

Wei Xu,

Xiang Bai

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Liang_2023_CVPR, author = {Liang, Dingkang and Xie, Jiahao and Zou, Zhikang and Ye, Xiaoqing and Xu, Wei and Bai, Xiang}, title = {CrowdCLIP: Unsupervised Crowd Counting via Vision-Language Model}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2893-2903} }

Toward Stable, Interpretable, and Lightweight Hyperspectral Super-Resolution

Wen-jin Guo,

Weiying Xie,

Kai Jiang,

Yunsong Li,

Jie Lei,

Leyuan Fang

[pdf] [supp]

[bibtex]

@InProceedings{Guo_2023_CVPR, author = {Guo, Wen-jin and Xie, Weiying and Jiang, Kai and Li, Yunsong and Lei, Jie and Fang, Leyuan}, title = {Toward Stable, Interpretable, and Lightweight Hyperspectral Super-Resolution}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {22272-22281} }

Masked Auto-Encoders Meet Generative Adversarial Networks and Beyond

Zhengcong Fei,

Mingyuan Fan,

Li Zhu,

Junshi Huang,

Xiaoming Wei,

Xiaolin Wei

[pdf] [supp]

[bibtex]

@InProceedings{Fei_2023_CVPR, author = {Fei, Zhengcong and Fan, Mingyuan and Zhu, Li and Huang, Junshi and Wei, Xiaoming and Wei, Xiaolin}, title = {Masked Auto-Encoders Meet Generative Adversarial Networks and Beyond}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {24449-24459} }

iCLIP: Bridging Image Classification and Contrastive Language-Image Pre-Training for Visual Recognition

Yixuan Wei,

Yue Cao,

Zheng Zhang,

Houwen Peng,

Zhuliang Yao,

Zhenda Xie,

Han Hu,

Baining Guo

[pdf] [supp]

[bibtex]

@InProceedings{Wei_2023_CVPR, author = {Wei, Yixuan and Cao, Yue and Zhang, Zheng and Peng, Houwen and Yao, Zhuliang and Xie, Zhenda and Hu, Han and Guo, Baining}, title = {iCLIP: Bridging Image Classification and Contrastive Language-Image Pre-Training for Visual Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2776-2786} }

Learning Neural Volumetric Representations of Dynamic Humans in Minutes

Chen Geng,

Sida Peng,

Zhen Xu,

Hujun Bao,

Xiaowei Zhou

[pdf] [arXiv]

[bibtex]

@InProceedings{Geng_2023_CVPR, author = {Geng, Chen and Peng, Sida and Xu, Zhen and Bao, Hujun and Zhou, Xiaowei}, title = {Learning Neural Volumetric Representations of Dynamic Humans in Minutes}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8759-8770} }

Streaming Video Model

Yucheng Zhao,

Chong Luo,

Chuanxin Tang,

Dongdong Chen,

Noel Codella,

Zheng-Jun Zha

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Zhao_2023_CVPR, author = {Zhao, Yucheng and Luo, Chong and Tang, Chuanxin and Chen, Dongdong and Codella, Noel and Zha, Zheng-Jun}, title = {Streaming Video Model}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14602-14612} }

CapDet: Unifying Dense Captioning and Open-World Detection Pretraining

Yanxin Long,

Youpeng Wen,

Jianhua Han,

Hang Xu,

Pengzhen Ren,

Wei Zhang,

Shen Zhao,

Xiaodan Liang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Long_2023_CVPR, author = {Long, Yanxin and Wen, Youpeng and Han, Jianhua and Xu, Hang and Ren, Pengzhen and Zhang, Wei and Zhao, Shen and Liang, Xiaodan}, title = {CapDet: Unifying Dense Captioning and Open-World Detection Pretraining}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15233-15243} }

Bayesian Posterior Approximation With Stochastic Ensembles

Oleksandr Balabanov,

Bernhard Mehlig,

Hampus Linander

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Balabanov_2023_CVPR, author = {Balabanov, Oleksandr and Mehlig, Bernhard and Linander, Hampus}, title = {Bayesian Posterior Approximation With Stochastic Ensembles}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13701-13711} }

RILS: Masked Visual Reconstruction in Language Semantic Space

Shusheng Yang,

Yixiao Ge,

Kun Yi,

Dian Li,

Ying Shan,

Xiaohu Qie,

Xinggang Wang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Yang_2023_CVPR, author = {Yang, Shusheng and Ge, Yixiao and Yi, Kun and Li, Dian and Shan, Ying and Qie, Xiaohu and Wang, Xinggang}, title = {RILS: Masked Visual Reconstruction in Language Semantic Space}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {23304-23314} }

Decoupling Learning and Remembering: A Bilevel Memory Framework With Knowledge Projection for Task-Incremental Learning

Wenju Sun,

Qingyong Li,

Jing Zhang,

Wen Wang,

Yangli-ao Geng

[pdf] [supp]

[bibtex]

@InProceedings{Sun_2023_CVPR, author = {Sun, Wenju and Li, Qingyong and Zhang, Jing and Wang, Wen and Geng, Yangli-ao}, title = {Decoupling Learning and Remembering: A Bilevel Memory Framework With Knowledge Projection for Task-Incremental Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {20186-20195} }

R2Former: Unified Retrieval and Reranking Transformer for Place Recognition

Sijie Zhu,

Linjie Yang,

Chen Chen,

Mubarak Shah,

Xiaohui Shen,

Heng Wang

[pdf] [supp]

[bibtex]

@InProceedings{Zhu_2023_CVPR, author = {Zhu, Sijie and Yang, Linjie and Chen, Chen and Shah, Mubarak and Shen, Xiaohui and Wang, Heng}, title = {R2Former: Unified Retrieval and Reranking Transformer for Place Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {19370-19380} }

RepMode: Learning to Re-Parameterize Diverse Experts for Subcellular Structure Prediction

Donghao Zhou,

Chunbin Gu,

Junde Xu,

Furui Liu,

Qiong Wang,

Guangyong Chen,

Pheng-Ann Heng

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Zhou_2023_CVPR, author = {Zhou, Donghao and Gu, Chunbin and Xu, Junde and Liu, Furui and Wang, Qiong and Chen, Guangyong and Heng, Pheng-Ann}, title = {RepMode: Learning to Re-Parameterize Diverse Experts for Subcellular Structure Prediction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3312-3322} }

Symmetric Shape-Preserving Autoencoder for Unsupervised Real Scene Point Cloud Completion

Changfeng Ma,

Yinuo Chen,

Pengxiao Guo,

Jie Guo,

Chongjun Wang,

Yanwen Guo

[pdf] [supp]

[bibtex]

@InProceedings{Ma_2023_CVPR, author = {Ma, Changfeng and Chen, Yinuo and Guo, Pengxiao and Guo, Jie and Wang, Chongjun and Guo, Yanwen}, title = {Symmetric Shape-Preserving Autoencoder for Unsupervised Real Scene Point Cloud Completion}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13560-13569} }

Modality-Agnostic Debiasing for Single Domain Generalization

Sanqing Qu,

Yingwei Pan,

Guang Chen,

Ting Yao,

Changjun Jiang,

Tao Mei

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Qu_2023_CVPR, author = {Qu, Sanqing and Pan, Yingwei and Chen, Guang and Yao, Ting and Jiang, Changjun and Mei, Tao}, title = {Modality-Agnostic Debiasing for Single Domain Generalization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {24142-24151} }

Difficulty-Based Sampling for Debiased Contrastive Representation Learning

Taeuk Jang,

Xiaoqian Wang

[pdf] [supp]

[bibtex]

@InProceedings{Jang_2023_CVPR, author = {Jang, Taeuk and Wang, Xiaoqian}, title = {Difficulty-Based Sampling for Debiased Contrastive Representation Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {24039-24048} }

Masked Motion Encoding for Self-Supervised Video Representation Learning

Xinyu Sun,

Peihao Chen,

Liangwei Chen,

Changhao Li,

Thomas H. Li,

Mingkui Tan,

Chuang Gan

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Sun_2023_CVPR, author = {Sun, Xinyu and Chen, Peihao and Chen, Liangwei and Li, Changhao and Li, Thomas H. and Tan, Mingkui and Gan, Chuang}, title = {Masked Motion Encoding for Self-Supervised Video Representation Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2235-2245} }

CompletionFormer: Depth Completion With Convolutions and Vision Transformers

Youmin Zhang,

Xianda Guo,

Matteo Poggi,

Zheng Zhu,

Guan Huang,

Stefano Mattoccia

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Zhang_2023_CVPR, author = {Zhang, Youmin and Guo, Xianda and Poggi, Matteo and Zhu, Zheng and Huang, Guan and Mattoccia, Stefano}, title = {CompletionFormer: Depth Completion With Convolutions and Vision Transformers}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {18527-18536} }

Comprehensive and Delicate: An Efficient Transformer for Image Restoration

Haiyu Zhao,

Yuanbiao Gou,

Boyun Li,

Dezhong Peng,

Jiancheng Lv,

Xi Peng

[pdf] [supp]

[bibtex]

@InProceedings{Zhao_2023_CVPR, author = {Zhao, Haiyu and Gou, Yuanbiao and Li, Boyun and Peng, Dezhong and Lv, Jiancheng and Peng, Xi}, title = {Comprehensive and Delicate: An Efficient Transformer for Image Restoration}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14122-14132} }

Zero-Shot Model Diagnosis

Jinqi Luo,

Zhaoning Wang,

Chen Henry Wu,

Dong Huang,

Fernando De la Torre

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Luo_2023_CVPR, author = {Luo, Jinqi and Wang, Zhaoning and Wu, Chen Henry and Huang, Dong and De la Torre, Fernando}, title = {Zero-Shot Model Diagnosis}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11631-11640} }

Improving Visual Grounding by Encouraging Consistent Gradient-Based Explanations

Ziyan Yang,

Kushal Kafle,

Franck Dernoncourt,

Vicente Ordonez

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Yang_2023_CVPR, author = {Yang, Ziyan and Kafle, Kushal and Dernoncourt, Franck and Ordonez, Vicente}, title = {Improving Visual Grounding by Encouraging Consistent Gradient-Based Explanations}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {19165-19174} }

Physically Realizable Natural-Looking Clothing Textures Evade Person Detectors via 3D Modeling

Zhanhao Hu,

Wenda Chu,

Xiaopei Zhu,

Hui Zhang,

Bo Zhang,

Xiaolin Hu

[pdf] [supp]

[bibtex]

@InProceedings{Hu_2023_CVPR, author = {Hu, Zhanhao and Chu, Wenda and Zhu, Xiaopei and Zhang, Hui and Zhang, Bo and Hu, Xiaolin}, title = {Physically Realizable Natural-Looking Clothing Textures Evade Person Detectors via 3D Modeling}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16975-16984} }

ShadowDiffusion: When Degradation Prior Meets Diffusion Model for Shadow Removal

Lanqing Guo,

Chong Wang,

Wenhan Yang,

Siyu Huang,

Yufei Wang,

Hanspeter Pfister,

Bihan Wen

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Guo_2023_CVPR, author = {Guo, Lanqing and Wang, Chong and Yang, Wenhan and Huang, Siyu and Wang, Yufei and Pfister, Hanspeter and Wen, Bihan}, title = {ShadowDiffusion: When Degradation Prior Meets Diffusion Model for Shadow Removal}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14049-14058} }

FFHQ-UV: Normalized Facial UV-Texture Dataset for 3D Face Reconstruction

Haoran Bai,

Di Kang,

Haoxian Zhang,

Jinshan Pan,

Linchao Bao

[pdf] [supp]

[bibtex]

@InProceedings{Bai_2023_CVPR, author = {Bai, Haoran and Kang, Di and Zhang, Haoxian and Pan, Jinshan and Bao, Linchao}, title = {FFHQ-UV: Normalized Facial UV-Texture Dataset for 3D Face Reconstruction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {362-371} }

Pruning Parameterization With Bi-Level Optimization for Efficient Semantic Segmentation on the Edge

Changdi Yang,

Pu Zhao,

Yanyu Li,

Wei Niu,

Jiexiong Guan,

Hao Tang,

Minghai Qin,

Bin Ren,

Xue Lin,

Yanzhi Wang

[pdf] [supp]

[bibtex]

@InProceedings{Yang_2023_CVPR, author = {Yang, Changdi and Zhao, Pu and Li, Yanyu and Niu, Wei and Guan, Jiexiong and Tang, Hao and Qin, Minghai and Ren, Bin and Lin, Xue and Wang, Yanzhi}, title = {Pruning Parameterization With Bi-Level Optimization for Efficient Semantic Segmentation on the Edge}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15402-15412} }

Camouflaged Object Detection With Feature Decomposition and Edge Reconstruction

Chunming He,

Kai Li,

Yachao Zhang,

Longxiang Tang,

Yulun Zhang,

Zhenhua Guo,

Xiu Li

[pdf] [supp]

[bibtex]

@InProceedings{He_2023_CVPR, author = {He, Chunming and Li, Kai and Zhang, Yachao and Tang, Longxiang and Zhang, Yulun and Guo, Zhenhua and Li, Xiu}, title = {Camouflaged Object Detection With Feature Decomposition and Edge Reconstruction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {22046-22055} }

ALOFT: A Lightweight MLP-Like Architecture With Dynamic Low-Frequency Transform for Domain Generalization

Jintao Guo,

Na Wang,

Lei Qi,

Yinghuan Shi

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Guo_2023_CVPR, author = {Guo, Jintao and Wang, Na and Qi, Lei and Shi, Yinghuan}, title = {ALOFT: A Lightweight MLP-Like Architecture With Dynamic Low-Frequency Transform for Domain Generalization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {24132-24141} }

NLOST: Non-Line-of-Sight Imaging With Transformer

Yue Li,

Jiayong Peng,

Juntian Ye,

Yueyi Zhang,

Feihu Xu,

Zhiwei Xiong

[pdf] [supp]

[bibtex]

@InProceedings{Li_2023_CVPR, author = {Li, Yue and Peng, Jiayong and Ye, Juntian and Zhang, Yueyi and Xu, Feihu and Xiong, Zhiwei}, title = {NLOST: Non-Line-of-Sight Imaging With Transformer}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13313-13322} }

Text-Visual Prompting for Efficient 2D Temporal Video Grounding

Yimeng Zhang,

Xin Chen,

Jinghan Jia,

Sijia Liu,

Ke Ding

[pdf] [arXiv]

[bibtex]

@InProceedings{Zhang_2023_CVPR, author = {Zhang, Yimeng and Chen, Xin and Jia, Jinghan and Liu, Sijia and Ding, Ke}, title = {Text-Visual Prompting for Efficient 2D Temporal Video Grounding}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14794-14804} }

SurfelNeRF: Neural Surfel Radiance Fields for Online Photorealistic Reconstruction of Indoor Scenes

Yiming Gao,

Yan-Pei Cao,

Ying Shan

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Gao_2023_CVPR, author = {Gao, Yiming and Cao, Yan-Pei and Shan, Ying}, title = {SurfelNeRF: Neural Surfel Radiance Fields for Online Photorealistic Reconstruction of Indoor Scenes}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {108-118} }

Learning Visual Representations via Language-Guided Sampling

Mohamed El Banani,

Karan Desai,

Justin Johnson

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{El_Banani_2023_CVPR, author = {El Banani, Mohamed and Desai, Karan and Johnson, Justin}, title = {Learning Visual Representations via Language-Guided Sampling}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {19208-19220} }

Logical Implications for Visual Question Answering Consistency

Sergio Tascon-Morales,

Pablo Márquez-Neila,

Raphael Sznitman

[pdf] [supp]

[bibtex]

@InProceedings{Tascon-Morales_2023_CVPR, author = {Tascon-Morales, Sergio and M\'arquez-Neila, Pablo and Sznitman, Raphael}, title = {Logical Implications for Visual Question Answering Consistency}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6725-6735} }

NeUDF: Leaning Neural Unsigned Distance Fields With Volume Rendering

Yu-Tao Liu,

Li Wang,

Jie Yang,

Weikai Chen,

Xiaoxu Meng,

Bo Yang,

Lin Gao

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Liu_2023_CVPR, author = {Liu, Yu-Tao and Wang, Li and Yang, Jie and Chen, Weikai and Meng, Xiaoxu and Yang, Bo and Gao, Lin}, title = {NeUDF: Leaning Neural Unsigned Distance Fields With Volume Rendering}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {237-247} }

Master: Meta Style Transformer for Controllable Zero-Shot and Few-Shot Artistic Style Transfer

Hao Tang,

Songhua Liu,

Tianwei Lin,

Shaoli Huang,

Fu Li,

Dongliang He,

Xinchao Wang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Tang_2023_CVPR, author = {Tang, Hao and Liu, Songhua and Lin, Tianwei and Huang, Shaoli and Li, Fu and He, Dongliang and Wang, Xinchao}, title = {Master: Meta Style Transformer for Controllable Zero-Shot and Few-Shot Artistic Style Transfer}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {18329-18338} }

Affordance Diffusion: Synthesizing Hand-Object Interactions

Yufei Ye,

Xueting Li,

Abhinav Gupta,

Shalini De Mello,

Stan Birchfield,

Jiaming Song,

Shubham Tulsiani,

Sifei Liu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Ye_2023_CVPR, author = {Ye, Yufei and Li, Xueting and Gupta, Abhinav and De Mello, Shalini and Birchfield, Stan and Song, Jiaming and Tulsiani, Shubham and Liu, Sifei}, title = {Affordance Diffusion: Synthesizing Hand-Object Interactions}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {22479-22489} }

NEF: Neural Edge Fields for 3D Parametric Curve Reconstruction From Multi-View Images

Yunfan Ye,

Renjiao Yi,

Zhirui Gao,

Chenyang Zhu,

Zhiping Cai,

Kai Xu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Ye_2023_CVPR, author = {Ye, Yunfan and Yi, Renjiao and Gao, Zhirui and Zhu, Chenyang and Cai, Zhiping and Xu, Kai}, title = {NEF: Neural Edge Fields for 3D Parametric Curve Reconstruction From Multi-View Images}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8486-8495} }

Geometric Visual Similarity Learning in 3D Medical Image Self-Supervised Pre-Training

Yuting He,

Guanyu Yang,

Rongjun Ge,

Yang Chen,

Jean-Louis Coatrieux,

Boyu Wang,

Shuo Li

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{He_2023_CVPR, author = {He, Yuting and Yang, Guanyu and Ge, Rongjun and Chen, Yang and Coatrieux, Jean-Louis and Wang, Boyu and Li, Shuo}, title = {Geometric Visual Similarity Learning in 3D Medical Image Self-Supervised Pre-Training}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9538-9547} }

Towards Artistic Image Aesthetics Assessment: A Large-Scale Dataset and a New Method

Ran Yi,

Haoyuan Tian,

Zhihao Gu,

Yu-Kun Lai,

Paul L. Rosin

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Yi_2023_CVPR, author = {Yi, Ran and Tian, Haoyuan and Gu, Zhihao and Lai, Yu-Kun and Rosin, Paul L.}, title = {Towards Artistic Image Aesthetics Assessment: A Large-Scale Dataset and a New Method}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {22388-22397} }

MM-3DScene: 3D Scene Understanding by Customizing Masked Modeling With Informative-Preserved Reconstruction and Self-Distilled Consistency

Mingye Xu,

Mutian Xu,

Tong He,

Wanli Ouyang,

Yali Wang,

Xiaoguang Han,

Yu Qiao

[pdf] [supp]

[bibtex]

@InProceedings{Xu_2023_CVPR, author = {Xu, Mingye and Xu, Mutian and He, Tong and Ouyang, Wanli and Wang, Yali and Han, Xiaoguang and Qiao, Yu}, title = {MM-3DScene: 3D Scene Understanding by Customizing Masked Modeling With Informative-Preserved Reconstruction and Self-Distilled Consistency}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4380-4390} }

Plug-and-Play Diffusion Features for Text-Driven Image-to-Image Translation

Narek Tumanyan,

Michal Geyer,

Shai Bagon,

Tali Dekel

[pdf] [arXiv]

[bibtex]

@InProceedings{Tumanyan_2023_CVPR, author = {Tumanyan, Narek and Geyer, Michal and Bagon, Shai and Dekel, Tali}, title = {Plug-and-Play Diffusion Features for Text-Driven Image-to-Image Translation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1921-1930} }

Inverting the Imaging Process by Learning an Implicit Camera Model

Xin Huang,

Qi Zhang,

Ying Feng,

Hongdong Li,

Qing Wang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Huang_2023_CVPR, author = {Huang, Xin and Zhang, Qi and Feng, Ying and Li, Hongdong and Wang, Qing}, title = {Inverting the Imaging Process by Learning an Implicit Camera Model}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {21456-21465} }

Fast Contextual Scene Graph Generation With Unbiased Context Augmentation

Tianlei Jin,

Fangtai Guo,

Qiwei Meng,

Shiqiang Zhu,

Xiangming Xi,

Wen Wang,

Zonghao Mu,

Wei Song

[pdf]

[bibtex]

@InProceedings{Jin_2023_CVPR, author = {Jin, Tianlei and Guo, Fangtai and Meng, Qiwei and Zhu, Shiqiang and Xi, Xiangming and Wang, Wen and Mu, Zonghao and Song, Wei}, title = {Fast Contextual Scene Graph Generation With Unbiased Context Augmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6302-6311} }

Less Is More: Reducing Task and Model Complexity for 3D Point Cloud Semantic Segmentation

Li Li,

Hubert P. H. Shum,

Toby P. Breckon

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Li_2023_CVPR, author = {Li, Li and Shum, Hubert P. H. and Breckon, Toby P.}, title = {Less Is More: Reducing Task and Model Complexity for 3D Point Cloud Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9361-9371} }

Re-Thinking Federated Active Learning Based on Inter-Class Diversity

SangMook Kim,

Sangmin Bae,

Hwanjun Song,

Se-Young Yun

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Kim_2023_CVPR, author = {Kim, SangMook and Bae, Sangmin and Song, Hwanjun and Yun, Se-Young}, title = {Re-Thinking Federated Active Learning Based on Inter-Class Diversity}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3944-3953} }

Enhanced Training of Query-Based Object Detection via Selective Query Recollection

Fangyi Chen,

Han Zhang,

Kai Hu,

Yu-Kai Huang,

Chenchen Zhu,

Marios Savvides

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Chen_2023_CVPR, author = {Chen, Fangyi and Zhang, Han and Hu, Kai and Huang, Yu-Kai and Zhu, Chenchen and Savvides, Marios}, title = {Enhanced Training of Query-Based Object Detection via Selective Query Recollection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {23756-23765} }

AdaMAE: Adaptive Masking for Efficient Spatiotemporal Learning With Masked Autoencoders

Wele Gedara Chaminda Bandara,

Naman Patel,

Ali Gholami,

Mehdi Nikkhah,

Motilal Agrawal,

Vishal M. Patel

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Bandara_2023_CVPR, author = {Bandara, Wele Gedara Chaminda and Patel, Naman and Gholami, Ali and Nikkhah, Mehdi and Agrawal, Motilal and Patel, Vishal M.}, title = {AdaMAE: Adaptive Masking for Efficient Spatiotemporal Learning With Masked Autoencoders}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14507-14517} }

Detecting Human-Object Contact in Images

Yixin Chen,

Sai Kumar Dwivedi,

Michael J. Black,

Dimitrios Tzionas

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Chen_2023_CVPR, author = {Chen, Yixin and Dwivedi, Sai Kumar and Black, Michael J. and Tzionas, Dimitrios}, title = {Detecting Human-Object Contact in Images}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {17100-17110} }

PointClustering: Unsupervised Point Cloud Pre-Training Using Transformation Invariance in Clustering

Fuchen Long,

Ting Yao,

Zhaofan Qiu,

Lusong Li,

Tao Mei

[pdf]

[bibtex]

@InProceedings{Long_2023_CVPR, author = {Long, Fuchen and Yao, Ting and Qiu, Zhaofan and Li, Lusong and Mei, Tao}, title = {PointClustering: Unsupervised Point Cloud Pre-Training Using Transformation Invariance in Clustering}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {21824-21834} }

CiaoSR: Continuous Implicit Attention-in-Attention Network for Arbitrary-Scale Image Super-Resolution

Jiezhang Cao,

Qin Wang,

Yongqin Xian,

Yawei Li,

Bingbing Ni,

Zhiming Pi,

Kai Zhang,

Yulun Zhang,

Radu Timofte,

Luc Van Gool

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Cao_2023_CVPR, author = {Cao, Jiezhang and Wang, Qin and Xian, Yongqin and Li, Yawei and Ni, Bingbing and Pi, Zhiming and Zhang, Kai and Zhang, Yulun and Timofte, Radu and Van Gool, Luc}, title = {CiaoSR: Continuous Implicit Attention-in-Attention Network for Arbitrary-Scale Image Super-Resolution}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1796-1807} }

Out-of-Distributed Semantic Pruning for Robust Semi-Supervised Learning

Yu Wang,

Pengchong Qiao,

Chang Liu,

Guoli Song,

Xiawu Zheng,

Jie Chen

[pdf] [supp]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Yu and Qiao, Pengchong and Liu, Chang and Song, Guoli and Zheng, Xiawu and Chen, Jie}, title = {Out-of-Distributed Semantic Pruning for Robust Semi-Supervised Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {23849-23858} }

The Best Defense Is a Good Offense: Adversarial Augmentation Against Adversarial Attacks

Iuri Frosio,

Jan Kautz

[pdf] [supp]

[bibtex]

@InProceedings{Frosio_2023_CVPR, author = {Frosio, Iuri and Kautz, Jan}, title = {The Best Defense Is a Good Offense: Adversarial Augmentation Against Adversarial Attacks}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4067-4076} }

GaitGCI: Generative Counterfactual Intervention for Gait Recognition

Huanzhang Dou,

Pengyi Zhang,

Wei Su,

Yunlong Yu,

Yining Lin,

Xi Li

[pdf] [supp]

[bibtex]

@InProceedings{Dou_2023_CVPR, author = {Dou, Huanzhang and Zhang, Pengyi and Su, Wei and Yu, Yunlong and Lin, Yining and Li, Xi}, title = {GaitGCI: Generative Counterfactual Intervention for Gait Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5578-5588} }

Constructing Deep Spiking Neural Networks From Artificial Neural Networks With Knowledge Distillation

Qi Xu,

Yaxin Li,

Jiangrong Shen,

Jian K. Liu,

Huajin Tang,

Gang Pan

[pdf] [arXiv]

[bibtex]

@InProceedings{Xu_2023_CVPR, author = {Xu, Qi and Li, Yaxin and Shen, Jiangrong and Liu, Jian K. and Tang, Huajin and Pan, Gang}, title = {Constructing Deep Spiking Neural Networks From Artificial Neural Networks With Knowledge Distillation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7886-7895} }

Understanding and Improving Visual Prompting: A Label-Mapping Perspective

Aochuan Chen,

Yuguang Yao,

Pin-Yu Chen,

Yihua Zhang,

Sijia Liu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Chen_2023_CVPR, author = {Chen, Aochuan and Yao, Yuguang and Chen, Pin-Yu and Zhang, Yihua and Liu, Sijia}, title = {Understanding and Improving Visual Prompting: A Label-Mapping Perspective}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {19133-19143} }

Directional Connectivity-Based Segmentation of Medical Images

Ziyun Yang,

Sina Farsiu

[pdf] [arXiv]

[bibtex]

@InProceedings{Yang_2023_CVPR, author = {Yang, Ziyun and Farsiu, Sina}, title = {Directional Connectivity-Based Segmentation of Medical Images}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11525-11535} }

Towards Flexible Multi-Modal Document Models

Naoto Inoue,

Kotaro Kikuchi,

Edgar Simo-Serra,

Mayu Otani,

Kota Yamaguchi

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Inoue_2023_CVPR, author = {Inoue, Naoto and Kikuchi, Kotaro and Simo-Serra, Edgar and Otani, Mayu and Yamaguchi, Kota}, title = {Towards Flexible Multi-Modal Document Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14287-14296} }

DegAE: A New Pretraining Paradigm for Low-Level Vision

Yihao Liu,

Jingwen He,

Jinjin Gu,

Xiangtao Kong,

Yu Qiao,

Chao Dong

[pdf] [supp]

[bibtex]

@InProceedings{Liu_2023_CVPR, author = {Liu, Yihao and He, Jingwen and Gu, Jinjin and Kong, Xiangtao and Qiao, Yu and Dong, Chao}, title = {DegAE: A New Pretraining Paradigm for Low-Level Vision}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {23292-23303} }

The Differentiable Lens: Compound Lens Search Over Glass Surfaces and Materials for Object Detection

Geoffroi Côté,

Fahim Mannan,

Simon Thibault,

Jean-François Lalonde,

Felix Heide

[pdf] [supp]

[bibtex]

@InProceedings{Cote_2023_CVPR, author = {C\^ot\'e, Geoffroi and Mannan, Fahim and Thibault, Simon and Lalonde, Jean-Fran\c{c}ois and Heide, Felix}, title = {The Differentiable Lens: Compound Lens Search Over Glass Surfaces and Materials for Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {20803-20812} }

Adversarially Masking Synthetic To Mimic Real: Adaptive Noise Injection for Point Cloud Segmentation Adaptation

Guangrui Li,

Guoliang Kang,

Xiaohan Wang,

Yunchao Wei,

Yi Yang

[pdf] [supp]

[bibtex]

@InProceedings{Li_2023_CVPR, author = {Li, Guangrui and Kang, Guoliang and Wang, Xiaohan and Wei, Yunchao and Yang, Yi}, title = {Adversarially Masking Synthetic To Mimic Real: Adaptive Noise Injection for Point Cloud Segmentation Adaptation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {20464-20474} }

KERM: Knowledge Enhanced Reasoning for Vision-and-Language Navigation

Xiangyang Li,

Zihan Wang,

Jiahao Yang,

Yaowei Wang,

Shuqiang Jiang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Li_2023_CVPR, author = {Li, Xiangyang and Wang, Zihan and Yang, Jiahao and Wang, Yaowei and Jiang, Shuqiang}, title = {KERM: Knowledge Enhanced Reasoning for Vision-and-Language Navigation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2583-2592} }

LiDAR-in-the-Loop Hyperparameter Optimization

Félix Goudreault,

Dominik Scheuble,

Mario Bijelic,

Nicolas Robidoux,

Felix Heide

[pdf] [supp]

[bibtex]

@InProceedings{Goudreault_2023_CVPR, author = {Goudreault, F\'elix and Scheuble, Dominik and Bijelic, Mario and Robidoux, Nicolas and Heide, Felix}, title = {LiDAR-in-the-Loop Hyperparameter Optimization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13404-13414} }

Local 3D Editing via 3D Distillation of CLIP Knowledge

Junha Hyung,

Sungwon Hwang,

Daejin Kim,

Hyunji Lee,

Jaegul Choo

[pdf] [supp]

[bibtex]

@InProceedings{Hyung_2023_CVPR, author = {Hyung, Junha and Hwang, Sungwon and Kim, Daejin and Lee, Hyunji and Choo, Jaegul}, title = {Local 3D Editing via 3D Distillation of CLIP Knowledge}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12674-12684} }

Abstract Visual Reasoning: An Algebraic Approach for Solving Raven's Progressive Matrices

Jingyi Xu,

Tushar Vaidya,

Yufei Wu,

Saket Chandra,

Zhangsheng Lai,

Kai Fong Ernest Chong

[pdf] [supp]

[bibtex]

@InProceedings{Xu_2023_CVPR, author = {Xu, Jingyi and Vaidya, Tushar and Wu, Yufei and Chandra, Saket and Lai, Zhangsheng and Chong, Kai Fong Ernest}, title = {Abstract Visual Reasoning: An Algebraic Approach for Solving Raven's Progressive Matrices}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6715-6724} }

3D-Aware Conditional Image Synthesis

Kangle Deng,

Gengshan Yang,

Deva Ramanan,

Jun-Yan Zhu

[pdf] [arXiv]

[bibtex]

@InProceedings{Deng_2023_CVPR, author = {Deng, Kangle and Yang, Gengshan and Ramanan, Deva and Zhu, Jun-Yan}, title = {3D-Aware Conditional Image Synthesis}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4434-4445} }

Understanding Deep Generative Models With Generalized Empirical Likelihoods

Suman Ravuri,

Mélanie Rey,

Shakir Mohamed,

Marc Peter Deisenroth

[pdf] [supp]

[bibtex]

@InProceedings{Ravuri_2023_CVPR, author = {Ravuri, Suman and Rey, M\'elanie and Mohamed, Shakir and Deisenroth, Marc Peter}, title = {Understanding Deep Generative Models With Generalized Empirical Likelihoods}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {24395-24405} }

ABCD: Arbitrary Bitwise Coefficient for De-Quantization

Woo Kyoung Han,

Byeonghun Lee,

Sang Hyun Park,

Kyong Hwan Jin

[pdf] [supp]

[bibtex]

@InProceedings{Han_2023_CVPR, author = {Han, Woo Kyoung and Lee, Byeonghun and Park, Sang Hyun and Jin, Kyong Hwan}, title = {ABCD: Arbitrary Bitwise Coefficient for De-Quantization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5876-5885} }

Event-Based Blurry Frame Interpolation Under Blind Exposure

Wenming Weng,

Yueyi Zhang,

Zhiwei Xiong

[pdf] [supp]

[bibtex]

@InProceedings{Weng_2023_CVPR, author = {Weng, Wenming and Zhang, Yueyi and Xiong, Zhiwei}, title = {Event-Based Blurry Frame Interpolation Under Blind Exposure}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1588-1598} }

Human Body Shape Completion With Implicit Shape and Flow Learning

Boyao Zhou,

Di Meng,

Jean-Sébastien Franco,

Edmond Boyer

[pdf] [supp]

[bibtex]

@InProceedings{Zhou_2023_CVPR, author = {Zhou, Boyao and Meng, Di and Franco, Jean-S\'ebastien and Boyer, Edmond}, title = {Human Body Shape Completion With Implicit Shape and Flow Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12901-12911} }

Spider GAN: Leveraging Friendly Neighbors To Accelerate GAN Training

Siddarth Asokan,

Chandra Sekhar Seelamantula

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Asokan_2023_CVPR, author = {Asokan, Siddarth and Seelamantula, Chandra Sekhar}, title = {Spider GAN: Leveraging Friendly Neighbors To Accelerate GAN Training}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3883-3893} }

CLIPPING: Distilling CLIP-Based Models With a Student Base for Video-Language Retrieval

Renjing Pei,

Jianzhuang Liu,

Weimian Li,

Bin Shao,

Songcen Xu,

Peng Dai,

Juwei Lu,

Youliang Yan

[pdf] [supp]

[bibtex]

@InProceedings{Pei_2023_CVPR, author = {Pei, Renjing and Liu, Jianzhuang and Li, Weimian and Shao, Bin and Xu, Songcen and Dai, Peng and Lu, Juwei and Yan, Youliang}, title = {CLIPPING: Distilling CLIP-Based Models With a Student Base for Video-Language Retrieval}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {18983-18992} }

ScaleDet: A Scalable Multi-Dataset Object Detector

Yanbei Chen,

Manchen Wang,

Abhay Mittal,

Zhenlin Xu,

Paolo Favaro,

Joseph Tighe,

Davide Modolo

[pdf] [supp]

[bibtex]

@InProceedings{Chen_2023_CVPR, author = {Chen, Yanbei and Wang, Manchen and Mittal, Abhay and Xu, Zhenlin and Favaro, Paolo and Tighe, Joseph and Modolo, Davide}, title = {ScaleDet: A Scalable Multi-Dataset Object Detector}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7288-7297} }

Unbiased Multiple Instance Learning for Weakly Supervised Video Anomaly Detection

Hui Lv,

Zhongqi Yue,

Qianru Sun,

Bin Luo,

Zhen Cui,

Hanwang Zhang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Lv_2023_CVPR, author = {Lv, Hui and Yue, Zhongqi and Sun, Qianru and Luo, Bin and Cui, Zhen and Zhang, Hanwang}, title = {Unbiased Multiple Instance Learning for Weakly Supervised Video Anomaly Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8022-8031} }

BEVHeight: A Robust Framework for Vision-Based Roadside 3D Object Detection

Lei Yang,

Kaicheng Yu,

Tao Tang,

Jun Li,

Kun Yuan,

Li Wang,

Xinyu Zhang,

Peng Chen

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Yang_2023_CVPR, author = {Yang, Lei and Yu, Kaicheng and Tang, Tao and Li, Jun and Yuan, Kun and Wang, Li and Zhang, Xinyu and Chen, Peng}, title = {BEVHeight: A Robust Framework for Vision-Based Roadside 3D Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {21611-21620} }

Towards Unbiased Volume Rendering of Neural Implicit Surfaces With Geometry Priors

Yongqiang Zhang,

Zhipeng Hu,

Haoqian Wu,

Minda Zhao,

Lincheng Li,

Zhengxia Zou,

Changjie Fan

[pdf] [supp]

[bibtex]

@InProceedings{Zhang_2023_CVPR, author = {Zhang, Yongqiang and Hu, Zhipeng and Wu, Haoqian and Zhao, Minda and Li, Lincheng and Zou, Zhengxia and Fan, Changjie}, title = {Towards Unbiased Volume Rendering of Neural Implicit Surfaces With Geometry Priors}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4359-4368} }

Modular Memorability: Tiered Representations for Video Memorability Prediction

Théo Dumont,

Juan Segundo Hevia,

Camilo L. Fosco

[pdf] [supp]

[bibtex]

@InProceedings{Dumont_2023_CVPR, author = {Dumont, Th\'eo and Hevia, Juan Segundo and Fosco, Camilo L.}, title = {Modular Memorability: Tiered Representations for Video Memorability Prediction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10751-10760} }

Weakly-Supervised Domain Adaptive Semantic Segmentation With Prototypical Contrastive Learning

Anurag Das,

Yongqin Xian,

Dengxin Dai,

Bernt Schiele

[pdf] [supp]

[bibtex]

@InProceedings{Das_2023_CVPR, author = {Das, Anurag and Xian, Yongqin and Dai, Dengxin and Schiele, Bernt}, title = {Weakly-Supervised Domain Adaptive Semantic Segmentation With Prototypical Contrastive Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15434-15443} }

Language-Guided Music Recommendation for Video via Prompt Analogies

Daniel McKee,

Justin Salamon,

Josef Sivic,

Bryan Russell

[pdf] [supp]

[bibtex]

@InProceedings{McKee_2023_CVPR, author = {McKee, Daniel and Salamon, Justin and Sivic, Josef and Russell, Bryan}, title = {Language-Guided Music Recommendation for Video via Prompt Analogies}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14784-14793} }

Re2TAL: Rewiring Pretrained Video Backbones for Reversible Temporal Action Localization

Chen Zhao,

Shuming Liu,

Karttikeya Mangalam,

Bernard Ghanem

[pdf] [supp]

[bibtex]

@InProceedings{Zhao_2023_CVPR, author = {Zhao, Chen and Liu, Shuming and Mangalam, Karttikeya and Ghanem, Bernard}, title = {Re2TAL: Rewiring Pretrained Video Backbones for Reversible Temporal Action Localization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10637-10647} }

Neuro-Modulated Hebbian Learning for Fully Test-Time Adaptation

Yushun Tang,

Ce Zhang,

Heng Xu,

Shuoshuo Chen,

Jie Cheng,

Luziwei Leng,

Qinghai Guo,

Zhihai He

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Tang_2023_CVPR, author = {Tang, Yushun and Zhang, Ce and Xu, Heng and Chen, Shuoshuo and Cheng, Jie and Leng, Luziwei and Guo, Qinghai and He, Zhihai}, title = {Neuro-Modulated Hebbian Learning for Fully Test-Time Adaptation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3728-3738} }

NeRFLight: Fast and Light Neural Radiance Fields Using a Shared Feature Grid

Fernando Rivas-Manzaneque,

Jorge Sierra-Acosta,

Adrian Penate-Sanchez,

Francesc Moreno-Noguer,

Angela Ribeiro

[pdf] [supp]

[bibtex]

@InProceedings{Rivas-Manzaneque_2023_CVPR, author = {Rivas-Manzaneque, Fernando and Sierra-Acosta, Jorge and Penate-Sanchez, Adrian and Moreno-Noguer, Francesc and Ribeiro, Angela}, title = {NeRFLight: Fast and Light Neural Radiance Fields Using a Shared Feature Grid}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12417-12427} }

MVImgNet: A Large-Scale Dataset of Multi-View Images

Xianggang Yu,

Mutian Xu,

Yidan Zhang,

Haolin Liu,

Chongjie Ye,

Yushuang Wu,

Zizheng Yan,

Chenming Zhu,

Zhangyang Xiong,

Tianyou Liang,

Guanying Chen,

Shuguang Cui,

Xiaoguang Han

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Yu_2023_CVPR, author = {Yu, Xianggang and Xu, Mutian and Zhang, Yidan and Liu, Haolin and Ye, Chongjie and Wu, Yushuang and Yan, Zizheng and Zhu, Chenming and Xiong, Zhangyang and Liang, Tianyou and Chen, Guanying and Cui, Shuguang and Han, Xiaoguang}, title = {MVImgNet: A Large-Scale Dataset of Multi-View Images}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9150-9161} }

LASP: Text-to-Text Optimization for Language-Aware Soft Prompting of Vision & Language Models

Adrian Bulat,

Georgios Tzimiropoulos

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Bulat_2023_CVPR, author = {Bulat, Adrian and Tzimiropoulos, Georgios}, title = {LASP: Text-to-Text Optimization for Language-Aware Soft Prompting of Vision \& Language Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {23232-23241} }

Implicit Identity Leakage: The Stumbling Block to Improving Deepfake Detection Generalization

Shichao Dong,

Jin Wang,

Renhe Ji,

Jiajun Liang,

Haoqiang Fan,

Zheng Ge

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Dong_2023_CVPR, author = {Dong, Shichao and Wang, Jin and Ji, Renhe and Liang, Jiajun and Fan, Haoqiang and Ge, Zheng}, title = {Implicit Identity Leakage: The Stumbling Block to Improving Deepfake Detection Generalization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3994-4004} }

Learning Federated Visual Prompt in Null Space for MRI Reconstruction

Chun-Mei Feng,

Bangjun Li,

Xinxing Xu,

Yong Liu,

Huazhu Fu,

Wangmeng Zuo

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Feng_2023_CVPR, author = {Feng, Chun-Mei and Li, Bangjun and Xu, Xinxing and Liu, Yong and Fu, Huazhu and Zuo, Wangmeng}, title = {Learning Federated Visual Prompt in Null Space for MRI Reconstruction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8064-8073} }

A New Benchmark: On the Utility of Synthetic Data With Blender for Bare Supervised Learning and Downstream Domain Adaptation

Hui Tang,

Kui Jia

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Tang_2023_CVPR, author = {Tang, Hui and Jia, Kui}, title = {A New Benchmark: On the Utility of Synthetic Data With Blender for Bare Supervised Learning and Downstream Domain Adaptation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15954-15964} }

Data-Driven Feature Tracking for Event Cameras

Nico Messikommer,

Carter Fang,

Mathias Gehrig,

Davide Scaramuzza

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Messikommer_2023_CVPR, author = {Messikommer, Nico and Fang, Carter and Gehrig, Mathias and Scaramuzza, Davide}, title = {Data-Driven Feature Tracking for Event Cameras}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5642-5651} }

Temporal Consistent 3D LiDAR Representation Learning for Semantic Perception in Autonomous Driving

Lucas Nunes,

Louis Wiesmann,

Rodrigo Marcuzzi,

Xieyuanli Chen,

Jens Behley,

Cyrill Stachniss

[pdf] [supp]

[bibtex]

@InProceedings{Nunes_2023_CVPR, author = {Nunes, Lucas and Wiesmann, Louis and Marcuzzi, Rodrigo and Chen, Xieyuanli and Behley, Jens and Stachniss, Cyrill}, title = {Temporal Consistent 3D LiDAR Representation Learning for Semantic Perception in Autonomous Driving}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5217-5228} }

AutoAD: Movie Description in Context

Tengda Han,

Max Bain,

Arsha Nagrani,

Gül Varol,

Weidi Xie,

Andrew Zisserman

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Han_2023_CVPR, author = {Han, Tengda and Bain, Max and Nagrani, Arsha and Varol, G\"ul and Xie, Weidi and Zisserman, Andrew}, title = {AutoAD: Movie Description in Context}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {18930-18940} }

DiffTalk: Crafting Diffusion Models for Generalized Audio-Driven Portraits Animation

Shuai Shen,

Wenliang Zhao,

Zibin Meng,

Wanhua Li,

Zheng Zhu,

Jie Zhou,

Jiwen Lu

[pdf] [arXiv]

[bibtex]

@InProceedings{Shen_2023_CVPR, author = {Shen, Shuai and Zhao, Wenliang and Meng, Zibin and Li, Wanhua and Zhu, Zheng and Zhou, Jie and Lu, Jiwen}, title = {DiffTalk: Crafting Diffusion Models for Generalized Audio-Driven Portraits Animation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1982-1991} }

Autoregressive Visual Tracking

Xing Wei,

Yifan Bai,

Yongchao Zheng,

Dahu Shi,

Yihong Gong

[pdf]

[bibtex]

@InProceedings{Wei_2023_CVPR, author = {Wei, Xing and Bai, Yifan and Zheng, Yongchao and Shi, Dahu and Gong, Yihong}, title = {Autoregressive Visual Tracking}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9697-9706} }

SceneComposer: Any-Level Semantic Image Synthesis

Yu Zeng,

Zhe Lin,

Jianming Zhang,

Qing Liu,

John Collomosse,

Jason Kuen,

Vishal M. Patel

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Zeng_2023_CVPR, author = {Zeng, Yu and Lin, Zhe and Zhang, Jianming and Liu, Qing and Collomosse, John and Kuen, Jason and Patel, Vishal M.}, title = {SceneComposer: Any-Level Semantic Image Synthesis}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {22468-22478} }

Visual Query Tuning: Towards Effective Usage of Intermediate Representations for Parameter and Memory Efficient Transfer Learning

Cheng-Hao Tu,

Zheda Mai,

Wei-Lun Chao

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Tu_2023_CVPR, author = {Tu, Cheng-Hao and Mai, Zheda and Chao, Wei-Lun}, title = {Visual Query Tuning: Towards Effective Usage of Intermediate Representations for Parameter and Memory Efficient Transfer Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7725-7735} }

MaPLe: Multi-Modal Prompt Learning

Muhammad Uzair Khattak,

Hanoona Rasheed,

Muhammad Maaz,

Salman Khan,

Fahad Shahbaz Khan

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Khattak_2023_CVPR, author = {Khattak, Muhammad Uzair and Rasheed, Hanoona and Maaz, Muhammad and Khan, Salman and Khan, Fahad Shahbaz}, title = {MaPLe: Multi-Modal Prompt Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {19113-19122} }

Unsupervised Domain Adaption With Pixel-Level Discriminator for Image-Aware Layout Generation

Chenchen Xu,

Min Zhou,

Tiezheng Ge,

Yuning Jiang,

Weiwei Xu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Xu_2023_CVPR, author = {Xu, Chenchen and Zhou, Min and Ge, Tiezheng and Jiang, Yuning and Xu, Weiwei}, title = {Unsupervised Domain Adaption With Pixel-Level Discriminator for Image-Aware Layout Generation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10114-10123} }

Compressing Volumetric Radiance Fields to 1 MB

Lingzhi Li,

Zhen Shen,

Zhongshu Wang,

Li Shen,

Liefeng Bo

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Li_2023_CVPR, author = {Li, Lingzhi and Shen, Zhen and Wang, Zhongshu and Shen, Li and Bo, Liefeng}, title = {Compressing Volumetric Radiance Fields to 1 MB}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4222-4231} }

Real-Time 6K Image Rescaling With Rate-Distortion Optimization

Chenyang Qi,

Xin Yang,

Ka Leong Cheng,

Ying-Cong Chen,

Qifeng Chen

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Qi_2023_CVPR, author = {Qi, Chenyang and Yang, Xin and Cheng, Ka Leong and Chen, Ying-Cong and Chen, Qifeng}, title = {Real-Time 6K Image Rescaling With Rate-Distortion Optimization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14092-14101} }

Gated Stereo: Joint Depth Estimation From Gated and Wide-Baseline Active Stereo Cues

Stefanie Walz,

Mario Bijelic,

Andrea Ramazzina,

Amanpreet Walia,

Fahim Mannan,

Felix Heide

[pdf] [supp]

[bibtex]

@InProceedings{Walz_2023_CVPR, author = {Walz, Stefanie and Bijelic, Mario and Ramazzina, Andrea and Walia, Amanpreet and Mannan, Fahim and Heide, Felix}, title = {Gated Stereo: Joint Depth Estimation From Gated and Wide-Baseline Active Stereo Cues}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13252-13262} }

Label Information Bottleneck for Label Enhancement

Qinghai Zheng,

Jihua Zhu,

Haoyu Tang

[pdf] [arXiv]

[bibtex]

@InProceedings{Zheng_2023_CVPR, author = {Zheng, Qinghai and Zhu, Jihua and Tang, Haoyu}, title = {Label Information Bottleneck for Label Enhancement}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7497-7506} }

Multi-Modal Representation Learning With Text-Driven Soft Masks

Jaeyoo Park,

Bohyung Han

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Park_2023_CVPR, author = {Park, Jaeyoo and Han, Bohyung}, title = {Multi-Modal Representation Learning With Text-Driven Soft Masks}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2798-2807} }

Gazeformer: Scalable, Effective and Fast Prediction of Goal-Directed Human Attention

Sounak Mondal,

Zhibo Yang,

Seoyoung Ahn,

Dimitris Samaras,

Gregory Zelinsky,

Minh Hoai

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Mondal_2023_CVPR, author = {Mondal, Sounak and Yang, Zhibo and Ahn, Seoyoung and Samaras, Dimitris and Zelinsky, Gregory and Hoai, Minh}, title = {Gazeformer: Scalable, Effective and Fast Prediction of Goal-Directed Human Attention}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1441-1450} }

MammalNet: A Large-Scale Video Benchmark for Mammal Recognition and Behavior Understanding

Jun Chen,

Ming Hu,

Darren J. Coker,

Michael L. Berumen,

Blair Costelloe,

Sara Beery,

Anna Rohrbach,

Mohamed Elhoseiny

[pdf] [supp]

[bibtex]

@InProceedings{Chen_2023_CVPR, author = {Chen, Jun and Hu, Ming and Coker, Darren J. and Berumen, Michael L. and Costelloe, Blair and Beery, Sara and Rohrbach, Anna and Elhoseiny, Mohamed}, title = {MammalNet: A Large-Scale Video Benchmark for Mammal Recognition and Behavior Understanding}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13052-13061} }

Hand Avatar: Free-Pose Hand Animation and Rendering From Monocular Video

Xingyu Chen,

Baoyuan Wang,

Heung-Yeung Shum

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Chen_2023_CVPR, author = {Chen, Xingyu and Wang, Baoyuan and Shum, Heung-Yeung}, title = {Hand Avatar: Free-Pose Hand Animation and Rendering From Monocular Video}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8683-8693} }

Rethinking the Correlation in Few-Shot Segmentation: A Buoys View

Yuan Wang,

Rui Sun,

Tianzhu Zhang

[pdf] [supp]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Yuan and Sun, Rui and Zhang, Tianzhu}, title = {Rethinking the Correlation in Few-Shot Segmentation: A Buoys View}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7183-7192} }

VindLU: A Recipe for Effective Video-and-Language Pretraining

Feng Cheng,

Xizi Wang,

Jie Lei,

David Crandall,

Mohit Bansal,

Gedas Bertasius

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Cheng_2023_CVPR, author = {Cheng, Feng and Wang, Xizi and Lei, Jie and Crandall, David and Bansal, Mohit and Bertasius, Gedas}, title = {VindLU: A Recipe for Effective Video-and-Language Pretraining}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10739-10750} }

Scaling Language-Image Pre-Training via Masking

Yanghao Li,

Haoqi Fan,

Ronghang Hu,

Christoph Feichtenhofer,

Kaiming He

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Li_2023_CVPR, author = {Li, Yanghao and Fan, Haoqi and Hu, Ronghang and Feichtenhofer, Christoph and He, Kaiming}, title = {Scaling Language-Image Pre-Training via Masking}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {23390-23400} }

OmniAvatar: Geometry-Guided Controllable 3D Head Synthesis

Hongyi Xu,

Guoxian Song,

Zihang Jiang,

Jianfeng Zhang,

Yichun Shi,

Jing Liu,

Wanchun Ma,

Jiashi Feng,

Linjie Luo

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Xu_2023_CVPR, author = {Xu, Hongyi and Song, Guoxian and Jiang, Zihang and Zhang, Jianfeng and Shi, Yichun and Liu, Jing and Ma, Wanchun and Feng, Jiashi and Luo, Linjie}, title = {OmniAvatar: Geometry-Guided Controllable 3D Head Synthesis}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12814-12824} }

DiffRF: Rendering-Guided 3D Radiance Field Diffusion

Norman Müller,

Yawar Siddiqui,

Lorenzo Porzi,

Samuel Rota Bulò,

Peter Kontschieder,

Matthias Nießner

[pdf] [supp]

[bibtex]

@InProceedings{Muller_2023_CVPR, author = {M\"uller, Norman and Siddiqui, Yawar and Porzi, Lorenzo and Bul\`o, Samuel Rota and Kontschieder, Peter and Nie{\ss}ner, Matthias}, title = {DiffRF: Rendering-Guided 3D Radiance Field Diffusion}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4328-4338} }

DNF: Decouple and Feedback Network for Seeing in the Dark

Xin Jin,

Ling-Hao Han,

Zhen Li,

Chun-Le Guo,

Zhi Chai,

Chongyi Li

[pdf] [supp]

[bibtex]

@InProceedings{Jin_2023_CVPR, author = {Jin, Xin and Han, Ling-Hao and Li, Zhen and Guo, Chun-Le and Chai, Zhi and Li, Chongyi}, title = {DNF: Decouple and Feedback Network for Seeing in the Dark}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {18135-18144} }

SUDS: Scalable Urban Dynamic Scenes

Haithem Turki,

Jason Y. Zhang,

Francesco Ferroni,

Deva Ramanan

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Turki_2023_CVPR, author = {Turki, Haithem and Zhang, Jason Y. and Ferroni, Francesco and Ramanan, Deva}, title = {SUDS: Scalable Urban Dynamic Scenes}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12375-12385} }

Deformable Mesh Transformer for 3D Human Mesh Recovery

Yusuke Yoshiyasu

[pdf] [supp]

[bibtex]

@InProceedings{Yoshiyasu_2023_CVPR, author = {Yoshiyasu, Yusuke}, title = {Deformable Mesh Transformer for 3D Human Mesh Recovery}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {17006-17015} }

Vita-CLIP: Video and Text Adaptive CLIP via Multimodal Prompting

Syed Talal Wasim,

Muzammal Naseer,

Salman Khan,

Fahad Shahbaz Khan,

Mubarak Shah

[pdf]

[bibtex]

@InProceedings{Wasim_2023_CVPR, author = {Wasim, Syed Talal and Naseer, Muzammal and Khan, Salman and Khan, Fahad Shahbaz and Shah, Mubarak}, title = {Vita-CLIP: Video and Text Adaptive CLIP via Multimodal Prompting}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {23034-23044} }

HS-Pose: Hybrid Scope Feature Extraction for Category-Level Object Pose Estimation

Linfang Zheng,

Chen Wang,

Yinghan Sun,

Esha Dasgupta,

Hua Chen,

Aleš Leonardis,

Wei Zhang,

Hyung Jin Chang

[pdf] [supp]

[bibtex]

@InProceedings{Zheng_2023_CVPR, author = {Zheng, Linfang and Wang, Chen and Sun, Yinghan and Dasgupta, Esha and Chen, Hua and Leonardis, Ale\v{s} and Zhang, Wei and Chang, Hyung Jin}, title = {HS-Pose: Hybrid Scope Feature Extraction for Category-Level Object Pose Estimation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {17163-17173} }

Cloud-Device Collaborative Adaptation to Continual Changing Environments in the Real-World

Yulu Gan,

Mingjie Pan,

Rongyu Zhang,

Zijian Ling,

Lingran Zhao,

Jiaming Liu,

Shanghang Zhang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Gan_2023_CVPR, author = {Gan, Yulu and Pan, Mingjie and Zhang, Rongyu and Ling, Zijian and Zhao, Lingran and Liu, Jiaming and Zhang, Shanghang}, title = {Cloud-Device Collaborative Adaptation to Continual Changing Environments in the Real-World}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12157-12166} }

Parts2Words: Learning Joint Embedding of Point Clouds and Texts by Bidirectional Matching Between Parts and Words

Chuan Tang,

Xi Yang,

Bojian Wu,

Zhizhong Han,

Yi Chang

[pdf] [arXiv]

[bibtex]

@InProceedings{Tang_2023_CVPR, author = {Tang, Chuan and Yang, Xi and Wu, Bojian and Han, Zhizhong and Chang, Yi}, title = {Parts2Words: Learning Joint Embedding of Point Clouds and Texts by Bidirectional Matching Between Parts and Words}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6884-6893} }

Proposal-Based Multiple Instance Learning for Weakly-Supervised Temporal Action Localization

Huan Ren,

Wenfei Yang,

Tianzhu Zhang,

Yongdong Zhang

[pdf]

[bibtex]

@InProceedings{Ren_2023_CVPR, author = {Ren, Huan and Yang, Wenfei and Zhang, Tianzhu and Zhang, Yongdong}, title = {Proposal-Based Multiple Instance Learning for Weakly-Supervised Temporal Action Localization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2394-2404} }

LayoutDM: Transformer-Based Diffusion Model for Layout Generation

Shang Chai,

Liansheng Zhuang,

Fengying Yan

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Chai_2023_CVPR, author = {Chai, Shang and Zhuang, Liansheng and Yan, Fengying}, title = {LayoutDM: Transformer-Based Diffusion Model for Layout Generation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {18349-18358} }

HandNeRF: Neural Radiance Fields for Animatable Interacting Hands

Zhiyang Guo,

Wengang Zhou,

Min Wang,

Li Li,

Houqiang Li

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Guo_2023_CVPR, author = {Guo, Zhiyang and Zhou, Wengang and Wang, Min and Li, Li and Li, Houqiang}, title = {HandNeRF: Neural Radiance Fields for Animatable Interacting Hands}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {21078-21087} }

ASPnet: Action Segmentation With Shared-Private Representation of Multiple Data Sources

Beatrice van Amsterdam,

Abdolrahim Kadkhodamohammadi,

Imanol Luengo,

Danail Stoyanov

[pdf]

[bibtex]

@InProceedings{van_Amsterdam_2023_CVPR, author = {van Amsterdam, Beatrice and Kadkhodamohammadi, Abdolrahim and Luengo, Imanol and Stoyanov, Danail}, title = {ASPnet: Action Segmentation With Shared-Private Representation of Multiple Data Sources}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2384-2393} }

Seasoning Model Soups for Robustness to Adversarial and Natural Distribution Shifts

Francesco Croce,

Sylvestre-Alvise Rebuffi,

Evan Shelhamer,

Sven Gowal

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Croce_2023_CVPR, author = {Croce, Francesco and Rebuffi, Sylvestre-Alvise and Shelhamer, Evan and Gowal, Sven}, title = {Seasoning Model Soups for Robustness to Adversarial and Natural Distribution Shifts}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12313-12323} }

Introducing Competition To Boost the Transferability of Targeted Adversarial Examples Through Clean Feature Mixup

Junyoung Byun,

Myung-Joon Kwon,

Seungju Cho,

Yoonji Kim,

Changick Kim

[pdf] [supp]

[bibtex]

@InProceedings{Byun_2023_CVPR, author = {Byun, Junyoung and Kwon, Myung-Joon and Cho, Seungju and Kim, Yoonji and Kim, Changick}, title = {Introducing Competition To Boost the Transferability of Targeted Adversarial Examples Through Clean Feature Mixup}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {24648-24657} }

Ingredient-Oriented Multi-Degradation Learning for Image Restoration

Jinghao Zhang,

Jie Huang,

Mingde Yao,

Zizheng Yang,

Hu Yu,

Man Zhou,

Feng Zhao

[pdf] [supp]

[bibtex]

@InProceedings{Zhang_2023_CVPR, author = {Zhang, Jinghao and Huang, Jie and Yao, Mingde and Yang, Zizheng and Yu, Hu and Zhou, Man and Zhao, Feng}, title = {Ingredient-Oriented Multi-Degradation Learning for Image Restoration}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5825-5835} }

How To Prevent the Continuous Damage of Noises To Model Training?

Xiaotian Yu,

Yang Jiang,

Tianqi Shi,

Zunlei Feng,

Yuexuan Wang,

Mingli Song,

Li Sun

[pdf] [supp]

[bibtex]

@InProceedings{Yu_2023_CVPR, author = {Yu, Xiaotian and Jiang, Yang and Shi, Tianqi and Feng, Zunlei and Wang, Yuexuan and Song, Mingli and Sun, Li}, title = {How To Prevent the Continuous Damage of Noises To Model Training?}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12054-12063} }

A Whac-a-Mole Dilemma: Shortcuts Come in Multiples Where Mitigating One Amplifies Others

Zhiheng Li,

Ivan Evtimov,

Albert Gordo,

Caner Hazirbas,

Tal Hassner,

Cristian Canton Ferrer,

Chenliang Xu,

Mark Ibrahim

[pdf] [supp]

[bibtex]

@InProceedings{Li_2023_CVPR, author = {Li, Zhiheng and Evtimov, Ivan and Gordo, Albert and Hazirbas, Caner and Hassner, Tal and Ferrer, Cristian Canton and Xu, Chenliang and Ibrahim, Mark}, title = {A Whac-a-Mole Dilemma: Shortcuts Come in Multiples Where Mitigating One Amplifies Others}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {20071-20082} }

Skinned Motion Retargeting With Residual Perception of Motion Semantics & Geometry

Jiaxu Zhang,

Junwu Weng,

Di Kang,

Fang Zhao,

Shaoli Huang,

Xuefei Zhe,

Linchao Bao,

Ying Shan,

Jue Wang,

Zhigang Tu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Zhang_2023_CVPR, author = {Zhang, Jiaxu and Weng, Junwu and Kang, Di and Zhao, Fang and Huang, Shaoli and Zhe, Xuefei and Bao, Linchao and Shan, Ying and Wang, Jue and Tu, Zhigang}, title = {Skinned Motion Retargeting With Residual Perception of Motion Semantics \& Geometry}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13864-13872} }

Weakly-Supervised Single-View Image Relighting

Renjiao Yi,

Chenyang Zhu,

Kai Xu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Yi_2023_CVPR, author = {Yi, Renjiao and Zhu, Chenyang and Xu, Kai}, title = {Weakly-Supervised Single-View Image Relighting}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8402-8411} }

DualVector: Unsupervised Vector Font Synthesis With Dual-Part Representation

Ying-Tian Liu,

Zhifei Zhang,

Yuan-Chen Guo,

Matthew Fisher,

Zhaowen Wang,

Song-Hai Zhang

[pdf] [supp]

[bibtex]

@InProceedings{Liu_2023_CVPR, author = {Liu, Ying-Tian and Zhang, Zhifei and Guo, Yuan-Chen and Fisher, Matthew and Wang, Zhaowen and Zhang, Song-Hai}, title = {DualVector: Unsupervised Vector Font Synthesis With Dual-Part Representation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14193-14202} }

Efficient Scale-Invariant Generator With Column-Row Entangled Pixel Synthesis

Thuan Hoang Nguyen,

Thanh Van Le,

Anh Tran

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Nguyen_2023_CVPR, author = {Nguyen, Thuan Hoang and Van Le, Thanh and Tran, Anh}, title = {Efficient Scale-Invariant Generator With Column-Row Entangled Pixel Synthesis}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {22408-22417} }

ReasonNet: End-to-End Driving With Temporal and Global Reasoning

Hao Shao,

Letian Wang,

Ruobing Chen,

Steven L. Waslander,

Hongsheng Li,

Yu Liu

[pdf] [supp]

[bibtex]

@InProceedings{Shao_2023_CVPR, author = {Shao, Hao and Wang, Letian and Chen, Ruobing and Waslander, Steven L. and Li, Hongsheng and Liu, Yu}, title = {ReasonNet: End-to-End Driving With Temporal and Global Reasoning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13723-13733} }

Learning Situation Hyper-Graphs for Video Question Answering

Aisha Urooj,

Hilde Kuehne,

Bo Wu,

Kim Chheu,

Walid Bousselham,

Chuang Gan,

Niels Lobo,

Mubarak Shah

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Urooj_2023_CVPR, author = {Urooj, Aisha and Kuehne, Hilde and Wu, Bo and Chheu, Kim and Bousselham, Walid and Gan, Chuang and Lobo, Niels and Shah, Mubarak}, title = {Learning Situation Hyper-Graphs for Video Question Answering}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14879-14889} }

H2ONet: Hand-Occlusion-and-Orientation-Aware Network for Real-Time 3D Hand Mesh Reconstruction

Hao Xu,

Tianyu Wang,

Xiao Tang,

Chi-Wing Fu

[pdf] [supp]

[bibtex]

@InProceedings{Xu_2023_CVPR, author = {Xu, Hao and Wang, Tianyu and Tang, Xiao and Fu, Chi-Wing}, title = {H2ONet: Hand-Occlusion-and-Orientation-Aware Network for Real-Time 3D Hand Mesh Reconstruction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {17048-17058} }

Interventional Bag Multi-Instance Learning on Whole-Slide Pathological Images

Tiancheng Lin,

Zhimiao Yu,

Hongyu Hu,

Yi Xu,

Chang-Wen Chen

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Lin_2023_CVPR, author = {Lin, Tiancheng and Yu, Zhimiao and Hu, Hongyu and Xu, Yi and Chen, Chang-Wen}, title = {Interventional Bag Multi-Instance Learning on Whole-Slide Pathological Images}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {19830-19839} }

GazeNeRF: 3D-Aware Gaze Redirection With Neural Radiance Fields

Alessandro Ruzzi,

Xiangwei Shi,

Xi Wang,

Gengyan Li,

Shalini De Mello,

Hyung Jin Chang,

Xucong Zhang,

Otmar Hilliges

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Ruzzi_2023_CVPR, author = {Ruzzi, Alessandro and Shi, Xiangwei and Wang, Xi and Li, Gengyan and De Mello, Shalini and Chang, Hyung Jin and Zhang, Xucong and Hilliges, Otmar}, title = {GazeNeRF: 3D-Aware Gaze Redirection With Neural Radiance Fields}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9676-9685} }

How Can Objects Help Action Recognition?

Xingyi Zhou,

Anurag Arnab,

Chen Sun,

Cordelia Schmid

[pdf]

[bibtex]

@InProceedings{Zhou_2023_CVPR, author = {Zhou, Xingyi and Arnab, Anurag and Sun, Chen and Schmid, Cordelia}, title = {How Can Objects Help Action Recognition?}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2353-2362} }

Realistic Saliency Guided Image Enhancement

S. Mahdi H. Miangoleh,

Zoya Bylinskii,

Eric Kee,

Eli Shechtman,

Yağiz Aksoy

[pdf] [supp]

[bibtex]

@InProceedings{Miangoleh_2023_CVPR, author = {Miangoleh, S. Mahdi H. and Bylinskii, Zoya and Kee, Eric and Shechtman, Eli and Aksoy, Ya\u{g}iz}, title = {Realistic Saliency Guided Image Enhancement}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {186-194} }

SLOPER4D: A Scene-Aware Dataset for Global 4D Human Pose Estimation in Urban Environments

Yudi Dai,

Yitai Lin,

Xiping Lin,

Chenglu Wen,

Lan Xu,

Hongwei Yi,

Siqi Shen,

Yuexin Ma,

Cheng Wang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Dai_2023_CVPR, author = {Dai, Yudi and Lin, Yitai and Lin, Xiping and Wen, Chenglu and Xu, Lan and Yi, Hongwei and Shen, Siqi and Ma, Yuexin and Wang, Cheng}, title = {SLOPER4D: A Scene-Aware Dataset for Global 4D Human Pose Estimation in Urban Environments}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {682-692} }

SegLoc: Learning Segmentation-Based Representations for Privacy-Preserving Visual Localization

Maxime Pietrantoni,

Martin Humenberger,

Torsten Sattler,

Gabriela Csurka

[pdf] [supp]

[bibtex]

@InProceedings{Pietrantoni_2023_CVPR, author = {Pietrantoni, Maxime and Humenberger, Martin and Sattler, Torsten and Csurka, Gabriela}, title = {SegLoc: Learning Segmentation-Based Representations for Privacy-Preserving Visual Localization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15380-15391} }

Efficient Hierarchical Entropy Model for Learned Point Cloud Compression

Rui Song,

Chunyang Fu,

Shan Liu,

Ge Li

[pdf] [supp]

[bibtex]

@InProceedings{Song_2023_CVPR, author = {Song, Rui and Fu, Chunyang and Liu, Shan and Li, Ge}, title = {Efficient Hierarchical Entropy Model for Learned Point Cloud Compression}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14368-14377} }

RankMix: Data Augmentation for Weakly Supervised Learning of Classifying Whole Slide Images With Diverse Sizes and Imbalanced Categories

Yuan-Chih Chen,

Chun-Shien Lu

[pdf] [supp]

[bibtex]

@InProceedings{Chen_2023_CVPR, author = {Chen, Yuan-Chih and Lu, Chun-Shien}, title = {RankMix: Data Augmentation for Weakly Supervised Learning of Classifying Whole Slide Images With Diverse Sizes and Imbalanced Categories}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {23936-23945} }

ActMAD: Activation Matching To Align Distributions for Test-Time-Training

Muhammad Jehanzeb Mirza,

Pol Jané Soneira,

Wei Lin,

Mateusz Kozinski,

Horst Possegger,

Horst Bischof

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Mirza_2023_CVPR, author = {Mirza, Muhammad Jehanzeb and Soneira, Pol Jan\'e and Lin, Wei and Kozinski, Mateusz and Possegger, Horst and Bischof, Horst}, title = {ActMAD: Activation Matching To Align Distributions for Test-Time-Training}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {24152-24161} }

DKM: Dense Kernelized Feature Matching for Geometry Estimation

Johan Edstedt,

Ioannis Athanasiadis,

Mårten Wadenbäck,

Michael Felsberg

[pdf] [supp]

[bibtex]

@InProceedings{Edstedt_2023_CVPR, author = {Edstedt, Johan and Athanasiadis, Ioannis and Wadenb\"ack, M\r{a}rten and Felsberg, Michael}, title = {DKM: Dense Kernelized Feature Matching for Geometry Estimation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {17765-17775} }

Image Cropping With Spatial-Aware Feature and Rank Consistency

Chao Wang,

Li Niu,

Bo Zhang,

Liqing Zhang

[pdf] [supp]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Chao and Niu, Li and Zhang, Bo and Zhang, Liqing}, title = {Image Cropping With Spatial-Aware Feature and Rank Consistency}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10052-10061} }

SVGformer: Representation Learning for Continuous Vector Graphics Using Transformers

Defu Cao,

Zhaowen Wang,

Jose Echevarria,

Yan Liu

[pdf] [supp]

[bibtex]

@InProceedings{Cao_2023_CVPR, author = {Cao, Defu and Wang, Zhaowen and Echevarria, Jose and Liu, Yan}, title = {SVGformer: Representation Learning for Continuous Vector Graphics Using Transformers}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10093-10102} }

Structured 3D Features for Reconstructing Controllable Avatars

Enric Corona,

Mihai Zanfir,

Thiemo Alldieck,

Eduard Gabriel Bazavan,

Andrei Zanfir,

Cristian Sminchisescu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Corona_2023_CVPR, author = {Corona, Enric and Zanfir, Mihai and Alldieck, Thiemo and Bazavan, Eduard Gabriel and Zanfir, Andrei and Sminchisescu, Cristian}, title = {Structured 3D Features for Reconstructing Controllable Avatars}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16954-16964} }

Mask-Guided Matting in the Wild

Kwanyong Park,

Sanghyun Woo,

Seoung Wug Oh,

In So Kweon,

Joon-Young Lee

[pdf] [supp]

[bibtex]

@InProceedings{Park_2023_CVPR, author = {Park, Kwanyong and Woo, Sanghyun and Oh, Seoung Wug and Kweon, In So and Lee, Joon-Young}, title = {Mask-Guided Matting in the Wild}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1992-2001} }

Dynamic Conceptional Contrastive Learning for Generalized Category Discovery

Nan Pu,

Zhun Zhong,

Nicu Sebe

[pdf] [arXiv]

[bibtex]

@InProceedings{Pu_2023_CVPR, author = {Pu, Nan and Zhong, Zhun and Sebe, Nicu}, title = {Dynamic Conceptional Contrastive Learning for Generalized Category Discovery}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7579-7588} }

Neumann Network With Recursive Kernels for Single Image Defocus Deblurring

Yuhui Quan,

Zicong Wu,

Hui Ji

[pdf] [supp]

[bibtex]

@InProceedings{Quan_2023_CVPR, author = {Quan, Yuhui and Wu, Zicong and Ji, Hui}, title = {Neumann Network With Recursive Kernels for Single Image Defocus Deblurring}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5754-5763} }

Active Finetuning: Exploiting Annotation Budget in the Pretraining-Finetuning Paradigm

Yichen Xie,

Han Lu,

Junchi Yan,

Xiaokang Yang,

Masayoshi Tomizuka,

Wei Zhan

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Xie_2023_CVPR, author = {Xie, Yichen and Lu, Han and Yan, Junchi and Yang, Xiaokang and Tomizuka, Masayoshi and Zhan, Wei}, title = {Active Finetuning: Exploiting Annotation Budget in the Pretraining-Finetuning Paradigm}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {23715-23724} }

Learning Attribute and Class-Specific Representation Duet for Fine-Grained Fashion Analysis

Yang Jiao,

Yan Gao,

Jingjing Meng,

Jin Shang,

Yi Sun

[pdf] [supp]

[bibtex]

@InProceedings{Jiao_2023_CVPR, author = {Jiao, Yang and Gao, Yan and Meng, Jingjing and Shang, Jin and Sun, Yi}, title = {Learning Attribute and Class-Specific Representation Duet for Fine-Grained Fashion Analysis}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11050-11059} }

Pixels, Regions, and Objects: Multiple Enhancement for Salient Object Detection

Yi Wang,

Ruili Wang,

Xin Fan,

Tianzhu Wang,

Xiangjian He

[pdf] [supp]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Yi and Wang, Ruili and Fan, Xin and Wang, Tianzhu and He, Xiangjian}, title = {Pixels, Regions, and Objects: Multiple Enhancement for Salient Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10031-10040} }

Leveraging Temporal Context in Low Representational Power Regimes

Camilo L. Fosco,

SouYoung Jin,

Emilie Josephs,

Aude Oliva

[pdf] [supp]

[bibtex]

@InProceedings{Fosco_2023_CVPR, author = {Fosco, Camilo L. and Jin, SouYoung and Josephs, Emilie and Oliva, Aude}, title = {Leveraging Temporal Context in Low Representational Power Regimes}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10693-10703} }

Guided Recommendation for Model Fine-Tuning

Hao Li,

Charless Fowlkes,

Hao Yang,

Onkar Dabeer,

Zhuowen Tu,

Stefano Soatto

[pdf] [supp]

[bibtex]

@InProceedings{Li_2023_CVPR, author = {Li, Hao and Fowlkes, Charless and Yang, Hao and Dabeer, Onkar and Tu, Zhuowen and Soatto, Stefano}, title = {Guided Recommendation for Model Fine-Tuning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3633-3642} }

Masked Image Training for Generalizable Deep Image Denoising

Haoyu Chen,

Jinjin Gu,

Yihao Liu,

Salma Abdel Magid,

Chao Dong,

Qiong Wang,

Hanspeter Pfister,

Lei Zhu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Chen_2023_CVPR, author = {Chen, Haoyu and Gu, Jinjin and Liu, Yihao and Magid, Salma Abdel and Dong, Chao and Wang, Qiong and Pfister, Hanspeter and Zhu, Lei}, title = {Masked Image Training for Generalizable Deep Image Denoising}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1692-1703} }

In-Hand 3D Object Scanning From an RGB Sequence

Shreyas Hampali,

Tomas Hodan,

Luan Tran,

Lingni Ma,

Cem Keskin,

Vincent Lepetit

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Hampali_2023_CVPR, author = {Hampali, Shreyas and Hodan, Tomas and Tran, Luan and Ma, Lingni and Keskin, Cem and Lepetit, Vincent}, title = {In-Hand 3D Object Scanning From an RGB Sequence}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {17079-17088} }

Zero-Shot Referring Image Segmentation With Global-Local Context Features

Seonghoon Yu,

Paul Hongsuck Seo,

Jeany Son

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Yu_2023_CVPR, author = {Yu, Seonghoon and Seo, Paul Hongsuck and Son, Jeany}, title = {Zero-Shot Referring Image Segmentation With Global-Local Context Features}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {19456-19465} }

SketchXAI: A First Look at Explainability for Human Sketches

Zhiyu Qu,

Yulia Gryaditskaya,

Ke Li,

Kaiyue Pang,

Tao Xiang,

Yi-Zhe Song

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Qu_2023_CVPR, author = {Qu, Zhiyu and Gryaditskaya, Yulia and Li, Ke and Pang, Kaiyue and Xiang, Tao and Song, Yi-Zhe}, title = {SketchXAI: A First Look at Explainability for Human Sketches}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {23327-23337} }

Omni3D: A Large Benchmark and Model for 3D Object Detection in the Wild

Garrick Brazil,

Abhinav Kumar,

Julian Straub,

Nikhila Ravi,

Justin Johnson,

Georgia Gkioxari

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Brazil_2023_CVPR, author = {Brazil, Garrick and Kumar, Abhinav and Straub, Julian and Ravi, Nikhila and Johnson, Justin and Gkioxari, Georgia}, title = {Omni3D: A Large Benchmark and Model for 3D Object Detection in the Wild}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13154-13164} }

OT-Filter: An Optimal Transport Filter for Learning With Noisy Labels

Chuanwen Feng,

Yilong Ren,

Xike Xie

[pdf]

[bibtex]

@InProceedings{Feng_2023_CVPR, author = {Feng, Chuanwen and Ren, Yilong and Xie, Xike}, title = {OT-Filter: An Optimal Transport Filter for Learning With Noisy Labels}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16164-16174} }

Rebalancing Batch Normalization for Exemplar-Based Class-Incremental Learning

Sungmin Cha,

Sungjun Cho,

Dasol Hwang,

Sunwon Hong,

Moontae Lee,

Taesup Moon

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Cha_2023_CVPR, author = {Cha, Sungmin and Cho, Sungjun and Hwang, Dasol and Hong, Sunwon and Lee, Moontae and Moon, Taesup}, title = {Rebalancing Batch Normalization for Exemplar-Based Class-Incremental Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {20127-20136} }

OmniVidar: Omnidirectional Depth Estimation From Multi-Fisheye Images

Sheng Xie,

Daochuan Wang,

Yun-Hui Liu

[pdf]

[bibtex]

@InProceedings{Xie_2023_CVPR, author = {Xie, Sheng and Wang, Daochuan and Liu, Yun-Hui}, title = {OmniVidar: Omnidirectional Depth Estimation From Multi-Fisheye Images}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {21529-21538} }

RWSC-Fusion: Region-Wise Style-Controlled Fusion Network for the Prohibited X-Ray Security Image Synthesis

Luwen Duan,

Min Wu,

Lijian Mao,

Jun Yin,

Jianping Xiong,

Xi Li

[pdf] [supp]

[bibtex]

@InProceedings{Duan_2023_CVPR, author = {Duan, Luwen and Wu, Min and Mao, Lijian and Yin, Jun and Xiong, Jianping and Li, Xi}, title = {RWSC-Fusion: Region-Wise Style-Controlled Fusion Network for the Prohibited X-Ray Security Image Synthesis}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {22398-22407} }

Octree Guided Unoriented Surface Reconstruction

Chamin Hewa Koneputugodage,

Yizhak Ben-Shabat,

Stephen Gould

[pdf] [supp]

[bibtex]

@InProceedings{Koneputugodage_2023_CVPR, author = {Koneputugodage, Chamin Hewa and Ben-Shabat, Yizhak and Gould, Stephen}, title = {Octree Guided Unoriented Surface Reconstruction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16717-16726} }

Rigidity-Aware Detection for 6D Object Pose Estimation

Yang Hai,

Rui Song,

Jiaojiao Li,

Mathieu Salzmann,

Yinlin Hu

[pdf] [arXiv]

[bibtex]

@InProceedings{Hai_2023_CVPR, author = {Hai, Yang and Song, Rui and Li, Jiaojiao and Salzmann, Mathieu and Hu, Yinlin}, title = {Rigidity-Aware Detection for 6D Object Pose Estimation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8927-8936} }

ToThePoint: Efficient Contrastive Learning of 3D Point Clouds via Recycling

Xinglin Li,

Jiajing Chen,

Jinhui Ouyang,

Hanhui Deng,

Senem Velipasalar,

Di Wu

[pdf] [supp]

[bibtex]

@InProceedings{Li_2023_CVPR, author = {Li, Xinglin and Chen, Jiajing and Ouyang, Jinhui and Deng, Hanhui and Velipasalar, Senem and Wu, Di}, title = {ToThePoint: Efficient Contrastive Learning of 3D Point Clouds via Recycling}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {21781-21790} }

Clover: Towards a Unified Video-Language Alignment and Fusion Model

Jingjia Huang,

Yinan Li,

Jiashi Feng,

Xinglong Wu,

Xiaoshuai Sun,

Rongrong Ji

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Huang_2023_CVPR, author = {Huang, Jingjia and Li, Yinan and Feng, Jiashi and Wu, Xinglong and Sun, Xiaoshuai and Ji, Rongrong}, title = {Clover: Towards a Unified Video-Language Alignment and Fusion Model}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14856-14866} }

Weakly Supervised Monocular 3D Object Detection Using Multi-View Projection and Direction Consistency

Runzhou Tao,

Wencheng Han,

Zhongying Qiu,

Cheng-Zhong Xu,

Jianbing Shen

[pdf] [arXiv]

[bibtex]

@InProceedings{Tao_2023_CVPR, author = {Tao, Runzhou and Han, Wencheng and Qiu, Zhongying and Xu, Cheng-Zhong and Shen, Jianbing}, title = {Weakly Supervised Monocular 3D Object Detection Using Multi-View Projection and Direction Consistency}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {17482-17492} }

Self-Supervised Learning From Images With a Joint-Embedding Predictive Architecture

Mahmoud Assran,

Quentin Duval,

Ishan Misra,

Piotr Bojanowski,

Pascal Vincent,

Michael Rabbat,

Yann LeCun,

Nicolas Ballas

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Assran_2023_CVPR, author = {Assran, Mahmoud and Duval, Quentin and Misra, Ishan and Bojanowski, Piotr and Vincent, Pascal and Rabbat, Michael and LeCun, Yann and Ballas, Nicolas}, title = {Self-Supervised Learning From Images With a Joint-Embedding Predictive Architecture}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15619-15629} }

EDA: Explicit Text-Decoupling and Dense Alignment for 3D Visual Grounding

Yanmin Wu,

Xinhua Cheng,

Renrui Zhang,

Zesen Cheng,

Jian Zhang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Wu_2023_CVPR, author = {Wu, Yanmin and Cheng, Xinhua and Zhang, Renrui and Cheng, Zesen and Zhang, Jian}, title = {EDA: Explicit Text-Decoupling and Dense Alignment for 3D Visual Grounding}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {19231-19242} }

A2J-Transformer: Anchor-to-Joint Transformer Network for 3D Interacting Hand Pose Estimation From a Single RGB Image

Changlong Jiang,

Yang Xiao,

Cunlin Wu,

Mingyang Zhang,

Jinghong Zheng,

Zhiguo Cao,

Joey Tianyi Zhou

[pdf]

[bibtex]

@InProceedings{Jiang_2023_CVPR, author = {Jiang, Changlong and Xiao, Yang and Wu, Cunlin and Zhang, Mingyang and Zheng, Jinghong and Cao, Zhiguo and Zhou, Joey Tianyi}, title = {A2J-Transformer: Anchor-to-Joint Transformer Network for 3D Interacting Hand Pose Estimation From a Single RGB Image}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8846-8855} }

The Treasure Beneath Multiple Annotations: An Uncertainty-Aware Edge Detector

Caixia Zhou,

Yaping Huang,

Mengyang Pu,

Qingji Guan,

Li Huang,

Haibin Ling

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Zhou_2023_CVPR, author = {Zhou, Caixia and Huang, Yaping and Pu, Mengyang and Guan, Qingji and Huang, Li and Ling, Haibin}, title = {The Treasure Beneath Multiple Annotations: An Uncertainty-Aware Edge Detector}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15507-15517} }

DP-NeRF: Deblurred Neural Radiance Field With Physical Scene Priors

Dogyoon Lee,

Minhyeok Lee,

Chajin Shin,

Sangyoun Lee

[pdf] [supp]

[bibtex]

@InProceedings{Lee_2023_CVPR, author = {Lee, Dogyoon and Lee, Minhyeok and Shin, Chajin and Lee, Sangyoun}, title = {DP-NeRF: Deblurred Neural Radiance Field With Physical Scene Priors}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12386-12396} }

MixPHM: Redundancy-Aware Parameter-Efficient Tuning for Low-Resource Visual Question Answering

Jingjing Jiang,

Nanning Zheng

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Jiang_2023_CVPR, author = {Jiang, Jingjing and Zheng, Nanning}, title = {MixPHM: Redundancy-Aware Parameter-Efficient Tuning for Low-Resource Visual Question Answering}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {24203-24213} }

Self-Supervised Blind Motion Deblurring With Deep Expectation Maximization

Ji Li,

Weixi Wang,

Yuesong Nan,

Hui Ji

[pdf] [supp]

[bibtex]

@InProceedings{Li_2023_CVPR, author = {Li, Ji and Wang, Weixi and Nan, Yuesong and Ji, Hui}, title = {Self-Supervised Blind Motion Deblurring With Deep Expectation Maximization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13986-13996} }

DeAR: Debiasing Vision-Language Models With Additive Residuals

Ashish Seth,

Mayur Hemani,

Chirag Agarwal

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Seth_2023_CVPR, author = {Seth, Ashish and Hemani, Mayur and Agarwal, Chirag}, title = {DeAR: Debiasing Vision-Language Models With Additive Residuals}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6820-6829} }

E2PN: Efficient SE(3)-Equivariant Point Network

Minghan Zhu,

Maani Ghaffari,

William A. Clark,

Huei Peng

[pdf] [supp]

[bibtex]

@InProceedings{Zhu_2023_CVPR, author = {Zhu, Minghan and Ghaffari, Maani and Clark, William A. and Peng, Huei}, title = {E2PN: Efficient SE(3)-Equivariant Point Network}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1223-1232} }

Understanding Masked Image Modeling via Learning Occlusion Invariant Feature

Xiangwen Kong,

Xiangyu Zhang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Kong_2023_CVPR, author = {Kong, Xiangwen and Zhang, Xiangyu}, title = {Understanding Masked Image Modeling via Learning Occlusion Invariant Feature}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6241-6251} }

Grounding Counterfactual Explanation of Image Classifiers to Textual Concept Space

Siwon Kim,

Jinoh Oh,

Sungjin Lee,

Seunghak Yu,

Jaeyoung Do,

Tara Taghavi

[pdf] [supp]

[bibtex]

@InProceedings{Kim_2023_CVPR, author = {Kim, Siwon and Oh, Jinoh and Lee, Sungjin and Yu, Seunghak and Do, Jaeyoung and Taghavi, Tara}, title = {Grounding Counterfactual Explanation of Image Classifiers to Textual Concept Space}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10942-10950} }

A Dynamic Multi-Scale Voxel Flow Network for Video Prediction

Xiaotao Hu,

Zhewei Huang,

Ailin Huang,

Jun Xu,

Shuchang Zhou

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Hu_2023_CVPR, author = {Hu, Xiaotao and Huang, Zhewei and Huang, Ailin and Xu, Jun and Zhou, Shuchang}, title = {A Dynamic Multi-Scale Voxel Flow Network for Video Prediction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6121-6131} }

UniDistill: A Universal Cross-Modality Knowledge Distillation Framework for 3D Object Detection in Bird's-Eye View

Shengchao Zhou,

Weizhou Liu,

Chen Hu,

Shuchang Zhou,

Chao Ma

[pdf] [supp]

[bibtex]

@InProceedings{Zhou_2023_CVPR, author = {Zhou, Shengchao and Liu, Weizhou and Hu, Chen and Zhou, Shuchang and Ma, Chao}, title = {UniDistill: A Universal Cross-Modality Knowledge Distillation Framework for 3D Object Detection in Bird's-Eye View}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5116-5125} }

SemiCVT: Semi-Supervised Convolutional Vision Transformer for Semantic Segmentation

Huimin Huang,

Shiao Xie,

Lanfen Lin,

Ruofeng Tong,

Yen-Wei Chen,

Yuexiang Li,

Hong Wang,

Yawen Huang,

Yefeng Zheng

[pdf]

[bibtex]

@InProceedings{Huang_2023_CVPR, author = {Huang, Huimin and Xie, Shiao and Lin, Lanfen and Tong, Ruofeng and Chen, Yen-Wei and Li, Yuexiang and Wang, Hong and Huang, Yawen and Zheng, Yefeng}, title = {SemiCVT: Semi-Supervised Convolutional Vision Transformer for Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11340-11349} }

Fine-Tuned CLIP Models Are Efficient Video Learners

Hanoona Rasheed,

Muhammad Uzair Khattak,

Muhammad Maaz,

Salman Khan,

Fahad Shahbaz Khan

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Rasheed_2023_CVPR, author = {Rasheed, Hanoona and Khattak, Muhammad Uzair and Maaz, Muhammad and Khan, Salman and Khan, Fahad Shahbaz}, title = {Fine-Tuned CLIP Models Are Efficient Video Learners}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6545-6554} }

Towards Open-World Segmentation of Parts

Tai-Yu Pan,

Qing Liu,

Wei-Lun Chao,

Brian Price

[pdf] [supp]

[bibtex]

@InProceedings{Pan_2023_CVPR, author = {Pan, Tai-Yu and Liu, Qing and Chao, Wei-Lun and Price, Brian}, title = {Towards Open-World Segmentation of Parts}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15392-15401} }

Stitchable Neural Networks

Zizheng Pan,

Jianfei Cai,

Bohan Zhuang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Pan_2023_CVPR, author = {Pan, Zizheng and Cai, Jianfei and Zhuang, Bohan}, title = {Stitchable Neural Networks}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16102-16112} }

Collaborative Diffusion for Multi-Modal Face Generation and Editing

Ziqi Huang,

Kelvin C.K. Chan,

Yuming Jiang,

Ziwei Liu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Huang_2023_CVPR, author = {Huang, Ziqi and Chan, Kelvin C.K. and Jiang, Yuming and Liu, Ziwei}, title = {Collaborative Diffusion for Multi-Modal Face Generation and Editing}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6080-6090} }

DejaVu: Conditional Regenerative Learning To Enhance Dense Prediction

Shubhankar Borse,

Debasmit Das,

Hyojin Park,

Hong Cai,

Risheek Garrepalli,

Fatih Porikli

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Borse_2023_CVPR, author = {Borse, Shubhankar and Das, Debasmit and Park, Hyojin and Cai, Hong and Garrepalli, Risheek and Porikli, Fatih}, title = {DejaVu: Conditional Regenerative Learning To Enhance Dense Prediction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {19466-19477} }

MACARONS: Mapping and Coverage Anticipation With RGB Online Self-Supervision

Antoine Guédon,

Tom Monnier,

Pascal Monasse,

Vincent Lepetit

[pdf] [supp]

[bibtex]

@InProceedings{Guedon_2023_CVPR, author = {Gu\'edon, Antoine and Monnier, Tom and Monasse, Pascal and Lepetit, Vincent}, title = {MACARONS: Mapping and Coverage Anticipation With RGB Online Self-Supervision}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {940-951} }

Audio-Visual Grouping Network for Sound Localization From Mixtures

Shentong Mo,

Yapeng Tian

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Mo_2023_CVPR, author = {Mo, Shentong and Tian, Yapeng}, title = {Audio-Visual Grouping Network for Sound Localization From Mixtures}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10565-10574} }

Fair Federated Medical Image Segmentation via Client Contribution Estimation

Meirui Jiang,

Holger R. Roth,

Wenqi Li,

Dong Yang,

Can Zhao,

Vishwesh Nath,

Daguang Xu,

Qi Dou,

Ziyue Xu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Jiang_2023_CVPR, author = {Jiang, Meirui and Roth, Holger R. and Li, Wenqi and Yang, Dong and Zhao, Can and Nath, Vishwesh and Xu, Daguang and Dou, Qi and Xu, Ziyue}, title = {Fair Federated Medical Image Segmentation via Client Contribution Estimation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16302-16311} }

Dynamic Generative Targeted Attacks With Pattern Injection

Weiwei Feng,

Nanqing Xu,

Tianzhu Zhang,

Yongdong Zhang

[pdf] [supp]

[bibtex]

@InProceedings{Feng_2023_CVPR, author = {Feng, Weiwei and Xu, Nanqing and Zhang, Tianzhu and Zhang, Yongdong}, title = {Dynamic Generative Targeted Attacks With Pattern Injection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16404-16414} }

Tracking Multiple Deformable Objects in Egocentric Videos

Mingzhen Huang,

Xiaoxing Li,

Jun Hu,

Honghong Peng,

Siwei Lyu

[pdf]

[bibtex]

@InProceedings{Huang_2023_CVPR, author = {Huang, Mingzhen and Li, Xiaoxing and Hu, Jun and Peng, Honghong and Lyu, Siwei}, title = {Tracking Multiple Deformable Objects in Egocentric Videos}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1461-1471} }

Visual Recognition by Request

Chufeng Tang,

Lingxi Xie,

Xiaopeng Zhang,

Xiaolin Hu,

Qi Tian

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Tang_2023_CVPR, author = {Tang, Chufeng and Xie, Lingxi and Zhang, Xiaopeng and Hu, Xiaolin and Tian, Qi}, title = {Visual Recognition by Request}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15265-15274} }

SmartBrush: Text and Shape Guided Object Inpainting With Diffusion Model

Shaoan Xie,

Zhifei Zhang,

Zhe Lin,

Tobias Hinz,

Kun Zhang

[pdf] [arXiv]

[bibtex]

@InProceedings{Xie_2023_CVPR, author = {Xie, Shaoan and Zhang, Zhifei and Lin, Zhe and Hinz, Tobias and Zhang, Kun}, title = {SmartBrush: Text and Shape Guided Object Inpainting With Diffusion Model}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {22428-22437} }

REC-MV: REconstructing 3D Dynamic Cloth From Monocular Videos

Lingteng Qiu,

Guanying Chen,

Jiapeng Zhou,

Mutian Xu,

Junle Wang,

Xiaoguang Han

[pdf] [supp]

[bibtex]

@InProceedings{Qiu_2023_CVPR, author = {Qiu, Lingteng and Chen, Guanying and Zhou, Jiapeng and Xu, Mutian and Wang, Junle and Han, Xiaoguang}, title = {REC-MV: REconstructing 3D Dynamic Cloth From Monocular Videos}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4637-4646} }

JRDB-Pose: A Large-Scale Dataset for Multi-Person Pose Estimation and Tracking

Edward Vendrow,

Duy Tho Le,

Jianfei Cai,

Hamid Rezatofighi

[pdf] [supp]

[bibtex]

@InProceedings{Vendrow_2023_CVPR, author = {Vendrow, Edward and Le, Duy Tho and Cai, Jianfei and Rezatofighi, Hamid}, title = {JRDB-Pose: A Large-Scale Dataset for Multi-Person Pose Estimation and Tracking}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4811-4820} }

AsyFOD: An Asymmetric Adaptation Paradigm for Few-Shot Domain Adaptive Object Detection

Yipeng Gao,

Kun-Yu Lin,

Junkai Yan,

Yaowei Wang,

Wei-Shi Zheng

[pdf]

[bibtex]

@InProceedings{Gao_2023_CVPR, author = {Gao, Yipeng and Lin, Kun-Yu and Yan, Junkai and Wang, Yaowei and Zheng, Wei-Shi}, title = {AsyFOD: An Asymmetric Adaptation Paradigm for Few-Shot Domain Adaptive Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3261-3271} }

RUST: Latent Neural Scene Representations From Unposed Imagery

Mehdi S. M. Sajjadi,

Aravindh Mahendran,

Thomas Kipf,

Etienne Pot,

Daniel Duckworth,

Mario Lučić,

Klaus Greff

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Sajjadi_2023_CVPR, author = {Sajjadi, Mehdi S. M. and Mahendran, Aravindh and Kipf, Thomas and Pot, Etienne and Duckworth, Daniel and Lu\v{c}i\'c, Mario and Greff, Klaus}, title = {RUST: Latent Neural Scene Representations From Unposed Imagery}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {17297-17306} }

PointCert: Point Cloud Classification With Deterministic Certified Robustness Guarantees

Jinghuai Zhang,

Jinyuan Jia,

Hongbin Liu,

Neil Zhenqiang Gong

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Zhang_2023_CVPR, author = {Zhang, Jinghuai and Jia, Jinyuan and Liu, Hongbin and Gong, Neil Zhenqiang}, title = {PointCert: Point Cloud Classification With Deterministic Certified Robustness Guarantees}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9496-9505} }

Open Set Action Recognition via Multi-Label Evidential Learning

Chen Zhao,

Dawei Du,

Anthony Hoogs,

Christopher Funk

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Zhao_2023_CVPR, author = {Zhao, Chen and Du, Dawei and Hoogs, Anthony and Funk, Christopher}, title = {Open Set Action Recognition via Multi-Label Evidential Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {22982-22991} }

MAP: Multimodal Uncertainty-Aware Vision-Language Pre-Training Model

Yatai Ji,

Junjie Wang,

Yuan Gong,

Lin Zhang,

Yanru Zhu,

Hongfa Wang,

Jiaxing Zhang,

Tetsuya Sakai,

Yujiu Yang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Ji_2023_CVPR, author = {Ji, Yatai and Wang, Junjie and Gong, Yuan and Zhang, Lin and Zhu, Yanru and Wang, Hongfa and Zhang, Jiaxing and Sakai, Tetsuya and Yang, Yujiu}, title = {MAP: Multimodal Uncertainty-Aware Vision-Language Pre-Training Model}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {23262-23271} }

DualRel: Semi-Supervised Mitochondria Segmentation From a Prototype Perspective

Huayu Mai,

Rui Sun,

Tianzhu Zhang,

Zhiwei Xiong,

Feng Wu

[pdf] [supp]

[bibtex]

@InProceedings{Mai_2023_CVPR, author = {Mai, Huayu and Sun, Rui and Zhang, Tianzhu and Xiong, Zhiwei and Wu, Feng}, title = {DualRel: Semi-Supervised Mitochondria Segmentation From a Prototype Perspective}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {19617-19626} }

Federated Learning With Data-Agnostic Distribution Fusion

Jian-hui Duan,

Wenzhong Li,

Derun Zou,

Ruichen Li,

Sanglu Lu

[pdf] [supp]

[bibtex]

@InProceedings{Duan_2023_CVPR, author = {Duan, Jian-hui and Li, Wenzhong and Zou, Derun and Li, Ruichen and Lu, Sanglu}, title = {Federated Learning With Data-Agnostic Distribution Fusion}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8074-8083} }

Cap4Video: What Can Auxiliary Captions Do for Text-Video Retrieval?

Wenhao Wu,

Haipeng Luo,

Bo Fang,

Jingdong Wang,

Wanli Ouyang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Wu_2023_CVPR, author = {Wu, Wenhao and Luo, Haipeng and Fang, Bo and Wang, Jingdong and Ouyang, Wanli}, title = {Cap4Video: What Can Auxiliary Captions Do for Text-Video Retrieval?}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10704-10713} }

Progressive Semantic-Visual Mutual Adaption for Generalized Zero-Shot Learning

Man Liu,

Feng Li,

Chunjie Zhang,

Yunchao Wei,

Huihui Bai,

Yao Zhao

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Liu_2023_CVPR, author = {Liu, Man and Li, Feng and Zhang, Chunjie and Wei, Yunchao and Bai, Huihui and Zhao, Yao}, title = {Progressive Semantic-Visual Mutual Adaption for Generalized Zero-Shot Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15337-15346} }

Gated Multi-Resolution Transfer Network for Burst Restoration and Enhancement

Nancy Mehta,

Akshay Dudhane,

Subrahmanyam Murala,

Syed Waqas Zamir,

Salman Khan,

Fahad Shahbaz Khan

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Mehta_2023_CVPR, author = {Mehta, Nancy and Dudhane, Akshay and Murala, Subrahmanyam and Zamir, Syed Waqas and Khan, Salman and Khan, Fahad Shahbaz}, title = {Gated Multi-Resolution Transfer Network for Burst Restoration and Enhancement}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {22201-22210} }

Improving Commonsense in Vision-Language Models via Knowledge Graph Riddles

Shuquan Ye,

Yujia Xie,

Dongdong Chen,

Yichong Xu,

Lu Yuan,

Chenguang Zhu,

Jing Liao

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Ye_2023_CVPR, author = {Ye, Shuquan and Xie, Yujia and Chen, Dongdong and Xu, Yichong and Yuan, Lu and Zhu, Chenguang and Liao, Jing}, title = {Improving Commonsense in Vision-Language Models via Knowledge Graph Riddles}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2634-2645} }

S3C: Semi-Supervised VQA Natural Language Explanation via Self-Critical Learning

Wei Suo,

Mengyang Sun,

Weisong Liu,

Yiqi Gao,

Peng Wang,

Yanning Zhang,

Qi Wu

[pdf]

[bibtex]

@InProceedings{Suo_2023_CVPR, author = {Suo, Wei and Sun, Mengyang and Liu, Weisong and Gao, Yiqi and Wang, Peng and Zhang, Yanning and Wu, Qi}, title = {S3C: Semi-Supervised VQA Natural Language Explanation via Self-Critical Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2646-2656} }

Spatio-Focal Bidirectional Disparity Estimation From a Dual-Pixel Image

Donggun Kim,

Hyeonjoong Jang,

Inchul Kim,

Min H. Kim

[pdf] [supp]

[bibtex]

@InProceedings{Kim_2023_CVPR, author = {Kim, Donggun and Jang, Hyeonjoong and Kim, Inchul and Kim, Min H.}, title = {Spatio-Focal Bidirectional Disparity Estimation From a Dual-Pixel Image}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5023-5032} }

Block Selection Method for Using Feature Norm in Out-of-Distribution Detection

Yeonguk Yu,

Sungho Shin,

Seongju Lee,

Changhyun Jun,

Kyoobin Lee

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Yu_2023_CVPR, author = {Yu, Yeonguk and Shin, Sungho and Lee, Seongju and Jun, Changhyun and Lee, Kyoobin}, title = {Block Selection Method for Using Feature Norm in Out-of-Distribution Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15701-15711} }

PIDNet: A Real-Time Semantic Segmentation Network Inspired by PID Controllers

Jiacong Xu,

Zixiang Xiong,

Shankar P. Bhattacharyya

[pdf] [arXiv]

[bibtex]

@InProceedings{Xu_2023_CVPR, author = {Xu, Jiacong and Xiong, Zixiang and Bhattacharyya, Shankar P.}, title = {PIDNet: A Real-Time Semantic Segmentation Network Inspired by PID Controllers}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {19529-19539} }

Four-View Geometry With Unknown Radial Distortion

Petr Hruby,

Viktor Korotynskiy,

Timothy Duff,

Luke Oeding,

Marc Pollefeys,

Tomas Pajdla,

Viktor Larsson

[pdf] [supp]

[bibtex]

@InProceedings{Hruby_2023_CVPR, author = {Hruby, Petr and Korotynskiy, Viktor and Duff, Timothy and Oeding, Luke and Pollefeys, Marc and Pajdla, Tomas and Larsson, Viktor}, title = {Four-View Geometry With Unknown Radial Distortion}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8990-9000} }

Rethinking Optical Flow From Geometric Matching Consistent Perspective

Qiaole Dong,

Chenjie Cao,

Yanwei Fu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Dong_2023_CVPR, author = {Dong, Qiaole and Cao, Chenjie and Fu, Yanwei}, title = {Rethinking Optical Flow From Geometric Matching Consistent Perspective}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1337-1347} }

Frustratingly Easy Regularization on Representation Can Boost Deep Reinforcement Learning

Qiang He,

Huangyuan Su,

Jieyu Zhang,

Xinwen Hou

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{He_2023_CVPR, author = {He, Qiang and Su, Huangyuan and Zhang, Jieyu and Hou, Xinwen}, title = {Frustratingly Easy Regularization on Representation Can Boost Deep Reinforcement Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {20215-20225} }

PointDistiller: Structured Knowledge Distillation Towards Efficient and Compact 3D Detection

Linfeng Zhang,

Runpei Dong,

Hung-Shuo Tai,

Kaisheng Ma

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Zhang_2023_CVPR, author = {Zhang, Linfeng and Dong, Runpei and Tai, Hung-Shuo and Ma, Kaisheng}, title = {PointDistiller: Structured Knowledge Distillation Towards Efficient and Compact 3D Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {21791-21801} }

Learning Optical Expansion From Scale Matching

Han Ling,

Yinghui Sun,

Quansen Sun,

Zhenwen Ren

[pdf] [supp]

[bibtex]

@InProceedings{Ling_2023_CVPR, author = {Ling, Han and Sun, Yinghui and Sun, Quansen and Ren, Zhenwen}, title = {Learning Optical Expansion From Scale Matching}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5445-5454} }

LEMaRT: Label-Efficient Masked Region Transform for Image Harmonization

Sheng Liu,

Cong Phuoc Huynh,

Cong Chen,

Maxim Arap,

Raffay Hamid

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Liu_2023_CVPR, author = {Liu, Sheng and Huynh, Cong Phuoc and Chen, Cong and Arap, Maxim and Hamid, Raffay}, title = {LEMaRT: Label-Efficient Masked Region Transform for Image Harmonization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {18290-18299} }

How To Prevent the Poor Performance Clients for Personalized Federated Learning?

Zhe Qu,

Xingyu Li,

Xiao Han,

Rui Duan,

Chengchao Shen,

Lixing Chen

[pdf] [supp]

[bibtex]

@InProceedings{Qu_2023_CVPR, author = {Qu, Zhe and Li, Xingyu and Han, Xiao and Duan, Rui and Shen, Chengchao and Chen, Lixing}, title = {How To Prevent the Poor Performance Clients for Personalized Federated Learning?}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12167-12176} }

TopDiG: Class-Agnostic Topological Directional Graph Extraction From Remote Sensing Images

Bingnan Yang,

Mi Zhang,

Zhan Zhang,

Zhili Zhang,

Xiangyun Hu

[pdf] [supp]

[bibtex]

@InProceedings{Yang_2023_CVPR, author = {Yang, Bingnan and Zhang, Mi and Zhang, Zhan and Zhang, Zhili and Hu, Xiangyun}, title = {TopDiG: Class-Agnostic Topological Directional Graph Extraction From Remote Sensing Images}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1265-1274} }

Galactic: Scaling End-to-End Reinforcement Learning for Rearrangement at 100k Steps-per-Second

Vincent-Pierre Berges,

Andrew Szot,

Devendra Singh Chaplot,

Aaron Gokaslan,

Roozbeh Mottaghi,

Dhruv Batra,

Eric Undersander

[pdf] [supp]

[bibtex]

@InProceedings{Berges_2023_CVPR, author = {Berges, Vincent-Pierre and Szot, Andrew and Chaplot, Devendra Singh and Gokaslan, Aaron and Mottaghi, Roozbeh and Batra, Dhruv and Undersander, Eric}, title = {Galactic: Scaling End-to-End Reinforcement Learning for Rearrangement at 100k Steps-per-Second}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13767-13777} }

StyleIPSB: Identity-Preserving Semantic Basis of StyleGAN for High Fidelity Face Swapping

Diqiong Jiang,

Dan Song,

Ruofeng Tong,

Min Tang

[pdf] [supp]

[bibtex]

@InProceedings{Jiang_2023_CVPR, author = {Jiang, Diqiong and Song, Dan and Tong, Ruofeng and Tang, Min}, title = {StyleIPSB: Identity-Preserving Semantic Basis of StyleGAN for High Fidelity Face Swapping}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {352-361} }

Unknown Sniffer for Object Detection: Don't Turn a Blind Eye to Unknown Objects

Wenteng Liang,

Feng Xue,

Yihao Liu,

Guofeng Zhong,

Anlong Ming

[pdf] [supp]

[bibtex]

@InProceedings{Liang_2023_CVPR, author = {Liang, Wenteng and Xue, Feng and Liu, Yihao and Zhong, Guofeng and Ming, Anlong}, title = {Unknown Sniffer for Object Detection: Don't Turn a Blind Eye to Unknown Objects}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3230-3239} }

Discriminator-Cooperated Feature Map Distillation for GAN Compression

Tie Hu,

Mingbao Lin,

Lizhou You,

Fei Chao,

Rongrong Ji

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Hu_2023_CVPR, author = {Hu, Tie and Lin, Mingbao and You, Lizhou and Chao, Fei and Ji, Rongrong}, title = {Discriminator-Cooperated Feature Map Distillation for GAN Compression}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {20351-20360} }

Learning on Gradients: Generalized Artifacts Representation for GAN-Generated Images Detection

Chuangchuang Tan,

Yao Zhao,

Shikui Wei,

Guanghua Gu,

Yunchao Wei

[pdf]

[bibtex]

@InProceedings{Tan_2023_CVPR, author = {Tan, Chuangchuang and Zhao, Yao and Wei, Shikui and Gu, Guanghua and Wei, Yunchao}, title = {Learning on Gradients: Generalized Artifacts Representation for GAN-Generated Images Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12105-12114} }

Don't Lie to Me! Robust and Efficient Explainability With Verified Perturbation Analysis

Thomas Fel,

Melanie Ducoffe,

David Vigouroux,

Rémi Cadène,

Mikaël Capelle,

Claire Nicodème,

Thomas Serre

[pdf] [supp]

[bibtex]

@InProceedings{Fel_2023_CVPR, author = {Fel, Thomas and Ducoffe, Melanie and Vigouroux, David and Cad\`ene, R\'emi and Capelle, Mika\"el and Nicod\`eme, Claire and Serre, Thomas}, title = {Don't Lie to Me! Robust and Efficient Explainability With Verified Perturbation Analysis}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16153-16163} }

StyleAdv: Meta Style Adversarial Training for Cross-Domain Few-Shot Learning

Yuqian Fu,

Yu Xie,

Yanwei Fu,

Yu-Gang Jiang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Fu_2023_CVPR, author = {Fu, Yuqian and Xie, Yu and Fu, Yanwei and Jiang, Yu-Gang}, title = {StyleAdv: Meta Style Adversarial Training for Cross-Domain Few-Shot Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {24575-24584} }

Multi-Concept Customization of Text-to-Image Diffusion

Nupur Kumari,

Bingliang Zhang,

Richard Zhang,

Eli Shechtman,

Jun-Yan Zhu

[pdf] [arXiv]

[bibtex]

@InProceedings{Kumari_2023_CVPR, author = {Kumari, Nupur and Zhang, Bingliang and Zhang, Richard and Shechtman, Eli and Zhu, Jun-Yan}, title = {Multi-Concept Customization of Text-to-Image Diffusion}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1931-1941} }

Defending Against Patch-Based Backdoor Attacks on Self-Supervised Learning

Ajinkya Tejankar,

Maziar Sanjabi,

Qifan Wang,

Sinong Wang,

Hamed Firooz,

Hamed Pirsiavash,

Liang Tan

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Tejankar_2023_CVPR, author = {Tejankar, Ajinkya and Sanjabi, Maziar and Wang, Qifan and Wang, Sinong and Firooz, Hamed and Pirsiavash, Hamed and Tan, Liang}, title = {Defending Against Patch-Based Backdoor Attacks on Self-Supervised Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12239-12249} }

Long-Tailed Visual Recognition via Self-Heterogeneous Integration With Knowledge Excavation

Yan Jin,

Mengke Li,

Yang Lu,

Yiu-ming Cheung,

Hanzi Wang

[pdf] [arXiv]

[bibtex]

@InProceedings{Jin_2023_CVPR, author = {Jin, Yan and Li, Mengke and Lu, Yang and Cheung, Yiu-ming and Wang, Hanzi}, title = {Long-Tailed Visual Recognition via Self-Heterogeneous Integration With Knowledge Excavation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {23695-23704} }

GeoNet: Benchmarking Unsupervised Adaptation Across Geographies

Tarun Kalluri,

Wangdong Xu,

Manmohan Chandraker

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Kalluri_2023_CVPR, author = {Kalluri, Tarun and Xu, Wangdong and Chandraker, Manmohan}, title = {GeoNet: Benchmarking Unsupervised Adaptation Across Geographies}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15368-15379} }

Context De-Confounded Emotion Recognition

Dingkang Yang,

Zhaoyu Chen,

Yuzheng Wang,

Shunli Wang,

Mingcheng Li,

Siao Liu,

Xiao Zhao,

Shuai Huang,

Zhiyan Dong,

Peng Zhai,

Lihua Zhang

[pdf] [arXiv]

[bibtex]

@InProceedings{Yang_2023_CVPR, author = {Yang, Dingkang and Chen, Zhaoyu and Wang, Yuzheng and Wang, Shunli and Li, Mingcheng and Liu, Siao and Zhao, Xiao and Huang, Shuai and Dong, Zhiyan and Zhai, Peng and Zhang, Lihua}, title = {Context De-Confounded Emotion Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {19005-19015} }

LinK: Linear Kernel for LiDAR-Based 3D Perception

Tao Lu,

Xiang Ding,

Haisong Liu,

Gangshan Wu,

Limin Wang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Lu_2023_CVPR, author = {Lu, Tao and Ding, Xiang and Liu, Haisong and Wu, Gangshan and Wang, Limin}, title = {LinK: Linear Kernel for LiDAR-Based 3D Perception}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1105-1115} }

CP3: Channel Pruning Plug-In for Point-Based Networks

Yaomin Huang,

Ning Liu,

Zhengping Che,

Zhiyuan Xu,

Chaomin Shen,

Yaxin Peng,

Guixu Zhang,

Xinmei Liu,

Feifei Feng,

Jian Tang

[pdf] [supp]

[bibtex]

@InProceedings{Huang_2023_CVPR, author = {Huang, Yaomin and Liu, Ning and Che, Zhengping and Xu, Zhiyuan and Shen, Chaomin and Peng, Yaxin and Zhang, Guixu and Liu, Xinmei and Feng, Feifei and Tang, Jian}, title = {CP3: Channel Pruning Plug-In for Point-Based Networks}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5302-5312} }

InstructPix2Pix: Learning To Follow Image Editing Instructions

Tim Brooks,

Aleksander Holynski,

Alexei A. Efros

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Brooks_2023_CVPR, author = {Brooks, Tim and Holynski, Aleksander and Efros, Alexei A.}, title = {InstructPix2Pix: Learning To Follow Image Editing Instructions}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {18392-18402} }

Learning Transformation-Predictive Representations for Detection and Description of Local Features

Zihao Wang,

Chunxu Wu,

Yifei Yang,

Zhen Li

[pdf] [supp]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Zihao and Wu, Chunxu and Yang, Yifei and Li, Zhen}, title = {Learning Transformation-Predictive Representations for Detection and Description of Local Features}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11464-11473} }

Two-Way Multi-Label Loss

Takumi Kobayashi

[pdf] [supp]

[bibtex]

@InProceedings{Kobayashi_2023_CVPR, author = {Kobayashi, Takumi}, title = {Two-Way Multi-Label Loss}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7476-7485} }

Progressive Disentangled Representation Learning for Fine-Grained Controllable Talking Head Synthesis

Duomin Wang,

Yu Deng,

Zixin Yin,

Heung-Yeung Shum,

Baoyuan Wang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Duomin and Deng, Yu and Yin, Zixin and Shum, Heung-Yeung and Wang, Baoyuan}, title = {Progressive Disentangled Representation Learning for Fine-Grained Controllable Talking Head Synthesis}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {17979-17989} }

Breaking the "Object" in Video Object Segmentation

Pavel Tokmakov,

Jie Li,

Adrien Gaidon

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Tokmakov_2023_CVPR, author = {Tokmakov, Pavel and Li, Jie and Gaidon, Adrien}, title = {Breaking the ''Object'' in Video Object Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {22836-22845} }

Where Is My Wallet? Modeling Object Proposal Sets for Egocentric Visual Query Localization

Mengmeng Xu,

Yanghao Li,

Cheng-Yang Fu,

Bernard Ghanem,

Tao Xiang,

Juan-Manuel Pérez-Rúa

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Xu_2023_CVPR, author = {Xu, Mengmeng and Li, Yanghao and Fu, Cheng-Yang and Ghanem, Bernard and Xiang, Tao and P\'erez-R\'ua, Juan-Manuel}, title = {Where Is My Wallet? Modeling Object Proposal Sets for Egocentric Visual Query Localization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2593-2603} }

Dionysus: Recovering Scene Structures by Dividing Into Semantic Pieces

Likang Wang,

Lei Chen

[pdf]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Likang and Chen, Lei}, title = {Dionysus: Recovering Scene Structures by Dividing Into Semantic Pieces}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12576-12587} }

ReDirTrans: Latent-to-Latent Translation for Gaze and Head Redirection

Shiwei Jin,

Zhen Wang,

Lei Wang,

Ning Bi,

Truong Nguyen

[pdf] [supp]

[bibtex]

@InProceedings{Jin_2023_CVPR, author = {Jin, Shiwei and Wang, Zhen and Wang, Lei and Bi, Ning and Nguyen, Truong}, title = {ReDirTrans: Latent-to-Latent Translation for Gaze and Head Redirection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5547-5556} }

Advancing Visual Grounding With Scene Knowledge: Benchmark and Method

Zhihong Chen,

Ruifei Zhang,

Yibing Song,

Xiang Wan,

Guanbin Li

[pdf]

[bibtex]

@InProceedings{Chen_2023_CVPR, author = {Chen, Zhihong and Zhang, Ruifei and Song, Yibing and Wan, Xiang and Li, Guanbin}, title = {Advancing Visual Grounding With Scene Knowledge: Benchmark and Method}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15039-15049} }

Noisy Correspondence Learning With Meta Similarity Correction

Haochen Han,

Kaiyao Miao,

Qinghua Zheng,

Minnan Luo

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Han_2023_CVPR, author = {Han, Haochen and Miao, Kaiyao and Zheng, Qinghua and Luo, Minnan}, title = {Noisy Correspondence Learning With Meta Similarity Correction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7517-7526} }

CoWs on Pasture: Baselines and Benchmarks for Language-Driven Zero-Shot Object Navigation

Samir Yitzhak Gadre,

Mitchell Wortsman,

Gabriel Ilharco,

Ludwig Schmidt,

Shuran Song

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Gadre_2023_CVPR, author = {Gadre, Samir Yitzhak and Wortsman, Mitchell and Ilharco, Gabriel and Schmidt, Ludwig and Song, Shuran}, title = {CoWs on Pasture: Baselines and Benchmarks for Language-Driven Zero-Shot Object Navigation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {23171-23181} }

CIGAR: Cross-Modality Graph Reasoning for Domain Adaptive Object Detection

Yabo Liu,

Jinghua Wang,

Chao Huang,

Yaowei Wang,

Yong Xu

[pdf]

[bibtex]

@InProceedings{Liu_2023_CVPR, author = {Liu, Yabo and Wang, Jinghua and Huang, Chao and Wang, Yaowei and Xu, Yong}, title = {CIGAR: Cross-Modality Graph Reasoning for Domain Adaptive Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {23776-23786} }

Multiview Compressive Coding for 3D Reconstruction

Chao-Yuan Wu,

Justin Johnson,

Jitendra Malik,

Christoph Feichtenhofer,

Georgia Gkioxari

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Wu_2023_CVPR, author = {Wu, Chao-Yuan and Johnson, Justin and Malik, Jitendra and Feichtenhofer, Christoph and Gkioxari, Georgia}, title = {Multiview Compressive Coding for 3D Reconstruction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9065-9075} }

HOOD: Hierarchical Graphs for Generalized Modelling of Clothing Dynamics

Artur Grigorev,

Michael J. Black,

Otmar Hilliges

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Grigorev_2023_CVPR, author = {Grigorev, Artur and Black, Michael J. and Hilliges, Otmar}, title = {HOOD: Hierarchical Graphs for Generalized Modelling of Clothing Dynamics}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16965-16974} }

HyperReel: High-Fidelity 6-DoF Video With Ray-Conditioned Sampling

Benjamin Attal,

Jia-Bin Huang,

Christian Richardt,

Michael Zollhöfer,

Johannes Kopf,

Matthew O’Toole,

Changil Kim

[pdf] [supp]

[bibtex]

@InProceedings{Attal_2023_CVPR, author = {Attal, Benjamin and Huang, Jia-Bin and Richardt, Christian and Zollh\"ofer, Michael and Kopf, Johannes and O{\textquoteright}Toole, Matthew and Kim, Changil}, title = {HyperReel: High-Fidelity 6-DoF Video With Ray-Conditioned Sampling}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16610-16620} }

Rethinking Video ViTs: Sparse Video Tubes for Joint Image and Video Learning

AJ Piergiovanni,

Weicheng Kuo,

Anelia Angelova

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Piergiovanni_2023_CVPR, author = {Piergiovanni, AJ and Kuo, Weicheng and Angelova, Anelia}, title = {Rethinking Video ViTs: Sparse Video Tubes for Joint Image and Video Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2214-2224} }

Modeling Entities As Semantic Points for Visual Information Extraction in the Wild

Zhibo Yang,

Rujiao Long,

Pengfei Wang,

Sibo Song,

Humen Zhong,

Wenqing Cheng,

Xiang Bai,

Cong Yao

[pdf] [arXiv]

[bibtex]

@InProceedings{Yang_2023_CVPR, author = {Yang, Zhibo and Long, Rujiao and Wang, Pengfei and Song, Sibo and Zhong, Humen and Cheng, Wenqing and Bai, Xiang and Yao, Cong}, title = {Modeling Entities As Semantic Points for Visual Information Extraction in the Wild}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15358-15367} }

MobileVOS: Real-Time Video Object Segmentation Contrastive Learning Meets Knowledge Distillation

Roy Miles,

Mehmet Kerim Yucel,

Bruno Manganelli,

Albert Saà-Garriga

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Miles_2023_CVPR, author = {Miles, Roy and Yucel, Mehmet Kerim and Manganelli, Bruno and Sa\`a-Garriga, Albert}, title = {MobileVOS: Real-Time Video Object Segmentation Contrastive Learning Meets Knowledge Distillation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10480-10490} }

PCR: Proxy-Based Contrastive Replay for Online Class-Incremental Continual Learning

Huiwei Lin,

Baoquan Zhang,

Shanshan Feng,

Xutao Li,

Yunming Ye

[pdf] [arXiv]

[bibtex]

@InProceedings{Lin_2023_CVPR, author = {Lin, Huiwei and Zhang, Baoquan and Feng, Shanshan and Li, Xutao and Ye, Yunming}, title = {PCR: Proxy-Based Contrastive Replay for Online Class-Incremental Continual Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {24246-24255} }

Pose Synchronization Under Multiple Pair-Wise Relative Poses

Yifan Sun,

Qixing Huang

[pdf] [supp]

[bibtex]

@InProceedings{Sun_2023_CVPR, author = {Sun, Yifan and Huang, Qixing}, title = {Pose Synchronization Under Multiple Pair-Wise Relative Poses}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13072-13081} }

Unsupervised Continual Semantic Adaptation Through Neural Rendering

Zhizheng Liu,

Francesco Milano,

Jonas Frey,

Roland Siegwart,

Hermann Blum,

Cesar Cadena

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Liu_2023_CVPR, author = {Liu, Zhizheng and Milano, Francesco and Frey, Jonas and Siegwart, Roland and Blum, Hermann and Cadena, Cesar}, title = {Unsupervised Continual Semantic Adaptation Through Neural Rendering}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3031-3040} }

Controllable Light Diffusion for Portraits

David Futschik,

Kelvin Ritland,

James Vecore,

Sean Fanello,

Sergio Orts-Escolano,

Brian Curless,

Daniel Sýkora,

Rohit Pandey

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Futschik_2023_CVPR, author = {Futschik, David and Ritland, Kelvin and Vecore, James and Fanello, Sean and Orts-Escolano, Sergio and Curless, Brian and S\'ykora, Daniel and Pandey, Rohit}, title = {Controllable Light Diffusion for Portraits}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8412-8421} }

Token Boosting for Robust Self-Supervised Visual Transformer Pre-Training

Tianjiao Li,

Lin Geng Foo,

Ping Hu,

Xindi Shang,

Hossein Rahmani,

Zehuan Yuan,

Jun Liu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Li_2023_CVPR, author = {Li, Tianjiao and Foo, Lin Geng and Hu, Ping and Shang, Xindi and Rahmani, Hossein and Yuan, Zehuan and Liu, Jun}, title = {Token Boosting for Robust Self-Supervised Visual Transformer Pre-Training}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {24027-24038} }

Multi-View Adversarial Discriminator: Mine the Non-Causal Factors for Object Detection in Unseen Domains

Mingjun Xu,

Lingyun Qin,

Weijie Chen,

Shiliang Pu,

Lei Zhang

[pdf] [arXiv]

[bibtex]

@InProceedings{Xu_2023_CVPR, author = {Xu, Mingjun and Qin, Lingyun and Chen, Weijie and Pu, Shiliang and Zhang, Lei}, title = {Multi-View Adversarial Discriminator: Mine the Non-Causal Factors for Object Detection in Unseen Domains}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8103-8112} }

MaskCon: Masked Contrastive Learning for Coarse-Labelled Dataset

Chen Feng,

Ioannis Patras

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Feng_2023_CVPR, author = {Feng, Chen and Patras, Ioannis}, title = {MaskCon: Masked Contrastive Learning for Coarse-Labelled Dataset}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {19913-19922} }

Boosting Low-Data Instance Segmentation by Unsupervised Pre-Training With Saliency Prompt

Hao Li,

Dingwen Zhang,

Nian Liu,

Lechao Cheng,

Yalun Dai,

Chao Zhang,

Xinggang Wang,

Junwei Han

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Li_2023_CVPR, author = {Li, Hao and Zhang, Dingwen and Liu, Nian and Cheng, Lechao and Dai, Yalun and Zhang, Chao and Wang, Xinggang and Han, Junwei}, title = {Boosting Low-Data Instance Segmentation by Unsupervised Pre-Training With Saliency Prompt}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15485-15494} }

Virtual Occlusions Through Implicit Depth

Jamie Watson,

Mohamed Sayed,

Zawar Qureshi,

Gabriel J. Brostow,

Sara Vicente,

Oisin Mac Aodha,

Michael Firman

[pdf] [arXiv]

[bibtex]

@InProceedings{Watson_2023_CVPR, author = {Watson, Jamie and Sayed, Mohamed and Qureshi, Zawar and Brostow, Gabriel J. and Vicente, Sara and Mac Aodha, Oisin and Firman, Michael}, title = {Virtual Occlusions Through Implicit Depth}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9053-9064} }

AGAIN: Adversarial Training With Attribution Span Enlargement and Hybrid Feature Fusion

Shenglin Yin,

Kelu Yao,

Sheng Shi,

Yangzhou Du,

Zhen Xiao

[pdf] [supp]

[bibtex]

@InProceedings{Yin_2023_CVPR, author = {Yin, Shenglin and Yao, Kelu and Shi, Sheng and Du, Yangzhou and Xiao, Zhen}, title = {AGAIN: Adversarial Training With Attribution Span Enlargement and Hybrid Feature Fusion}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {20544-20553} }

Instance Relation Graph Guided Source-Free Domain Adaptive Object Detection

Vibashan VS,

Poojan Oza,

Vishal M. Patel

[pdf] [arXiv]

[bibtex]

@InProceedings{VS_2023_CVPR, author = {VS, Vibashan and Oza, Poojan and Patel, Vishal M.}, title = {Instance Relation Graph Guided Source-Free Domain Adaptive Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3520-3530} }

Instant Multi-View Head Capture Through Learnable Registration

Timo Bolkart,

Tianye Li,

Michael J. Black

[pdf] [supp]

[bibtex]

@InProceedings{Bolkart_2023_CVPR, author = {Bolkart, Timo and Li, Tianye and Black, Michael J.}, title = {Instant Multi-View Head Capture Through Learnable Registration}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {768-779} }

DiGA: Distil To Generalize and Then Adapt for Domain Adaptive Semantic Segmentation

Fengyi Shen,

Akhil Gurram,

Ziyuan Liu,

He Wang,

Alois Knoll

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Shen_2023_CVPR, author = {Shen, Fengyi and Gurram, Akhil and Liu, Ziyuan and Wang, He and Knoll, Alois}, title = {DiGA: Distil To Generalize and Then Adapt for Domain Adaptive Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15866-15877} }

DiffSwap: High-Fidelity and Controllable Face Swapping via 3D-Aware Masked Diffusion

Wenliang Zhao,

Yongming Rao,

Weikang Shi,

Zuyan Liu,

Jie Zhou,

Jiwen Lu

[pdf]

[bibtex]

@InProceedings{Zhao_2023_CVPR, author = {Zhao, Wenliang and Rao, Yongming and Shi, Weikang and Liu, Zuyan and Zhou, Jie and Lu, Jiwen}, title = {DiffSwap: High-Fidelity and Controllable Face Swapping via 3D-Aware Masked Diffusion}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8568-8577} }

GINA-3D: Learning To Generate Implicit Neural Assets in the Wild

Bokui Shen,

Xinchen Yan,

Charles R. Qi,

Mahyar Najibi,

Boyang Deng,

Leonidas Guibas,

Yin Zhou,

Dragomir Anguelov

[pdf] [supp]

[bibtex]

@InProceedings{Shen_2023_CVPR, author = {Shen, Bokui and Yan, Xinchen and Qi, Charles R. and Najibi, Mahyar and Deng, Boyang and Guibas, Leonidas and Zhou, Yin and Anguelov, Dragomir}, title = {GINA-3D: Learning To Generate Implicit Neural Assets in the Wild}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4913-4926} }

Consistent Direct Time-of-Flight Video Depth Super-Resolution

Zhanghao Sun,

Wei Ye,

Jinhui Xiong,

Gyeongmin Choe,

Jialiang Wang,

Shuochen Su,

Rakesh Ranjan

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Sun_2023_CVPR, author = {Sun, Zhanghao and Ye, Wei and Xiong, Jinhui and Choe, Gyeongmin and Wang, Jialiang and Su, Shuochen and Ranjan, Rakesh}, title = {Consistent Direct Time-of-Flight Video Depth Super-Resolution}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5075-5085} }

Crossing the Gap: Domain Generalization for Image Captioning

Yuchen Ren,

Zhendong Mao,

Shancheng Fang,

Yan Lu,

Tong He,

Hao Du,

Yongdong Zhang,

Wanli Ouyang

[pdf] [supp]

[bibtex]

@InProceedings{Ren_2023_CVPR, author = {Ren, Yuchen and Mao, Zhendong and Fang, Shancheng and Lu, Yan and He, Tong and Du, Hao and Zhang, Yongdong and Ouyang, Wanli}, title = {Crossing the Gap: Domain Generalization for Image Captioning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2871-2880} }

Probabilistic Prompt Learning for Dense Prediction

Hyeongjun Kwon,

Taeyong Song,

Somi Jeong,

Jin Kim,

Jinhyun Jang,

Kwanghoon Sohn

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Kwon_2023_CVPR, author = {Kwon, Hyeongjun and Song, Taeyong and Jeong, Somi and Kim, Jin and Jang, Jinhyun and Sohn, Kwanghoon}, title = {Probabilistic Prompt Learning for Dense Prediction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6768-6777} }

Learned Image Compression With Mixed Transformer-CNN Architectures

Jinming Liu,

Heming Sun,

Jiro Katto

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Liu_2023_CVPR, author = {Liu, Jinming and Sun, Heming and Katto, Jiro}, title = {Learned Image Compression With Mixed Transformer-CNN Architectures}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14388-14397} }

Exploring Intra-Class Variation Factors With Learnable Cluster Prompts for Semi-Supervised Image Synthesis

Yunfei Zhang,

Xiaoyang Huo,

Tianyi Chen,

Si Wu,

Hau San Wong

[pdf]

[bibtex]

@InProceedings{Zhang_2023_CVPR, author = {Zhang, Yunfei and Huo, Xiaoyang and Chen, Tianyi and Wu, Si and Wong, Hau San}, title = {Exploring Intra-Class Variation Factors With Learnable Cluster Prompts for Semi-Supervised Image Synthesis}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7392-7401} }

NeAT: Learning Neural Implicit Surfaces With Arbitrary Topologies From Multi-View Images

Xiaoxu Meng,

Weikai Chen,

Bo Yang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Meng_2023_CVPR, author = {Meng, Xiaoxu and Chen, Weikai and Yang, Bo}, title = {NeAT: Learning Neural Implicit Surfaces With Arbitrary Topologies From Multi-View Images}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {248-258} }

Quantum Multi-Model Fitting

Matteo Farina,

Luca Magri,

Willi Menapace,

Elisa Ricci,

Vladislav Golyanik,

Federica Arrigoni

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Farina_2023_CVPR, author = {Farina, Matteo and Magri, Luca and Menapace, Willi and Ricci, Elisa and Golyanik, Vladislav and Arrigoni, Federica}, title = {Quantum Multi-Model Fitting}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13640-13649} }

SPARF: Neural Radiance Fields From Sparse and Noisy Poses

Prune Truong,

Marie-Julie Rakotosaona,

Fabian Manhardt,

Federico Tombari

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Truong_2023_CVPR, author = {Truong, Prune and Rakotosaona, Marie-Julie and Manhardt, Fabian and Tombari, Federico}, title = {SPARF: Neural Radiance Fields From Sparse and Noisy Poses}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4190-4200} }

ABLE-NeRF: Attention-Based Rendering With Learnable Embeddings for Neural Radiance Field

Zhe Jun Tang,

Tat-Jen Cham,

Haiyu Zhao

[pdf] [supp]

[bibtex]

@InProceedings{Tang_2023_CVPR, author = {Tang, Zhe Jun and Cham, Tat-Jen and Zhao, Haiyu}, title = {ABLE-NeRF: Attention-Based Rendering With Learnable Embeddings for Neural Radiance Field}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16559-16568} }

Local Implicit Normalizing Flow for Arbitrary-Scale Image Super-Resolution

Jie-En Yao,

Li-Yuan Tsao,

Yi-Chen Lo,

Roy Tseng,

Chia-Che Chang,

Chun-Yi Lee

[pdf] [arXiv]

[bibtex]

@InProceedings{Yao_2023_CVPR, author = {Yao, Jie-En and Tsao, Li-Yuan and Lo, Yi-Chen and Tseng, Roy and Chang, Chia-Che and Lee, Chun-Yi}, title = {Local Implicit Normalizing Flow for Arbitrary-Scale Image Super-Resolution}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1776-1785} }

WinCLIP: Zero-/Few-Shot Anomaly Classification and Segmentation

Jongheon Jeong,

Yang Zou,

Taewan Kim,

Dongqing Zhang,

Avinash Ravichandran,

Onkar Dabeer

[pdf] [supp]

[bibtex]

@InProceedings{Jeong_2023_CVPR, author = {Jeong, Jongheon and Zou, Yang and Kim, Taewan and Zhang, Dongqing and Ravichandran, Avinash and Dabeer, Onkar}, title = {WinCLIP: Zero-/Few-Shot Anomaly Classification and Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {19606-19616} }

PermutoSDF: Fast Multi-View Reconstruction With Implicit Surfaces Using Permutohedral Lattices

Radu Alexandru Rosu,

Sven Behnke

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Rosu_2023_CVPR, author = {Rosu, Radu Alexandru and Behnke, Sven}, title = {PermutoSDF: Fast Multi-View Reconstruction With Implicit Surfaces Using Permutohedral Lattices}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8466-8475} }

TriDet: Temporal Action Detection With Relative Boundary Modeling

Dingfeng Shi,

Yujie Zhong,

Qiong Cao,

Lin Ma,

Jia Li,

Dacheng Tao

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Shi_2023_CVPR, author = {Shi, Dingfeng and Zhong, Yujie and Cao, Qiong and Ma, Lin and Li, Jia and Tao, Dacheng}, title = {TriDet: Temporal Action Detection With Relative Boundary Modeling}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {18857-18866} }

Detection Hub: Unifying Object Detection Datasets via Query Adaptation on Language Embedding

Lingchen Meng,

Xiyang Dai,

Yinpeng Chen,

Pengchuan Zhang,

Dongdong Chen,

Mengchen Liu,

Jianfeng Wang,

Zuxuan Wu,

Lu Yuan,

Yu-Gang Jiang

[pdf] [arXiv]

[bibtex]

@InProceedings{Meng_2023_CVPR, author = {Meng, Lingchen and Dai, Xiyang and Chen, Yinpeng and Zhang, Pengchuan and Chen, Dongdong and Liu, Mengchen and Wang, Jianfeng and Wu, Zuxuan and Yuan, Lu and Jiang, Yu-Gang}, title = {Detection Hub: Unifying Object Detection Datasets via Query Adaptation on Language Embedding}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11402-11411} }

Dream3D: Zero-Shot Text-to-3D Synthesis Using 3D Shape Prior and Text-to-Image Diffusion Models

Jiale Xu,

Xintao Wang,

Weihao Cheng,

Yan-Pei Cao,

Ying Shan,

Xiaohu Qie,

Shenghua Gao

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Xu_2023_CVPR, author = {Xu, Jiale and Wang, Xintao and Cheng, Weihao and Cao, Yan-Pei and Shan, Ying and Qie, Xiaohu and Gao, Shenghua}, title = {Dream3D: Zero-Shot Text-to-3D Synthesis Using 3D Shape Prior and Text-to-Image Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {20908-20918} }

Adversarial Normalization: I Can Visualize Everything (ICE)

Hoyoung Choi,

Seungwan Jin,

Kyungsik Han

[pdf]

[bibtex]

@InProceedings{Choi_2023_CVPR, author = {Choi, Hoyoung and Jin, Seungwan and Han, Kyungsik}, title = {Adversarial Normalization: I Can Visualize Everything (ICE)}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12115-12124} }

Reinforcement Learning-Based Black-Box Model Inversion Attacks

Gyojin Han,

Jaehyun Choi,

Haeil Lee,

Junmo Kim

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Han_2023_CVPR, author = {Han, Gyojin and Choi, Jaehyun and Lee, Haeil and Kim, Junmo}, title = {Reinforcement Learning-Based Black-Box Model Inversion Attacks}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {20504-20513} }

Learning a Deep Color Difference Metric for Photographic Images

Haoyu Chen,

Zhihua Wang,

Yang Yang,

Qilin Sun,

Kede Ma

[pdf] [arXiv]

[bibtex]

@InProceedings{Chen_2023_CVPR, author = {Chen, Haoyu and Wang, Zhihua and Yang, Yang and Sun, Qilin and Ma, Kede}, title = {Learning a Deep Color Difference Metric for Photographic Images}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {22242-22251} }

1000 FPS HDR Video With a Spike-RGB Hybrid Camera

Yakun Chang,

Chu Zhou,

Yuchen Hong,

Liwen Hu,

Chao Xu,

Tiejun Huang,

Boxin Shi

[pdf] [supp]

[bibtex]

@InProceedings{Chang_2023_CVPR, author = {Chang, Yakun and Zhou, Chu and Hong, Yuchen and Hu, Liwen and Xu, Chao and Huang, Tiejun and Shi, Boxin}, title = {1000 FPS HDR Video With a Spike-RGB Hybrid Camera}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {22180-22190} }

DINN360: Deformable Invertible Neural Network for Latitude-Aware 360deg Image Rescaling

Yichen Guo,

Mai Xu,

Lai Jiang,

Leonid Sigal,

Yunjin Chen

[pdf] [supp]

[bibtex]

@InProceedings{Guo_2023_CVPR, author = {Guo, Yichen and Xu, Mai and Jiang, Lai and Sigal, Leonid and Chen, Yunjin}, title = {DINN360: Deformable Invertible Neural Network for Latitude-Aware 360deg Image Rescaling}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {21519-21528} }

Learning Geometric-Aware Properties in 2D Representation Using Lightweight CAD Models, or Zero Real 3D Pairs

Pattaramanee Arsomngern,

Sarana Nutanong,

Supasorn Suwajanakorn

[pdf] [supp]

[bibtex]

@InProceedings{Arsomngern_2023_CVPR, author = {Arsomngern, Pattaramanee and Nutanong, Sarana and Suwajanakorn, Supasorn}, title = {Learning Geometric-Aware Properties in 2D Representation Using Lightweight CAD Models, or Zero Real 3D Pairs}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {21371-21381} }

Texts as Images in Prompt Tuning for Multi-Label Image Recognition

Zixian Guo,

Bowen Dong,

Zhilong Ji,

Jinfeng Bai,

Yiwen Guo,

Wangmeng Zuo

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Guo_2023_CVPR, author = {Guo, Zixian and Dong, Bowen and Ji, Zhilong and Bai, Jinfeng and Guo, Yiwen and Zuo, Wangmeng}, title = {Texts as Images in Prompt Tuning for Multi-Label Image Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2808-2817} }

Self-Correctable and Adaptable Inference for Generalizable Human Pose Estimation

Zhehan Kan,

Shuoshuo Chen,

Ce Zhang,

Yushun Tang,

Zhihai He

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Kan_2023_CVPR, author = {Kan, Zhehan and Chen, Shuoshuo and Zhang, Ce and Tang, Yushun and He, Zhihai}, title = {Self-Correctable and Adaptable Inference for Generalizable Human Pose Estimation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5537-5546} }

Few-Shot Learning With Visual Distribution Calibration and Cross-Modal Distribution Alignment

Runqi Wang,

Hao Zheng,

Xiaoyue Duan,

Jianzhuang Liu,

Yuning Lu,

Tian Wang,

Songcen Xu,

Baochang Zhang

[pdf] [supp]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Runqi and Zheng, Hao and Duan, Xiaoyue and Liu, Jianzhuang and Lu, Yuning and Wang, Tian and Xu, Songcen and Zhang, Baochang}, title = {Few-Shot Learning With Visual Distribution Calibration and Cross-Modal Distribution Alignment}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {23445-23454} }

Referring Multi-Object Tracking

Dongming Wu,

Wencheng Han,

Tiancai Wang,

Xingping Dong,

Xiangyu Zhang,

Jianbing Shen

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Wu_2023_CVPR, author = {Wu, Dongming and Han, Wencheng and Wang, Tiancai and Dong, Xingping and Zhang, Xiangyu and Shen, Jianbing}, title = {Referring Multi-Object Tracking}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14633-14642} }

Finetune Like You Pretrain: Improved Finetuning of Zero-Shot Vision Models

Sachin Goyal,

Ananya Kumar,

Sankalp Garg,

Zico Kolter,

Aditi Raghunathan

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Goyal_2023_CVPR, author = {Goyal, Sachin and Kumar, Ananya and Garg, Sankalp and Kolter, Zico and Raghunathan, Aditi}, title = {Finetune Like You Pretrain: Improved Finetuning of Zero-Shot Vision Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {19338-19347} }

GradMA: A Gradient-Memory-Based Accelerated Federated Learning With Alleviated Catastrophic Forgetting

Kangyang Luo,

Xiang Li,

Yunshi Lan,

Ming Gao

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Luo_2023_CVPR, author = {Luo, Kangyang and Li, Xiang and Lan, Yunshi and Gao, Ming}, title = {GradMA: A Gradient-Memory-Based Accelerated Federated Learning With Alleviated Catastrophic Forgetting}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3708-3717} }

Weakly Supervised Temporal Sentence Grounding With Uncertainty-Guided Self-Training

Yifei Huang,

Lijin Yang,

Yoichi Sato

[pdf]

[bibtex]

@InProceedings{Huang_2023_CVPR, author = {Huang, Yifei and Yang, Lijin and Sato, Yoichi}, title = {Weakly Supervised Temporal Sentence Grounding With Uncertainty-Guided Self-Training}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {18908-18918} }

Hint-Aug: Drawing Hints From Foundation Vision Transformers Towards Boosted Few-Shot Parameter-Efficient Tuning

Zhongzhi Yu,

Shang Wu,

Yonggan Fu,

Shunyao Zhang,

Yingyan (Celine) Lin

[pdf]

[bibtex]

@InProceedings{Yu_2023_CVPR, author = {Yu, Zhongzhi and Wu, Shang and Fu, Yonggan and Zhang, Shunyao and Lin, Yingyan (Celine)}, title = {Hint-Aug: Drawing Hints From Foundation Vision Transformers Towards Boosted Few-Shot Parameter-Efficient Tuning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11102-11112} }

A Strong Baseline for Generalized Few-Shot Semantic Segmentation

Sina Hajimiri,

Malik Boudiaf,

Ismail Ben Ayed,

Jose Dolz

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Hajimiri_2023_CVPR, author = {Hajimiri, Sina and Boudiaf, Malik and Ben Ayed, Ismail and Dolz, Jose}, title = {A Strong Baseline for Generalized Few-Shot Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11269-11278} }

AutoRecon: Automated 3D Object Discovery and Reconstruction

Yuang Wang,

Xingyi He,

Sida Peng,

Haotong Lin,

Hujun Bao,

Xiaowei Zhou

[pdf] [arXiv]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Yuang and He, Xingyi and Peng, Sida and Lin, Haotong and Bao, Hujun and Zhou, Xiaowei}, title = {AutoRecon: Automated 3D Object Discovery and Reconstruction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {21382-21391} }

POTTER: Pooling Attention Transformer for Efficient Human Mesh Recovery

Ce Zheng,

Xianpeng Liu,

Guo-Jun Qi,

Chen Chen

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Zheng_2023_CVPR, author = {Zheng, Ce and Liu, Xianpeng and Qi, Guo-Jun and Chen, Chen}, title = {POTTER: Pooling Attention Transformer for Efficient Human Mesh Recovery}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1611-1620} }

Learning a Practical SDR-to-HDRTV Up-Conversion Using New Dataset and Degradation Models

Cheng Guo,

Leidong Fan,

Ziyu Xue,

Xiuhua Jiang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Guo_2023_CVPR, author = {Guo, Cheng and Fan, Leidong and Xue, Ziyu and Jiang, Xiuhua}, title = {Learning a Practical SDR-to-HDRTV Up-Conversion Using New Dataset and Degradation Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {22231-22241} }

Learning Detailed Radiance Manifolds for High-Fidelity and 3D-Consistent Portrait Synthesis From Monocular Image

Yu Deng,

Baoyuan Wang,

Heung-Yeung Shum

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Deng_2023_CVPR, author = {Deng, Yu and Wang, Baoyuan and Shum, Heung-Yeung}, title = {Learning Detailed Radiance Manifolds for High-Fidelity and 3D-Consistent Portrait Synthesis From Monocular Image}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4423-4433} }

Patch-Craft Self-Supervised Training for Correlated Image Denoising

Gregory Vaksman,

Michael Elad

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Vaksman_2023_CVPR, author = {Vaksman, Gregory and Elad, Michael}, title = {Patch-Craft Self-Supervised Training for Correlated Image Denoising}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5795-5804} }

Learning To Fuse Monocular and Multi-View Cues for Multi-Frame Depth Estimation in Dynamic Scenes

Rui Li,

Dong Gong,

Wei Yin,

Hao Chen,

Yu Zhu,

Kaixuan Wang,

Xiaozhi Chen,

Jinqiu Sun,

Yanning Zhang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Li_2023_CVPR, author = {Li, Rui and Gong, Dong and Yin, Wei and Chen, Hao and Zhu, Yu and Wang, Kaixuan and Chen, Xiaozhi and Sun, Jinqiu and Zhang, Yanning}, title = {Learning To Fuse Monocular and Multi-View Cues for Multi-Frame Depth Estimation in Dynamic Scenes}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {21539-21548} }

DynaFed: Tackling Client Data Heterogeneity With Global Dynamics

Renjie Pi,

Weizhong Zhang,

Yueqi Xie,

Jiahui Gao,

Xiaoyu Wang,

Sunghun Kim,

Qifeng Chen

[pdf] [arXiv]

[bibtex]

@InProceedings{Pi_2023_CVPR, author = {Pi, Renjie and Zhang, Weizhong and Xie, Yueqi and Gao, Jiahui and Wang, Xiaoyu and Kim, Sunghun and Chen, Qifeng}, title = {DynaFed: Tackling Client Data Heterogeneity With Global Dynamics}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12177-12186} }

Bias-Eliminating Augmentation Learning for Debiased Federated Learning

Yuan-Yi Xu,

Ci-Siang Lin,

Yu-Chiang Frank Wang

[pdf]

[bibtex]

@InProceedings{Xu_2023_CVPR, author = {Xu, Yuan-Yi and Lin, Ci-Siang and Wang, Yu-Chiang Frank}, title = {Bias-Eliminating Augmentation Learning for Debiased Federated Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {20442-20452} }

DistilPose: Tokenized Pose Regression With Heatmap Distillation

Suhang Ye,

Yingyi Zhang,

Jie Hu,

Liujuan Cao,

Shengchuan Zhang,

Lei Shen,

Jun Wang,

Shouhong Ding,

Rongrong Ji

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Ye_2023_CVPR, author = {Ye, Suhang and Zhang, Yingyi and Hu, Jie and Cao, Liujuan and Zhang, Shengchuan and Shen, Lei and Wang, Jun and Ding, Shouhong and Ji, Rongrong}, title = {DistilPose: Tokenized Pose Regression With Heatmap Distillation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2163-2172} }

Understanding the Robustness of 3D Object Detection With Bird's-Eye-View Representations in Autonomous Driving

Zijian Zhu,

Yichi Zhang,

Hai Chen,

Yinpeng Dong,

Shu Zhao,

Wenbo Ding,

Jiachen Zhong,

Shibao Zheng

[pdf] [supp]

[bibtex]

@InProceedings{Zhu_2023_CVPR, author = {Zhu, Zijian and Zhang, Yichi and Chen, Hai and Dong, Yinpeng and Zhao, Shu and Ding, Wenbo and Zhong, Jiachen and Zheng, Shibao}, title = {Understanding the Robustness of 3D Object Detection With Bird's-Eye-View Representations in Autonomous Driving}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {21600-21610} }

Neural Volumetric Memory for Visual Locomotion Control

Ruihan Yang,

Ge Yang,

Xiaolong Wang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Yang_2023_CVPR, author = {Yang, Ruihan and Yang, Ge and Wang, Xiaolong}, title = {Neural Volumetric Memory for Visual Locomotion Control}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1430-1440} }

CUF: Continuous Upsampling Filters

Cristina N. Vasconcelos,

Cengiz Oztireli,

Mark Matthews,

Milad Hashemi,

Kevin Swersky,

Andrea Tagliasacchi

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Vasconcelos_2023_CVPR, author = {Vasconcelos, Cristina N. and Oztireli, Cengiz and Matthews, Mark and Hashemi, Milad and Swersky, Kevin and Tagliasacchi, Andrea}, title = {CUF: Continuous Upsampling Filters}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9999-10008} }

Generalist: Decoupling Natural and Robust Generalization

Hongjun Wang,

Yisen Wang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Hongjun and Wang, Yisen}, title = {Generalist: Decoupling Natural and Robust Generalization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {20554-20563} }

Propagate and Calibrate: Real-Time Passive Non-Line-of-Sight Tracking

Yihao Wang,

Zhigang Wang,

Bin Zhao,

Dong Wang,

Mulin Chen,

Xuelong Li

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Yihao and Wang, Zhigang and Zhao, Bin and Wang, Dong and Chen, Mulin and Li, Xuelong}, title = {Propagate and Calibrate: Real-Time Passive Non-Line-of-Sight Tracking}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {972-981} }

Learning Decorrelated Representations Efficiently Using Fast Fourier Transform

Yutaro Shigeto,

Masashi Shimbo,

Yuya Yoshikawa,

Akikazu Takeuchi

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Shigeto_2023_CVPR, author = {Shigeto, Yutaro and Shimbo, Masashi and Yoshikawa, Yuya and Takeuchi, Akikazu}, title = {Learning Decorrelated Representations Efficiently Using Fast Fourier Transform}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2052-2060} }

Quantitative Manipulation of Custom Attributes on 3D-Aware Image Synthesis

Hoseok Do,

EunKyung Yoo,

Taehyeong Kim,

Chul Lee,

Jin Young Choi

[pdf] [supp]

[bibtex]

@InProceedings{Do_2023_CVPR, author = {Do, Hoseok and Yoo, EunKyung and Kim, Taehyeong and Lee, Chul and Choi, Jin Young}, title = {Quantitative Manipulation of Custom Attributes on 3D-Aware Image Synthesis}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8529-8538} }

Explicit Visual Prompting for Low-Level Structure Segmentations

Weihuang Liu,

Xi Shen,

Chi-Man Pun,

Xiaodong Cun

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Liu_2023_CVPR, author = {Liu, Weihuang and Shen, Xi and Pun, Chi-Man and Cun, Xiaodong}, title = {Explicit Visual Prompting for Low-Level Structure Segmentations}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {19434-19445} }

HOTNAS: Hierarchical Optimal Transport for Neural Architecture Search

Jiechao Yang,

Yong Liu,

Hongteng Xu

[pdf] [supp]

[bibtex]

@InProceedings{Yang_2023_CVPR, author = {Yang, Jiechao and Liu, Yong and Xu, Hongteng}, title = {HOTNAS: Hierarchical Optimal Transport for Neural Architecture Search}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11990-12000} }

Two-Shot Video Object Segmentation

Kun Yan,

Xiao Li,

Fangyun Wei,

Jinglu Wang,

Chenbin Zhang,

Ping Wang,

Yan Lu

[pdf] [arXiv]

[bibtex]

@InProceedings{Yan_2023_CVPR, author = {Yan, Kun and Li, Xiao and Wei, Fangyun and Wang, Jinglu and Zhang, Chenbin and Wang, Ping and Lu, Yan}, title = {Two-Shot Video Object Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2257-2267} }

Neural Fields Meet Explicit Geometric Representations for Inverse Rendering of Urban Scenes

Zian Wang,

Tianchang Shen,

Jun Gao,

Shengyu Huang,

Jacob Munkberg,

Jon Hasselgren,

Zan Gojcic,

Wenzheng Chen,

Sanja Fidler

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Zian and Shen, Tianchang and Gao, Jun and Huang, Shengyu and Munkberg, Jacob and Hasselgren, Jon and Gojcic, Zan and Chen, Wenzheng and Fidler, Sanja}, title = {Neural Fields Meet Explicit Geometric Representations for Inverse Rendering of Urban Scenes}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8370-8380} }

Practical Network Acceleration With Tiny Sets

Guo-Hua Wang,

Jianxin Wu

[pdf] [supp]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Guo-Hua and Wu, Jianxin}, title = {Practical Network Acceleration With Tiny Sets}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {20331-20340} }

NeRF-RPN: A General Framework for Object Detection in NeRFs

Benran Hu,

Junkai Huang,

Yichen Liu,

Yu-Wing Tai,

Chi-Keung Tang

[pdf] [supp]

[bibtex]

@InProceedings{Hu_2023_CVPR, author = {Hu, Benran and Huang, Junkai and Liu, Yichen and Tai, Yu-Wing and Tang, Chi-Keung}, title = {NeRF-RPN: A General Framework for Object Detection in NeRFs}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {23528-23538} }

Cross-Image-Attention for Conditional Embeddings in Deep Metric Learning

Dmytro Kotovenko,

Pingchuan Ma,

Timo Milbich,

Björn Ommer

[pdf] [supp]

[bibtex]

@InProceedings{Kotovenko_2023_CVPR, author = {Kotovenko, Dmytro and Ma, Pingchuan and Milbich, Timo and Ommer, Bj\"orn}, title = {Cross-Image-Attention for Conditional Embeddings in Deep Metric Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11070-11081} }

Masked Wavelet Representation for Compact Neural Radiance Fields

Daniel Rho,

Byeonghyeon Lee,

Seungtae Nam,

Joo Chan Lee,

Jong Hwan Ko,

Eunbyung Park

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Rho_2023_CVPR, author = {Rho, Daniel and Lee, Byeonghyeon and Nam, Seungtae and Lee, Joo Chan and Ko, Jong Hwan and Park, Eunbyung}, title = {Masked Wavelet Representation for Compact Neural Radiance Fields}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {20680-20690} }

PiMAE: Point Cloud and Image Interactive Masked Autoencoders for 3D Object Detection

Anthony Chen,

Kevin Zhang,

Renrui Zhang,

Zihan Wang,

Yuheng Lu,

Yandong Guo,

Shanghang Zhang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Chen_2023_CVPR, author = {Chen, Anthony and Zhang, Kevin and Zhang, Renrui and Wang, Zihan and Lu, Yuheng and Guo, Yandong and Zhang, Shanghang}, title = {PiMAE: Point Cloud and Image Interactive Masked Autoencoders for 3D Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5291-5301} }

ObjectStitch: Object Compositing With Diffusion Model

Yizhi Song,

Zhifei Zhang,

Zhe Lin,

Scott Cohen,

Brian Price,

Jianming Zhang,

Soo Ye Kim,

Daniel Aliaga

[pdf] [supp]

[bibtex]

@InProceedings{Song_2023_CVPR, author = {Song, Yizhi and Zhang, Zhifei and Lin, Zhe and Cohen, Scott and Price, Brian and Zhang, Jianming and Kim, Soo Ye and Aliaga, Daniel}, title = {ObjectStitch: Object Compositing With Diffusion Model}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {18310-18319} }

High-Fidelity 3D GAN Inversion by Pseudo-Multi-View Optimization

Jiaxin Xie,

Hao Ouyang,

Jingtan Piao,

Chenyang Lei,

Qifeng Chen

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Xie_2023_CVPR, author = {Xie, Jiaxin and Ouyang, Hao and Piao, Jingtan and Lei, Chenyang and Chen, Qifeng}, title = {High-Fidelity 3D GAN Inversion by Pseudo-Multi-View Optimization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {321-331} }

Anchor3DLane: Learning To Regress 3D Anchors for Monocular 3D Lane Detection

Shaofei Huang,

Zhenwei Shen,

Zehao Huang,

Zi-han Ding,

Jiao Dai,

Jizhong Han,

Naiyan Wang,

Si Liu

[pdf] [arXiv]

[bibtex]

@InProceedings{Huang_2023_CVPR, author = {Huang, Shaofei and Shen, Zhenwei and Huang, Zehao and Ding, Zi-han and Dai, Jiao and Han, Jizhong and Wang, Naiyan and Liu, Si}, title = {Anchor3DLane: Learning To Regress 3D Anchors for Monocular 3D Lane Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {17451-17460} }

Class-Balancing Diffusion Models

Yiming Qin,

Huangjie Zheng,

Jiangchao Yao,

Mingyuan Zhou,

Ya Zhang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Qin_2023_CVPR, author = {Qin, Yiming and Zheng, Huangjie and Yao, Jiangchao and Zhou, Mingyuan and Zhang, Ya}, title = {Class-Balancing Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {18434-18443} }

AstroNet: When Astrocyte Meets Artificial Neural Network

Mengqiao Han,

Liyuan Pan,

Xiabi Liu

[pdf] [supp]

[bibtex]

@InProceedings{Han_2023_CVPR, author = {Han, Mengqiao and Pan, Liyuan and Liu, Xiabi}, title = {AstroNet: When Astrocyte Meets Artificial Neural Network}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {20258-20268} }

Feature Alignment and Uniformity for Test Time Adaptation

Shuai Wang,

Daoan Zhang,

Zipei Yan,

Jianguo Zhang,

Rui Li

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Shuai and Zhang, Daoan and Yan, Zipei and Zhang, Jianguo and Li, Rui}, title = {Feature Alignment and Uniformity for Test Time Adaptation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {20050-20060} }

Balanced Product of Calibrated Experts for Long-Tailed Recognition

Emanuel Sanchez Aimar,

Arvi Jonnarth,

Michael Felsberg,

Marco Kuhlmann

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Aimar_2023_CVPR, author = {Aimar, Emanuel Sanchez and Jonnarth, Arvi and Felsberg, Michael and Kuhlmann, Marco}, title = {Balanced Product of Calibrated Experts for Long-Tailed Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {19967-19977} }

Single Image Backdoor Inversion via Robust Smoothed Classifiers

Mingjie Sun,

Zico Kolter

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Sun_2023_CVPR, author = {Sun, Mingjie and Kolter, Zico}, title = {Single Image Backdoor Inversion via Robust Smoothed Classifiers}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8113-8122} }

PanoSwin: A Pano-Style Swin Transformer for Panorama Understanding

Zhixin Ling,

Zhen Xing,

Xiangdong Zhou,

Manliang Cao,

Guichun Zhou

[pdf] [supp]

[bibtex]

@InProceedings{Ling_2023_CVPR, author = {Ling, Zhixin and Xing, Zhen and Zhou, Xiangdong and Cao, Manliang and Zhou, Guichun}, title = {PanoSwin: A Pano-Style Swin Transformer for Panorama Understanding}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {17755-17764} }

Parameter Efficient Local Implicit Image Function Network for Face Segmentation

Mausoom Sarkar,

Nikitha SR,

Mayur Hemani,

Rishabh Jain,

Balaji Krishnamurthy

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Sarkar_2023_CVPR, author = {Sarkar, Mausoom and Nikitha, SR and Hemani, Mayur and Jain, Rishabh and Krishnamurthy, Balaji}, title = {Parameter Efficient Local Implicit Image Function Network for Face Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {20970-20980} }

A Hierarchical Representation Network for Accurate and Detailed Face Reconstruction From In-the-Wild Images

Biwen Lei,

Jianqiang Ren,

Mengyang Feng,

Miaomiao Cui,

Xuansong Xie

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Lei_2023_CVPR, author = {Lei, Biwen and Ren, Jianqiang and Feng, Mengyang and Cui, Miaomiao and Xie, Xuansong}, title = {A Hierarchical Representation Network for Accurate and Detailed Face Reconstruction From In-the-Wild Images}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {394-403} }

PersonNeRF: Personalized Reconstruction From Photo Collections

Chung-Yi Weng,

Pratul P. Srinivasan,

Brian Curless,

Ira Kemelmacher-Shlizerman

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Weng_2023_CVPR, author = {Weng, Chung-Yi and Srinivasan, Pratul P. and Curless, Brian and Kemelmacher-Shlizerman, Ira}, title = {PersonNeRF: Personalized Reconstruction From Photo Collections}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {524-533} }

Enhanced Multimodal Representation Learning With Cross-Modal KD

Mengxi Chen,

Linyu Xing,

Yu Wang,

Ya Zhang

[pdf] [supp]

[bibtex]

@InProceedings{Chen_2023_CVPR, author = {Chen, Mengxi and Xing, Linyu and Wang, Yu and Zhang, Ya}, title = {Enhanced Multimodal Representation Learning With Cross-Modal KD}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11766-11775} }

Learning a Depth Covariance Function

Eric Dexheimer,

Andrew J. Davison

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Dexheimer_2023_CVPR, author = {Dexheimer, Eric and Davison, Andrew J.}, title = {Learning a Depth Covariance Function}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13122-13131} }

Evading DeepFake Detectors via Adversarial Statistical Consistency

Yang Hou,

Qing Guo,

Yihao Huang,

Xiaofei Xie,

Lei Ma,

Jianjun Zhao

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Hou_2023_CVPR, author = {Hou, Yang and Guo, Qing and Huang, Yihao and Xie, Xiaofei and Ma, Lei and Zhao, Jianjun}, title = {Evading DeepFake Detectors via Adversarial Statistical Consistency}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12271-12280} }

Referring Image Matting

Jizhizi Li,

Jing Zhang,

Dacheng Tao

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Li_2023_CVPR, author = {Li, Jizhizi and Zhang, Jing and Tao, Dacheng}, title = {Referring Image Matting}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {22448-22457} }

V2V4Real: A Real-World Large-Scale Dataset for Vehicle-to-Vehicle Cooperative Perception

Runsheng Xu,

Xin Xia,

Jinlong Li,

Hanzhao Li,

Shuo Zhang,

Zhengzhong Tu,

Zonglin Meng,

Hao Xiang,

Xiaoyu Dong,

Rui Song,

Hongkai Yu,

Bolei Zhou,

Jiaqi Ma

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Xu_2023_CVPR, author = {Xu, Runsheng and Xia, Xin and Li, Jinlong and Li, Hanzhao and Zhang, Shuo and Tu, Zhengzhong and Meng, Zonglin and Xiang, Hao and Dong, Xiaoyu and Song, Rui and Yu, Hongkai and Zhou, Bolei and Ma, Jiaqi}, title = {V2V4Real: A Real-World Large-Scale Dataset for Vehicle-to-Vehicle Cooperative Perception}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13712-13722} }

RMLVQA: A Margin Loss Approach for Visual Question Answering With Language Biases

Abhipsa Basu,

Sravanti Addepalli,

R. Venkatesh Babu

[pdf] [supp]

[bibtex]

@InProceedings{Basu_2023_CVPR, author = {Basu, Abhipsa and Addepalli, Sravanti and Babu, R. Venkatesh}, title = {RMLVQA: A Margin Loss Approach for Visual Question Answering With Language Biases}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11671-11680} }

NeuralLift-360: Lifting an In-the-Wild 2D Photo to a 3D Object With 360deg Views

Dejia Xu,

Yifan Jiang,

Peihao Wang,

Zhiwen Fan,

Yi Wang,

Zhangyang Wang

[pdf] [supp]

[bibtex]

@InProceedings{Xu_2023_CVPR, author = {Xu, Dejia and Jiang, Yifan and Wang, Peihao and Fan, Zhiwen and Wang, Yi and Wang, Zhangyang}, title = {NeuralLift-360: Lifting an In-the-Wild 2D Photo to a 3D Object With 360deg Views}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4479-4489} }

ViP3D: End-to-End Visual Trajectory Prediction via 3D Agent Queries

Junru Gu,

Chenxu Hu,

Tianyuan Zhang,

Xuanyao Chen,

Yilun Wang,

Yue Wang,

Hang Zhao

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Gu_2023_CVPR, author = {Gu, Junru and Hu, Chenxu and Zhang, Tianyuan and Chen, Xuanyao and Wang, Yilun and Wang, Yue and Zhao, Hang}, title = {ViP3D: End-to-End Visual Trajectory Prediction via 3D Agent Queries}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5496-5506} }

Modality-Invariant Visual Odometry for Embodied Vision

Marius Memmel,

Roman Bachmann,

Amir Zamir

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Memmel_2023_CVPR, author = {Memmel, Marius and Bachmann, Roman and Zamir, Amir}, title = {Modality-Invariant Visual Odometry for Embodied Vision}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {21549-21559} }

What You Can Reconstruct From a Shadow

Ruoshi Liu,

Sachit Menon,

Chengzhi Mao,

Dennis Park,

Simon Stent,

Carl Vondrick

[pdf] [supp]

[bibtex]

@InProceedings{Liu_2023_CVPR, author = {Liu, Ruoshi and Menon, Sachit and Mao, Chengzhi and Park, Dennis and Stent, Simon and Vondrick, Carl}, title = {What You Can Reconstruct From a Shadow}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {17059-17068} }

Adaptive Sparse Convolutional Networks With Global Context Enhancement for Faster Object Detection on Drone Images

Bowei Du,

Yecheng Huang,

Jiaxin Chen,

Di Huang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Du_2023_CVPR, author = {Du, Bowei and Huang, Yecheng and Chen, Jiaxin and Huang, Di}, title = {Adaptive Sparse Convolutional Networks With Global Context Enhancement for Faster Object Detection on Drone Images}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13435-13444} }

LidarGait: Benchmarking 3D Gait Recognition With Point Clouds

Chuanfu Shen,

Chao Fan,

Wei Wu,

Rui Wang,

George Q. Huang,

Shiqi Yu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Shen_2023_CVPR, author = {Shen, Chuanfu and Fan, Chao and Wu, Wei and Wang, Rui and Huang, George Q. and Yu, Shiqi}, title = {LidarGait: Benchmarking 3D Gait Recognition With Point Clouds}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1054-1063} }

Command-Driven Articulated Object Understanding and Manipulation

Ruihang Chu,

Zhengzhe Liu,

Xiaoqing Ye,

Xiao Tan,

Xiaojuan Qi,

Chi-Wing Fu,

Jiaya Jia

[pdf] [supp]

[bibtex]

@InProceedings{Chu_2023_CVPR, author = {Chu, Ruihang and Liu, Zhengzhe and Ye, Xiaoqing and Tan, Xiao and Qi, Xiaojuan and Fu, Chi-Wing and Jia, Jiaya}, title = {Command-Driven Articulated Object Understanding and Manipulation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8813-8823} }

D2Former: Jointly Learning Hierarchical Detectors and Contextual Descriptors via Agent-Based Transformers

Jianfeng He,

Yuan Gao,

Tianzhu Zhang,

Zhe Zhang,

Feng Wu

[pdf] [supp]

[bibtex]

@InProceedings{He_2023_CVPR, author = {He, Jianfeng and Gao, Yuan and Zhang, Tianzhu and Zhang, Zhe and Wu, Feng}, title = {D2Former: Jointly Learning Hierarchical Detectors and Contextual Descriptors via Agent-Based Transformers}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2904-2914} }

ConStruct-VL: Data-Free Continual Structured VL Concepts Learning

James Seale Smith,

Paola Cascante-Bonilla,

Assaf Arbelle,

Donghyun Kim,

Rameswar Panda,

David Cox,

Diyi Yang,

Zsolt Kira,

Rogerio Feris,

Leonid Karlinsky

[pdf] [supp]

[bibtex]

@InProceedings{Smith_2023_CVPR, author = {Smith, James Seale and Cascante-Bonilla, Paola and Arbelle, Assaf and Kim, Donghyun and Panda, Rameswar and Cox, David and Yang, Diyi and Kira, Zsolt and Feris, Rogerio and Karlinsky, Leonid}, title = {ConStruct-VL: Data-Free Continual Structured VL Concepts Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14994-15004} }

Lite DETR: An Interleaved Multi-Scale Encoder for Efficient DETR

Feng Li,

Ailing Zeng,

Shilong Liu,

Hao Zhang,

Hongyang Li,

Lei Zhang,

Lionel M. Ni

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Li_2023_CVPR, author = {Li, Feng and Zeng, Ailing and Liu, Shilong and Zhang, Hao and Li, Hongyang and Zhang, Lei and Ni, Lionel M.}, title = {Lite DETR: An Interleaved Multi-Scale Encoder for Efficient DETR}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {18558-18567} }

HelixSurf: A Robust and Efficient Neural Implicit Surface Learning of Indoor Scenes With Iterative Intertwined Regularization

Zhihao Liang,

Zhangjin Huang,

Changxing Ding,

Kui Jia

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Liang_2023_CVPR, author = {Liang, Zhihao and Huang, Zhangjin and Ding, Changxing and Jia, Kui}, title = {HelixSurf: A Robust and Efficient Neural Implicit Surface Learning of Indoor Scenes With Iterative Intertwined Regularization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13165-13174} }

Joint Appearance and Motion Learning for Efficient Rolling Shutter Correction

Bin Fan,

Yuxin Mao,

Yuchao Dai,

Zhexiong Wan,

Qi Liu

[pdf] [supp]

[bibtex]

@InProceedings{Fan_2023_CVPR, author = {Fan, Bin and Mao, Yuxin and Dai, Yuchao and Wan, Zhexiong and Liu, Qi}, title = {Joint Appearance and Motion Learning for Efficient Rolling Shutter Correction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5671-5681} }

Towards a Smaller Student: Capacity Dynamic Distillation for Efficient Image Retrieval

Yi Xie,

Huaidong Zhang,

Xuemiao Xu,

Jianqing Zhu,

Shengfeng He

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Xie_2023_CVPR, author = {Xie, Yi and Zhang, Huaidong and Xu, Xuemiao and Zhu, Jianqing and He, Shengfeng}, title = {Towards a Smaller Student: Capacity Dynamic Distillation for Efficient Image Retrieval}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16006-16015} }

Federated Incremental Semantic Segmentation

Jiahua Dong,

Duzhen Zhang,

Yang Cong,

Wei Cong,

Henghui Ding,

Dengxin Dai

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Dong_2023_CVPR, author = {Dong, Jiahua and Zhang, Duzhen and Cong, Yang and Cong, Wei and Ding, Henghui and Dai, Dengxin}, title = {Federated Incremental Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3934-3943} }

3D-Aware Facial Landmark Detection via Multi-View Consistent Training on Synthetic Data

Libing Zeng,

Lele Chen,

Wentao Bao,

Zhong Li,

Yi Xu,

Junsong Yuan,

Nima Khademi Kalantari

[pdf] [supp]

[bibtex]

@InProceedings{Zeng_2023_CVPR, author = {Zeng, Libing and Chen, Lele and Bao, Wentao and Li, Zhong and Xu, Yi and Yuan, Junsong and Kalantari, Nima Khademi}, title = {3D-Aware Facial Landmark Detection via Multi-View Consistent Training on Synthetic Data}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12747-12758} }

Attention-Based Point Cloud Edge Sampling

Chengzhi Wu,

Junwei Zheng,

Julius Pfrommer,

Jürgen Beyerer

[pdf] [arXiv]

[bibtex]

@InProceedings{Wu_2023_CVPR, author = {Wu, Chengzhi and Zheng, Junwei and Pfrommer, Julius and Beyerer, J\"urgen}, title = {Attention-Based Point Cloud Edge Sampling}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5333-5343} }

Avatars Grow Legs: Generating Smooth Human Motion From Sparse Tracking Inputs With Diffusion Model

Yuming Du,

Robin Kips,

Albert Pumarola,

Sebastian Starke,

Ali Thabet,

Artsiom Sanakoyeu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Du_2023_CVPR, author = {Du, Yuming and Kips, Robin and Pumarola, Albert and Starke, Sebastian and Thabet, Ali and Sanakoyeu, Artsiom}, title = {Avatars Grow Legs: Generating Smooth Human Motion From Sparse Tracking Inputs With Diffusion Model}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {481-490} }

MobileNeRF: Exploiting the Polygon Rasterization Pipeline for Efficient Neural Field Rendering on Mobile Architectures

Zhiqin Chen,

Thomas Funkhouser,

Peter Hedman,

Andrea Tagliasacchi

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Chen_2023_CVPR, author = {Chen, Zhiqin and Funkhouser, Thomas and Hedman, Peter and Tagliasacchi, Andrea}, title = {MobileNeRF: Exploiting the Polygon Rasterization Pipeline for Efficient Neural Field Rendering on Mobile Architectures}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16569-16578} }

Pseudo-Label Guided Contrastive Learning for Semi-Supervised Medical Image Segmentation

Hritam Basak,

Zhaozheng Yin

[pdf]

[bibtex]

@InProceedings{Basak_2023_CVPR, author = {Basak, Hritam and Yin, Zhaozheng}, title = {Pseudo-Label Guided Contrastive Learning for Semi-Supervised Medical Image Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {19786-19797} }

Learning Neural Proto-Face Field for Disentangled 3D Face Modeling in the Wild

Zhenyu Zhang,

Renwang Chen,

Weijian Cao,

Ying Tai,

Chengjie Wang

[pdf] [supp]

[bibtex]

@InProceedings{Zhang_2023_CVPR, author = {Zhang, Zhenyu and Chen, Renwang and Cao, Weijian and Tai, Ying and Wang, Chengjie}, title = {Learning Neural Proto-Face Field for Disentangled 3D Face Modeling in the Wild}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {382-393} }

Self-Supervised Geometry-Aware Encoder for Style-Based 3D GAN Inversion

Yushi Lan,

Xuyi Meng,

Shuai Yang,

Chen Change Loy,

Bo Dai

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Lan_2023_CVPR, author = {Lan, Yushi and Meng, Xuyi and Yang, Shuai and Loy, Chen Change and Dai, Bo}, title = {Self-Supervised Geometry-Aware Encoder for Style-Based 3D GAN Inversion}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {20940-20949} }

PC2: Projection-Conditioned Point Cloud Diffusion for Single-Image 3D Reconstruction

Luke Melas-Kyriazi,

Christian Rupprecht,

Andrea Vedaldi

[pdf] [supp]

[bibtex]

@InProceedings{Melas-Kyriazi_2023_CVPR, author = {Melas-Kyriazi, Luke and Rupprecht, Christian and Vedaldi, Andrea}, title = {PC2: Projection-Conditioned Point Cloud Diffusion for Single-Image 3D Reconstruction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12923-12932} }

Gradient-Based Uncertainty Attribution for Explainable Bayesian Deep Learning

Hanjing Wang,

Dhiraj Joshi,

Shiqiang Wang,

Qiang Ji

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Hanjing and Joshi, Dhiraj and Wang, Shiqiang and Ji, Qiang}, title = {Gradient-Based Uncertainty Attribution for Explainable Bayesian Deep Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12044-12053} }

Manipulating Transfer Learning for Property Inference

Yulong Tian,

Fnu Suya,

Anshuman Suri,

Fengyuan Xu,

David Evans

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Tian_2023_CVPR, author = {Tian, Yulong and Suya, Fnu and Suri, Anshuman and Xu, Fengyuan and Evans, David}, title = {Manipulating Transfer Learning for Property Inference}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15975-15984} }

POEM: Reconstructing Hand in a Point Embedded Multi-View Stereo

Lixin Yang,

Jian Xu,

Licheng Zhong,

Xinyu Zhan,

Zhicheng Wang,

Kejian Wu,

Cewu Lu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Yang_2023_CVPR, author = {Yang, Lixin and Xu, Jian and Zhong, Licheng and Zhan, Xinyu and Wang, Zhicheng and Wu, Kejian and Lu, Cewu}, title = {POEM: Reconstructing Hand in a Point Embedded Multi-View Stereo}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {21108-21117} }

BUFFER: Balancing Accuracy, Efficiency, and Generalizability in Point Cloud Registration

Sheng Ao,

Qingyong Hu,

Hanyun Wang,

Kai Xu,

Yulan Guo

[pdf] [supp]

[bibtex]

@InProceedings{Ao_2023_CVPR, author = {Ao, Sheng and Hu, Qingyong and Wang, Hanyun and Xu, Kai and Guo, Yulan}, title = {BUFFER: Balancing Accuracy, Efficiency, and Generalizability in Point Cloud Registration}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1255-1264} }

CrOC: Cross-View Online Clustering for Dense Visual Representation Learning

Thomas Stegmüller,

Tim Lebailly,

Behzad Bozorgtabar,

Tinne Tuytelaars,

Jean-Philippe Thiran

[pdf] [supp]

[bibtex]

@InProceedings{Stegmuller_2023_CVPR, author = {Stegm\"uller, Thomas and Lebailly, Tim and Bozorgtabar, Behzad and Tuytelaars, Tinne and Thiran, Jean-Philippe}, title = {CrOC: Cross-View Online Clustering for Dense Visual Representation Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7000-7009} }

Class Adaptive Network Calibration

Bingyuan Liu,

Jérôme Rony,

Adrian Galdran,

Jose Dolz,

Ismail Ben Ayed

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Liu_2023_CVPR, author = {Liu, Bingyuan and Rony, J\'er\^ome and Galdran, Adrian and Dolz, Jose and Ben Ayed, Ismail}, title = {Class Adaptive Network Calibration}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16070-16079} }

DrapeNet: Garment Generation and Self-Supervised Draping

Luca De Luigi,

Ren Li,

Benoît Guillard,

Mathieu Salzmann,

Pascal Fua

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{De_Luigi_2023_CVPR, author = {De Luigi, Luca and Li, Ren and Guillard, Beno{\^\i}t and Salzmann, Mathieu and Fua, Pascal}, title = {DrapeNet: Garment Generation and Self-Supervised Draping}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1451-1460} }

Evading Forensic Classifiers With Attribute-Conditioned Adversarial Faces

Fahad Shamshad,

Koushik Srivatsan,

Karthik Nandakumar

[pdf] [supp]

[bibtex]

@InProceedings{Shamshad_2023_CVPR, author = {Shamshad, Fahad and Srivatsan, Koushik and Nandakumar, Karthik}, title = {Evading Forensic Classifiers With Attribute-Conditioned Adversarial Faces}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16469-16478} }

FeatureBooster: Boosting Feature Descriptors With a Lightweight Neural Network

Xinjiang Wang,

Zeyu Liu,

Yu Hu,

Wei Xi,

Wenxian Yu,

Danping Zou

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Xinjiang and Liu, Zeyu and Hu, Yu and Xi, Wei and Yu, Wenxian and Zou, Danping}, title = {FeatureBooster: Boosting Feature Descriptors With a Lightweight Neural Network}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7630-7639} }

Progressively Optimized Local Radiance Fields for Robust View Synthesis

Andréas Meuleman,

Yu-Lun Liu,

Chen Gao,

Jia-Bin Huang,

Changil Kim,

Min H. Kim,

Johannes Kopf

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Meuleman_2023_CVPR, author = {Meuleman, Andr\'eas and Liu, Yu-Lun and Gao, Chen and Huang, Jia-Bin and Kim, Changil and Kim, Min H. and Kopf, Johannes}, title = {Progressively Optimized Local Radiance Fields for Robust View Synthesis}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16539-16548} }

Towards Efficient Use of Multi-Scale Features in Transformer-Based Object Detectors

Gongjie Zhang,

Zhipeng Luo,

Zichen Tian,

Jingyi Zhang,

Xiaoqin Zhang,

Shijian Lu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Zhang_2023_CVPR, author = {Zhang, Gongjie and Luo, Zhipeng and Tian, Zichen and Zhang, Jingyi and Zhang, Xiaoqin and Lu, Shijian}, title = {Towards Efficient Use of Multi-Scale Features in Transformer-Based Object Detectors}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6206-6216} }

Delivering Arbitrary-Modal Semantic Segmentation

Jiaming Zhang,

Ruiping Liu,

Hao Shi,

Kailun Yang,

Simon Reiß,

Kunyu Peng,

Haodong Fu,

Kaiwei Wang,

Rainer Stiefelhagen

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Zhang_2023_CVPR, author = {Zhang, Jiaming and Liu, Ruiping and Shi, Hao and Yang, Kailun and Rei{\ss}, Simon and Peng, Kunyu and Fu, Haodong and Wang, Kaiwei and Stiefelhagen, Rainer}, title = {Delivering Arbitrary-Modal Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1136-1147} }

GeoMVSNet: Learning Multi-View Stereo With Geometry Perception

Zhe Zhang,

Rui Peng,

Yuxi Hu,

Ronggang Wang

[pdf] [supp]

[bibtex]

@InProceedings{Zhang_2023_CVPR, author = {Zhang, Zhe and Peng, Rui and Hu, Yuxi and Wang, Ronggang}, title = {GeoMVSNet: Learning Multi-View Stereo With Geometry Perception}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {21508-21518} }

Consistent-Teacher: Towards Reducing Inconsistent Pseudo-Targets in Semi-Supervised Object Detection

Xinjiang Wang,

Xingyi Yang,

Shilong Zhang,

Yijiang Li,

Litong Feng,

Shijie Fang,

Chengqi Lyu,

Kai Chen,

Wayne Zhang

[pdf] [supp]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Xinjiang and Yang, Xingyi and Zhang, Shilong and Li, Yijiang and Feng, Litong and Fang, Shijie and Lyu, Chengqi and Chen, Kai and Zhang, Wayne}, title = {Consistent-Teacher: Towards Reducing Inconsistent Pseudo-Targets in Semi-Supervised Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3240-3249} }

OCTET: Object-Aware Counterfactual Explanations

Mehdi Zemni,

Mickaël Chen,

Éloi Zablocki,

Hédi Ben-Younes,

Patrick Pérez,

Matthieu Cord

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Zemni_2023_CVPR, author = {Zemni, Mehdi and Chen, Micka\"el and Zablocki, \'Eloi and Ben-Younes, H\'edi and P\'erez, Patrick and Cord, Matthieu}, title = {OCTET: Object-Aware Counterfactual Explanations}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15062-15071} }

TeSLA: Test-Time Self-Learning With Automatic Adversarial Augmentation

Devavrat Tomar,

Guillaume Vray,

Behzad Bozorgtabar,

Jean-Philippe Thiran

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Tomar_2023_CVPR, author = {Tomar, Devavrat and Vray, Guillaume and Bozorgtabar, Behzad and Thiran, Jean-Philippe}, title = {TeSLA: Test-Time Self-Learning With Automatic Adversarial Augmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {20341-20350} }

DNeRV: Modeling Inherent Dynamics via Difference Neural Representation for Videos

Qi Zhao,

M. Salman Asif,

Zhan Ma

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Zhao_2023_CVPR, author = {Zhao, Qi and Asif, M. Salman and Ma, Zhan}, title = {DNeRV: Modeling Inherent Dynamics via Difference Neural Representation for Videos}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2031-2040} }

RefTeacher: A Strong Baseline for Semi-Supervised Referring Expression Comprehension

Jiamu Sun,

Gen Luo,

Yiyi Zhou,

Xiaoshuai Sun,

Guannan Jiang,

Zhiyu Wang,

Rongrong Ji

[pdf]

[bibtex]

@InProceedings{Sun_2023_CVPR, author = {Sun, Jiamu and Luo, Gen and Zhou, Yiyi and Sun, Xiaoshuai and Jiang, Guannan and Wang, Zhiyu and Ji, Rongrong}, title = {RefTeacher: A Strong Baseline for Semi-Supervised Referring Expression Comprehension}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {19144-19154} }

Handwritten Text Generation From Visual Archetypes

Vittorio Pippi,

Silvia Cascianelli,

Rita Cucchiara

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Pippi_2023_CVPR, author = {Pippi, Vittorio and Cascianelli, Silvia and Cucchiara, Rita}, title = {Handwritten Text Generation From Visual Archetypes}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {22458-22467} }

Unicode Analogies: An Anti-Objectivist Visual Reasoning Challenge

Steven Spratley,

Krista A. Ehinger,

Tim Miller

[pdf] [supp]

[bibtex]

@InProceedings{Spratley_2023_CVPR, author = {Spratley, Steven and Ehinger, Krista A. and Miller, Tim}, title = {Unicode Analogies: An Anti-Objectivist Visual Reasoning Challenge}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {19082-19091} }

FFF: Fragment-Guided Flexible Fitting for Building Complete Protein Structures

Weijie Chen,

Xinyan Wang,

Yuhang Wang

[pdf]

[bibtex]

@InProceedings{Chen_2023_CVPR, author = {Chen, Weijie and Wang, Xinyan and Wang, Yuhang}, title = {FFF: Fragment-Guided Flexible Fitting for Building Complete Protein Structures}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {19776-19785} }

Polarized Color Image Denoising

Zhuoxiao Li,

Haiyang Jiang,

Mingdeng Cao,

Yinqiang Zheng

[pdf] [supp]

[bibtex]

@InProceedings{Li_2023_CVPR, author = {Li, Zhuoxiao and Jiang, Haiyang and Cao, Mingdeng and Zheng, Yinqiang}, title = {Polarized Color Image Denoising}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9873-9882} }

Continuous Pseudo-Label Rectified Domain Adaptive Semantic Segmentation With Implicit Neural Representations

Rui Gong,

Qin Wang,

Martin Danelljan,

Dengxin Dai,

Luc Van Gool

[pdf] [supp]

[bibtex]

@InProceedings{Gong_2023_CVPR, author = {Gong, Rui and Wang, Qin and Danelljan, Martin and Dai, Dengxin and Van Gool, Luc}, title = {Continuous Pseudo-Label Rectified Domain Adaptive Semantic Segmentation With Implicit Neural Representations}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7225-7235} }

Hyperbolic Contrastive Learning for Visual Representations Beyond Objects

Songwei Ge,

Shlok Mishra,

Simon Kornblith,

Chun-Liang Li,

David Jacobs

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Ge_2023_CVPR, author = {Ge, Songwei and Mishra, Shlok and Kornblith, Simon and Li, Chun-Liang and Jacobs, David}, title = {Hyperbolic Contrastive Learning for Visual Representations Beyond Objects}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6840-6849} }

Align Your Latents: High-Resolution Video Synthesis With Latent Diffusion Models

Andreas Blattmann,

Robin Rombach,

Huan Ling,

Tim Dockhorn,

Seung Wook Kim,

Sanja Fidler,

Karsten Kreis

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Blattmann_2023_CVPR, author = {Blattmann, Andreas and Rombach, Robin and Ling, Huan and Dockhorn, Tim and Kim, Seung Wook and Fidler, Sanja and Kreis, Karsten}, title = {Align Your Latents: High-Resolution Video Synthesis With Latent Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {22563-22575} }

AligNeRF: High-Fidelity Neural Radiance Fields via Alignment-Aware Training

Yifan Jiang,

Peter Hedman,

Ben Mildenhall,

Dejia Xu,

Jonathan T. Barron,

Zhangyang Wang,

Tianfan Xue

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Jiang_2023_CVPR, author = {Jiang, Yifan and Hedman, Peter and Mildenhall, Ben and Xu, Dejia and Barron, Jonathan T. and Wang, Zhangyang and Xue, Tianfan}, title = {AligNeRF: High-Fidelity Neural Radiance Fields via Alignment-Aware Training}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {46-55} }

NAR-Former: Neural Architecture Representation Learning Towards Holistic Attributes Prediction

Yun Yi,

Haokui Zhang,

Wenze Hu,

Nannan Wang,

Xiaoyu Wang

[pdf] [supp]

[bibtex]

@InProceedings{Yi_2023_CVPR, author = {Yi, Yun and Zhang, Haokui and Hu, Wenze and Wang, Nannan and Wang, Xiaoyu}, title = {NAR-Former: Neural Architecture Representation Learning Towards Holistic Attributes Prediction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7715-7724} }

Implicit 3D Human Mesh Recovery Using Consistency With Pose and Shape From Unseen-View

Hanbyel Cho,

Yooshin Cho,

Jaesung Ahn,

Junmo Kim

[pdf] [supp]

[bibtex]

@InProceedings{Cho_2023_CVPR, author = {Cho, Hanbyel and Cho, Yooshin and Ahn, Jaesung and Kim, Junmo}, title = {Implicit 3D Human Mesh Recovery Using Consistency With Pose and Shape From Unseen-View}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {21148-21158} }

UniDAformer: Unified Domain Adaptive Panoptic Segmentation Transformer via Hierarchical Mask Calibration

Jingyi Zhang,

Jiaxing Huang,

Xiaoqin Zhang,

Shijian Lu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Zhang_2023_CVPR, author = {Zhang, Jingyi and Huang, Jiaxing and Zhang, Xiaoqin and Lu, Shijian}, title = {UniDAformer: Unified Domain Adaptive Panoptic Segmentation Transformer via Hierarchical Mask Calibration}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11227-11237} }

Non-Contrastive Learning Meets Language-Image Pre-Training

Jinghao Zhou,

Li Dong,

Zhe Gan,

Lijuan Wang,

Furu Wei

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Zhou_2023_CVPR, author = {Zhou, Jinghao and Dong, Li and Gan, Zhe and Wang, Lijuan and Wei, Furu}, title = {Non-Contrastive Learning Meets Language-Image Pre-Training}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11028-11038} }

Teaching Structured Vision & Language Concepts to Vision & Language Models

Sivan Doveh,

Assaf Arbelle,

Sivan Harary,

Eli Schwartz,

Roei Herzig,

Raja Giryes,

Rogerio Feris,

Rameswar Panda,

Shimon Ullman,

Leonid Karlinsky

[pdf] [supp]

[bibtex]

@InProceedings{Doveh_2023_CVPR, author = {Doveh, Sivan and Arbelle, Assaf and Harary, Sivan and Schwartz, Eli and Herzig, Roei and Giryes, Raja and Feris, Rogerio and Panda, Rameswar and Ullman, Shimon and Karlinsky, Leonid}, title = {Teaching Structured Vision \& Language Concepts to Vision \& Language Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2657-2668} }

Teleidoscopic Imaging System for Microscale 3D Shape Reconstruction

Ryo Kawahara,

Meng-Yu Jennifer Kuo,

Shohei Nobuhara

[pdf] [supp]

[bibtex]

@InProceedings{Kawahara_2023_CVPR, author = {Kawahara, Ryo and Kuo, Meng-Yu Jennifer and Nobuhara, Shohei}, title = {Teleidoscopic Imaging System for Microscale 3D Shape Reconstruction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {20813-20822} }

UV Volumes for Real-Time Rendering of Editable Free-View Human Performance

Yue Chen,

Xuan Wang,

Xingyu Chen,

Qi Zhang,

Xiaoyu Li,

Yu Guo,

Jue Wang,

Fei Wang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Chen_2023_CVPR, author = {Chen, Yue and Wang, Xuan and Chen, Xingyu and Zhang, Qi and Li, Xiaoyu and Guo, Yu and Wang, Jue and Wang, Fei}, title = {UV Volumes for Real-Time Rendering of Editable Free-View Human Performance}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16621-16631} }

NULL-Text Inversion for Editing Real Images Using Guided Diffusion Models

Ron Mokady,

Amir Hertz,

Kfir Aberman,

Yael Pritch,

Daniel Cohen-Or

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Mokady_2023_CVPR, author = {Mokady, Ron and Hertz, Amir and Aberman, Kfir and Pritch, Yael and Cohen-Or, Daniel}, title = {NULL-Text Inversion for Editing Real Images Using Guided Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6038-6047} }

JacobiNeRF: NeRF Shaping With Mutual Information Gradients

Xiaomeng Xu,

Yanchao Yang,

Kaichun Mo,

Boxiao Pan,

Li Yi,

Leonidas Guibas

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Xu_2023_CVPR, author = {Xu, Xiaomeng and Yang, Yanchao and Mo, Kaichun and Pan, Boxiao and Yi, Li and Guibas, Leonidas}, title = {JacobiNeRF: NeRF Shaping With Mutual Information Gradients}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16498-16507} }

Selective Structured State-Spaces for Long-Form Video Understanding

Jue Wang,

Wentao Zhu,

Pichao Wang,

Xiang Yu,

Linda Liu,

Mohamed Omar,

Raffay Hamid

[pdf] [arXiv]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Jue and Zhu, Wentao and Wang, Pichao and Yu, Xiang and Liu, Linda and Omar, Mohamed and Hamid, Raffay}, title = {Selective Structured State-Spaces for Long-Form Video Understanding}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6387-6397} }

Open-Set Representation Learning Through Combinatorial Embedding

Geeho Kim,

Junoh Kang,

Bohyung Han

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Kim_2023_CVPR, author = {Kim, Geeho and Kang, Junoh and Han, Bohyung}, title = {Open-Set Representation Learning Through Combinatorial Embedding}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {19744-19753} }

Multi-View Stereo Representation Revist: Region-Aware MVSNet

Yisu Zhang,

Jianke Zhu,

Lixiang Lin

[pdf]

[bibtex]

@InProceedings{Zhang_2023_CVPR, author = {Zhang, Yisu and Zhu, Jianke and Lin, Lixiang}, title = {Multi-View Stereo Representation Revist: Region-Aware MVSNet}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {17376-17385} }

A Unified HDR Imaging Method With Pixel and Patch Level

Qingsen Yan,

Weiye Chen,

Song Zhang,

Yu Zhu,

Jinqiu Sun,

Yanning Zhang

[pdf] [arXiv]

[bibtex]

@InProceedings{Yan_2023_CVPR, author = {Yan, Qingsen and Chen, Weiye and Zhang, Song and Zhu, Yu and Sun, Jinqiu and Zhang, Yanning}, title = {A Unified HDR Imaging Method With Pixel and Patch Level}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {22211-22220} }

Motion Information Propagation for Neural Video Compression

Linfeng Qi,

Jiahao Li,

Bin Li,

Houqiang Li,

Yan Lu

[pdf] [supp]

[bibtex]

@InProceedings{Qi_2023_CVPR, author = {Qi, Linfeng and Li, Jiahao and Li, Bin and Li, Houqiang and Lu, Yan}, title = {Motion Information Propagation for Neural Video Compression}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6111-6120} }

Accelerated Coordinate Encoding: Learning to Relocalize in Minutes Using RGB and Poses

Eric Brachmann,

Tommaso Cavallari,

Victor Adrian Prisacariu

[pdf] [supp]

[bibtex]

@InProceedings{Brachmann_2023_CVPR, author = {Brachmann, Eric and Cavallari, Tommaso and Prisacariu, Victor Adrian}, title = {Accelerated Coordinate Encoding: Learning to Relocalize in Minutes Using RGB and Poses}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5044-5053} }

Switchable Representation Learning Framework With Self-Compatibility

Shengsen Wu,

Yan Bai,

Yihang Lou,

Xiongkun Linghu,

Jianzhong He,

Ling-Yu Duan

[pdf] [arXiv]

[bibtex]

@InProceedings{Wu_2023_CVPR, author = {Wu, Shengsen and Bai, Yan and Lou, Yihang and Linghu, Xiongkun and He, Jianzhong and Duan, Ling-Yu}, title = {Switchable Representation Learning Framework With Self-Compatibility}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15943-15953} }

Partial Network Cloning

Jingwen Ye,

Songhua Liu,

Xinchao Wang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Ye_2023_CVPR, author = {Ye, Jingwen and Liu, Songhua and Wang, Xinchao}, title = {Partial Network Cloning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {20137-20146} }

MOTRv2: Bootstrapping End-to-End Multi-Object Tracking by Pretrained Object Detectors

Yuang Zhang,

Tiancai Wang,

Xiangyu Zhang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Zhang_2023_CVPR, author = {Zhang, Yuang and Wang, Tiancai and Zhang, Xiangyu}, title = {MOTRv2: Bootstrapping End-to-End Multi-Object Tracking by Pretrained Object Detectors}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {22056-22065} }

Zero-Shot Dual-Lens Super-Resolution

Ruikang Xu,

Mingde Yao,

Zhiwei Xiong

[pdf] [supp]

[bibtex]

@InProceedings{Xu_2023_CVPR, author = {Xu, Ruikang and Yao, Mingde and Xiong, Zhiwei}, title = {Zero-Shot Dual-Lens Super-Resolution}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9130-9139} }

Robust Dynamic Radiance Fields

Yu-Lun Liu,

Chen Gao,

Andréas Meuleman,

Hung-Yu Tseng,

Ayush Saraf,

Changil Kim,

Yung-Yu Chuang,

Johannes Kopf,

Jia-Bin Huang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Liu_2023_CVPR, author = {Liu, Yu-Lun and Gao, Chen and Meuleman, Andr\'eas and Tseng, Hung-Yu and Saraf, Ayush and Kim, Changil and Chuang, Yung-Yu and Kopf, Johannes and Huang, Jia-Bin}, title = {Robust Dynamic Radiance Fields}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13-23} }

Improving Vision-and-Language Navigation by Generating Future-View Image Semantics

Jialu Li,

Mohit Bansal

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Li_2023_CVPR, author = {Li, Jialu and Bansal, Mohit}, title = {Improving Vision-and-Language Navigation by Generating Future-View Image Semantics}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10803-10812} }

PLIKS: A Pseudo-Linear Inverse Kinematic Solver for 3D Human Body Estimation

Karthik Shetty,

Annette Birkhold,

Srikrishna Jaganathan,

Norbert Strobel,

Markus Kowarschik,

Andreas Maier,

Bernhard Egger

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Shetty_2023_CVPR, author = {Shetty, Karthik and Birkhold, Annette and Jaganathan, Srikrishna and Strobel, Norbert and Kowarschik, Markus and Maier, Andreas and Egger, Bernhard}, title = {PLIKS: A Pseudo-Linear Inverse Kinematic Solver for 3D Human Body Estimation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {574-584} }

Promoting Semantic Connectivity: Dual Nearest Neighbors Contrastive Learning for Unsupervised Domain Generalization

Yuchen Liu,

Yaoming Wang,

Yabo Chen,

Wenrui Dai,

Chenglin Li,

Junni Zou,

Hongkai Xiong

[pdf] [supp]

[bibtex]

@InProceedings{Liu_2023_CVPR, author = {Liu, Yuchen and Wang, Yaoming and Chen, Yabo and Dai, Wenrui and Li, Chenglin and Zou, Junni and Xiong, Hongkai}, title = {Promoting Semantic Connectivity: Dual Nearest Neighbors Contrastive Learning for Unsupervised Domain Generalization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3510-3519} }

Interactive Segmentation of Radiance Fields

Rahul Goel,

Dhawal Sirikonda,

Saurabh Saini,

P. J. Narayanan

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Goel_2023_CVPR, author = {Goel, Rahul and Sirikonda, Dhawal and Saini, Saurabh and Narayanan, P. J.}, title = {Interactive Segmentation of Radiance Fields}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4201-4211} }

gSDF: Geometry-Driven Signed Distance Functions for 3D Hand-Object Reconstruction

Zerui Chen,

Shizhe Chen,

Cordelia Schmid,

Ivan Laptev

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Chen_2023_CVPR, author = {Chen, Zerui and Chen, Shizhe and Schmid, Cordelia and Laptev, Ivan}, title = {gSDF: Geometry-Driven Signed Distance Functions for 3D Hand-Object Reconstruction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12890-12900} }

Principles of Forgetting in Domain-Incremental Semantic Segmentation in Adverse Weather Conditions

Tobias Kalb,

Jürgen Beyerer

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Kalb_2023_CVPR, author = {Kalb, Tobias and Beyerer, J\"urgen}, title = {Principles of Forgetting in Domain-Incremental Semantic Segmentation in Adverse Weather Conditions}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {19508-19518} }

Neural Texture Synthesis With Guided Correspondence

Yang Zhou,

Kaijian Chen,

Rongjun Xiao,

Hui Huang

[pdf] [supp]

[bibtex]

@InProceedings{Zhou_2023_CVPR, author = {Zhou, Yang and Chen, Kaijian and Xiao, Rongjun and Huang, Hui}, title = {Neural Texture Synthesis With Guided Correspondence}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {18095-18104} }

Exploring and Utilizing Pattern Imbalance

Shibin Mei,

Chenglong Zhao,

Shengchao Yuan,

Bingbing Ni

[pdf] [supp]

[bibtex]

@InProceedings{Mei_2023_CVPR, author = {Mei, Shibin and Zhao, Chenglong and Yuan, Shengchao and Ni, Bingbing}, title = {Exploring and Utilizing Pattern Imbalance}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7569-7578} }

Are Data-Driven Explanations Robust Against Out-of-Distribution Data?

Tang Li,

Fengchun Qiao,

Mengmeng Ma,

Xi Peng

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Li_2023_CVPR, author = {Li, Tang and Qiao, Fengchun and Ma, Mengmeng and Peng, Xi}, title = {Are Data-Driven Explanations Robust Against Out-of-Distribution Data?}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3821-3831} }

Top-Down Visual Attention From Analysis by Synthesis

Baifeng Shi,

Trevor Darrell,

Xin Wang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Shi_2023_CVPR, author = {Shi, Baifeng and Darrell, Trevor and Wang, Xin}, title = {Top-Down Visual Attention From Analysis by Synthesis}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2102-2112} }

Hierarchical Fine-Grained Image Forgery Detection and Localization

Xiao Guo,

Xiaohong Liu,

Zhiyuan Ren,

Steven Grosz,

Iacopo Masi,

Xiaoming Liu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Guo_2023_CVPR, author = {Guo, Xiao and Liu, Xiaohong and Ren, Zhiyuan and Grosz, Steven and Masi, Iacopo and Liu, Xiaoming}, title = {Hierarchical Fine-Grained Image Forgery Detection and Localization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3155-3165} }

CIMI4D: A Large Multimodal Climbing Motion Dataset Under Human-Scene Interactions

Ming Yan,

Xin Wang,

Yudi Dai,

Siqi Shen,

Chenglu Wen,

Lan Xu,

Yuexin Ma,

Cheng Wang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Yan_2023_CVPR, author = {Yan, Ming and Wang, Xin and Dai, Yudi and Shen, Siqi and Wen, Chenglu and Xu, Lan and Ma, Yuexin and Wang, Cheng}, title = {CIMI4D: A Large Multimodal Climbing Motion Dataset Under Human-Scene Interactions}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12977-12988} }

Fantastic Breaks: A Dataset of Paired 3D Scans of Real-World Broken Objects and Their Complete Counterparts

Nikolas Lamb,

Cameron Palmer,

Benjamin Molloy,

Sean Banerjee,

Natasha Kholgade Banerjee

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Lamb_2023_CVPR, author = {Lamb, Nikolas and Palmer, Cameron and Molloy, Benjamin and Banerjee, Sean and Banerjee, Natasha Kholgade}, title = {Fantastic Breaks: A Dataset of Paired 3D Scans of Real-World Broken Objects and Their Complete Counterparts}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4681-4691} }

Modernizing Old Photos Using Multiple References via Photorealistic Style Transfer

Agus Gunawan,

Soo Ye Kim,

Hyeonjun Sim,

Jae-Ho Lee,

Munchurl Kim

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Gunawan_2023_CVPR, author = {Gunawan, Agus and Kim, Soo Ye and Sim, Hyeonjun and Lee, Jae-Ho and Kim, Munchurl}, title = {Modernizing Old Photos Using Multiple References via Photorealistic Style Transfer}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12460-12469} }

Interactive Cartoonization With Controllable Perceptual Factors

Namhyuk Ahn,

Patrick Kwon,

Jihye Back,

Kibeom Hong,

Seungkwon Kim

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Ahn_2023_CVPR, author = {Ahn, Namhyuk and Kwon, Patrick and Back, Jihye and Hong, Kibeom and Kim, Seungkwon}, title = {Interactive Cartoonization With Controllable Perceptual Factors}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16827-16835} }

Curvature-Balanced Feature Manifold Learning for Long-Tailed Classification

Yanbiao Ma,

Licheng Jiao,

Fang Liu,

Shuyuan Yang,

Xu Liu,

Lingling Li

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Ma_2023_CVPR, author = {Ma, Yanbiao and Jiao, Licheng and Liu, Fang and Yang, Shuyuan and Liu, Xu and Li, Lingling}, title = {Curvature-Balanced Feature Manifold Learning for Long-Tailed Classification}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15824-15835} }

Back