Papers
- Back
GFPose: Learning 3D Human Pose Prior With Gradient Fields-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[pdf]
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[pdf]
[supp]
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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?-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[pdf]
[supp]
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[pdf]
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[pdf]
[supp]
[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-
[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-
[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-
[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-
[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-
[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-
[pdf]
[supp]
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[pdf]
[supp]
[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-
[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-
[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-
[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-
[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-
[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-
[pdf]
[supp]
[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-
[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} }
Vision Transformer With Super Token Sampling-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Huang_2023_CVPR, author = {Huang, Huaibo and Zhou, Xiaoqiang and Cao, Jie and He, Ran and Tan, Tieniu}, title = {Vision Transformer With Super Token Sampling}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {22690-22699} }
RA-CLIP: Retrieval Augmented Contrastive Language-Image Pre-Training-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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?-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[pdf]
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[pdf]
[supp]
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[pdf]
[supp]
[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-
[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-
[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-
[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-
[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-
[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-
[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- [