CVPR 2023 Open Access Repository

Papers

Back
Deep Frequency Filtering for Domain Generalization: Shiqi Lin,

Zhizheng Zhang,

Zhipeng Huang,

Yan Lu,

Cuiling Lan,

Peng Chu,

Quanzeng You,

Jiang Wang,

Zicheng Liu,

Amey Parulkar,

Viraj Navkal,

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

Yue Bai,

Chang Liu,

Huan Wang,

Sheng Li,

Yun Fu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhang_2023_CVPR, author = {Zhang, Yitian and Bai, Yue and Liu, Chang and Wang, Huan and Li, Sheng and Fu, Yun}, title = {Frame Flexible Network}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10504-10513} }
Unsupervised Cumulative Domain Adaptation for Foggy Scene Optical Flow: Hanyu Zhou,

Yi Chang,

Wending Yan,

Luxin Yan; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhou_2023_CVPR, author = {Zhou, Hanyu and Chang, Yi and Yan, Wending and Yan, Luxin}, title = {Unsupervised Cumulative Domain Adaptation for Foggy Scene Optical Flow}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9569-9578} }
MarS3D: A Plug-and-Play Motion-Aware Model for Semantic Segmentation on Multi-Scan 3D Point Clouds: Jiahui Liu,

Chirui Chang,

Jianhui Liu,

Xiaoyang Wu,

Lan Ma,

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

Stefania Calarasanu,

Davide Garcia-Civiero,

Théo Cayla,

Sira Ferradans,

Jean Ponce; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chahine_2023_CVPR, author = {Chahine, Nicolas and Calarasanu, Stefania and Garcia-Civiero, Davide and Cayla, Th\'eo and Ferradans, Sira and Ponce, Jean}, title = {An Image Quality Assessment Dataset for Portraits}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9968-9978} }
Painting 3D Nature in 2D: View Synthesis of Natural Scenes From a Single Semantic Mask: Shangzhan Zhang,

Sida Peng,

Tianrun Chen,

Linzhan Mou,

Haotong Lin,

Kaicheng Yu,

Yiyi Liao,

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

Dilin Wang,

Chengyue Gong,

Xingchao Liu,

Yunyang Xiong,

Rakesh Ranjan,

Raghuraman Krishnamoorthi,

Vikas Chandra,

Qiang Liu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wu_2023_CVPR, author = {Wu, Lemeng and Wang, Dilin and Gong, Chengyue and Liu, Xingchao and Xiong, Yunyang and Ranjan, Rakesh and Krishnamoorthi, Raghuraman and Chandra, Vikas and Liu, Qiang}, title = {Fast Point Cloud Generation With Straight Flows}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9445-9454} }
Achieving a Better Stability-Plasticity Trade-Off via Auxiliary Networks in Continual Learning: Sanghwan Kim,

Lorenzo Noci,

Antonio Orvieto,

Thomas Hofmann; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kim_2023_CVPR, author = {Kim, Sanghwan and Noci, Lorenzo and Orvieto, Antonio and Hofmann, Thomas}, title = {Achieving a Better Stability-Plasticity Trade-Off via Auxiliary Networks in Continual Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11930-11939} }
Video Event Restoration Based on Keyframes for Video Anomaly Detection: Zhiwei Yang,

Jing Liu,

Zhaoyang Wu,

Peng Wu,

Xiaotao Liu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yang_2023_CVPR, author = {Yang, Zhiwei and Liu, Jing and Wu, Zhaoyang and Wu, Peng and Liu, Xiaotao}, title = {Video Event Restoration Based on Keyframes for Video Anomaly Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14592-14601} }
EcoTTA: Memory-Efficient Continual Test-Time Adaptation via Self-Distilled Regularization: Junha Song,

Jungsoo Lee,

In So Kweon,

Sungha Choi; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Song_2023_CVPR, author = {Song, Junha and Lee, Jungsoo and Kweon, In So and Choi, Sungha}, title = {EcoTTA: Memory-Efficient Continual Test-Time Adaptation via Self-Distilled Regularization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11920-11929} }
Tri-Perspective View for Vision-Based 3D Semantic Occupancy Prediction: Yuanhui Huang,

Wenzhao Zheng,

Yunpeng Zhang,

Jie Zhou,

Jiwen Lu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Huang_2023_CVPR, author = {Huang, Yuanhui and Zheng, Wenzhao and Zhang, Yunpeng and Zhou, Jie and Lu, Jiwen}, title = {Tri-Perspective View for Vision-Based 3D Semantic Occupancy Prediction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9223-9232} }
Castling-ViT: Compressing Self-Attention via Switching Towards Linear-Angular Attention at Vision Transformer Inference: Haoran You,

Yunyang Xiong,

Xiaoliang Dai,

Bichen Wu,

Peizhao Zhang,

Haoqi Fan,

Peter Vajda,

Yingyan (Celine) Lin; [pdf] [supp]
[bibtex]
@InProceedings{You_2023_CVPR, author = {You, Haoran and Xiong, Yunyang and Dai, Xiaoliang and Wu, Bichen and Zhang, Peizhao and Fan, Haoqi and Vajda, Peter and Lin, Yingyan (Celine)}, title = {Castling-ViT: Compressing Self-Attention via Switching Towards Linear-Angular Attention at Vision Transformer Inference}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14431-14442} }
Rethinking Federated Learning With Domain Shift: A Prototype View: Wenke Huang,

Mang Ye,

Zekun Shi,

He Li,

Bo Du; [pdf]
[bibtex]
@InProceedings{Huang_2023_CVPR, author = {Huang, Wenke and Ye, Mang and Shi, Zekun and Li, He and Du, Bo}, title = {Rethinking Federated Learning With Domain Shift: A Prototype View}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16312-16322} }
HGFormer: Hierarchical Grouping Transformer for Domain Generalized Semantic Segmentation: Jian Ding,

Nan Xue,

Gui-Song Xia,

Bernt Schiele,

Dengxin Dai; [pdf] [arXiv]
[bibtex]
@InProceedings{Ding_2023_CVPR, author = {Ding, Jian and Xue, Nan and Xia, Gui-Song and Schiele, Bernt and Dai, Dengxin}, title = {HGFormer: Hierarchical Grouping Transformer for Domain Generalized Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15413-15423} }
Distilling Vision-Language Pre-Training To Collaborate With Weakly-Supervised Temporal Action Localization: Chen Ju,

Kunhao Zheng,

Jinxiang Liu,

Peisen Zhao,

Ya Zhang,

Jianlong Chang,

Qi Tian,

Yanfeng Wang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ju_2023_CVPR, author = {Ju, Chen and Zheng, Kunhao and Liu, Jinxiang and Zhao, Peisen and Zhang, Ya and Chang, Jianlong and Tian, Qi and Wang, Yanfeng}, title = {Distilling Vision-Language Pre-Training To Collaborate With Weakly-Supervised Temporal Action Localization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14751-14762} }
Augmentation Matters: A Simple-Yet-Effective Approach to Semi-Supervised Semantic Segmentation: Zhen Zhao,

Lihe Yang,

Sifan Long,

Jimin Pi,

Luping Zhou,

Jingdong Wang; [pdf] [arXiv]
[bibtex]
@InProceedings{Zhao_2023_CVPR, author = {Zhao, Zhen and Yang, Lihe and Long, Sifan and Pi, Jimin and Zhou, Luping and Wang, Jingdong}, title = {Augmentation Matters: A Simple-Yet-Effective Approach to Semi-Supervised Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11350-11359} }
Boosting Verified Training for Robust Image Classifications via Abstraction: Zhaodi Zhang,

Zhiyi Xue,

Yang Chen,

Si Liu,

Yueling Zhang,

Jing Liu,

Min Zhang; [pdf] [arXiv]
[bibtex]
@InProceedings{Zhang_2023_CVPR, author = {Zhang, Zhaodi and Xue, Zhiyi and Chen, Yang and Liu, Si and Zhang, Yueling and Liu, Jing and Zhang, Min}, title = {Boosting Verified Training for Robust Image Classifications via Abstraction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16251-16260} }
3D Shape Reconstruction of Semi-Transparent Worms: Thomas P. Ilett,

Omer Yuval,

Thomas Ranner,

Netta Cohen,

David C. Hogg; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ilett_2023_CVPR, author = {Ilett, Thomas P. and Yuval, Omer and Ranner, Thomas and Cohen, Netta and Hogg, David C.}, title = {3D Shape Reconstruction of Semi-Transparent Worms}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12565-12575} }
Mapping Degeneration Meets Label Evolution: Learning Infrared Small Target Detection With Single Point Supervision: Xinyi Ying,

Li Liu,

Yingqian Wang,

Ruojing Li,

Nuo Chen,

Zaiping Lin,

Weidong Sheng,

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

Anat Levin,

Ioannis Gkioulekas; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kotwal_2023_CVPR, author = {Kotwal, Alankar and Levin, Anat and Gkioulekas, Ioannis}, title = {Swept-Angle Synthetic Wavelength Interferometry}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8233-8243} }
Adaptive Global Decay Process for Event Cameras: Urbano Miguel Nunes,

Ryad Benosman,

Sio-Hoi Ieng; [pdf] [supp]
[bibtex]
@InProceedings{Nunes_2023_CVPR, author = {Nunes, Urbano Miguel and Benosman, Ryad and Ieng, Sio-Hoi}, title = {Adaptive Global Decay Process for Event Cameras}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9771-9780} }
Multi-Space Neural Radiance Fields: Ze-Xin Yin,

Jiaxiong Qiu,

Ming-Ming Cheng,

Bo Ren; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yin_2023_CVPR, author = {Yin, Ze-Xin and Qiu, Jiaxiong and Cheng, Ming-Ming and Ren, Bo}, title = {Multi-Space Neural Radiance Fields}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12407-12416} }
Bitstream-Corrupted JPEG Images Are Restorable: Two-Stage Compensation and Alignment Framework for Image Restoration: Wenyang Liu,

Yi Wang,

Kim-Hui Yap,

Lap-Pui Chau; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Liu_2023_CVPR, author = {Liu, Wenyang and Wang, Yi and Yap, Kim-Hui and Chau, Lap-Pui}, title = {Bitstream-Corrupted JPEG Images Are Restorable: Two-Stage Compensation and Alignment Framework for Image Restoration}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9979-9988} }
Histopathology Whole Slide Image Analysis With Heterogeneous Graph Representation Learning: Tsai Hor Chan,

Fernando Julio Cendra,

Lan Ma,

Guosheng Yin,

Lequan Yu; [pdf] [supp]
[bibtex]
@InProceedings{Chan_2023_CVPR, author = {Chan, Tsai Hor and Cendra, Fernando Julio and Ma, Lan and Yin, Guosheng and Yu, Lequan}, title = {Histopathology Whole Slide Image Analysis With Heterogeneous Graph Representation Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15661-15670} }
Towards All-in-One Pre-Training via Maximizing Multi-Modal Mutual Information: Weijie Su,

Xizhou Zhu,

Chenxin Tao,

Lewei Lu,

Bin Li,

Gao Huang,

Yu Qiao,

Xiaogang Wang,

Jie Zhou,

Jifeng Dai; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Su_2023_CVPR, author = {Su, Weijie and Zhu, Xizhou and Tao, Chenxin and Lu, Lewei and Li, Bin and Huang, Gao and Qiao, Yu and Wang, Xiaogang and Zhou, Jie and Dai, Jifeng}, title = {Towards All-in-One Pre-Training via Maximizing Multi-Modal Mutual Information}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15888-15899} }
Aligning Bag of Regions for Open-Vocabulary Object Detection: Size Wu,

Wenwei Zhang,

Sheng Jin,

Wentao Liu,

Chen Change Loy; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wu_2023_CVPR, author = {Wu, Size and Zhang, Wenwei and Jin, Sheng and Liu, Wentao and Loy, Chen Change}, title = {Aligning Bag of Regions for Open-Vocabulary Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15254-15264} }
Two-View Geometry Scoring Without Correspondences: Axel Barroso-Laguna,

Eric Brachmann,

Victor Adrian Prisacariu,

Gabriel J. Brostow,

Daniyar Turmukhambetov; [pdf] [supp]
[bibtex]
@InProceedings{Barroso-Laguna_2023_CVPR, author = {Barroso-Laguna, Axel and Brachmann, Eric and Prisacariu, Victor Adrian and Brostow, Gabriel J. and Turmukhambetov, Daniyar}, title = {Two-View Geometry Scoring Without Correspondences}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8979-8989} }
Annealing-Based Label-Transfer Learning for Open World Object Detection: Yuqing Ma,

Hainan Li,

Zhange Zhang,

Jinyang Guo,

Shanghang Zhang,

Ruihao Gong,

Xianglong Liu; [pdf] [supp]
[bibtex]
@InProceedings{Ma_2023_CVPR, author = {Ma, Yuqing and Li, Hainan and Zhang, Zhange and Guo, Jinyang and Zhang, Shanghang and Gong, Ruihao and Liu, Xianglong}, title = {Annealing-Based Label-Transfer Learning for Open World Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11454-11463} }
Self-Supervised Video Forensics by Audio-Visual Anomaly Detection: Chao Feng,

Ziyang Chen,

Andrew Owens; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Feng_2023_CVPR, author = {Feng, Chao and Chen, Ziyang and Owens, Andrew}, title = {Self-Supervised Video Forensics by Audio-Visual Anomaly Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10491-10503} }
Class Balanced Adaptive Pseudo Labeling for Federated Semi-Supervised Learning: Ming Li,

Qingli Li,

Yan Wang; [pdf] [supp]
[bibtex]
@InProceedings{Li_2023_CVPR, author = {Li, Ming and Li, Qingli and Wang, Yan}, title = {Class Balanced Adaptive Pseudo Labeling for Federated Semi-Supervised Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16292-16301} }
Rethinking Out-of-Distribution (OOD) Detection: Masked Image Modeling Is All You Need: Jingyao Li,

Pengguang Chen,

Zexin He,

Shaozuo Yu,

Shu Liu,

Jiaya Jia; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Li_2023_CVPR, author = {Li, Jingyao and Chen, Pengguang and He, Zexin and Yu, Shaozuo and Liu, Shu and Jia, Jiaya}, title = {Rethinking Out-of-Distribution (OOD) Detection: Masked Image Modeling Is All You Need}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11578-11589} }
Masked Scene Contrast: A Scalable Framework for Unsupervised 3D Representation Learning: Xiaoyang Wu,

Xin Wen,

Xihui Liu,

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

Subrahmanyam Murala,

G. Sankara Raju Kosuru; [pdf] [supp]
[bibtex]
@InProceedings{Singh_2023_CVPR, author = {Singh, Jasdeep and Murala, Subrahmanyam and Kosuru, G. Sankara Raju}, title = {Multi Domain Learning for Motion Magnification}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13914-13923} }
A Simple Baseline for Video Restoration With Grouped Spatial-Temporal Shift: Dasong Li,

Xiaoyu Shi,

Yi Zhang,

Ka Chun Cheung,

Simon See,

Xiaogang Wang,

Hongwei Qin,

Hongsheng Li; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Li_2023_CVPR, author = {Li, Dasong and Shi, Xiaoyu and Zhang, Yi and Cheung, Ka Chun and See, Simon and Wang, Xiaogang and Qin, Hongwei and Li, Hongsheng}, title = {A Simple Baseline for Video Restoration With Grouped Spatial-Temporal Shift}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9822-9832} }
itKD: Interchange Transfer-Based Knowledge Distillation for 3D Object Detection: Hyeon Cho,

Junyong Choi,

Geonwoo Baek,

Wonjun Hwang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Cho_2023_CVPR, author = {Cho, Hyeon and Choi, Junyong and Baek, Geonwoo and Hwang, Wonjun}, title = {itKD: Interchange Transfer-Based Knowledge Distillation for 3D Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13540-13549} }
2PCNet: Two-Phase Consistency Training for Day-to-Night Unsupervised Domain Adaptive Object Detection: Mikhail Kennerley,

Jian-Gang Wang,

Bharadwaj Veeravalli,

Robby T. Tan; [pdf] [arXiv]
[bibtex]
@InProceedings{Kennerley_2023_CVPR, author = {Kennerley, Mikhail and Wang, Jian-Gang and Veeravalli, Bharadwaj and Tan, Robby T.}, title = {2PCNet: Two-Phase Consistency Training for Day-to-Night Unsupervised Domain Adaptive Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11484-11493} }
Panoptic Lifting for 3D Scene Understanding With Neural Fields: Yawar Siddiqui,

Lorenzo Porzi,

Samuel Rota Bulò,

Norman Müller,

Matthias Nießner,

Angela Dai,

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

Yunhao Ba,

Ethan Yang,

Varan Mehra,

Blake Gella,

Akira Suzuki,

Arnold Pfahnl,

Chethan Chinder Chandrappa,

Alex Wong,

Achuta Kadambi; [pdf] [supp]
[bibtex]
@InProceedings{Zhang_2023_CVPR, author = {Zhang, Howard and Ba, Yunhao and Yang, Ethan and Mehra, Varan and Gella, Blake and Suzuki, Akira and Pfahnl, Arnold and Chandrappa, Chethan Chinder and Wong, Alex and Kadambi, Achuta}, title = {WeatherStream: Light Transport Automation of Single Image Deweathering}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13499-13509} }
Learning To Detect Mirrors From Videos via Dual Correspondences: Jiaying Lin,

Xin Tan,

Rynson W.H. Lau; [pdf] [supp]
[bibtex]
@InProceedings{Lin_2023_CVPR, author = {Lin, Jiaying and Tan, Xin and Lau, Rynson W.H.}, title = {Learning To Detect Mirrors From Videos via Dual Correspondences}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9109-9118} }
The Devil Is in the Points: Weakly Semi-Supervised Instance Segmentation via Point-Guided Mask Representation: Beomyoung Kim,

Joonhyun Jeong,

Dongyoon Han,

Sung Ju Hwang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kim_2023_CVPR, author = {Kim, Beomyoung and Jeong, Joonhyun and Han, Dongyoon and Hwang, Sung Ju}, title = {The Devil Is in the Points: Weakly Semi-Supervised Instance Segmentation via Point-Guided Mask Representation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11360-11370} }
Language-Guided Audio-Visual Source Separation via Trimodal Consistency: Reuben Tan,

Arijit Ray,

Andrea Burns,

Bryan A. Plummer,

Justin Salamon,

Oriol Nieto,

Bryan Russell,

Kate Saenko; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Tan_2023_CVPR, author = {Tan, Reuben and Ray, Arijit and Burns, Andrea and Plummer, Bryan A. and Salamon, Justin and Nieto, Oriol and Russell, Bryan and Saenko, Kate}, title = {Language-Guided Audio-Visual Source Separation via Trimodal Consistency}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10575-10584} }
DynaMask: Dynamic Mask Selection for Instance Segmentation: Ruihuang Li,

Chenhang He,

Shuai Li,

Yabin Zhang,

Lei Zhang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Li_2023_CVPR, author = {Li, Ruihuang and He, Chenhang and Li, Shuai and Zhang, Yabin and Zhang, Lei}, title = {DynaMask: Dynamic Mask Selection for Instance Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11279-11288} }
SAP-DETR: Bridging the Gap Between Salient Points and Queries-Based Transformer Detector for Fast Model Convergency: Yang Liu,

Yao Zhang,

Yixin Wang,

Yang Zhang,

Jiang Tian,

Zhongchao Shi,

Jianping Fan,

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

Tong He,

Jiaheng Liu,

Hua Chen,

Boxi Wu,

Binbin Lin,

Xiaofei He,

Wanli Ouyang; [pdf] [supp]
[bibtex]
@InProceedings{Yang_2023_CVPR, author = {Yang, Honghui and He, Tong and Liu, Jiaheng and Chen, Hua and Wu, Boxi and Lin, Binbin and He, Xiaofei and Ouyang, Wanli}, title = {GD-MAE: Generative Decoder for MAE Pre-Training on LiDAR Point Clouds}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9403-9414} }
Re-Thinking Model Inversion Attacks Against Deep Neural Networks: Ngoc-Bao Nguyen,

Keshigeyan Chandrasegaran,

Milad Abdollahzadeh,

Ngai-Man Cheung; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Nguyen_2023_CVPR, author = {Nguyen, Ngoc-Bao and Chandrasegaran, Keshigeyan and Abdollahzadeh, Milad and Cheung, Ngai-Man}, title = {Re-Thinking Model Inversion Attacks Against Deep Neural Networks}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16384-16393} }
You Need Multiple Exiting: Dynamic Early Exiting for Accelerating Unified Vision Language Model: Shengkun Tang,

Yaqing Wang,

Zhenglun Kong,

Tianchi Zhang,

Yao Li,

Caiwen Ding,

Yanzhi Wang,

Yi Liang,

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

Kuan-Chieh Wang,

Serena Yeung; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zohar_2023_CVPR, author = {Zohar, Orr and Wang, Kuan-Chieh and Yeung, Serena}, title = {PROB: Probabilistic Objectness for Open World Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11444-11453} }
SparseFusion: Distilling View-Conditioned Diffusion for 3D Reconstruction: Zhizhuo Zhou,

Shubham Tulsiani; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhou_2023_CVPR, author = {Zhou, Zhizhuo and Tulsiani, Shubham}, title = {SparseFusion: Distilling View-Conditioned Diffusion for 3D Reconstruction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12588-12597} }
Dynamic Focus-Aware Positional Queries for Semantic Segmentation: Haoyu He,

Jianfei Cai,

Zizheng Pan,

Jing Liu,

Jing Zhang,

Dacheng Tao,

Bohan Zhuang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{He_2023_CVPR, author = {He, Haoyu and Cai, Jianfei and Pan, Zizheng and Liu, Jing and Zhang, Jing and Tao, Dacheng and Zhuang, Bohan}, title = {Dynamic Focus-Aware Positional Queries for Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11299-11308} }
HARP: Personalized Hand Reconstruction From a Monocular RGB Video: Korrawe Karunratanakul,

Sergey Prokudin,

Otmar Hilliges,

Siyu Tang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Karunratanakul_2023_CVPR, author = {Karunratanakul, Korrawe and Prokudin, Sergey and Hilliges, Otmar and Tang, Siyu}, title = {HARP: Personalized Hand Reconstruction From a Monocular RGB Video}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12802-12813} }
DART: Diversify-Aggregate-Repeat Training Improves Generalization of Neural Networks: Samyak Jain,

Sravanti Addepalli,

Pawan Kumar Sahu,

Priyam Dey,

R. Venkatesh Babu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Jain_2023_CVPR, author = {Jain, Samyak and Addepalli, Sravanti and Sahu, Pawan Kumar and Dey, Priyam and Babu, R. Venkatesh}, title = {DART: Diversify-Aggregate-Repeat Training Improves Generalization of Neural Networks}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16048-16059} }
EvShutter: Transforming Events for Unconstrained Rolling Shutter Correction: Julius Erbach,

Stepan Tulyakov,

Patricia Vitoria,

Alfredo Bochicchio,

Yuanyou Li; [pdf] [supp]
[bibtex]
@InProceedings{Erbach_2023_CVPR, author = {Erbach, Julius and Tulyakov, Stepan and Vitoria, Patricia and Bochicchio, Alfredo and Li, Yuanyou}, title = {EvShutter: Transforming Events for Unconstrained Rolling Shutter Correction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13904-13913} }
Ambiguity-Resistant Semi-Supervised Learning for Dense Object Detection: Chang Liu,

Weiming Zhang,

Xiangru Lin,

Wei Zhang,

Xiao Tan,

Junyu Han,

Xiaomao Li,

Errui Ding,

Jingdong Wang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Liu_2023_CVPR, author = {Liu, Chang and Zhang, Weiming and Lin, Xiangru and Zhang, Wei and Tan, Xiao and Han, Junyu and Li, Xiaomao and Ding, Errui and Wang, Jingdong}, title = {Ambiguity-Resistant Semi-Supervised Learning for Dense Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15579-15588} }
Scalable, Detailed and Mask-Free Universal Photometric Stereo: Satoshi Ikehata; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ikehata_2023_CVPR, author = {Ikehata, Satoshi}, title = {Scalable, Detailed and Mask-Free Universal Photometric Stereo}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13198-13207} }
Towards High-Quality and Efficient Video Super-Resolution via Spatial-Temporal Data Overfitting: Gen Li,

Jie Ji,

Minghai Qin,

Wei Niu,

Bin Ren,

Fatemeh Afghah,

Linke Guo,

Xiaolong Ma; [pdf] [arXiv]
[bibtex]
@InProceedings{Li_2023_CVPR, author = {Li, Gen and Ji, Jie and Qin, Minghai and Niu, Wei and Ren, Bin and Afghah, Fatemeh and Guo, Linke and Ma, Xiaolong}, title = {Towards High-Quality and Efficient Video Super-Resolution via Spatial-Temporal Data Overfitting}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10259-10269} }
BiFormer: Vision Transformer With Bi-Level Routing Attention: Lei Zhu,

Xinjiang Wang,

Zhanghan Ke,

Wayne Zhang,

Rynson W.H. Lau; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhu_2023_CVPR, author = {Zhu, Lei and Wang, Xinjiang and Ke, Zhanghan and Zhang, Wayne and Lau, Rynson W.H.}, title = {BiFormer: Vision Transformer With Bi-Level Routing Attention}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10323-10333} }
Class-Incremental Exemplar Compression for Class-Incremental Learning: Zilin Luo,

Yaoyao Liu,

Bernt Schiele,

Qianru Sun; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Luo_2023_CVPR, author = {Luo, Zilin and Liu, Yaoyao and Schiele, Bernt and Sun, Qianru}, title = {Class-Incremental Exemplar Compression for Class-Incremental Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11371-11380} }
Behind the Scenes: Density Fields for Single View Reconstruction: Felix Wimbauer,

Nan Yang,

Christian Rupprecht,

Daniel Cremers; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wimbauer_2023_CVPR, author = {Wimbauer, Felix and Yang, Nan and Rupprecht, Christian and Cremers, Daniel}, title = {Behind the Scenes: Density Fields for Single View Reconstruction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9076-9086} }
StyleGAN Salon: Multi-View Latent Optimization for Pose-Invariant Hairstyle Transfer: Sasikarn Khwanmuang,

Pakkapon Phongthawee,

Patsorn Sangkloy,

Supasorn Suwajanakorn; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Khwanmuang_2023_CVPR, author = {Khwanmuang, Sasikarn and Phongthawee, Pakkapon and Sangkloy, Patsorn and Suwajanakorn, Supasorn}, title = {StyleGAN Salon: Multi-View Latent Optimization for Pose-Invariant Hairstyle Transfer}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8609-8618} }
Resource-Efficient RGBD Aerial Tracking: Jinyu Yang,

Shang Gao,

Zhe Li,

Feng Zheng,

Aleš Leonardis; [pdf] [supp]
[bibtex]
@InProceedings{Yang_2023_CVPR, author = {Yang, Jinyu and Gao, Shang and Li, Zhe and Zheng, Feng and Leonardis, Ale\v{s}}, title = {Resource-Efficient RGBD Aerial Tracking}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13374-13383} }
Bilateral Memory Consolidation for Continual Learning: Xing Nie,

Shixiong Xu,

Xiyan Liu,

Gaofeng Meng,

Chunlei Huo,

Shiming Xiang; [pdf] [supp]
[bibtex]
@InProceedings{Nie_2023_CVPR, author = {Nie, Xing and Xu, Shixiong and Liu, Xiyan and Meng, Gaofeng and Huo, Chunlei and Xiang, Shiming}, title = {Bilateral Memory Consolidation for Continual Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16026-16035} }
Search-Map-Search: A Frame Selection Paradigm for Action Recognition: Mingjun Zhao,

Yakun Yu,

Xiaoli Wang,

Lei Yang,

Di Niu; [pdf] [supp]
[bibtex]
@InProceedings{Zhao_2023_CVPR, author = {Zhao, Mingjun and Yu, Yakun and Wang, Xiaoli and Yang, Lei and Niu, Di}, title = {Search-Map-Search: A Frame Selection Paradigm for Action Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10627-10636} }
Uncovering the Missing Pattern: Unified Framework Towards Trajectory Imputation and Prediction: Yi Xu,

Armin Bazarjani,

Hyung-gun Chi,

Chiho Choi,

Yun Fu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Xu_2023_CVPR, author = {Xu, Yi and Bazarjani, Armin and Chi, Hyung-gun and Choi, Chiho and Fu, Yun}, title = {Uncovering the Missing Pattern: Unified Framework Towards Trajectory Imputation and Prediction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9632-9643} }
FlexiViT: One Model for All Patch Sizes: Lucas Beyer,

Pavel Izmailov,

Alexander Kolesnikov,

Mathilde Caron,

Simon Kornblith,

Xiaohua Zhai,

Matthias Minderer,

Michael Tschannen,

Ibrahim Alabdulmohsin,

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

Zhiyuan Mao,

Stanley H. Chan; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Sanghvi_2023_CVPR, author = {Sanghvi, Yash and Mao, Zhiyuan and Chan, Stanley H.}, title = {Structured Kernel Estimation for Photon-Limited Deconvolution}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9863-9872} }
Frame Interpolation Transformer and Uncertainty Guidance: Markus Plack,

Karlis Martins Briedis,

Abdelaziz Djelouah,

Matthias B. Hullin,

Markus Gross,

Christopher Schroers; [pdf] [supp]
[bibtex]
@InProceedings{Plack_2023_CVPR, author = {Plack, Markus and Briedis, Karlis Martins and Djelouah, Abdelaziz and Hullin, Matthias B. and Gross, Markus and Schroers, Christopher}, title = {Frame Interpolation Transformer and Uncertainty Guidance}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9811-9821} }
Neural Preset for Color Style Transfer: Zhanghan Ke,

Yuhao Liu,

Lei Zhu,

Nanxuan Zhao,

Rynson W.H. Lau; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ke_2023_CVPR, author = {Ke, Zhanghan and Liu, Yuhao and Zhu, Lei and Zhao, Nanxuan and Lau, Rynson W.H.}, title = {Neural Preset for Color Style Transfer}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14173-14182} }
Wavelet Diffusion Models Are Fast and Scalable Image Generators: Hao Phung,

Quan Dao,

Anh Tran; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Phung_2023_CVPR, author = {Phung, Hao and Dao, Quan and Tran, Anh}, title = {Wavelet Diffusion Models Are Fast and Scalable Image Generators}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10199-10208} }
PA&DA: Jointly Sampling Path and Data for Consistent NAS: Shun Lu,

Yu Hu,

Longxing Yang,

Zihao Sun,

Jilin Mei,

Jianchao Tan,

Chengru Song; [pdf] [supp]
[bibtex]
@InProceedings{Lu_2023_CVPR, author = {Lu, Shun and Hu, Yu and Yang, Longxing and Sun, Zihao and Mei, Jilin and Tan, Jianchao and Song, Chengru}, title = {PA\&DA: Jointly Sampling Path and Data for Consistent NAS}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11940-11949} }
3D Spatial Multimodal Knowledge Accumulation for Scene Graph Prediction in Point Cloud: Mingtao Feng,

Haoran Hou,

Liang Zhang,

Zijie Wu,

Yulan Guo,

Ajmal Mian; [pdf] [supp]
[bibtex]
@InProceedings{Feng_2023_CVPR, author = {Feng, Mingtao and Hou, Haoran and Zhang, Liang and Wu, Zijie and Guo, Yulan and Mian, Ajmal}, title = {3D Spatial Multimodal Knowledge Accumulation for Scene Graph Prediction in Point Cloud}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9182-9191} }
ViTs for SITS: Vision Transformers for Satellite Image Time Series: Michail Tarasiou,

Erik Chavez,

Stefanos Zafeiriou; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Tarasiou_2023_CVPR, author = {Tarasiou, Michail and Chavez, Erik and Zafeiriou, Stefanos}, title = {ViTs for SITS: Vision Transformers for Satellite Image Time Series}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10418-10428} }
Prompt, Generate, Then Cache: Cascade of Foundation Models Makes Strong Few-Shot Learners: Renrui Zhang,

Xiangfei Hu,

Bohao Li,

Siyuan Huang,

Hanqiu Deng,

Yu Qiao,

Peng Gao,

Hongsheng Li; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhang_2023_CVPR, author = {Zhang, Renrui and Hu, Xiangfei and Li, Bohao and Huang, Siyuan and Deng, Hanqiu and Qiao, Yu and Gao, Peng and Li, Hongsheng}, title = {Prompt, Generate, Then Cache: Cascade of Foundation Models Makes Strong Few-Shot Learners}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15211-15222} }
VideoMAE V2: Scaling Video Masked Autoencoders With Dual Masking: Limin Wang,

Bingkun Huang,

Zhiyu Zhao,

Zhan Tong,

Yinan He,

Yi Wang,

Yali Wang,

Yu Qiao; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2023_CVPR, author = {Wang, Limin and Huang, Bingkun and Zhao, Zhiyu and Tong, Zhan and He, Yinan and Wang, Yi and Wang, Yali and Qiao, Yu}, title = {VideoMAE V2: Scaling Video Masked Autoencoders With Dual Masking}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14549-14560} }
Perception and Semantic Aware Regularization for Sequential Confidence Calibration: Zhenghua Peng,

Yu Luo,

Tianshui Chen,

Keke Xu,

Shuangping Huang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Peng_2023_CVPR, author = {Peng, Zhenghua and Luo, Yu and Chen, Tianshui and Xu, Keke and Huang, Shuangping}, title = {Perception and Semantic Aware Regularization for Sequential Confidence Calibration}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10658-10668} }
Vid2Seq: Large-Scale Pretraining of a Visual Language Model for Dense Video Captioning: Antoine Yang,

Arsha Nagrani,

Paul Hongsuck Seo,

Antoine Miech,

Jordi Pont-Tuset,

Ivan Laptev,

Josef Sivic,

Cordelia Schmid; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yang_2023_CVPR, author = {Yang, Antoine and Nagrani, Arsha and Seo, Paul Hongsuck and Miech, Antoine and Pont-Tuset, Jordi and Laptev, Ivan and Sivic, Josef and Schmid, Cordelia}, title = {Vid2Seq: Large-Scale Pretraining of a Visual Language Model for Dense Video Captioning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10714-10726} }
ERNIE-ViLG 2.0: Improving Text-to-Image Diffusion Model With Knowledge-Enhanced Mixture-of-Denoising-Experts: Zhida Feng,

Zhenyu Zhang,

Xintong Yu,

Yewei Fang,

Lanxin Li,

Xuyi Chen,

Yuxiang Lu,

Jiaxiang Liu,

Weichong Yin,

Shikun Feng,

Yu Sun,

Li Chen,

Hao Tian,

Hua Wu,

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

Yuyao Ye,

Yang Zhao,

Ronggang Wang; [pdf] [supp]
[bibtex]
@InProceedings{Zhang_2023_CVPR, author = {Zhang, Ning and Ye, Yuyao and Zhao, Yang and Wang, Ronggang}, title = {Revisiting the Stack-Based Inverse Tone Mapping}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9162-9171} }
Exploiting Completeness and Uncertainty of Pseudo Labels for Weakly Supervised Video Anomaly Detection: Chen Zhang,

Guorong Li,

Yuankai Qi,

Shuhui Wang,

Laiyun Qing,

Qingming Huang,

Ming-Hsuan Yang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhang_2023_CVPR, author = {Zhang, Chen and Li, Guorong and Qi, Yuankai and Wang, Shuhui and Qing, Laiyun and Huang, Qingming and Yang, Ming-Hsuan}, title = {Exploiting Completeness and Uncertainty of Pseudo Labels for Weakly Supervised Video Anomaly Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16271-16280} }
Full or Weak Annotations? An Adaptive Strategy for Budget-Constrained Annotation Campaigns: Javier Gamazo Tejero,

Martin S. Zinkernagel,

Sebastian Wolf,

Raphael Sznitman,

Pablo Márquez-Neila; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Tejero_2023_CVPR, author = {Tejero, Javier Gamazo and Zinkernagel, Martin S. and Wolf, Sebastian and Sznitman, Raphael and M\'arquez-Neila, Pablo}, title = {Full or Weak Annotations? An Adaptive Strategy for Budget-Constrained Annotation Campaigns}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11381-11391} }
Backdoor Defense via Deconfounded Representation Learning: Zaixi Zhang,

Qi Liu,

Zhicai Wang,

Zepu Lu,

Qingyong Hu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhang_2023_CVPR, author = {Zhang, Zaixi and Liu, Qi and Wang, Zhicai and Lu, Zepu and Hu, Qingyong}, title = {Backdoor Defense via Deconfounded Representation Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12228-12238} }
HairStep: Transfer Synthetic to Real Using Strand and Depth Maps for Single-View 3D Hair Modeling: Yujian Zheng,

Zirong Jin,

Moran Li,

Haibin Huang,

Chongyang Ma,

Shuguang Cui,

Xiaoguang Han; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zheng_2023_CVPR, author = {Zheng, Yujian and Jin, Zirong and Li, Moran and Huang, Haibin and Ma, Chongyang and Cui, Shuguang and Han, Xiaoguang}, title = {HairStep: Transfer Synthetic to Real Using Strand and Depth Maps for Single-View 3D Hair Modeling}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12726-12735} }
MoDAR: Using Motion Forecasting for 3D Object Detection in Point Cloud Sequences: Yingwei Li,

Charles R. Qi,

Yin Zhou,

Chenxi Liu,

Dragomir Anguelov; [pdf] [supp]
[bibtex]
@InProceedings{Li_2023_CVPR, author = {Li, Yingwei and Qi, Charles R. and Zhou, Yin and Liu, Chenxi and Anguelov, Dragomir}, title = {MoDAR: Using Motion Forecasting for 3D Object Detection in Point Cloud Sequences}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9329-9339} }
ALSO: Automotive Lidar Self-Supervision by Occupancy Estimation: Alexandre Boulch,

Corentin Sautier,

Björn Michele,

Gilles Puy,

Renaud Marlet; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Boulch_2023_CVPR, author = {Boulch, Alexandre and Sautier, Corentin and Michele, Bj\"orn and Puy, Gilles and Marlet, Renaud}, title = {ALSO: Automotive Lidar Self-Supervision by Occupancy Estimation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13455-13465} }
Learning Dynamic Style Kernels for Artistic Style Transfer: Wenju Xu,

Chengjiang Long,

Yongwei Nie; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Xu_2023_CVPR, author = {Xu, Wenju and Long, Chengjiang and Nie, Yongwei}, title = {Learning Dynamic Style Kernels for Artistic Style Transfer}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10083-10092} }
Chat2Map: Efficient Scene Mapping From Multi-Ego Conversations: Sagnik Majumder,

Hao Jiang,

Pierre Moulon,

Ethan Henderson,

Paul Calamia,

Kristen Grauman,

Vamsi Krishna Ithapu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Majumder_2023_CVPR, author = {Majumder, Sagnik and Jiang, Hao and Moulon, Pierre and Henderson, Ethan and Calamia, Paul and Grauman, Kristen and Ithapu, Vamsi Krishna}, title = {Chat2Map: Efficient Scene Mapping From Multi-Ego Conversations}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10554-10564} }
GeoMAE: Masked Geometric Target Prediction for Self-Supervised Point Cloud Pre-Training: Xiaoyu Tian,

Haoxi Ran,

Yue Wang,

Hang Zhao; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Tian_2023_CVPR, author = {Tian, Xiaoyu and Ran, Haoxi and Wang, Yue and Zhao, Hang}, title = {GeoMAE: Masked Geometric Target Prediction for Self-Supervised Point Cloud Pre-Training}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13570-13580} }
Learning Conditional Attributes for Compositional Zero-Shot Learning: Qingsheng Wang,

Lingqiao Liu,

Chenchen Jing,

Hao Chen,

Guoqiang Liang,

Peng Wang,

Chunhua Shen; [pdf] [arXiv]
[bibtex]
@InProceedings{Wang_2023_CVPR, author = {Wang, Qingsheng and Liu, Lingqiao and Jing, Chenchen and Chen, Hao and Liang, Guoqiang and Wang, Peng and Shen, Chunhua}, title = {Learning Conditional Attributes for Compositional Zero-Shot Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11197-11206} }
Complete 3D Human Reconstruction From a Single Incomplete Image: Junying Wang,

Jae Shin Yoon,

Tuanfeng Y. Wang,

Krishna Kumar Singh,

Ulrich Neumann; [pdf] [supp]
[bibtex]
@InProceedings{Wang_2023_CVPR, author = {Wang, Junying and Yoon, Jae Shin and Wang, Tuanfeng Y. and Singh, Krishna Kumar and Neumann, Ulrich}, title = {Complete 3D Human Reconstruction From a Single Incomplete Image}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8748-8758} }
PVT-SSD: Single-Stage 3D Object Detector With Point-Voxel Transformer: Honghui Yang,

Wenxiao Wang,

Minghao Chen,

Binbin Lin,

Tong He,

Hua Chen,

Xiaofei He,

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

Jiang Wang,

Kun Luo,

Kevin Lin,

Linjie Li,

Lijuan Wang,

Zicheng Liu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Lin_2023_CVPR, author = {Lin, Chung-Ching and Wang, Jiang and Luo, Kun and Lin, Kevin and Li, Linjie and Wang, Lijuan and Liu, Zicheng}, title = {Adaptive Human Matting for Dynamic Videos}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10229-10238} }
Learning Common Rationale To Improve Self-Supervised Representation for Fine-Grained Visual Recognition Problems: Yangyang Shu,

Anton van den Hengel,

Lingqiao Liu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Shu_2023_CVPR, author = {Shu, Yangyang and van den Hengel, Anton and Liu, Lingqiao}, title = {Learning Common Rationale To Improve Self-Supervised Representation for Fine-Grained Visual Recognition Problems}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11392-11401} }
High-Fidelity 3D Human Digitization From Single 2K Resolution Images: Sang-Hun Han,

Min-Gyu Park,

Ju Hong Yoon,

Ju-Mi Kang,

Young-Jae Park,

Hae-Gon Jeon; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Han_2023_CVPR, author = {Han, Sang-Hun and Park, Min-Gyu and Yoon, Ju Hong and Kang, Ju-Mi and Park, Young-Jae and Jeon, Hae-Gon}, title = {High-Fidelity 3D Human Digitization From Single 2K Resolution Images}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12869-12879} }
Fully Self-Supervised Depth Estimation From Defocus Clue: Haozhe Si,

Bin Zhao,

Dong Wang,

Yunpeng Gao,

Mulin Chen,

Zhigang Wang,

Xuelong Li; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Si_2023_CVPR, author = {Si, Haozhe and Zhao, Bin and Wang, Dong and Gao, Yunpeng and Chen, Mulin and Wang, Zhigang and Li, Xuelong}, title = {Fully Self-Supervised Depth Estimation From Defocus Clue}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9140-9149} }
Prompting Large Language Models With Answer Heuristics for Knowledge-Based Visual Question Answering: Zhenwei Shao,

Zhou Yu,

Meng Wang,

Jun Yu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Shao_2023_CVPR, author = {Shao, Zhenwei and Yu, Zhou and Wang, Meng and Yu, Jun}, title = {Prompting Large Language Models With Answer Heuristics for Knowledge-Based Visual Question Answering}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14974-14983} }
Improving Robustness of Semantic Segmentation to Motion-Blur Using Class-Centric Augmentation: Aakanksha,

A. N. Rajagopalan; [pdf] [supp]
[bibtex]
@InProceedings{Aakanksha_2023_CVPR, author = {Aakanksha and Rajagopalan, A. N.}, title = {Improving Robustness of Semantic Segmentation to Motion-Blur Using Class-Centric Augmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10470-10479} }
Progressive Open Space Expansion for Open-Set Model Attribution: Tianyun Yang,

Danding Wang,

Fan Tang,

Xinying Zhao,

Juan Cao,

Sheng Tang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yang_2023_CVPR, author = {Yang, Tianyun and Wang, Danding and Tang, Fan and Zhao, Xinying and Cao, Juan and Tang, Sheng}, title = {Progressive Open Space Expansion for Open-Set Model Attribution}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15856-15865} }
Backdoor Cleansing With Unlabeled Data: Lu Pang,

Tao Sun,

Haibin Ling,

Chao Chen; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Pang_2023_CVPR, author = {Pang, Lu and Sun, Tao and Ling, Haibin and Chen, Chao}, title = {Backdoor Cleansing With Unlabeled Data}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12218-12227} }
Harmonious Feature Learning for Interactive Hand-Object Pose Estimation: Zhifeng Lin,

Changxing Ding,

Huan Yao,

Zengsheng Kuang,

Shaoli Huang; [pdf] [supp]
[bibtex]
@InProceedings{Lin_2023_CVPR, author = {Lin, Zhifeng and Ding, Changxing and Yao, Huan and Kuang, Zengsheng and Huang, Shaoli}, title = {Harmonious Feature Learning for Interactive Hand-Object Pose Estimation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12989-12998} }
CLOTH4D: A Dataset for Clothed Human Reconstruction: Xingxing Zou,

Xintong Han,

Waikeung Wong; [pdf] [supp]
[bibtex]
@InProceedings{Zou_2023_CVPR, author = {Zou, Xingxing and Han, Xintong and Wong, Waikeung}, title = {CLOTH4D: A Dataset for Clothed Human Reconstruction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12847-12857} }
Generative Bias for Robust Visual Question Answering: Jae Won Cho,

Dong-Jin Kim,

Hyeonggon Ryu,

In So Kweon; [pdf] [arXiv]
[bibtex]
@InProceedings{Cho_2023_CVPR, author = {Cho, Jae Won and Kim, Dong-Jin and Ryu, Hyeonggon and Kweon, In So}, title = {Generative Bias for Robust Visual Question Answering}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11681-11690} }
Data-Free Sketch-Based Image Retrieval: Abhra Chaudhuri,

Ayan Kumar Bhunia,

Yi-Zhe Song,

Anjan Dutta; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chaudhuri_2023_CVPR, author = {Chaudhuri, Abhra and Bhunia, Ayan Kumar and Song, Yi-Zhe and Dutta, Anjan}, title = {Data-Free Sketch-Based Image Retrieval}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12084-12093} }
Multi-Object Manipulation via Object-Centric Neural Scattering Functions: Stephen Tian,

Yancheng Cai,

Hong-Xing Yu,

Sergey Zakharov,

Katherine Liu,

Adrien Gaidon,

Yunzhu Li,

Jiajun Wu; [pdf] [supp]
[bibtex]
@InProceedings{Tian_2023_CVPR, author = {Tian, Stephen and Cai, Yancheng and Yu, Hong-Xing and Zakharov, Sergey and Liu, Katherine and Gaidon, Adrien and Li, Yunzhu and Wu, Jiajun}, title = {Multi-Object Manipulation via Object-Centric Neural Scattering Functions}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9021-9031} }
The Wisdom of Crowds: Temporal Progressive Attention for Early Action Prediction: Alexandros Stergiou,

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

Aliaksandr Siarohin,

Riza Alp Guler,

Menglei Chai,

Jian Ren,

Sergey Tulyakov,

Igor Gilitschenski; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kant_2023_CVPR, author = {Kant, Yash and Siarohin, Aliaksandr and Guler, Riza Alp and Chai, Menglei and Ren, Jian and Tulyakov, Sergey and Gilitschenski, Igor}, title = {Invertible Neural Skinning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8715-8725} }
Weakly Supervised Semantic Segmentation via Adversarial Learning of Classifier and Reconstructor: Hyeokjun Kweon,

Sung-Hoon Yoon,

Kuk-Jin Yoon; [pdf] [supp]
[bibtex]
@InProceedings{Kweon_2023_CVPR, author = {Kweon, Hyeokjun and Yoon, Sung-Hoon and Yoon, Kuk-Jin}, title = {Weakly Supervised Semantic Segmentation via Adversarial Learning of Classifier and Reconstructor}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11329-11339} }
Distilling Cross-Temporal Contexts for Continuous Sign Language Recognition: Leming Guo,

Wanli Xue,

Qing Guo,

Bo Liu,

Kaihua Zhang,

Tiantian Yuan,

Shengyong Chen; [pdf] [supp]
[bibtex]
@InProceedings{Guo_2023_CVPR, author = {Guo, Leming and Xue, Wanli and Guo, Qing and Liu, Bo and Zhang, Kaihua and Yuan, Tiantian and Chen, Shengyong}, title = {Distilling Cross-Temporal Contexts for Continuous Sign Language Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10771-10780} }
Unsupervised Deep Probabilistic Approach for Partial Point Cloud Registration: Guofeng Mei,

Hao Tang,

Xiaoshui Huang,

Weijie Wang,

Juan Liu,

Jian Zhang,

Luc Van Gool,

Qiang Wu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Mei_2023_CVPR, author = {Mei, Guofeng and Tang, Hao and Huang, Xiaoshui and Wang, Weijie and Liu, Juan and Zhang, Jian and Van Gool, Luc and Wu, Qiang}, title = {Unsupervised Deep Probabilistic Approach for Partial Point Cloud Registration}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13611-13620} }
Similarity Metric Learning for RGB-Infrared Group Re-Identification: Jianghao Xiong,

Jianhuang Lai; [pdf] [supp]
[bibtex]
@InProceedings{Xiong_2023_CVPR, author = {Xiong, Jianghao and Lai, Jianhuang}, title = {Similarity Metric Learning for RGB-Infrared Group Re-Identification}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13662-13671} }
Train/Test-Time Adaptation With Retrieval: Luca Zancato,

Alessandro Achille,

Tian Yu Liu,

Matthew Trager,

Pramuditha Perera,

Stefano Soatto; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zancato_2023_CVPR, author = {Zancato, Luca and Achille, Alessandro and Liu, Tian Yu and Trager, Matthew and Perera, Pramuditha and Soatto, Stefano}, title = {Train/Test-Time Adaptation With Retrieval}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15911-15921} }
ProxyFormer: Proxy Alignment Assisted Point Cloud Completion With Missing Part Sensitive Transformer: Shanshan Li,

Pan Gao,

Xiaoyang Tan,

Mingqiang Wei; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Li_2023_CVPR, author = {Li, Shanshan and Gao, Pan and Tan, Xiaoyang and Wei, Mingqiang}, title = {ProxyFormer: Proxy Alignment Assisted Point Cloud Completion With Missing Part Sensitive Transformer}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9466-9475} }
Mod-Squad: Designing Mixtures of Experts As Modular Multi-Task Learners: Zitian Chen,

Yikang Shen,

Mingyu Ding,

Zhenfang Chen,

Hengshuang Zhao,

Erik G. Learned-Miller,

Chuang Gan; [pdf] [supp]
[bibtex]
@InProceedings{Chen_2023_CVPR, author = {Chen, Zitian and Shen, Yikang and Ding, Mingyu and Chen, Zhenfang and Zhao, Hengshuang and Learned-Miller, Erik G. and Gan, Chuang}, title = {Mod-Squad: Designing Mixtures of Experts As Modular Multi-Task Learners}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11828-11837} }
Learning Customized Visual Models With Retrieval-Augmented Knowledge: Haotian Liu,

Kilho Son,

Jianwei Yang,

Ce Liu,

Jianfeng Gao,

Yong Jae Lee,

Chunyuan Li; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Liu_2023_CVPR, author = {Liu, Haotian and Son, Kilho and Yang, Jianwei and Liu, Ce and Gao, Jianfeng and Lee, Yong Jae and Li, Chunyuan}, title = {Learning Customized Visual Models With Retrieval-Augmented Knowledge}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15148-15158} }
Run, Don't Walk: Chasing Higher FLOPS for Faster Neural Networks: Jierun Chen,

Shiu-hong Kao,

Hao He,

Weipeng Zhuo,

Song Wen,

Chul-Ho Lee,

S.-H. Gary Chan; [pdf] [supp]
[bibtex]
@InProceedings{Chen_2023_CVPR, author = {Chen, Jierun and Kao, Shiu-hong and He, Hao and Zhuo, Weipeng and Wen, Song and Lee, Chul-Ho and Chan, S.-H. Gary}, title = {Run, Don't Walk: Chasing Higher FLOPS for Faster Neural Networks}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12021-12031} }
Learning Procedure-Aware Video Representation From Instructional Videos and Their Narrations: Yiwu Zhong,

Licheng Yu,

Yang Bai,

Shangwen Li,

Xueting Yan,

Yin Li; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhong_2023_CVPR, author = {Zhong, Yiwu and Yu, Licheng and Bai, Yang and Li, Shangwen and Yan, Xueting and Li, Yin}, title = {Learning Procedure-Aware Video Representation From Instructional Videos and Their Narrations}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14825-14835} }
Co-Training 2L Submodels for Visual Recognition: Hugo Touvron,

Matthieu Cord,

Maxime Oquab,

Piotr Bojanowski,

Jakob Verbeek,

Hervé Jégou; [pdf] [supp]
[bibtex]
@InProceedings{Touvron_2023_CVPR, author = {Touvron, Hugo and Cord, Matthieu and Oquab, Maxime and Bojanowski, Piotr and Verbeek, Jakob and J\'egou, Herv\'e}, title = {Co-Training 2L Submodels for Visual Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11701-11710} }
K-Planes: Explicit Radiance Fields in Space, Time, and Appearance: Sara Fridovich-Keil,

Giacomo Meanti,

Frederik Rahbæk Warburg,

Benjamin Recht,

Angjoo Kanazawa; [pdf] [supp]
[bibtex]
@InProceedings{Fridovich-Keil_2023_CVPR, author = {Fridovich-Keil, Sara and Meanti, Giacomo and Warburg, Frederik Rahb{\ae}k and Recht, Benjamin and Kanazawa, Angjoo}, title = {K-Planes: Explicit Radiance Fields in Space, Time, and Appearance}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12479-12488} }
Multi-Mode Online Knowledge Distillation for Self-Supervised Visual Representation Learning: Kaiyou Song,

Jin Xie,

Shan Zhang,

Zimeng Luo; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Song_2023_CVPR, author = {Song, Kaiyou and Xie, Jin and Zhang, Shan and Luo, Zimeng}, title = {Multi-Mode Online Knowledge Distillation for Self-Supervised Visual Representation Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11848-11857} }
Viewpoint Equivariance for Multi-View 3D Object Detection: Dian Chen,

Jie Li,

Vitor Guizilini,

Rares Andrei Ambrus,

Adrien Gaidon; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chen_2023_CVPR, author = {Chen, Dian and Li, Jie and Guizilini, Vitor and Ambrus, Rares Andrei and Gaidon, Adrien}, title = {Viewpoint Equivariance for Multi-View 3D Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9213-9222} }
A Generalized Framework for Video Instance Segmentation: Miran Heo,

Sukjun Hwang,

Jeongseok Hyun,

Hanjung Kim,

Seoung Wug Oh,

Joon-Young Lee,

Seon Joo Kim; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Heo_2023_CVPR, author = {Heo, Miran and Hwang, Sukjun and Hyun, Jeongseok and Kim, Hanjung and Oh, Seoung Wug and Lee, Joon-Young and Kim, Seon Joo}, title = {A Generalized Framework for Video Instance Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14623-14632} }
On Distillation of Guided Diffusion Models: Chenlin Meng,

Robin Rombach,

Ruiqi Gao,

Diederik Kingma,

Stefano Ermon,

Jonathan Ho,

Tim Salimans; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Meng_2023_CVPR, author = {Meng, Chenlin and Rombach, Robin and Gao, Ruiqi and Kingma, Diederik and Ermon, Stefano and Ho, Jonathan and Salimans, Tim}, title = {On Distillation of Guided Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14297-14306} }
Disentangled Representation Learning for Unsupervised Neural Quantization: Haechan Noh,

Sangeek Hyun,

Woojin Jeong,

Hanshin Lim,

Jae-Pil Heo; [pdf]
[bibtex]
@InProceedings{Noh_2023_CVPR, author = {Noh, Haechan and Hyun, Sangeek and Jeong, Woojin and Lim, Hanshin and Heo, Jae-Pil}, title = {Disentangled Representation Learning for Unsupervised Neural Quantization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12001-12010} }
Zero-Shot Pose Transfer for Unrigged Stylized 3D Characters: Jiashun Wang,

Xueting Li,

Sifei Liu,

Shalini De Mello,

Orazio Gallo,

Xiaolong Wang,

Jan Kautz; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2023_CVPR, author = {Wang, Jiashun and Li, Xueting and Liu, Sifei and De Mello, Shalini and Gallo, Orazio and Wang, Xiaolong and Kautz, Jan}, title = {Zero-Shot Pose Transfer for Unrigged Stylized 3D Characters}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8704-8714} }
Listening Human Behavior: 3D Human Pose Estimation With Acoustic Signals: Yuto Shibata,

Yutaka Kawashima,

Mariko Isogawa,

Go Irie,

Akisato Kimura,

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

Duhun Hwang,

Moonjung Eo,

Taesup Kim,

Wonjong Rhee; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kang_2023_CVPR, author = {Kang, Suhyun and Hwang, Duhun and Eo, Moonjung and Kim, Taesup and Rhee, Wonjong}, title = {Meta-Learning With a Geometry-Adaptive Preconditioner}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16080-16090} }
NeuralDome: A Neural Modeling Pipeline on Multi-View Human-Object Interactions: Juze Zhang,

Haimin Luo,

Hongdi Yang,

Xinru Xu,

Qianyang Wu,

Ye Shi,

Jingyi Yu,

Lan Xu,

Jingya Wang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhang_2023_CVPR, author = {Zhang, Juze and Luo, Haimin and Yang, Hongdi and Xu, Xinru and Wu, Qianyang and Shi, Ye and Yu, Jingyi and Xu, Lan and Wang, Jingya}, title = {NeuralDome: A Neural Modeling Pipeline on Multi-View Human-Object Interactions}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8834-8845} }
No One Left Behind: Improving the Worst Categories in Long-Tailed Learning: Yingxiao Du,

Jianxin Wu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Du_2023_CVPR, author = {Du, Yingxiao and Wu, Jianxin}, title = {No One Left Behind: Improving the Worst Categories in Long-Tailed Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15804-15813} }
Target-Referenced Reactive Grasping for Dynamic Objects: Jirong Liu,

Ruo Zhang,

Hao-Shu Fang,

Minghao Gou,

Hongjie Fang,

Chenxi Wang,

Sheng Xu,

Hengxu Yan,

Cewu Lu; [pdf] [supp]
[bibtex]
@InProceedings{Liu_2023_CVPR, author = {Liu, Jirong and Zhang, Ruo and Fang, Hao-Shu and Gou, Minghao and Fang, Hongjie and Wang, Chenxi and Xu, Sheng and Yan, Hengxu and Lu, Cewu}, title = {Target-Referenced Reactive Grasping for Dynamic Objects}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8824-8833} }
Complexity-Guided Slimmable Decoder for Efficient Deep Video Compression: Zhihao Hu,

Dong Xu; [pdf] [supp]
[bibtex]
@InProceedings{Hu_2023_CVPR, author = {Hu, Zhihao and Xu, Dong}, title = {Complexity-Guided Slimmable Decoder for Efficient Deep Video Compression}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14358-14367} }
MarginMatch: Improving Semi-Supervised Learning with Pseudo-Margins: Tiberiu Sosea,

Cornelia Caragea; [pdf] [supp]
[bibtex]
@InProceedings{Sosea_2023_CVPR, author = {Sosea, Tiberiu and Caragea, Cornelia}, title = {MarginMatch: Improving Semi-Supervised Learning with Pseudo-Margins}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15773-15782} }
Beyond Appearance: A Semantic Controllable Self-Supervised Learning Framework for Human-Centric Visual Tasks: Weihua Chen,

Xianzhe Xu,

Jian Jia,

Hao Luo,

Yaohua Wang,

Fan Wang,

Rong Jin,

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

Yuhe Jin,

Kwang Moo Yi; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wu_2023_CVPR, author = {Wu, Zhijie and Jin, Yuhe and Yi, Kwang Moo}, title = {Neural Fourier Filter Bank}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14153-14163} }
NeRFInvertor: High Fidelity NeRF-GAN Inversion for Single-Shot Real Image Animation: Yu Yin,

Kamran Ghasedi,

HsiangTao Wu,

Jiaolong Yang,

Xin Tong,

Yun Fu; [pdf] [arXiv]
[bibtex]
@InProceedings{Yin_2023_CVPR, author = {Yin, Yu and Ghasedi, Kamran and Wu, HsiangTao and Yang, Jiaolong and Tong, Xin and Fu, Yun}, title = {NeRFInvertor: High Fidelity NeRF-GAN Inversion for Single-Shot Real Image Animation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8539-8548} }
Trace and Pace: Controllable Pedestrian Animation via Guided Trajectory Diffusion: Davis Rempe,

Zhengyi Luo,

Xue Bin Peng,

Ye Yuan,

Kris Kitani,

Karsten Kreis,

Sanja Fidler,

Or Litany; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Rempe_2023_CVPR, author = {Rempe, Davis and Luo, Zhengyi and Bin Peng, Xue and Yuan, Ye and Kitani, Kris and Kreis, Karsten and Fidler, Sanja and Litany, Or}, title = {Trace and Pace: Controllable Pedestrian Animation via Guided Trajectory Diffusion}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13756-13766} }
Overlooked Factors in Concept-Based Explanations: Dataset Choice, Concept Learnability, and Human Capability: Vikram V. Ramaswamy,

Sunnie S. Y. Kim,

Ruth Fong,

Olga Russakovsky; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ramaswamy_2023_CVPR, author = {Ramaswamy, Vikram V. and Kim, Sunnie S. Y. and Fong, Ruth and Russakovsky, Olga}, title = {Overlooked Factors in Concept-Based Explanations: Dataset Choice, Concept Learnability, and Human Capability}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10932-10941} }
Unsupervised 3D Shape Reconstruction by Part Retrieval and Assembly: Xianghao Xu,

Paul Guerrero,

Matthew Fisher,

Siddhartha Chaudhuri,

Daniel Ritchie; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Xu_2023_CVPR, author = {Xu, Xianghao and Guerrero, Paul and Fisher, Matthew and Chaudhuri, Siddhartha and Ritchie, Daniel}, title = {Unsupervised 3D Shape Reconstruction by Part Retrieval and Assembly}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8559-8567} }
SeqTrack: Sequence to Sequence Learning for Visual Object Tracking: Xin Chen,

Houwen Peng,

Dong Wang,

Huchuan Lu,

Han Hu; [pdf] [arXiv]
[bibtex]
@InProceedings{Chen_2023_CVPR, author = {Chen, Xin and Peng, Houwen and Wang, Dong and Lu, Huchuan and Hu, Han}, title = {SeqTrack: Sequence to Sequence Learning for Visual Object Tracking}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14572-14581} }
AutoLabel: CLIP-Based Framework for Open-Set Video Domain Adaptation: Giacomo Zara,

Subhankar Roy,

Paolo Rota,

Elisa Ricci; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zara_2023_CVPR, author = {Zara, Giacomo and Roy, Subhankar and Rota, Paolo and Ricci, Elisa}, title = {AutoLabel: CLIP-Based Framework for Open-Set Video Domain Adaptation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11504-11513} }
DINER: Depth-Aware Image-Based NEural Radiance Fields: Malte Prinzler,

Otmar Hilliges,

Justus Thies; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Prinzler_2023_CVPR, author = {Prinzler, Malte and Hilliges, Otmar and Thies, Justus}, title = {DINER: Depth-Aware Image-Based NEural Radiance Fields}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12449-12459} }
Reconstructing Signing Avatars From Video Using Linguistic Priors: Maria-Paola Forte,

Peter Kulits,

Chun-Hao P. Huang,

Vasileios Choutas,

Dimitrios Tzionas,

Katherine J. Kuchenbecker,

Michael J. Black; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Forte_2023_CVPR, author = {Forte, Maria-Paola and Kulits, Peter and Huang, Chun-Hao P. and Choutas, Vasileios and Tzionas, Dimitrios and Kuchenbecker, Katherine J. and Black, Michael J.}, title = {Reconstructing Signing Avatars From Video Using Linguistic Priors}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12791-12801} }
DeepMapping2: Self-Supervised Large-Scale LiDAR Map Optimization: Chao Chen,

Xinhao Liu,

Yiming Li,

Li Ding,

Chen Feng; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chen_2023_CVPR, author = {Chen, Chao and Liu, Xinhao and Li, Yiming and Ding, Li and Feng, Chen}, title = {DeepMapping2: Self-Supervised Large-Scale LiDAR Map Optimization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9306-9316} }
DoNet: Deep De-Overlapping Network for Cytology Instance Segmentation: Hao Jiang,

Rushan Zhang,

Yanning Zhou,

Yumeng Wang,

Hao Chen; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Jiang_2023_CVPR, author = {Jiang, Hao and Zhang, Rushan and Zhou, Yanning and Wang, Yumeng and Chen, Hao}, title = {DoNet: Deep De-Overlapping Network for Cytology Instance Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15641-15650} }
Instant Domain Augmentation for LiDAR Semantic Segmentation: Kwonyoung Ryu,

Soonmin Hwang,

Jaesik Park; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ryu_2023_CVPR, author = {Ryu, Kwonyoung and Hwang, Soonmin and Park, Jaesik}, title = {Instant Domain Augmentation for LiDAR Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9350-9360} }
A Characteristic Function-Based Method for Bottom-Up Human Pose Estimation: Haoxuan Qu,

Yujun Cai,

Lin Geng Foo,

Ajay Kumar,

Jun Liu; [pdf] [supp]
[bibtex]
@InProceedings{Qu_2023_CVPR, author = {Qu, Haoxuan and Cai, Yujun and Foo, Lin Geng and Kumar, Ajay and Liu, Jun}, title = {A Characteristic Function-Based Method for Bottom-Up Human Pose Estimation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13009-13018} }
SceneTrilogy: On Human Scene-Sketch and Its Complementarity With Photo and Text: Pinaki Nath Chowdhury,

Ayan Kumar Bhunia,

Aneeshan Sain,

Subhadeep Koley,

Tao Xiang,

Yi-Zhe Song; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chowdhury_2023_CVPR, author = {Chowdhury, Pinaki Nath and Bhunia, Ayan Kumar and Sain, Aneeshan and Koley, Subhadeep and Xiang, Tao and Song, Yi-Zhe}, title = {SceneTrilogy: On Human Scene-Sketch and Its Complementarity With Photo and Text}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10972-10983} }
RefSR-NeRF: Towards High Fidelity and Super Resolution View Synthesis: Xudong Huang,

Wei Li,

Jie Hu,

Hanting Chen,

Yunhe Wang; [pdf] [supp]
[bibtex]
@InProceedings{Huang_2023_CVPR, author = {Huang, Xudong and Li, Wei and Hu, Jie and Chen, Hanting and Wang, Yunhe}, title = {RefSR-NeRF: Towards High Fidelity and Super Resolution View Synthesis}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8244-8253} }
Polarimetric iToF: Measuring High-Fidelity Depth Through Scattering Media: Daniel S. Jeon,

Andréas Meuleman,

Seung-Hwan Baek,

Min H. Kim; [pdf] [supp]
[bibtex]
@InProceedings{Jeon_2023_CVPR, author = {Jeon, Daniel S. and Meuleman, Andr\'eas and Baek, Seung-Hwan and Kim, Min H.}, title = {Polarimetric iToF: Measuring High-Fidelity Depth Through Scattering Media}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12353-12362} }
Mobile User Interface Element Detection via Adaptively Prompt Tuning: Zhangxuan Gu,

Zhuoer Xu,

Haoxing Chen,

Jun Lan,

Changhua Meng,

Weiqiang Wang; [pdf] [arXiv]
[bibtex]
@InProceedings{Gu_2023_CVPR, author = {Gu, Zhangxuan and Xu, Zhuoer and Chen, Haoxing and Lan, Jun and Meng, Changhua and Wang, Weiqiang}, title = {Mobile User Interface Element Detection via Adaptively Prompt Tuning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11155-11164} }
Sparse Multi-Modal Graph Transformer With Shared-Context Processing for Representation Learning of Giga-Pixel Images: Ramin Nakhli,

Puria Azadi Moghadam,

Haoyang Mi,

Hossein Farahani,

Alexander Baras,

Blake Gilks,

Ali Bashashati; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Nakhli_2023_CVPR, author = {Nakhli, Ramin and Moghadam, Puria Azadi and Mi, Haoyang and Farahani, Hossein and Baras, Alexander and Gilks, Blake and Bashashati, Ali}, title = {Sparse Multi-Modal Graph Transformer With Shared-Context Processing for Representation Learning of Giga-Pixel Images}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11547-11557} }
Generating Human Motion From Textual Descriptions With Discrete Representations: Jianrong Zhang,

Yangsong Zhang,

Xiaodong Cun,

Yong Zhang,

Hongwei Zhao,

Hongtao Lu,

Xi Shen,

Ying Shan; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhang_2023_CVPR, author = {Zhang, Jianrong and Zhang, Yangsong and Cun, Xiaodong and Zhang, Yong and Zhao, Hongwei and Lu, Hongtao and Shen, Xi and Shan, Ying}, title = {Generating Human Motion From Textual Descriptions With Discrete Representations}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14730-14740} }
Spatial-Temporal Concept Based Explanation of 3D ConvNets: Ying Ji,

Yu Wang,

Jien Kato; [pdf] [arXiv]
[bibtex]
@InProceedings{Ji_2023_CVPR, author = {Ji, Ying and Wang, Yu and Kato, Jien}, title = {Spatial-Temporal Concept Based Explanation of 3D ConvNets}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15444-15453} }
Robust Test-Time Adaptation in Dynamic Scenarios: Longhui Yuan,

Binhui Xie,

Shuang Li; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yuan_2023_CVPR, author = {Yuan, Longhui and Xie, Binhui and Li, Shuang}, title = {Robust Test-Time Adaptation in Dynamic Scenarios}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15922-15932} }
Global and Local Mixture Consistency Cumulative Learning for Long-Tailed Visual Recognitions: Fei Du,

Peng Yang,

Qi Jia,

Fengtao Nan,

Xiaoting Chen,

Yun Yang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Du_2023_CVPR, author = {Du, Fei and Yang, Peng and Jia, Qi and Nan, Fengtao and Chen, Xiaoting and Yang, Yun}, title = {Global and Local Mixture Consistency Cumulative Learning for Long-Tailed Visual Recognitions}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15814-15823} }
NIRVANA: Neural Implicit Representations of Videos With Adaptive Networks and Autoregressive Patch-Wise Modeling: Shishira R. Maiya,

Sharath Girish,

Max Ehrlich,

Hanyu Wang,

Kwot Sin Lee,

Patrick Poirson,

Pengxiang Wu,

Chen Wang,

Abhinav Shrivastava; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Maiya_2023_CVPR, author = {Maiya, Shishira R. and Girish, Sharath and Ehrlich, Max and Wang, Hanyu and Lee, Kwot Sin and Poirson, Patrick and Wu, Pengxiang and Wang, Chen and Shrivastava, Abhinav}, title = {NIRVANA: Neural Implicit Representations of Videos With Adaptive Networks and Autoregressive Patch-Wise Modeling}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14378-14387} }
Collaboration Helps Camera Overtake LiDAR in 3D Detection: Yue Hu,

Yifan Lu,

Runsheng Xu,

Weidi Xie,

Siheng Chen,

Yanfeng Wang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Hu_2023_CVPR, author = {Hu, Yue and Lu, Yifan and Xu, Runsheng and Xie, Weidi and Chen, Siheng and Wang, Yanfeng}, title = {Collaboration Helps Camera Overtake LiDAR in 3D Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9243-9252} }
ReCo: Region-Controlled Text-to-Image Generation: Zhengyuan Yang,

Jianfeng Wang,

Zhe Gan,

Linjie Li,

Kevin Lin,

Chenfei Wu,

Nan Duan,

Zicheng Liu,

Ce Liu,

Michael Zeng,

Lijuan Wang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yang_2023_CVPR, author = {Yang, Zhengyuan and Wang, Jianfeng and Gan, Zhe and Li, Linjie and Lin, Kevin and Wu, Chenfei and Duan, Nan and Liu, Zicheng and Liu, Ce and Zeng, Michael and Wang, Lijuan}, title = {ReCo: Region-Controlled Text-to-Image Generation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14246-14255} }
Fix the Noise: Disentangling Source Feature for Controllable Domain Translation: Dongyeun Lee,

Jae Young Lee,

Doyeon Kim,

Jaehyun Choi,

Jaejun Yoo,

Junmo Kim; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Lee_2023_CVPR, author = {Lee, Dongyeun and Lee, Jae Young and Kim, Doyeon and Choi, Jaehyun and Yoo, Jaejun and Kim, Junmo}, title = {Fix the Noise: Disentangling Source Feature for Controllable Domain Translation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14224-14234} }
Sparsely Annotated Semantic Segmentation With Adaptive Gaussian Mixtures: Linshan Wu,

Zhun Zhong,

Leyuan Fang,

Xingxin He,

Qiang Liu,

Jiayi Ma,

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

Xiaoyi Dong,

Dongdong Chen,

Weiming Zhang,

Feifei Wang,

Gang Hua,

Nenghai Yu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Huang_2023_CVPR, author = {Huang, Qidong and Dong, Xiaoyi and Chen, Dongdong and Zhang, Weiming and Wang, Feifei and Hua, Gang and Yu, Nenghai}, title = {Diversity-Aware Meta Visual Prompting}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10878-10887} }
FaceLit: Neural 3D Relightable Faces: Anurag Ranjan,

Kwang Moo Yi,

Jen-Hao Rick Chang,

Oncel Tuzel; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ranjan_2023_CVPR, author = {Ranjan, Anurag and Yi, Kwang Moo and Chang, Jen-Hao Rick and Tuzel, Oncel}, title = {FaceLit: Neural 3D Relightable Faces}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8619-8628} }
Visual Programming: Compositional Visual Reasoning Without Training: Tanmay Gupta,

Aniruddha Kembhavi; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Gupta_2023_CVPR, author = {Gupta, Tanmay and Kembhavi, Aniruddha}, title = {Visual Programming: Compositional Visual Reasoning Without Training}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14953-14962} }
Real-Time Evaluation in Online Continual Learning: A New Hope: Yasir Ghunaim,

Adel Bibi,

Kumail Alhamoud,

Motasem Alfarra,

Hasan Abed Al Kader Hammoud,

Ameya Prabhu,

Philip H.S. Torr,

Bernard Ghanem; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ghunaim_2023_CVPR, author = {Ghunaim, Yasir and Bibi, Adel and Alhamoud, Kumail and Alfarra, Motasem and Al Kader Hammoud, Hasan Abed and Prabhu, Ameya and Torr, Philip H.S. and Ghanem, Bernard}, title = {Real-Time Evaluation in Online Continual Learning: A New Hope}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11888-11897} }
BAAM: Monocular 3D Pose and Shape Reconstruction With Bi-Contextual Attention Module and Attention-Guided Modeling: Hyo-Jun Lee,

Hanul Kim,

Su-Min Choi,

Seong-Gyun Jeong,

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

Zhiwu Huang,

Qianru Sun,

Li Song,

Wenjun Zhang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Xue_2023_CVPR, author = {Xue, Han and Huang, Zhiwu and Sun, Qianru and Song, Li and Zhang, Wenjun}, title = {Freestyle Layout-to-Image Synthesis}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14256-14266} }
Visual Dependency Transformers: Dependency Tree Emerges From Reversed Attention: Mingyu Ding,

Yikang Shen,

Lijie Fan,

Zhenfang Chen,

Zitian Chen,

Ping Luo,

Joshua B. Tenenbaum,

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

Yonggang Li,

Xiangyu Zhang,

Yongtao Wang,

Jian Sun; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhang_2023_CVPR, author = {Zhang, Xuanyang and Li, Yonggang and Zhang, Xiangyu and Wang, Yongtao and Sun, Jian}, title = {Differentiable Architecture Search With Random Features}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16060-16069} }
Enhanced Stable View Synthesis: Nishant Jain,

Suryansh Kumar,

Luc Van Gool; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Jain_2023_CVPR, author = {Jain, Nishant and Kumar, Suryansh and Van Gool, Luc}, title = {Enhanced Stable View Synthesis}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13208-13217} }
Breaching FedMD: Image Recovery via Paired-Logits Inversion Attack: Hideaki Takahashi,

Jingjing Liu,

Yang Liu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Takahashi_2023_CVPR, author = {Takahashi, Hideaki and Liu, Jingjing and Liu, Yang}, title = {Breaching FedMD: Image Recovery via Paired-Logits Inversion Attack}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12198-12207} }
Biomechanics-Guided Facial Action Unit Detection Through Force Modeling: Zijun Cui,

Chenyi Kuang,

Tian Gao,

Kartik Talamadupula,

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

Xuhao Sun,

Xiu-Shen Wei; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Shen_2023_CVPR, author = {Shen, Yang and Sun, Xuhao and Wei, Xiu-Shen}, title = {Equiangular Basis Vectors}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11755-11765} }
Cross-Guided Optimization of Radiance Fields With Multi-View Image Super-Resolution for High-Resolution Novel View Synthesis: Youngho Yoon,

Kuk-Jin Yoon; [pdf] [supp]
[bibtex]
@InProceedings{Yoon_2023_CVPR, author = {Yoon, Youngho and Yoon, Kuk-Jin}, title = {Cross-Guided Optimization of Radiance Fields With Multi-View Image Super-Resolution for High-Resolution Novel View Synthesis}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12428-12438} }
Unified Pose Sequence Modeling: Lin Geng Foo,

Tianjiao Li,

Hossein Rahmani,

Qiuhong Ke,

Jun Liu; [pdf]
[bibtex]
@InProceedings{Foo_2023_CVPR, author = {Foo, Lin Geng and Li, Tianjiao and Rahmani, Hossein and Ke, Qiuhong and Liu, Jun}, title = {Unified Pose Sequence Modeling}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13019-13030} }
Probability-Based Global Cross-Modal Upsampling for Pansharpening: Zeyu Zhu,

Xiangyong Cao,

Man Zhou,

Junhao Huang,

Deyu Meng; [pdf] [arXiv]
[bibtex]
@InProceedings{Zhu_2023_CVPR, author = {Zhu, Zeyu and Cao, Xiangyong and Zhou, Man and Huang, Junhao and Meng, Deyu}, title = {Probability-Based Global Cross-Modal Upsampling for Pansharpening}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14039-14048} }
FAC: 3D Representation Learning via Foreground Aware Feature Contrast: Kangcheng Liu,

Aoran Xiao,

Xiaoqin Zhang,

Shijian Lu,

Ling Shao; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Liu_2023_CVPR, author = {Liu, Kangcheng and Xiao, Aoran and Zhang, Xiaoqin and Lu, Shijian and Shao, Ling}, title = {FAC: 3D Representation Learning via Foreground Aware Feature Contrast}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9476-9485} }
Improving Visual Representation Learning Through Perceptual Understanding: Samyakh Tukra,

Frederick Hoffman,

Ken Chatfield; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Tukra_2023_CVPR, author = {Tukra, Samyakh and Hoffman, Frederick and Chatfield, Ken}, title = {Improving Visual Representation Learning Through Perceptual Understanding}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14486-14495} }
Learning Bottleneck Concepts in Image Classification: Bowen Wang,

Liangzhi Li,

Yuta Nakashima,

Hajime Nagahara; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2023_CVPR, author = {Wang, Bowen and Li, Liangzhi and Nakashima, Yuta and Nagahara, Hajime}, title = {Learning Bottleneck Concepts in Image Classification}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10962-10971} }
Inversion-Based Style Transfer With Diffusion Models: Yuxin Zhang,

Nisha Huang,

Fan Tang,

Haibin Huang,

Chongyang Ma,

Weiming Dong,

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

Ruikang Liu,

Shuo Yang,

Zenghao Chai,

Chun Yuan; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Xu_2023_CVPR, author = {Xu, Zhengzhuo and Liu, Ruikang and Yang, Shuo and Chai, Zenghao and Yuan, Chun}, title = {Learning Imbalanced Data With Vision Transformers}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15793-15803} }
PHA: Patch-Wise High-Frequency Augmentation for Transformer-Based Person Re-Identification: Guiwei Zhang,

Yongfei Zhang,

Tianyu Zhang,

Bo Li,

Shiliang Pu; [pdf]
[bibtex]
@InProceedings{Zhang_2023_CVPR, author = {Zhang, Guiwei and Zhang, Yongfei and Zhang, Tianyu and Li, Bo and Pu, Shiliang}, title = {PHA: Patch-Wise High-Frequency Augmentation for Transformer-Based Person Re-Identification}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14133-14142} }
Learning Instance-Level Representation for Large-Scale Multi-Modal Pretraining in E-Commerce: Yang Jin,

Yongzhi Li,

Zehuan Yuan,

Yadong Mu; [pdf] [supp]
[bibtex]
@InProceedings{Jin_2023_CVPR, author = {Jin, Yang and Li, Yongzhi and Yuan, Zehuan and Mu, Yadong}, title = {Learning Instance-Level Representation for Large-Scale Multi-Modal Pretraining in E-Commerce}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11060-11069} }
Conditional Text Image Generation With Diffusion Models: Yuanzhi Zhu,

Zhaohai Li,

Tianwei Wang,

Mengchao He,

Cong Yao; [pdf]
[bibtex]
@InProceedings{Zhu_2023_CVPR, author = {Zhu, Yuanzhi and Li, Zhaohai and Wang, Tianwei and He, Mengchao and Yao, Cong}, title = {Conditional Text Image Generation With Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14235-14245} }
AnchorFormer: Point Cloud Completion From Discriminative Nodes: Zhikai Chen,

Fuchen Long,

Zhaofan Qiu,

Ting Yao,

Wengang Zhou,

Jiebo Luo,

Tao Mei; [pdf]
[bibtex]
@InProceedings{Chen_2023_CVPR, author = {Chen, Zhikai and Long, Fuchen and Qiu, Zhaofan and Yao, Ting and Zhou, Wengang and Luo, Jiebo and Mei, Tao}, title = {AnchorFormer: Point Cloud Completion From Discriminative Nodes}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13581-13590} }
Co-SLAM: Joint Coordinate and Sparse Parametric Encodings for Neural Real-Time SLAM: Hengyi Wang,

Jingwen Wang,

Lourdes Agapito; [pdf] [supp]
[bibtex]
@InProceedings{Wang_2023_CVPR, author = {Wang, Hengyi and Wang, Jingwen and Agapito, Lourdes}, title = {Co-SLAM: Joint Coordinate and Sparse Parametric Encodings for Neural Real-Time SLAM}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13293-13302} }
Regularization of Polynomial Networks for Image Recognition: Grigorios G. Chrysos,

Bohan Wang,

Jiankang Deng,

Volkan Cevher; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chrysos_2023_CVPR, author = {Chrysos, Grigorios G. and Wang, Bohan and Deng, Jiankang and Cevher, Volkan}, title = {Regularization of Polynomial Networks for Image Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16123-16132} }
EfficientViT: Memory Efficient Vision Transformer With Cascaded Group Attention: Xinyu Liu,

Houwen Peng,

Ningxin Zheng,

Yuqing Yang,

Han Hu,

Yixuan Yuan; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Liu_2023_CVPR, author = {Liu, Xinyu and Peng, Houwen and Zheng, Ningxin and Yang, Yuqing and Hu, Han and Yuan, Yixuan}, title = {EfficientViT: Memory Efficient Vision Transformer With Cascaded Group Attention}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14420-14430} }
DiffCollage: Parallel Generation of Large Content With Diffusion Models: Qinsheng Zhang,

Jiaming Song,

Xun Huang,

Yongxin Chen,

Ming-Yu Liu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhang_2023_CVPR, author = {Zhang, Qinsheng and Song, Jiaming and Huang, Xun and Chen, Yongxin and Liu, Ming-Yu}, title = {DiffCollage: Parallel Generation of Large Content With Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10188-10198} }
Efficient Second-Order Plane Adjustment: Lipu Zhou; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhou_2023_CVPR, author = {Zhou, Lipu}, title = {Efficient Second-Order Plane Adjustment}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13113-13121} }
Mofusion: A Framework for Denoising-Diffusion-Based Motion Synthesis: Rishabh Dabral,

Muhammad Hamza Mughal,

Vladislav Golyanik,

Christian Theobalt; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Dabral_2023_CVPR, author = {Dabral, Rishabh and Mughal, Muhammad Hamza and Golyanik, Vladislav and Theobalt, Christian}, title = {Mofusion: A Framework for Denoising-Diffusion-Based Motion Synthesis}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9760-9770} }
PoseFormerV2: Exploring Frequency Domain for Efficient and Robust 3D Human Pose Estimation: Qitao Zhao,

Ce Zheng,

Mengyuan Liu,

Pichao Wang,

Chen Chen; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhao_2023_CVPR, author = {Zhao, Qitao and Zheng, Ce and Liu, Mengyuan and Wang, Pichao and Chen, Chen}, title = {PoseFormerV2: Exploring Frequency Domain for Efficient and Robust 3D Human Pose Estimation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8877-8886} }
Mask3D: Pre-Training 2D Vision Transformers by Learning Masked 3D Priors: Ji Hou,

Xiaoliang Dai,

Zijian He,

Angela Dai,

Matthias Nießner; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Hou_2023_CVPR, author = {Hou, Ji and Dai, Xiaoliang and He, Zijian and Dai, Angela and Nie{\ss}ner, Matthias}, title = {Mask3D: Pre-Training 2D Vision Transformers by Learning Masked 3D Priors}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13510-13519} }
Physically Adversarial Infrared Patches With Learnable Shapes and Locations: Xingxing Wei,

Jie Yu,

Yao Huang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wei_2023_CVPR, author = {Wei, Xingxing and Yu, Jie and Huang, Yao}, title = {Physically Adversarial Infrared Patches With Learnable Shapes and Locations}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12334-12342} }
Exemplar-FreeSOLO: Enhancing Unsupervised Instance Segmentation With Exemplars: Taoseef Ishtiak,

Qing En,

Yuhong Guo; [pdf] [supp]
[bibtex]
@InProceedings{Ishtiak_2023_CVPR, author = {Ishtiak, Taoseef and En, Qing and Guo, Yuhong}, title = {Exemplar-FreeSOLO: Enhancing Unsupervised Instance Segmentation With Exemplars}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15424-15433} }
Multimodal Prompting With Missing Modalities for Visual Recognition: Yi-Lun Lee,

Yi-Hsuan Tsai,

Wei-Chen Chiu,

Chen-Yu Lee; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Lee_2023_CVPR, author = {Lee, Yi-Lun and Tsai, Yi-Hsuan and Chiu, Wei-Chen and Lee, Chen-Yu}, title = {Multimodal Prompting With Missing Modalities for Visual Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14943-14952} }
Neural Koopman Pooling: Control-Inspired Temporal Dynamics Encoding for Skeleton-Based Action Recognition: Xinghan Wang,

Xin Xu,

Yadong Mu; [pdf] [supp]
[bibtex]
@InProceedings{Wang_2023_CVPR, author = {Wang, Xinghan and Xu, Xin and Mu, Yadong}, title = {Neural Koopman Pooling: Control-Inspired Temporal Dynamics Encoding for Skeleton-Based Action Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10597-10607} }
Blind Image Quality Assessment via Vision-Language Correspondence: A Multitask Learning Perspective: Weixia Zhang,

Guangtao Zhai,

Ying Wei,

Xiaokang Yang,

Kede Ma; [pdf] [arXiv]
[bibtex]
@InProceedings{Zhang_2023_CVPR, author = {Zhang, Weixia and Zhai, Guangtao and Wei, Ying and Yang, Xiaokang and Ma, Kede}, title = {Blind Image Quality Assessment via Vision-Language Correspondence: A Multitask Learning Perspective}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14071-14081} }
Integral Neural Networks: Kirill Solodskikh,

Azim Kurbanov,

Ruslan Aydarkhanov,

Irina Zhelavskaya,

Yury Parfenov,

Dehua Song,

Stamatios Lefkimmiatis; [pdf] [supp]
[bibtex]
@InProceedings{Solodskikh_2023_CVPR, author = {Solodskikh, Kirill and Kurbanov, Azim and Aydarkhanov, Ruslan and Zhelavskaya, Irina and Parfenov, Yury and Song, Dehua and Lefkimmiatis, Stamatios}, title = {Integral Neural Networks}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16113-16122} }
EXCALIBUR: Encouraging and Evaluating Embodied Exploration: Hao Zhu,

Raghav Kapoor,

So Yeon Min,

Winson Han,

Jiatai Li,

Kaiwen Geng,

Graham Neubig,

Yonatan Bisk,

Aniruddha Kembhavi,

Luca Weihs; [pdf] [supp]
[bibtex]
@InProceedings{Zhu_2023_CVPR, author = {Zhu, Hao and Kapoor, Raghav and Min, So Yeon and Han, Winson and Li, Jiatai and Geng, Kaiwen and Neubig, Graham and Bisk, Yonatan and Kembhavi, Aniruddha and Weihs, Luca}, title = {EXCALIBUR: Encouraging and Evaluating Embodied Exploration}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14931-14942} }
Visual DNA: Representing and Comparing Images Using Distributions of Neuron Activations: Benjamin Ramtoula,

Matthew Gadd,

Paul Newman,

Daniele De Martini; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ramtoula_2023_CVPR, author = {Ramtoula, Benjamin and Gadd, Matthew and Newman, Paul and De Martini, Daniele}, title = {Visual DNA: Representing and Comparing Images Using Distributions of Neuron Activations}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11113-11123} }
Recognizability Embedding Enhancement for Very Low-Resolution Face Recognition and Quality Estimation: Jacky Chen Long Chai,

Tiong-Sik Ng,

Cheng-Yaw Low,

Jaewoo Park,

Andrew Beng Jin Teoh; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chai_2023_CVPR, author = {Chai, Jacky Chen Long and Ng, Tiong-Sik and Low, Cheng-Yaw and Park, Jaewoo and Teoh, Andrew Beng Jin}, title = {Recognizability Embedding Enhancement for Very Low-Resolution Face Recognition and Quality Estimation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9957-9967} }
Accelerating Dataset Distillation via Model Augmentation: Lei Zhang,

Jie Zhang,

Bowen Lei,

Subhabrata Mukherjee,

Xiang Pan,

Bo Zhao,

Caiwen Ding,

Yao Li,

Dongkuan Xu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhang_2023_CVPR, author = {Zhang, Lei and Zhang, Jie and Lei, Bowen and Mukherjee, Subhabrata and Pan, Xiang and Zhao, Bo and Ding, Caiwen and Li, Yao and Xu, Dongkuan}, title = {Accelerating Dataset Distillation via Model Augmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11950-11959} }
Frame-Event Alignment and Fusion Network for High Frame Rate Tracking: Jiqing Zhang,

Yuanchen Wang,

Wenxi Liu,

Meng Li,

Jinpeng Bai,

Baocai Yin,

Xin Yang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhang_2023_CVPR, author = {Zhang, Jiqing and Wang, Yuanchen and Liu, Wenxi and Li, Meng and Bai, Jinpeng and Yin, Baocai and Yang, Xin}, title = {Frame-Event Alignment and Fusion Network for High Frame Rate Tracking}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9781-9790} }
Shape-Aware Text-Driven Layered Video Editing: Yao-Chih Lee,

Ji-Ze Genevieve Jang,

Yi-Ting Chen,

Elizabeth Qiu,

Jia-Bin Huang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Lee_2023_CVPR, author = {Lee, Yao-Chih and Jang, Ji-Ze Genevieve and Chen, Yi-Ting and Qiu, Elizabeth and Huang, Jia-Bin}, title = {Shape-Aware Text-Driven Layered Video Editing}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14317-14326} }
Solving Relaxations of MAP-MRF Problems: Combinatorial In-Face Frank-Wolfe Directions: Vladimir Kolmogorov; [pdf] [arXiv]
[bibtex]
@InProceedings{Kolmogorov_2023_CVPR, author = {Kolmogorov, Vladimir}, title = {Solving Relaxations of MAP-MRF Problems: Combinatorial In-Face Frank-Wolfe Directions}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11980-11989} }
MEGANE: Morphable Eyeglass and Avatar Network: Junxuan Li,

Shunsuke Saito,

Tomas Simon,

Stephen Lombardi,

Hongdong Li,

Jason Saragih; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Li_2023_CVPR, author = {Li, Junxuan and Saito, Shunsuke and Simon, Tomas and Lombardi, Stephen and Li, Hongdong and Saragih, Jason}, title = {MEGANE: Morphable Eyeglass and Avatar Network}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12769-12779} }
Enhancing Multiple Reliability Measures via Nuisance-Extended Information Bottleneck: Jongheon Jeong,

Sihyun Yu,

Hankook Lee,

Jinwoo Shin; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Jeong_2023_CVPR, author = {Jeong, Jongheon and Yu, Sihyun and Lee, Hankook and Shin, Jinwoo}, title = {Enhancing Multiple Reliability Measures via Nuisance-Extended Information Bottleneck}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16206-16218} }
Rethinking the Approximation Error in 3D Surface Fitting for Point Cloud Normal Estimation: Hang Du,

Xuejun Yan,

Jingjing Wang,

Di Xie,

Shiliang Pu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Du_2023_CVPR, author = {Du, Hang and Yan, Xuejun and Wang, Jingjing and Xie, Di and Pu, Shiliang}, title = {Rethinking the Approximation Error in 3D Surface Fitting for Point Cloud Normal Estimation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9486-9495} }
Objaverse: A Universe of Annotated 3D Objects: Matt Deitke,

Dustin Schwenk,

Jordi Salvador,

Luca Weihs,

Oscar Michel,

Eli VanderBilt,

Ludwig Schmidt,

Kiana Ehsani,

Aniruddha Kembhavi,

Ali Farhadi; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Deitke_2023_CVPR, author = {Deitke, Matt and Schwenk, Dustin and Salvador, Jordi and Weihs, Luca and Michel, Oscar and VanderBilt, Eli and Schmidt, Ludwig and Ehsani, Kiana and Kembhavi, Aniruddha and Farhadi, Ali}, title = {Objaverse: A Universe of Annotated 3D Objects}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13142-13153} }
A-Cap: Anticipation Captioning With Commonsense Knowledge: Duc Minh Vo,

Quoc-An Luong,

Akihiro Sugimoto,

Hideki Nakayama; [pdf] [supp]
[bibtex]
@InProceedings{Vo_2023_CVPR, author = {Vo, Duc Minh and Luong, Quoc-An and Sugimoto, Akihiro and Nakayama, Hideki}, title = {A-Cap: Anticipation Captioning With Commonsense Knowledge}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10824-10833} }
Domain Generalized Stereo Matching via Hierarchical Visual Transformation: Tianyu Chang,

Xun Yang,

Tianzhu Zhang,

Meng Wang; [pdf] [supp]
[bibtex]
@InProceedings{Chang_2023_CVPR, author = {Chang, Tianyu and Yang, Xun and Zhang, Tianzhu and Wang, Meng}, title = {Domain Generalized Stereo Matching via Hierarchical Visual Transformation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9559-9568} }
Adapting Shortcut With Normalizing Flow: An Efficient Tuning Framework for Visual Recognition: Yaoming Wang,

Bowen Shi,

Xiaopeng Zhang,

Jin Li,

Yuchen Liu,

Wenrui Dai,

Chenglin Li,

Hongkai Xiong,

Qi Tian; [pdf] [supp]
[bibtex]
@InProceedings{Wang_2023_CVPR, author = {Wang, Yaoming and Shi, Bowen and Zhang, Xiaopeng and Li, Jin and Liu, Yuchen and Dai, Wenrui and Li, Chenglin and Xiong, Hongkai and Tian, Qi}, title = {Adapting Shortcut With Normalizing Flow: An Efficient Tuning Framework for Visual Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15965-15974} }
Unpaired Image-to-Image Translation With Shortest Path Regularization: Shaoan Xie,

Yanwu Xu,

Mingming Gong,

Kun Zhang; [pdf]
[bibtex]
@InProceedings{Xie_2023_CVPR, author = {Xie, Shaoan and Xu, Yanwu and Gong, Mingming and Zhang, Kun}, title = {Unpaired Image-to-Image Translation With Shortest Path Regularization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10177-10187} }
MotionDiffuser: Controllable Multi-Agent Motion Prediction Using Diffusion: Chiyu “Max” Jiang,

Andre Cornman,

Cheolho Park,

Benjamin Sapp,

Yin Zhou,

Dragomir Anguelov; [pdf] [supp]
[bibtex]
@InProceedings{Jiang_2023_CVPR, author = {Jiang, Chiyu {\textquotedblleft}Max{\textquotedblright} and Cornman, Andre and Park, Cheolho and Sapp, Benjamin and Zhou, Yin and Anguelov, Dragomir}, title = {MotionDiffuser: Controllable Multi-Agent Motion Prediction Using Diffusion}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9644-9653} }
ConvNeXt V2: Co-Designing and Scaling ConvNets With Masked Autoencoders: Sanghyun Woo,

Shoubhik Debnath,

Ronghang Hu,

Xinlei Chen,

Zhuang Liu,

In So Kweon,

Saining Xie; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Woo_2023_CVPR, author = {Woo, Sanghyun and Debnath, Shoubhik and Hu, Ronghang and Chen, Xinlei and Liu, Zhuang and Kweon, In So and Xie, Saining}, title = {ConvNeXt V2: Co-Designing and Scaling ConvNets With Masked Autoencoders}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16133-16142} }
Unsupervised Deep Asymmetric Stereo Matching With Spatially-Adaptive Self-Similarity: Taeyong Song,

Sunok Kim,

Kwanghoon Sohn; [pdf] [supp]
[bibtex]
@InProceedings{Song_2023_CVPR, author = {Song, Taeyong and Kim, Sunok and Sohn, Kwanghoon}, title = {Unsupervised Deep Asymmetric Stereo Matching With Spatially-Adaptive Self-Similarity}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13672-13680} }
TWINS: A Fine-Tuning Framework for Improved Transferability of Adversarial Robustness and Generalization: Ziquan Liu,

Yi Xu,

Xiangyang Ji,

Antoni B. Chan; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Liu_2023_CVPR, author = {Liu, Ziquan and Xu, Yi and Ji, Xiangyang and Chan, Antoni B.}, title = {TWINS: A Fine-Tuning Framework for Improved Transferability of Adversarial Robustness and Generalization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16436-16446} }
Object-Aware Distillation Pyramid for Open-Vocabulary Object Detection: Luting Wang,

Yi Liu,

Penghui Du,

Zihan Ding,

Yue Liao,

Qiaosong Qi,

Biaolong Chen,

Si Liu; [pdf] [arXiv]
[bibtex]
@InProceedings{Wang_2023_CVPR, author = {Wang, Luting and Liu, Yi and Du, Penghui and Ding, Zihan and Liao, Yue and Qi, Qiaosong and Chen, Biaolong and Liu, Si}, title = {Object-Aware Distillation Pyramid for Open-Vocabulary Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11186-11196} }
Evolved Part Masking for Self-Supervised Learning: Zhanzhou Feng,

Shiliang Zhang; [pdf] [supp]
[bibtex]
@InProceedings{Feng_2023_CVPR, author = {Feng, Zhanzhou and Zhang, Shiliang}, title = {Evolved Part Masking for Self-Supervised Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10386-10395} }
MV-JAR: Masked Voxel Jigsaw and Reconstruction for LiDAR-Based Self-Supervised Pre-Training: Runsen Xu,

Tai Wang,

Wenwei Zhang,

Runjian Chen,

Jinkun Cao,

Jiangmiao Pang,

Dahua Lin; [pdf] [supp]
[bibtex]
@InProceedings{Xu_2023_CVPR, author = {Xu, Runsen and Wang, Tai and Zhang, Wenwei and Chen, Runjian and Cao, Jinkun and Pang, Jiangmiao and Lin, Dahua}, title = {MV-JAR: Masked Voxel Jigsaw and Reconstruction for LiDAR-Based Self-Supervised Pre-Training}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13445-13454} }
Open-Set Semantic Segmentation for Point Clouds via Adversarial Prototype Framework: Jianan Li,

Qiulei Dong; [pdf] [supp]
[bibtex]
@InProceedings{Li_2023_CVPR, author = {Li, Jianan and Dong, Qiulei}, title = {Open-Set Semantic Segmentation for Point Clouds via Adversarial Prototype Framework}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9425-9434} }
Learning Attention As Disentangler for Compositional Zero-Shot Learning: Shaozhe Hao,

Kai Han,

Kwan-Yee K. Wong; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Hao_2023_CVPR, author = {Hao, Shaozhe and Han, Kai and Wong, Kwan-Yee K.}, title = {Learning Attention As Disentangler for Compositional Zero-Shot Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15315-15324} }
MetaViewer: Towards a Unified Multi-View Representation: Ren Wang,

Haoliang Sun,

Yuling Ma,

Xiaoming Xi,

Yilong Yin; [pdf] [arXiv]
[bibtex]
@InProceedings{Wang_2023_CVPR, author = {Wang, Ren and Sun, Haoliang and Ma, Yuling and Xi, Xiaoming and Yin, Yilong}, title = {MetaViewer: Towards a Unified Multi-View Representation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11590-11599} }
Natural Language-Assisted Sign Language Recognition: Ronglai Zuo,

Fangyun Wei,

Brian Mak; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zuo_2023_CVPR, author = {Zuo, Ronglai and Wei, Fangyun and Mak, Brian}, title = {Natural Language-Assisted Sign Language Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14890-14900} }
Learning Semantic Relationship Among Instances for Image-Text Matching: Zheren Fu,

Zhendong Mao,

Yan Song,

Yongdong Zhang; [pdf]
[bibtex]
@InProceedings{Fu_2023_CVPR, author = {Fu, Zheren and Mao, Zhendong and Song, Yan and Zhang, Yongdong}, title = {Learning Semantic Relationship Among Instances for Image-Text Matching}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15159-15168} }
Global-to-Local Modeling for Video-Based 3D Human Pose and Shape Estimation: Xiaolong Shen,

Zongxin Yang,

Xiaohan Wang,

Jianxin Ma,

Chang Zhou,

Yi Yang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Shen_2023_CVPR, author = {Shen, Xiaolong and Yang, Zongxin and Wang, Xiaohan and Ma, Jianxin and Zhou, Chang and Yang, Yi}, title = {Global-to-Local Modeling for Video-Based 3D Human Pose and Shape Estimation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8887-8896} }
BEDLAM: A Synthetic Dataset of Bodies Exhibiting Detailed Lifelike Animated Motion: Michael J. Black,

Priyanka Patel,

Joachim Tesch,

Jinlong Yang; [pdf] [supp]
[bibtex]
@InProceedings{Black_2023_CVPR, author = {Black, Michael J. and Patel, Priyanka and Tesch, Joachim and Yang, Jinlong}, title = {BEDLAM: A Synthetic Dataset of Bodies Exhibiting Detailed Lifelike Animated Motion}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8726-8737} }
ProtoCon: Pseudo-Label Refinement via Online Clustering and Prototypical Consistency for Efficient Semi-Supervised Learning: Islam Nassar,

Munawar Hayat,

Ehsan Abbasnejad,

Hamid Rezatofighi,

Gholamreza Haffari; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Nassar_2023_CVPR, author = {Nassar, Islam and Hayat, Munawar and Abbasnejad, Ehsan and Rezatofighi, Hamid and Haffari, Gholamreza}, title = {ProtoCon: Pseudo-Label Refinement via Online Clustering and Prototypical Consistency for Efficient Semi-Supervised Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11641-11650} }
Image Super-Resolution Using T-Tetromino Pixels: Simon Grosche,

Andy Regensky,

Jürgen Seiler,

André Kaup; [pdf]
[bibtex]
@InProceedings{Grosche_2023_CVPR, author = {Grosche, Simon and Regensky, Andy and Seiler, J\"urgen and Kaup, Andr\'e}, title = {Image Super-Resolution Using T-Tetromino Pixels}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9989-9998} }
GFIE: A Dataset and Baseline for Gaze-Following From 2D to 3D in Indoor Environments: Zhengxi Hu,

Yuxue Yang,

Xiaolin Zhai,

Dingye Yang,

Bohan Zhou,

Jingtai Liu; [pdf] [supp]
[bibtex]
@InProceedings{Hu_2023_CVPR, author = {Hu, Zhengxi and Yang, Yuxue and Zhai, Xiaolin and Yang, Dingye and Zhou, Bohan and Liu, Jingtai}, title = {GFIE: A Dataset and Baseline for Gaze-Following From 2D to 3D in Indoor Environments}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8907-8916} }
BKinD-3D: Self-Supervised 3D Keypoint Discovery From Multi-View Videos: Jennifer J. Sun,

Lili Karashchuk,

Amil Dravid,

Serim Ryou,

Sonia Fereidooni,

John C. Tuthill,

Aggelos Katsaggelos,

Bingni W. Brunton,

Georgia Gkioxari,

Ann Kennedy,

Yisong Yue,

Pietro Perona; [pdf] [supp]
[bibtex]
@InProceedings{Sun_2023_CVPR, author = {Sun, Jennifer J. and Karashchuk, Lili and Dravid, Amil and Ryou, Serim and Fereidooni, Sonia and Tuthill, John C. and Katsaggelos, Aggelos and Brunton, Bingni W. and Gkioxari, Georgia and Kennedy, Ann and Yue, Yisong and Perona, Pietro}, title = {BKinD-3D: Self-Supervised 3D Keypoint Discovery From Multi-View Videos}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9001-9010} }
StyleRF: Zero-Shot 3D Style Transfer of Neural Radiance Fields: Kunhao Liu,

Fangneng Zhan,

Yiwen Chen,

Jiahui Zhang,

Yingchen Yu,

Abdulmotaleb El Saddik,

Shijian Lu,

Eric P. Xing; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Liu_2023_CVPR, author = {Liu, Kunhao and Zhan, Fangneng and Chen, Yiwen and Zhang, Jiahui and Yu, Yingchen and El Saddik, Abdulmotaleb and Lu, Shijian and Xing, Eric P.}, title = {StyleRF: Zero-Shot 3D Style Transfer of Neural Radiance Fields}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8338-8348} }
Accidental Light Probes: Hong-Xing Yu,

Samir Agarwala,

Charles Herrmann,

Richard Szeliski,

Noah Snavely,

Jiajun Wu,

Deqing Sun; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yu_2023_CVPR, author = {Yu, Hong-Xing and Agarwala, Samir and Herrmann, Charles and Szeliski, Richard and Snavely, Noah and Wu, Jiajun and Sun, Deqing}, title = {Accidental Light Probes}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12521-12530} }
Iterative Vision-and-Language Navigation: Jacob Krantz,

Shurjo Banerjee,

Wang Zhu,

Jason Corso,

Peter Anderson,

Stefan Lee,

Jesse Thomason; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Krantz_2023_CVPR, author = {Krantz, Jacob and Banerjee, Shurjo and Zhu, Wang and Corso, Jason and Anderson, Peter and Lee, Stefan and Thomason, Jesse}, title = {Iterative Vision-and-Language Navigation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14921-14930} }
Adversarial Counterfactual Visual Explanations: Guillaume Jeanneret,

Loïc Simon,

Frédéric Jurie; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Jeanneret_2023_CVPR, author = {Jeanneret, Guillaume and Simon, Lo{\"\i}c and Jurie, Fr\'ed\'eric}, title = {Adversarial Counterfactual Visual Explanations}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16425-16435} }
MaLP: Manipulation Localization Using a Proactive Scheme: Vishal Asnani,

Xi Yin,

Tal Hassner,

Xiaoming Liu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Asnani_2023_CVPR, author = {Asnani, Vishal and Yin, Xi and Hassner, Tal and Liu, Xiaoming}, title = {MaLP: Manipulation Localization Using a Proactive Scheme}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12343-12352} }
MM-Diffusion: Learning Multi-Modal Diffusion Models for Joint Audio and Video Generation: Ludan Ruan,

Yiyang Ma,

Huan Yang,

Huiguo He,

Bei Liu,

Jianlong Fu,

Nicholas Jing Yuan,

Qin Jin,

Baining Guo; [pdf] [supp]
[bibtex]
@InProceedings{Ruan_2023_CVPR, author = {Ruan, Ludan and Ma, Yiyang and Yang, Huan and He, Huiguo and Liu, Bei and Fu, Jianlong and Yuan, Nicholas Jing and Jin, Qin and Guo, Baining}, title = {MM-Diffusion: Learning Multi-Modal Diffusion Models for Joint Audio and Video Generation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10219-10228} }
Robust Generalization Against Photon-Limited Corruptions via Worst-Case Sharpness Minimization: Zhuo Huang,

Miaoxi Zhu,

Xiaobo Xia,

Li Shen,

Jun Yu,

Chen Gong,

Bo Han,

Bo Du,

Tongliang Liu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Huang_2023_CVPR, author = {Huang, Zhuo and Zhu, Miaoxi and Xia, Xiaobo and Shen, Li and Yu, Jun and Gong, Chen and Han, Bo and Du, Bo and Liu, Tongliang}, title = {Robust Generalization Against Photon-Limited Corruptions via Worst-Case Sharpness Minimization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16175-16185} }
Point2Pix: Photo-Realistic Point Cloud Rendering via Neural Radiance Fields: Tao Hu,

Xiaogang Xu,

Shu Liu,

Jiaya Jia; [pdf] [arXiv]
[bibtex]
@InProceedings{Hu_2023_CVPR, author = {Hu, Tao and Xu, Xiaogang and Liu, Shu and Jia, Jiaya}, title = {Point2Pix: Photo-Realistic Point Cloud Rendering via Neural Radiance Fields}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8349-8358} }
NICO++: Towards Better Benchmarking for Domain Generalization: Xingxuan Zhang,

Yue He,

Renzhe Xu,

Han Yu,

Zheyan Shen,

Peng Cui; [pdf] [supp]
[bibtex]
@InProceedings{Zhang_2023_CVPR, author = {Zhang, Xingxuan and He, Yue and Xu, Renzhe and Yu, Han and Shen, Zheyan and Cui, Peng}, title = {NICO++: Towards Better Benchmarking for Domain Generalization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16036-16047} }
CHMATCH: Contrastive Hierarchical Matching and Robust Adaptive Threshold Boosted Semi-Supervised Learning: Jianlong Wu,

Haozhe Yang,

Tian Gan,

Ning Ding,

Feijun Jiang,

Liqiang Nie; [pdf] [supp]
[bibtex]
@InProceedings{Wu_2023_CVPR, author = {Wu, Jianlong and Yang, Haozhe and Gan, Tian and Ding, Ning and Jiang, Feijun and Nie, Liqiang}, title = {CHMATCH: Contrastive Hierarchical Matching and Robust Adaptive Threshold Boosted Semi-Supervised Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15762-15772} }
Neural Dependencies Emerging From Learning Massive Categories: Ruili Feng,

Kecheng Zheng,

Kai Zhu,

Yujun Shen,

Jian Zhao,

Yukun Huang,

Deli Zhao,

Jingren Zhou,

Michael Jordan,

Zheng-Jun Zha; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Feng_2023_CVPR, author = {Feng, Ruili and Zheng, Kecheng and Zhu, Kai and Shen, Yujun and Zhao, Jian and Huang, Yukun and Zhao, Deli and Zhou, Jingren and Jordan, Michael and Zha, Zheng-Jun}, title = {Neural Dependencies Emerging From Learning Massive Categories}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11711-11720} }
ARCTIC: A Dataset for Dexterous Bimanual Hand-Object Manipulation: Zicong Fan,

Omid Taheri,

Dimitrios Tzionas,

Muhammed Kocabas,

Manuel Kaufmann,

Michael J. Black,

Otmar Hilliges; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Fan_2023_CVPR, author = {Fan, Zicong and Taheri, Omid and Tzionas, Dimitrios and Kocabas, Muhammed and Kaufmann, Manuel and Black, Michael J. and Hilliges, Otmar}, title = {ARCTIC: A Dataset for Dexterous Bimanual Hand-Object Manipulation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12943-12954} }
MAGVIT: Masked Generative Video Transformer: Lijun Yu,

Yong Cheng,

Kihyuk Sohn,

José Lezama,

Han Zhang,

Huiwen Chang,

Alexander G. Hauptmann,

Ming-Hsuan Yang,

Yuan Hao,

Irfan Essa,

Lu Jiang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yu_2023_CVPR, author = {Yu, Lijun and Cheng, Yong and Sohn, Kihyuk and Lezama, Jos\'e and Zhang, Han and Chang, Huiwen and Hauptmann, Alexander G. and Yang, Ming-Hsuan and Hao, Yuan and Essa, Irfan and Jiang, Lu}, title = {MAGVIT: Masked Generative Video Transformer}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10459-10469} }
Hidden Gems: 4D Radar Scene Flow Learning Using Cross-Modal Supervision: Fangqiang Ding,

Andras Palffy,

Dariu M. Gavrila,

Chris Xiaoxuan Lu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ding_2023_CVPR, author = {Ding, Fangqiang and Palffy, Andras and Gavrila, Dariu M. and Lu, Chris Xiaoxuan}, title = {Hidden Gems: 4D Radar Scene Flow Learning Using Cross-Modal Supervision}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9340-9349} }
OmniMAE: Single Model Masked Pretraining on Images and Videos: Rohit Girdhar,

Alaaeldin El-Nouby,

Mannat Singh,

Kalyan Vasudev Alwala,

Armand Joulin,

Ishan Misra; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Girdhar_2023_CVPR, author = {Girdhar, Rohit and El-Nouby, Alaaeldin and Singh, Mannat and Alwala, Kalyan Vasudev and Joulin, Armand and Misra, Ishan}, title = {OmniMAE: Single Model Masked Pretraining on Images and Videos}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10406-10417} }
Real-Time Neural Light Field on Mobile Devices: Junli Cao,

Huan Wang,

Pavlo Chemerys,

Vladislav Shakhrai,

Ju Hu,

Yun Fu,

Denys Makoviichuk,

Sergey Tulyakov,

Jian Ren; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Cao_2023_CVPR, author = {Cao, Junli and Wang, Huan and Chemerys, Pavlo and Shakhrai, Vladislav and Hu, Ju and Fu, Yun and Makoviichuk, Denys and Tulyakov, Sergey and Ren, Jian}, title = {Real-Time Neural Light Field on Mobile Devices}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8328-8337} }
End-to-End Video Matting With Trimap Propagation: Wei-Lun Huang,

Ming-Sui Lee; [pdf] [supp]
[bibtex]
@InProceedings{Huang_2023_CVPR, author = {Huang, Wei-Lun and Lee, Ming-Sui}, title = {End-to-End Video Matting With Trimap Propagation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14337-14347} }
DropMAE: Masked Autoencoders With Spatial-Attention Dropout for Tracking Tasks: Qiangqiang Wu,

Tianyu Yang,

Ziquan Liu,

Baoyuan Wu,

Ying Shan,

Antoni B. Chan; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wu_2023_CVPR, author = {Wu, Qiangqiang and Yang, Tianyu and Liu, Ziquan and Wu, Baoyuan and Shan, Ying and Chan, Antoni B.}, title = {DropMAE: Masked Autoencoders With Spatial-Attention Dropout for Tracking Tasks}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14561-14571} }
High-Fidelity Clothed Avatar Reconstruction From a Single Image: Tingting Liao,

Xiaomei Zhang,

Yuliang Xiu,

Hongwei Yi,

Xudong Liu,

Guo-Jun Qi,

Yong Zhang,

Xuan Wang,

Xiangyu Zhu,

Zhen Lei; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Liao_2023_CVPR, author = {Liao, Tingting and Zhang, Xiaomei and Xiu, Yuliang and Yi, Hongwei and Liu, Xudong and Qi, Guo-Jun and Zhang, Yong and Wang, Xuan and Zhu, Xiangyu and Lei, Zhen}, title = {High-Fidelity Clothed Avatar Reconstruction From a Single Image}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8662-8672} }
Zero-Shot Object Counting: Jingyi Xu,

Hieu Le,

Vu Nguyen,

Viresh Ranjan,

Dimitris Samaras; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Xu_2023_CVPR, author = {Xu, Jingyi and Le, Hieu and Nguyen, Vu and Ranjan, Viresh and Samaras, Dimitris}, title = {Zero-Shot Object Counting}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15548-15557} }
Implicit Diffusion Models for Continuous Super-Resolution: Sicheng Gao,

Xuhui Liu,

Bohan Zeng,

Sheng Xu,

Yanjing Li,

Xiaoyan Luo,

Jianzhuang Liu,

Xiantong Zhen,

Baochang Zhang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Gao_2023_CVPR, author = {Gao, Sicheng and Liu, Xuhui and Zeng, Bohan and Xu, Sheng and Li, Yanjing and Luo, Xiaoyan and Liu, Jianzhuang and Zhen, Xiantong and Zhang, Baochang}, title = {Implicit Diffusion Models for Continuous Super-Resolution}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10021-10030} }
Phase-Shifting Coder: Predicting Accurate Orientation in Oriented Object Detection: Yi Yu,

Feipeng Da; [pdf] [arXiv]
[bibtex]
@InProceedings{Yu_2023_CVPR, author = {Yu, Yi and Da, Feipeng}, title = {Phase-Shifting Coder: Predicting Accurate Orientation in Oriented Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13354-13363} }
Neural Lens Modeling: Wenqi Xian,

Aljaž Božič,

Noah Snavely,

Christoph Lassner; [pdf] [supp]
[bibtex]
@InProceedings{Xian_2023_CVPR, author = {Xian, Wenqi and Bo\v{z}i\v{c}, Alja\v{z} and Snavely, Noah and Lassner, Christoph}, title = {Neural Lens Modeling}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8435-8445} }
CoralStyleCLIP: Co-Optimized Region and Layer Selection for Image Editing: Ambareesh Revanur,

Debraj Basu,

Shradha Agrawal,

Dhwanit Agarwal,

Deepak Pai; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Revanur_2023_CVPR, author = {Revanur, Ambareesh and Basu, Debraj and Agrawal, Shradha and Agarwal, Dhwanit and Pai, Deepak}, title = {CoralStyleCLIP: Co-Optimized Region and Layer Selection for Image Editing}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12695-12704} }
GLeaD: Improving GANs With a Generator-Leading Task: Qingyan Bai,

Ceyuan Yang,

Yinghao Xu,

Xihui Liu,

Yujiu Yang,

Yujun Shen; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Bai_2023_CVPR, author = {Bai, Qingyan and Yang, Ceyuan and Xu, Yinghao and Liu, Xihui and Yang, Yujiu and Shen, Yujun}, title = {GLeaD: Improving GANs With a Generator-Leading Task}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12094-12104} }
GALIP: Generative Adversarial CLIPs for Text-to-Image Synthesis: Ming Tao,

Bing-Kun Bao,

Hao Tang,

Changsheng Xu; [pdf] [arXiv]
[bibtex]
@InProceedings{Tao_2023_CVPR, author = {Tao, Ming and Bao, Bing-Kun and Tang, Hao and Xu, Changsheng}, title = {GALIP: Generative Adversarial CLIPs for Text-to-Image Synthesis}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14214-14223} }
Indiscernible Object Counting in Underwater Scenes: Guolei Sun,

Zhaochong An,

Yun Liu,

Ce Liu,

Christos Sakaridis,

Deng-Ping Fan,

Luc Van Gool; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Sun_2023_CVPR, author = {Sun, Guolei and An, Zhaochong and Liu, Yun and Liu, Ce and Sakaridis, Christos and Fan, Deng-Ping and Van Gool, Luc}, title = {Indiscernible Object Counting in Underwater Scenes}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13791-13801} }
Low-Light Image Enhancement via Structure Modeling and Guidance: Xiaogang Xu,

Ruixing Wang,

Jiangbo Lu; [pdf] [arXiv]
[bibtex]
@InProceedings{Xu_2023_CVPR, author = {Xu, Xiaogang and Wang, Ruixing and Lu, Jiangbo}, title = {Low-Light Image Enhancement via Structure Modeling and Guidance}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9893-9903} }
Physics-Driven Diffusion Models for Impact Sound Synthesis From Videos: Kun Su,

Kaizhi Qian,

Eli Shlizerman,

Antonio Torralba,

Chuang Gan; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Su_2023_CVPR, author = {Su, Kun and Qian, Kaizhi and Shlizerman, Eli and Torralba, Antonio and Gan, Chuang}, title = {Physics-Driven Diffusion Models for Impact Sound Synthesis From Videos}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9749-9759} }
Alias-Free Convnets: Fractional Shift Invariance via Polynomial Activations: Hagay Michaeli,

Tomer Michaeli,

Daniel Soudry; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Michaeli_2023_CVPR, author = {Michaeli, Hagay and Michaeli, Tomer and Soudry, Daniel}, title = {Alias-Free Convnets: Fractional Shift Invariance via Polynomial Activations}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16333-16342} }
Shortcomings of Top-Down Randomization-Based Sanity Checks for Evaluations of Deep Neural Network Explanations: Alexander Binder,

Leander Weber,

Sebastian Lapuschkin,

Grégoire Montavon,

Klaus-Robert Müller,

Wojciech Samek; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Binder_2023_CVPR, author = {Binder, Alexander and Weber, Leander and Lapuschkin, Sebastian and Montavon, Gr\'egoire and M\"uller, Klaus-Robert and Samek, Wojciech}, title = {Shortcomings of Top-Down Randomization-Based Sanity Checks for Evaluations of Deep Neural Network Explanations}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16143-16152} }
Neural Part Priors: Learning To Optimize Part-Based Object Completion in RGB-D Scans: Aleksei Bokhovkin,

Angela Dai; [pdf] [supp]
[bibtex]
@InProceedings{Bokhovkin_2023_CVPR, author = {Bokhovkin, Aleksei and Dai, Angela}, title = {Neural Part Priors: Learning To Optimize Part-Based Object Completion in RGB-D Scans}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9032-9042} }
Towards Trustable Skin Cancer Diagnosis via Rewriting Model's Decision: Siyuan Yan,

Zhen Yu,

Xuelin Zhang,

Dwarikanath Mahapatra,

Shekhar S. Chandra,

Monika Janda,

Peter Soyer,

Zongyuan Ge; [pdf] [supp]
[bibtex]
@InProceedings{Yan_2023_CVPR, author = {Yan, Siyuan and Yu, Zhen and Zhang, Xuelin and Mahapatra, Dwarikanath and Chandra, Shekhar S. and Janda, Monika and Soyer, Peter and Ge, Zongyuan}, title = {Towards Trustable Skin Cancer Diagnosis via Rewriting Model's Decision}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11568-11577} }
FeatER: An Efficient Network for Human Reconstruction via Feature Map-Based TransformER: Ce Zheng,

Matias Mendieta,

Taojiannan Yang,

Guo-Jun Qi,

Chen Chen; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zheng_2023_CVPR, author = {Zheng, Ce and Mendieta, Matias and Yang, Taojiannan and Qi, Guo-Jun and Chen, Chen}, title = {FeatER: An Efficient Network for Human Reconstruction via Feature Map-Based TransformER}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13945-13954} }
Visibility Constrained Wide-Band Illumination Spectrum Design for Seeing-in-the-Dark: Muyao Niu,

Zhuoxiao Li,

Zhihang Zhong,

Yinqiang Zheng; [pdf] [arXiv]
[bibtex]
@InProceedings{Niu_2023_CVPR, author = {Niu, Muyao and Li, Zhuoxiao and Zhong, Zhihang and Zheng, Yinqiang}, title = {Visibility Constrained Wide-Band Illumination Spectrum Design for Seeing-in-the-Dark}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13976-13985} }
Learning With Noisy Labels via Self-Supervised Adversarial Noisy Masking: Yuanpeng Tu,

Boshen Zhang,

Yuxi Li,

Liang Liu,

Jian Li,

Jiangning Zhang,

Yabiao Wang,

Chengjie Wang,

Cai Rong Zhao; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Tu_2023_CVPR, author = {Tu, Yuanpeng and Zhang, Boshen and Li, Yuxi and Liu, Liang and Li, Jian and Zhang, Jiangning and Wang, Yabiao and Wang, Chengjie and Zhao, Cai Rong}, title = {Learning With Noisy Labels via Self-Supervised Adversarial Noisy Masking}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16186-16195} }
Towards Domain Generalization for Multi-View 3D Object Detection in Bird-Eye-View: Shuo Wang,

Xinhai Zhao,

Hai-Ming Xu,

Zehui Chen,

Dameng Yu,

Jiahao Chang,

Zhen Yang,

Feng Zhao; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2023_CVPR, author = {Wang, Shuo and Zhao, Xinhai and Xu, Hai-Ming and Chen, Zehui and Yu, Dameng and Chang, Jiahao and Yang, Zhen and Zhao, Feng}, title = {Towards Domain Generalization for Multi-View 3D Object Detection in Bird-Eye-View}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13333-13342} }
Q: How To Specialize Large Vision-Language Models to Data-Scarce VQA Tasks? A: Self-Train on Unlabeled Images!: Zaid Khan,

Vijay Kumar BG,

Samuel Schulter,

Xiang Yu,

Yun Fu,

Manmohan Chandraker; [pdf]
[bibtex]
@InProceedings{Khan_2023_CVPR, author = {Khan, Zaid and BG, Vijay Kumar and Schulter, Samuel and Yu, Xiang and Fu, Yun and Chandraker, Manmohan}, title = {Q: How To Specialize Large Vision-Language Models to Data-Scarce VQA Tasks? A: Self-Train on Unlabeled Images!}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15005-15015} }
Improving Robust Generalization by Direct PAC-Bayesian Bound Minimization: Zifan Wang,

Nan Ding,

Tomer Levinboim,

Xi Chen,

Radu Soricut; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2023_CVPR, author = {Wang, Zifan and Ding, Nan and Levinboim, Tomer and Chen, Xi and Soricut, Radu}, title = {Improving Robust Generalization by Direct PAC-Bayesian Bound Minimization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16458-16468} }
AssemblyHands: Towards Egocentric Activity Understanding via 3D Hand Pose Estimation: Takehiko Ohkawa,

Kun He,

Fadime Sener,

Tomas Hodan,

Luan Tran,

Cem Keskin; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ohkawa_2023_CVPR, author = {Ohkawa, Takehiko and He, Kun and Sener, Fadime and Hodan, Tomas and Tran, Luan and Keskin, Cem}, title = {AssemblyHands: Towards Egocentric Activity Understanding via 3D Hand Pose Estimation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12999-13008} }
Scene-Aware Egocentric 3D Human Pose Estimation: Jian Wang,

Diogo Luvizon,

Weipeng Xu,

Lingjie Liu,

Kripasindhu Sarkar,

Christian Theobalt; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2023_CVPR, author = {Wang, Jian and Luvizon, Diogo and Xu, Weipeng and Liu, Lingjie and Sarkar, Kripasindhu and Theobalt, Christian}, title = {Scene-Aware Egocentric 3D Human Pose Estimation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13031-13040} }
NeuralField-LDM: Scene Generation With Hierarchical Latent Diffusion Models: Seung Wook Kim,

Bradley Brown,

Kangxue Yin,

Karsten Kreis,

Katja Schwarz,

Daiqing Li,

Robin Rombach,

Antonio Torralba,

Sanja Fidler; [pdf] [supp]
[bibtex]
@InProceedings{Kim_2023_CVPR, author = {Kim, Seung Wook and Brown, Bradley and Yin, Kangxue and Kreis, Karsten and Schwarz, Katja and Li, Daiqing and Rombach, Robin and Torralba, Antonio and Fidler, Sanja}, title = {NeuralField-LDM: Scene Generation With Hierarchical Latent Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8496-8506} }
DPF: Learning Dense Prediction Fields With Weak Supervision: Xiaoxue Chen,

Yuhang Zheng,

Yupeng Zheng,

Qiang Zhou,

Hao Zhao,

Guyue Zhou,

Ya-Qin Zhang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chen_2023_CVPR, author = {Chen, Xiaoxue and Zheng, Yuhang and Zheng, Yupeng and Zhou, Qiang and Zhao, Hao and Zhou, Guyue and Zhang, Ya-Qin}, title = {DPF: Learning Dense Prediction Fields With Weak Supervision}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15347-15357} }
CNVid-3.5M: Build, Filter, and Pre-Train the Large-Scale Public Chinese Video-Text Dataset: Tian Gan,

Qing Wang,

Xingning Dong,

Xiangyuan Ren,

Liqiang Nie,

Qingpei Guo; [pdf] [supp]
[bibtex]
@InProceedings{Gan_2023_CVPR, author = {Gan, Tian and Wang, Qing and Dong, Xingning and Ren, Xiangyuan and Nie, Liqiang and Guo, Qingpei}, title = {CNVid-3.5M: Build, Filter, and Pre-Train the Large-Scale Public Chinese Video-Text Dataset}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14815-14824} }
iQuery: Instruments As Queries for Audio-Visual Sound Separation: Jiaben Chen,

Renrui Zhang,

Dongze Lian,

Jiaqi Yang,

Ziyao Zeng,

Jianbo Shi; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chen_2023_CVPR, author = {Chen, Jiaben and Zhang, Renrui and Lian, Dongze and Yang, Jiaqi and Zeng, Ziyao and Shi, Jianbo}, title = {iQuery: Instruments As Queries for Audio-Visual Sound Separation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14675-14686} }
Sampling Is Matter: Point-Guided 3D Human Mesh Reconstruction: Jeonghwan Kim,

Mi-Gyeong Gwon,

Hyunwoo Park,

Hyukmin Kwon,

Gi-Mun Um,

Wonjun Kim; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kim_2023_CVPR, author = {Kim, Jeonghwan and Gwon, Mi-Gyeong and Park, Hyunwoo and Kwon, Hyukmin and Um, Gi-Mun and Kim, Wonjun}, title = {Sampling Is Matter: Point-Guided 3D Human Mesh Reconstruction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12880-12889} }
Look Around for Anomalies: Weakly-Supervised Anomaly Detection via Context-Motion Relational Learning: MyeongAh Cho,

Minjung Kim,

Sangwon Hwang,

Chaewon Park,

Kyungjae Lee,

Sangyoun Lee; [pdf] [supp]
[bibtex]
@InProceedings{Cho_2023_CVPR, author = {Cho, MyeongAh and Kim, Minjung and Hwang, Sangwon and Park, Chaewon and Lee, Kyungjae and Lee, Sangyoun}, title = {Look Around for Anomalies: Weakly-Supervised Anomaly Detection via Context-Motion Relational Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12137-12146} }
Detecting Everything in the Open World: Towards Universal Object Detection: Zhenyu Wang,

Yali Li,

Xi Chen,

Ser-Nam Lim,

Antonio Torralba,

Hengshuang Zhao,

Shengjin Wang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2023_CVPR, author = {Wang, Zhenyu and Li, Yali and Chen, Xi and Lim, Ser-Nam and Torralba, Antonio and Zhao, Hengshuang and Wang, Shengjin}, title = {Detecting Everything in the Open World: Towards Universal Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11433-11443} }
NUWA-LIP: Language-Guided Image Inpainting With Defect-Free VQGAN: Minheng Ni,

Xiaoming Li,

Wangmeng Zuo; [pdf] [supp]
[bibtex]
@InProceedings{Ni_2023_CVPR, author = {Ni, Minheng and Li, Xiaoming and Zuo, Wangmeng}, title = {NUWA-LIP: Language-Guided Image Inpainting With Defect-Free VQGAN}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14183-14192} }
Language Adaptive Weight Generation for Multi-Task Visual Grounding: Wei Su,

Peihan Miao,

Huanzhang Dou,

Gaoang Wang,

Liang Qiao,

Zheyang Li,

Xi Li; [pdf] [supp]
[bibtex]
@InProceedings{Su_2023_CVPR, author = {Su, Wei and Miao, Peihan and Dou, Huanzhang and Wang, Gaoang and Qiao, Liang and Li, Zheyang and Li, Xi}, title = {Language Adaptive Weight Generation for Multi-Task Visual Grounding}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10857-10866} }
Continuous Intermediate Token Learning With Implicit Motion Manifold for Keyframe Based Motion Interpolation: Clinton A. Mo,

Kun Hu,

Chengjiang Long,

Zhiyong Wang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Mo_2023_CVPR, author = {Mo, Clinton A. and Hu, Kun and Long, Chengjiang and Wang, Zhiyong}, title = {Continuous Intermediate Token Learning With Implicit Motion Manifold for Keyframe Based Motion Interpolation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13894-13903} }
SGLoc: Scene Geometry Encoding for Outdoor LiDAR Localization: Wen Li,

Shangshu Yu,

Cheng Wang,

Guosheng Hu,

Siqi Shen,

Chenglu Wen; [pdf] [supp]
[bibtex]
@InProceedings{Li_2023_CVPR, author = {Li, Wen and Yu, Shangshu and Wang, Cheng and Hu, Guosheng and Shen, Siqi and Wen, Chenglu}, title = {SGLoc: Scene Geometry Encoding for Outdoor LiDAR Localization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9286-9295} }
Bridging Search Region Interaction With Template for RGB-T Tracking: Tianrui Hui,

Zizheng Xun,

Fengguang Peng,

Junshi Huang,

Xiaoming Wei,

Xiaolin Wei,

Jiao Dai,

Jizhong Han,

Si Liu; [pdf]
[bibtex]
@InProceedings{Hui_2023_CVPR, author = {Hui, Tianrui and Xun, Zizheng and Peng, Fengguang and Huang, Junshi and Wei, Xiaoming and Wei, Xiaolin and Dai, Jiao and Han, Jizhong and Liu, Si}, title = {Bridging Search Region Interaction With Template for RGB-T Tracking}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13630-13639} }
Indescribable Multi-Modal Spatial Evaluator: Lingke Kong,

X. Sharon Qi,

Qijin Shen,

Jiacheng Wang,

Jingyi Zhang,

Yanle Hu,

Qichao Zhou; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kong_2023_CVPR, author = {Kong, Lingke and Qi, X. Sharon and Shen, Qijin and Wang, Jiacheng and Zhang, Jingyi and Hu, Yanle and Zhou, Qichao}, title = {Indescribable Multi-Modal Spatial Evaluator}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9853-9862} }
ImageBind: One Embedding Space To Bind Them All: Rohit Girdhar,

Alaaeldin El-Nouby,

Zhuang Liu,

Mannat Singh,

Kalyan Vasudev Alwala,

Armand Joulin,

Ishan Misra; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Girdhar_2023_CVPR, author = {Girdhar, Rohit and El-Nouby, Alaaeldin and Liu, Zhuang and Singh, Mannat and Alwala, Kalyan Vasudev and Joulin, Armand and Misra, Ishan}, title = {ImageBind: One Embedding Space To Bind Them All}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15180-15190} }
Three Guidelines You Should Know for Universally Slimmable Self-Supervised Learning: Yun-Hao Cao,

Peiqin Sun,

Shuchang Zhou; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Cao_2023_CVPR, author = {Cao, Yun-Hao and Sun, Peiqin and Zhou, Shuchang}, title = {Three Guidelines You Should Know for Universally Slimmable Self-Supervised Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15742-15751} }
MetaFusion: Infrared and Visible Image Fusion via Meta-Feature Embedding From Object Detection: Wenda Zhao,

Shigeng Xie,

Fan Zhao,

You He,

Huchuan Lu; [pdf]
[bibtex]
@InProceedings{Zhao_2023_CVPR, author = {Zhao, Wenda and Xie, Shigeng and Zhao, Fan and He, You and Lu, Huchuan}, title = {MetaFusion: Infrared and Visible Image Fusion via Meta-Feature Embedding From Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13955-13965} }
End-to-End Vectorized HD-Map Construction With Piecewise Bezier Curve: Limeng Qiao,

Wenjie Ding,

Xi Qiu,

Chi Zhang; [pdf] [supp]
[bibtex]
@InProceedings{Qiao_2023_CVPR, author = {Qiao, Limeng and Ding, Wenjie and Qiu, Xi and Zhang, Chi}, title = {End-to-End Vectorized HD-Map Construction With Piecewise Bezier Curve}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13218-13228} }
On Data Scaling in Masked Image Modeling: Zhenda Xie,

Zheng Zhang,

Yue Cao,

Yutong Lin,

Yixuan Wei,

Qi Dai,

Han Hu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Xie_2023_CVPR, author = {Xie, Zhenda and Zhang, Zheng and Cao, Yue and Lin, Yutong and Wei, Yixuan and Dai, Qi and Hu, Han}, title = {On Data Scaling in Masked Image Modeling}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10365-10374} }
Balanced Energy Regularization Loss for Out-of-Distribution Detection: Hyunjun Choi,

Hawook Jeong,

Jin Young Choi; [pdf] [supp]
[bibtex]
@InProceedings{Choi_2023_CVPR, author = {Choi, Hyunjun and Jeong, Hawook and Choi, Jin Young}, title = {Balanced Energy Regularization Loss for Out-of-Distribution Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15691-15700} }
3D-Aware Face Swapping: Yixuan Li,

Chao Ma,

Yichao Yan,

Wenhan Zhu,

Xiaokang Yang; [pdf] [supp]
[bibtex]
@InProceedings{Li_2023_CVPR, author = {Li, Yixuan and Ma, Chao and Yan, Yichao and Zhu, Wenhan and Yang, Xiaokang}, title = {3D-Aware Face Swapping}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12705-12714} }
Phone2Proc: Bringing Robust Robots Into Our Chaotic World: Matt Deitke,

Rose Hendrix,

Ali Farhadi,

Kiana Ehsani,

Aniruddha Kembhavi; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Deitke_2023_CVPR, author = {Deitke, Matt and Hendrix, Rose and Farhadi, Ali and Ehsani, Kiana and Kembhavi, Aniruddha}, title = {Phone2Proc: Bringing Robust Robots Into Our Chaotic World}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9665-9675} }
Learning Articulated Shape With Keypoint Pseudo-Labels From Web Images: Anastasis Stathopoulos,

Georgios Pavlakos,

Ligong Han,

Dimitris N. Metaxas; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Stathopoulos_2023_CVPR, author = {Stathopoulos, Anastasis and Pavlakos, Georgios and Han, Ligong and Metaxas, Dimitris N.}, title = {Learning Articulated Shape With Keypoint Pseudo-Labels From Web Images}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13092-13101} }
Rethinking Image Super Resolution From Long-Tailed Distribution Learning Perspective: Yuanbiao Gou,

Peng Hu,

Jiancheng Lv,

Hongyuan Zhu,

Xi Peng; [pdf] [supp]
[bibtex]
@InProceedings{Gou_2023_CVPR, author = {Gou, Yuanbiao and Hu, Peng and Lv, Jiancheng and Zhu, Hongyuan and Peng, Xi}, title = {Rethinking Image Super Resolution From Long-Tailed Distribution Learning Perspective}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14327-14336} }
SCOTCH and SODA: A Transformer Video Shadow Detection Framework: Lihao Liu,

Jean Prost,

Lei Zhu,

Nicolas Papadakis,

Pietro Liò,

Carola-Bibiane Schönlieb,

Angelica I. Aviles-Rivero; [pdf] [arXiv]
[bibtex]
@InProceedings{Liu_2023_CVPR, author = {Liu, Lihao and Prost, Jean and Zhu, Lei and Papadakis, Nicolas and Li\`o, Pietro and Sch\"onlieb, Carola-Bibiane and Aviles-Rivero, Angelica I.}, title = {SCOTCH and SODA: A Transformer Video Shadow Detection Framework}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10449-10458} }
CodeTalker: Speech-Driven 3D Facial Animation With Discrete Motion Prior: Jinbo Xing,

Menghan Xia,

Yuechen Zhang,

Xiaodong Cun,

Jue Wang,

Tien-Tsin Wong; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Xing_2023_CVPR, author = {Xing, Jinbo and Xia, Menghan and Zhang, Yuechen and Cun, Xiaodong and Wang, Jue and Wong, Tien-Tsin}, title = {CodeTalker: Speech-Driven 3D Facial Animation With Discrete Motion Prior}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12780-12790} }
Improving Zero-Shot Generalization and Robustness of Multi-Modal Models: Yunhao Ge,

Jie Ren,

Andrew Gallagher,

Yuxiao Wang,

Ming-Hsuan Yang,

Hartwig Adam,

Laurent Itti,

Balaji Lakshminarayanan,

Jiaping Zhao; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ge_2023_CVPR, author = {Ge, Yunhao and Ren, Jie and Gallagher, Andrew and Wang, Yuxiao and Yang, Ming-Hsuan and Adam, Hartwig and Itti, Laurent and Lakshminarayanan, Balaji and Zhao, Jiaping}, title = {Improving Zero-Shot Generalization and Robustness of Multi-Modal Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11093-11101} }
CODA-Prompt: COntinual Decomposed Attention-Based Prompting for Rehearsal-Free Continual Learning: James Seale Smith,

Leonid Karlinsky,

Vyshnavi Gutta,

Paola Cascante-Bonilla,

Donghyun Kim,

Assaf Arbelle,

Rameswar Panda,

Rogerio Feris,

Zsolt Kira; [pdf] [supp]
[bibtex]
@InProceedings{Smith_2023_CVPR, author = {Smith, James Seale and Karlinsky, Leonid and Gutta, Vyshnavi and Cascante-Bonilla, Paola and Kim, Donghyun and Arbelle, Assaf and Panda, Rameswar and Feris, Rogerio and Kira, Zsolt}, title = {CODA-Prompt: COntinual Decomposed Attention-Based Prompting for Rehearsal-Free Continual Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11909-11919} }
Real-Time Multi-Person Eyeblink Detection in the Wild for Untrimmed Video: Wenzheng Zeng,

Yang Xiao,

Sicheng Wei,

Jinfang Gan,

Xintao Zhang,

Zhiguo Cao,

Zhiwen Fang,

Joey Tianyi Zhou; [pdf] [arXiv]
[bibtex]
@InProceedings{Zeng_2023_CVPR, author = {Zeng, Wenzheng and Xiao, Yang and Wei, Sicheng and Gan, Jinfang and Zhang, Xintao and Cao, Zhiguo and Fang, Zhiwen and Zhou, Joey Tianyi}, title = {Real-Time Multi-Person Eyeblink Detection in the Wild for Untrimmed Video}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13854-13863} }
Category Query Learning for Human-Object Interaction Classification: Chi Xie,

Fangao Zeng,

Yue Hu,

Shuang Liang,

Yichen Wei; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Xie_2023_CVPR, author = {Xie, Chi and Zeng, Fangao and Hu, Yue and Liang, Shuang and Wei, Yichen}, title = {Category Query Learning for Human-Object Interaction Classification}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15275-15284} }
MDQE: Mining Discriminative Query Embeddings To Segment Occluded Instances on Challenging Videos: Minghan Li,

Shuai Li,

Wangmeng Xiang,

Lei Zhang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Li_2023_CVPR, author = {Li, Minghan and Li, Shuai and Xiang, Wangmeng and Zhang, Lei}, title = {MDQE: Mining Discriminative Query Embeddings To Segment Occluded Instances on Challenging Videos}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10524-10533} }
Are We Ready for Vision-Centric Driving Streaming Perception? The ASAP Benchmark: Xiaofeng Wang,

Zheng Zhu,

Yunpeng Zhang,

Guan Huang,

Yun Ye,

Wenbo Xu,

Ziwei Chen,

Xingang Wang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2023_CVPR, author = {Wang, Xiaofeng and Zhu, Zheng and Zhang, Yunpeng and Huang, Guan and Ye, Yun and Xu, Wenbo and Chen, Ziwei and Wang, Xingang}, title = {Are We Ready for Vision-Centric Driving Streaming Perception? The ASAP Benchmark}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9600-9610} }
PDPP:Projected Diffusion for Procedure Planning in Instructional Videos: Hanlin Wang,

Yilu Wu,

Sheng Guo,

Limin Wang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2023_CVPR, author = {Wang, Hanlin and Wu, Yilu and Guo, Sheng and Wang, Limin}, title = {PDPP:Projected Diffusion for Procedure Planning in Instructional Videos}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14836-14845} }
Efficient Map Sparsification Based on 2D and 3D Discretized Grids: Xiaoyu Zhang,

Yun-Hui Liu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhang_2023_CVPR, author = {Zhang, Xiaoyu and Liu, Yun-Hui}, title = {Efficient Map Sparsification Based on 2D and 3D Discretized Grids}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12470-12478} }
Class Attention Transfer Based Knowledge Distillation: Ziyao Guo,

Haonan Yan,

Hui Li,

Xiaodong Lin; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Guo_2023_CVPR, author = {Guo, Ziyao and Yan, Haonan and Li, Hui and Lin, Xiaodong}, title = {Class Attention Transfer Based Knowledge Distillation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11868-11877} }
Temporally Consistent Online Depth Estimation Using Point-Based Fusion: Numair Khan,

Eric Penner,

Douglas Lanman,

Lei Xiao; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Khan_2023_CVPR, author = {Khan, Numair and Penner, Eric and Lanman, Douglas and Xiao, Lei}, title = {Temporally Consistent Online Depth Estimation Using Point-Based Fusion}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9119-9129} }
Generalizable Implicit Neural Representations via Instance Pattern Composers: Chiheon Kim,

Doyup Lee,

Saehoon Kim,

Minsu Cho,

Wook-Shin Han; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kim_2023_CVPR, author = {Kim, Chiheon and Lee, Doyup and Kim, Saehoon and Cho, Minsu and Han, Wook-Shin}, title = {Generalizable Implicit Neural Representations via Instance Pattern Composers}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11808-11817} }
What Can Human Sketches Do for Object Detection?: Pinaki Nath Chowdhury,

Ayan Kumar Bhunia,

Aneeshan Sain,

Subhadeep Koley,

Tao Xiang,

Yi-Zhe Song; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chowdhury_2023_CVPR, author = {Chowdhury, Pinaki Nath and Bhunia, Ayan Kumar and Sain, Aneeshan and Koley, Subhadeep and Xiang, Tao and Song, Yi-Zhe}, title = {What Can Human Sketches Do for Object Detection?}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15083-15094} }
Identity-Preserving Talking Face Generation With Landmark and Appearance Priors: Weizhi Zhong,

Chaowei Fang,

Yinqi Cai,

Pengxu Wei,

Gangming Zhao,

Liang Lin,

Guanbin Li; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhong_2023_CVPR, author = {Zhong, Weizhi and Fang, Chaowei and Cai, Yinqi and Wei, Pengxu and Zhao, Gangming and Lin, Liang and Li, Guanbin}, title = {Identity-Preserving Talking Face Generation With Landmark and Appearance Priors}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9729-9738} }
Weakly Supervised Segmentation With Point Annotations for Histopathology Images via Contrast-Based Variational Model: Hongrun Zhang,

Liam Burrows,

Yanda Meng,

Declan Sculthorpe,

Abhik Mukherjee,

Sarah E. Coupland,

Ke Chen,

Yalin Zheng; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhang_2023_CVPR, author = {Zhang, Hongrun and Burrows, Liam and Meng, Yanda and Sculthorpe, Declan and Mukherjee, Abhik and Coupland, Sarah E. and Chen, Ke and Zheng, Yalin}, title = {Weakly Supervised Segmentation With Point Annotations for Histopathology Images via Contrast-Based Variational Model}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15630-15640} }
Zero-Shot Generative Model Adaptation via Image-Specific Prompt Learning: Jiayi Guo,

Chaofei Wang,

You Wu,

Eric Zhang,

Kai Wang,

Xingqian Xu,

Shiji Song,

Humphrey Shi,

Gao Huang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Guo_2023_CVPR, author = {Guo, Jiayi and Wang, Chaofei and Wu, You and Zhang, Eric and Wang, Kai and Xu, Xingqian and Song, Shiji and Shi, Humphrey and Huang, Gao}, title = {Zero-Shot Generative Model Adaptation via Image-Specific Prompt Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11494-11503} }
CelebV-Text: A Large-Scale Facial Text-Video Dataset: Jianhui Yu,

Hao Zhu,

Liming Jiang,

Chen Change Loy,

Weidong Cai,

Wayne Wu; [pdf] [supp]
[bibtex]
@InProceedings{Yu_2023_CVPR, author = {Yu, Jianhui and Zhu, Hao and Jiang, Liming and Loy, Chen Change and Cai, Weidong and Wu, Wayne}, title = {CelebV-Text: A Large-Scale Facial Text-Video Dataset}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14805-14814} }
Hard Patches Mining for Masked Image Modeling: Haochen Wang,

Kaiyou Song,

Junsong Fan,

Yuxi Wang,

Jin Xie,

Zhaoxiang Zhang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2023_CVPR, author = {Wang, Haochen and Song, Kaiyou and Fan, Junsong and Wang, Yuxi and Xie, Jin and Zhang, Zhaoxiang}, title = {Hard Patches Mining for Masked Image Modeling}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10375-10385} }
Diffusion-SDF: Text-To-Shape via Voxelized Diffusion: Muheng Li,

Yueqi Duan,

Jie Zhou,

Jiwen Lu; [pdf] [supp]
[bibtex]
@InProceedings{Li_2023_CVPR, author = {Li, Muheng and Duan, Yueqi and Zhou, Jie and Lu, Jiwen}, title = {Diffusion-SDF: Text-To-Shape via Voxelized Diffusion}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12642-12651} }
Compositor: Bottom-Up Clustering and Compositing for Robust Part and Object Segmentation: Ju He,

Jieneng Chen,

Ming-Xian Lin,

Qihang Yu,

Alan L. Yuille; [pdf]
[bibtex]
@InProceedings{He_2023_CVPR, author = {He, Ju and Chen, Jieneng and Lin, Ming-Xian and Yu, Qihang and Yuille, Alan L.}, title = {Compositor: Bottom-Up Clustering and Compositing for Robust Part and Object Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11259-11268} }
Boundary-Aware Backward-Compatible Representation via Adversarial Learning in Image Retrieval: Tan Pan,

Furong Xu,

Xudong Yang,

Sifeng He,

Chen Jiang,

Qingpei Guo,

Feng Qian,

Xiaobo Zhang,

Yuan Cheng,

Lei Yang,

Wei Chu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Pan_2023_CVPR, author = {Pan, Tan and Xu, Furong and Yang, Xudong and He, Sifeng and Jiang, Chen and Guo, Qingpei and Qian, Feng and Zhang, Xiaobo and Cheng, Yuan and Yang, Lei and Chu, Wei}, title = {Boundary-Aware Backward-Compatible Representation via Adversarial Learning in Image Retrieval}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15201-15210} }
Super-CLEVR: A Virtual Benchmark To Diagnose Domain Robustness in Visual Reasoning: Zhuowan Li,

Xingrui Wang,

Elias Stengel-Eskin,

Adam Kortylewski,

Wufei Ma,

Benjamin Van Durme,

Alan L. Yuille; [pdf] [supp]
[bibtex]
@InProceedings{Li_2023_CVPR, author = {Li, Zhuowan and Wang, Xingrui and Stengel-Eskin, Elias and Kortylewski, Adam and Ma, Wufei and Van Durme, Benjamin and Yuille, Alan L.}, title = {Super-CLEVR: A Virtual Benchmark To Diagnose Domain Robustness in Visual Reasoning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14963-14973} }
Sliced Optimal Partial Transport: Yikun Bai,

Bernhard Schmitzer,

Matthew Thorpe,

Soheil Kolouri; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Bai_2023_CVPR, author = {Bai, Yikun and Schmitzer, Bernhard and Thorpe, Matthew and Kolouri, Soheil}, title = {Sliced Optimal Partial Transport}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13681-13690} }
Siamese DETR: Zeren Chen,

Gengshi Huang,

Wei Li,

Jianing Teng,

Kun Wang,

Jing Shao,

Chen Change Loy,

Lu Sheng; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chen_2023_CVPR, author = {Chen, Zeren and Huang, Gengshi and Li, Wei and Teng, Jianing and Wang, Kun and Shao, Jing and Loy, Chen Change and Sheng, Lu}, title = {Siamese DETR}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15722-15731} }
Turning Strengths Into Weaknesses: A Certified Robustness Inspired Attack Framework Against Graph Neural Networks: Binghui Wang,

Meng Pang,

Yun Dong; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2023_CVPR, author = {Wang, Binghui and Pang, Meng and Dong, Yun}, title = {Turning Strengths Into Weaknesses: A Certified Robustness Inspired Attack Framework Against Graph Neural Networks}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16394-16403} }
Demystifying Causal Features on Adversarial Examples and Causal Inoculation for Robust Network by Adversarial Instrumental Variable Regression: Junho Kim,

Byung-Kwan Lee,

Yong Man Ro; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kim_2023_CVPR, author = {Kim, Junho and Lee, Byung-Kwan and Ro, Yong Man}, title = {Demystifying Causal Features on Adversarial Examples and Causal Inoculation for Robust Network by Adversarial Instrumental Variable Regression}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12302-12312} }
B-Spline Texture Coefficients Estimator for Screen Content Image Super-Resolution: Byeonghyun Pak,

Jaewon Lee,

Kyong Hwan Jin; [pdf] [supp]
[bibtex]
@InProceedings{Pak_2023_CVPR, author = {Pak, Byeonghyun and Lee, Jaewon and Jin, Kyong Hwan}, title = {B-Spline Texture Coefficients Estimator for Screen Content Image Super-Resolution}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10062-10071} }
Domain Expansion of Image Generators: Yotam Nitzan,

Michaël Gharbi,

Richard Zhang,

Taesung Park,

Jun-Yan Zhu,

Daniel Cohen-Or,

Eli Shechtman; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Nitzan_2023_CVPR, author = {Nitzan, Yotam and Gharbi, Micha\"el and Zhang, Richard and Park, Taesung and Zhu, Jun-Yan and Cohen-Or, Daniel and Shechtman, Eli}, title = {Domain Expansion of Image Generators}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15933-15942} }
LVQAC: Lattice Vector Quantization Coupled With Spatially Adaptive Companding for Efficient Learned Image Compression: Xi Zhang,

Xiaolin Wu; [pdf] [arXiv]
[bibtex]
@InProceedings{Zhang_2023_CVPR, author = {Zhang, Xi and Wu, Xiaolin}, title = {LVQAC: Lattice Vector Quantization Coupled With Spatially Adaptive Companding for Efficient Learned Image Compression}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10239-10248} }
Fine-Grained Face Swapping via Regional GAN Inversion: Zhian Liu,

Maomao Li,

Yong Zhang,

Cairong Wang,

Qi Zhang,

Jue Wang,

Yongwei Nie; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Liu_2023_CVPR, author = {Liu, Zhian and Li, Maomao and Zhang, Yong and Wang, Cairong and Zhang, Qi and Wang, Jue and Nie, Yongwei}, title = {Fine-Grained Face Swapping via Regional GAN Inversion}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8578-8587} }
Taming Diffusion Models for Audio-Driven Co-Speech Gesture Generation: Lingting Zhu,

Xian Liu,

Xuanyu Liu,

Rui Qian,

Ziwei Liu,

Lequan Yu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhu_2023_CVPR, author = {Zhu, Lingting and Liu, Xian and Liu, Xuanyu and Qian, Rui and Liu, Ziwei and Yu, Lequan}, title = {Taming Diffusion Models for Audio-Driven Co-Speech Gesture Generation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10544-10553} }
NeRFLix: High-Quality Neural View Synthesis by Learning a Degradation-Driven Inter-Viewpoint MiXer: Kun Zhou,

Wenbo Li,

Yi Wang,

Tao Hu,

Nianjuan Jiang,

Xiaoguang Han,

Jiangbo Lu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhou_2023_CVPR, author = {Zhou, Kun and Li, Wenbo and Wang, Yi and Hu, Tao and Jiang, Nianjuan and Han, Xiaoguang and Lu, Jiangbo}, title = {NeRFLix: High-Quality Neural View Synthesis by Learning a Degradation-Driven Inter-Viewpoint MiXer}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12363-12374} }
STMixer: A One-Stage Sparse Action Detector: Tao Wu,

Mengqi Cao,

Ziteng Gao,

Gangshan Wu,

Limin Wang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wu_2023_CVPR, author = {Wu, Tao and Cao, Mengqi and Gao, Ziteng and Wu, Gangshan and Wang, Limin}, title = {STMixer: A One-Stage Sparse Action Detector}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14720-14729} }
Genie: Show Me the Data for Quantization: Yongkweon Jeon,

Chungman Lee,

Ho-young Kim; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Jeon_2023_CVPR, author = {Jeon, Yongkweon and Lee, Chungman and Kim, Ho-young}, title = {Genie: Show Me the Data for Quantization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12064-12073} }
Multi-Agent Automated Machine Learning: Zhaozhi Wang,

Kefan Su,

Jian Zhang,

Huizhu Jia,

Qixiang Ye,

Xiaodong Xie,

Zongqing Lu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2023_CVPR, author = {Wang, Zhaozhi and Su, Kefan and Zhang, Jian and Jia, Huizhu and Ye, Qixiang and Xie, Xiaodong and Lu, Zongqing}, title = {Multi-Agent Automated Machine Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11960-11969} }
Robot Structure Prior Guided Temporal Attention for Camera-to-Robot Pose Estimation From Image Sequence: Yang Tian,

Jiyao Zhang,

Zekai Yin,

Hao Dong; [pdf]
[bibtex]
@InProceedings{Tian_2023_CVPR, author = {Tian, Yang and Zhang, Jiyao and Yin, Zekai and Dong, Hao}, title = {Robot Structure Prior Guided Temporal Attention for Camera-to-Robot Pose Estimation From Image Sequence}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8917-8926} }
HRDFuse: Monocular 360deg Depth Estimation by Collaboratively Learning Holistic-With-Regional Depth Distributions: Hao Ai,

Zidong Cao,

Yan-Pei Cao,

Ying Shan,

Lin Wang; [pdf] [supp]
[bibtex]
@InProceedings{Ai_2023_CVPR, author = {Ai, Hao and Cao, Zidong and Cao, Yan-Pei and Shan, Ying and Wang, Lin}, title = {HRDFuse: Monocular 360deg Depth Estimation by Collaboratively Learning Holistic-With-Regional Depth Distributions}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13273-13282} }
StructVPR: Distill Structural Knowledge With Weighting Samples for Visual Place Recognition: Yanqing Shen,

Sanping Zhou,

Jingwen Fu,

Ruotong Wang,

Shitao Chen,

Nanning Zheng; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Shen_2023_CVPR, author = {Shen, Yanqing and Zhou, Sanping and Fu, Jingwen and Wang, Ruotong and Chen, Shitao and Zheng, Nanning}, title = {StructVPR: Distill Structural Knowledge With Weighting Samples for Visual Place Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11217-11226} }
Learning Human-to-Robot Handovers From Point Clouds: Sammy Christen,

Wei Yang,

Claudia Pérez-D’Arpino,

Otmar Hilliges,

Dieter Fox,

Yu-Wei Chao; [pdf] [supp]
[bibtex]
@InProceedings{Christen_2023_CVPR, author = {Christen, Sammy and Yang, Wei and P\'erez-D{\textquoteright}Arpino, Claudia and Hilliges, Otmar and Fox, Dieter and Chao, Yu-Wei}, title = {Learning Human-to-Robot Handovers From Point Clouds}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9654-9664} }
Score Jacobian Chaining: Lifting Pretrained 2D Diffusion Models for 3D Generation: Haochen Wang,

Xiaodan Du,

Jiahao Li,

Raymond A. Yeh,

Greg Shakhnarovich; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2023_CVPR, author = {Wang, Haochen and Du, Xiaodan and Li, Jiahao and Yeh, Raymond A. and Shakhnarovich, Greg}, title = {Score Jacobian Chaining: Lifting Pretrained 2D Diffusion Models for 3D Generation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12619-12629} }
Role of Transients in Two-Bounce Non-Line-of-Sight Imaging: Siddharth Somasundaram,

Akshat Dave,

Connor Henley,

Ashok Veeraraghavan,

Ramesh Raskar; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Somasundaram_2023_CVPR, author = {Somasundaram, Siddharth and Dave, Akshat and Henley, Connor and Veeraraghavan, Ashok and Raskar, Ramesh}, title = {Role of Transients in Two-Bounce Non-Line-of-Sight Imaging}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9192-9201} }
Elastic Aggregation for Federated Optimization: Dengsheng Chen,

Jie Hu,

Vince Junkai Tan,

Xiaoming Wei,

Enhua Wu; [pdf] [supp]
[bibtex]
@InProceedings{Chen_2023_CVPR, author = {Chen, Dengsheng and Hu, Jie and Tan, Vince Junkai and Wei, Xiaoming and Wu, Enhua}, title = {Elastic Aggregation for Federated Optimization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12187-12197} }
ObjectMatch: Robust Registration Using Canonical Object Correspondences: Can Gümeli,

Angela Dai,

Matthias Nießner; [pdf] [supp]
[bibtex]
@InProceedings{Gumeli_2023_CVPR, author = {G\"umeli, Can and Dai, Angela and Nie{\ss}ner, Matthias}, title = {ObjectMatch: Robust Registration Using Canonical Object Correspondences}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13082-13091} }
Center Focusing Network for Real-Time LiDAR Panoptic Segmentation: Xiaoyan Li,

Gang Zhang,

Boyue Wang,

Yongli Hu,

Baocai Yin; [pdf] [supp]
[bibtex]
@InProceedings{Li_2023_CVPR, author = {Li, Xiaoyan and Zhang, Gang and Wang, Boyue and Hu, Yongli and Yin, Baocai}, title = {Center Focusing Network for Real-Time LiDAR Panoptic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13425-13434} }
Restoration of Hand-Drawn Architectural Drawings Using Latent Space Mapping With Degradation Generator: Nakkwan Choi,

Seungjae Lee,

Yongsik Lee,

Seungjoon Yang; [pdf] [supp]
[bibtex]
@InProceedings{Choi_2023_CVPR, author = {Choi, Nakkwan and Lee, Seungjae and Lee, Yongsik and Yang, Seungjoon}, title = {Restoration of Hand-Drawn Architectural Drawings Using Latent Space Mapping With Degradation Generator}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14164-14172} }
Few-Shot Class-Incremental Learning via Class-Aware Bilateral Distillation: Linglan Zhao,

Jing Lu,

Yunlu Xu,

Zhanzhan Cheng,

Dashan Guo,

Yi Niu,

Xiangzhong Fang; [pdf] [supp]
[bibtex]
@InProceedings{Zhao_2023_CVPR, author = {Zhao, Linglan and Lu, Jing and Xu, Yunlu and Cheng, Zhanzhan and Guo, Dashan and Niu, Yi and Fang, Xiangzhong}, title = {Few-Shot Class-Incremental Learning via Class-Aware Bilateral Distillation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11838-11847} }
Learning To Dub Movies via Hierarchical Prosody Models: Gaoxiang Cong,

Liang Li,

Yuankai Qi,

Zheng-Jun Zha,

Qi Wu,

Wenyu Wang,

Bin Jiang,

Ming-Hsuan Yang,

Qingming Huang; [pdf] [arXiv]
[bibtex]
@InProceedings{Cong_2023_CVPR, author = {Cong, Gaoxiang and Li, Liang and Qi, Yuankai and Zha, Zheng-Jun and Wu, Qi and Wang, Wenyu and Jiang, Bin and Yang, Ming-Hsuan and Huang, Qingming}, title = {Learning To Dub Movies via Hierarchical Prosody Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14687-14697} }
DiffusionRig: Learning Personalized Priors for Facial Appearance Editing: Zheng Ding,

Xuaner Zhang,

Zhihao Xia,

Lars Jebe,

Zhuowen Tu,

Xiuming Zhang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ding_2023_CVPR, author = {Ding, Zheng and Zhang, Xuaner and Xia, Zhihao and Jebe, Lars and Tu, Zhuowen and Zhang, Xiuming}, title = {DiffusionRig: Learning Personalized Priors for Facial Appearance Editing}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12736-12746} }
Delving StyleGAN Inversion for Image Editing: A Foundation Latent Space Viewpoint: Hongyu Liu,

Yibing Song,

Qifeng Chen; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Liu_2023_CVPR, author = {Liu, Hongyu and Song, Yibing and Chen, Qifeng}, title = {Delving StyleGAN Inversion for Image Editing: A Foundation Latent Space Viewpoint}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10072-10082} }
Enlarging Instance-Specific and Class-Specific Information for Open-Set Action Recognition: Jun Cen,

Shiwei Zhang,

Xiang Wang,

Yixuan Pei,

Zhiwu Qing,

Yingya Zhang,

Qifeng Chen; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Cen_2023_CVPR, author = {Cen, Jun and Zhang, Shiwei and Wang, Xiang and Pei, Yixuan and Qing, Zhiwu and Zhang, Yingya and Chen, Qifeng}, title = {Enlarging Instance-Specific and Class-Specific Information for Open-Set Action Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15295-15304} }
Decoupled Semantic Prototypes Enable Learning From Diverse Annotation Types for Semi-Weakly Segmentation in Expert-Driven Domains: Simon Reiß,

Constantin Seibold,

Alexander Freytag,

Erik Rodner,

Rainer Stiefelhagen; [pdf] [supp]
[bibtex]
@InProceedings{Reiss_2023_CVPR, author = {Rei{\ss}, Simon and Seibold, Constantin and Freytag, Alexander and Rodner, Erik and Stiefelhagen, Rainer}, title = {Decoupled Semantic Prototypes Enable Learning From Diverse Annotation Types for Semi-Weakly Segmentation in Expert-Driven Domains}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15495-15506} }
Iterative Next Boundary Detection for Instance Segmentation of Tree Rings in Microscopy Images of Shrub Cross Sections: Alexander Gillert,

Giulia Resente,

Alba Anadon-Rosell,

Martin Wilmking,

Uwe Freiherr von Lukas; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Gillert_2023_CVPR, author = {Gillert, Alexander and Resente, Giulia and Anadon-Rosell, Alba and Wilmking, Martin and von Lukas, Uwe Freiherr}, title = {Iterative Next Boundary Detection for Instance Segmentation of Tree Rings in Microscopy Images of Shrub Cross Sections}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14540-14548} }
Learning and Aggregating Lane Graphs for Urban Automated Driving: Martin Büchner,

Jannik Zürn,

Ion-George Todoran,

Abhinav Valada,

Wolfram Burgard; [pdf] [supp]
[bibtex]
@InProceedings{Buchner_2023_CVPR, author = {B\"uchner, Martin and Z\"urn, Jannik and Todoran, Ion-George and Valada, Abhinav and Burgard, Wolfram}, title = {Learning and Aggregating Lane Graphs for Urban Automated Driving}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13415-13424} }
Universal Instance Perception As Object Discovery and Retrieval: Bin Yan,

Yi Jiang,

Jiannan Wu,

Dong Wang,

Ping Luo,

Zehuan Yuan,

Huchuan Lu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yan_2023_CVPR, author = {Yan, Bin and Jiang, Yi and Wu, Jiannan and Wang, Dong and Luo, Ping and Yuan, Zehuan and Lu, Huchuan}, title = {Universal Instance Perception As Object Discovery and Retrieval}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15325-15336} }
Transferable Adversarial Attacks on Vision Transformers With Token Gradient Regularization: Jianping Zhang,

Yizhan Huang,

Weibin Wu,

Michael R. Lyu; [pdf] [arXiv]
[bibtex]
@InProceedings{Zhang_2023_CVPR, author = {Zhang, Jianping and Huang, Yizhan and Wu, Weibin and Lyu, Michael R.}, title = {Transferable Adversarial Attacks on Vision Transformers With Token Gradient Regularization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16415-16424} }
MCF: Mutual Correction Framework for Semi-Supervised Medical Image Segmentation: Yongchao Wang,

Bin Xiao,

Xiuli Bi,

Weisheng Li,

Xinbo Gao; [pdf]
[bibtex]
@InProceedings{Wang_2023_CVPR, author = {Wang, Yongchao and Xiao, Bin and Bi, Xiuli and Li, Weisheng and Gao, Xinbo}, title = {MCF: Mutual Correction Framework for Semi-Supervised Medical Image Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15651-15660} }
Parametric Implicit Face Representation for Audio-Driven Facial Reenactment: Ricong Huang,

Peiwen Lai,

Yipeng Qin,

Guanbin Li; [pdf] [supp]
[bibtex]
@InProceedings{Huang_2023_CVPR, author = {Huang, Ricong and Lai, Peiwen and Qin, Yipeng and Li, Guanbin}, title = {Parametric Implicit Face Representation for Audio-Driven Facial Reenactment}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12759-12768} }
VILA: Learning Image Aesthetics From User Comments With Vision-Language Pretraining: Junjie Ke,

Keren Ye,

Jiahui Yu,

Yonghui Wu,

Peyman Milanfar,

Feng Yang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ke_2023_CVPR, author = {Ke, Junjie and Ye, Keren and Yu, Jiahui and Wu, Yonghui and Milanfar, Peyman and Yang, Feng}, title = {VILA: Learning Image Aesthetics From User Comments With Vision-Language Pretraining}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10041-10051} }
Procedure-Aware Pretraining for Instructional Video Understanding: Honglu Zhou,

Roberto Martín-Martín,

Mubbasir Kapadia,

Silvio Savarese,

Juan Carlos Niebles; [pdf] [supp]
[bibtex]
@InProceedings{Zhou_2023_CVPR, author = {Zhou, Honglu and Mart{\'\i}n-Mart{\'\i}n, Roberto and Kapadia, Mubbasir and Savarese, Silvio and Niebles, Juan Carlos}, title = {Procedure-Aware Pretraining for Instructional Video Understanding}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10727-10738} }
Fine-Grained Audible Video Description: Xuyang Shen,

Dong Li,

Jinxing Zhou,

Zhen Qin,

Bowen He,

Xiaodong Han,

Aixuan Li,

Yuchao Dai,

Lingpeng Kong,

Meng Wang,

Yu Qiao,

Yiran Zhong; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Shen_2023_CVPR, author = {Shen, Xuyang and Li, Dong and Zhou, Jinxing and Qin, Zhen and He, Bowen and Han, Xiaodong and Li, Aixuan and Dai, Yuchao and Kong, Lingpeng and Wang, Meng and Qiao, Yu and Zhong, Yiran}, title = {Fine-Grained Audible Video Description}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10585-10596} }
3D Semantic Segmentation in the Wild: Learning Generalized Models for Adverse-Condition Point Clouds: Aoran Xiao,

Jiaxing Huang,

Weihao Xuan,

Ruijie Ren,

Kangcheng Liu,

Dayan Guan,

Abdulmotaleb El Saddik,

Shijian Lu,

Eric P. Xing; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Xiao_2023_CVPR, author = {Xiao, Aoran and Huang, Jiaxing and Xuan, Weihao and Ren, Ruijie and Liu, Kangcheng and Guan, Dayan and El Saddik, Abdulmotaleb and Lu, Shijian and Xing, Eric P.}, title = {3D Semantic Segmentation in the Wild: Learning Generalized Models for Adverse-Condition Point Clouds}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9382-9392} }
RaBit: Parametric Modeling of 3D Biped Cartoon Characters With a Topological-Consistent Dataset: Zhongjin Luo,

Shengcai Cai,

Jinguo Dong,

Ruibo Ming,

Liangdong Qiu,

Xiaohang Zhan,

Xiaoguang Han; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Luo_2023_CVPR, author = {Luo, Zhongjin and Cai, Shengcai and Dong, Jinguo and Ming, Ruibo and Qiu, Liangdong and Zhan, Xiaohang and Han, Xiaoguang}, title = {RaBit: Parametric Modeling of 3D Biped Cartoon Characters With a Topological-Consistent Dataset}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12825-12835} }
Uni3D: A Unified Baseline for Multi-Dataset 3D Object Detection: Bo Zhang,

Jiakang Yuan,

Botian Shi,

Tao Chen,

Yikang Li,

Yu Qiao; [pdf] [arXiv]
[bibtex]
@InProceedings{Zhang_2023_CVPR, author = {Zhang, Bo and Yuan, Jiakang and Shi, Botian and Chen, Tao and Li, Yikang and Qiao, Yu}, title = {Uni3D: A Unified Baseline for Multi-Dataset 3D Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9253-9262} }
ACR: Attention Collaboration-Based Regressor for Arbitrary Two-Hand Reconstruction: Zhengdi Yu,

Shaoli Huang,

Chen Fang,

Toby P. Breckon,

Jue Wang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yu_2023_CVPR, author = {Yu, Zhengdi and Huang, Shaoli and Fang, Chen and Breckon, Toby P. and Wang, Jue}, title = {ACR: Attention Collaboration-Based Regressor for Arbitrary Two-Hand Reconstruction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12955-12964} }
Improving Table Structure Recognition With Visual-Alignment Sequential Coordinate Modeling: Yongshuai Huang,

Ning Lu,

Dapeng Chen,

Yibo Li,

Zecheng Xie,

Shenggao Zhu,

Liangcai Gao,

Wei Peng; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Huang_2023_CVPR, author = {Huang, Yongshuai and Lu, Ning and Chen, Dapeng and Li, Yibo and Xie, Zecheng and Zhu, Shenggao and Gao, Liangcai and Peng, Wei}, title = {Improving Table Structure Recognition With Visual-Alignment Sequential Coordinate Modeling}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11134-11143} }
HumanGen: Generating Human Radiance Fields With Explicit Priors: Suyi Jiang,

Haoran Jiang,

Ziyu Wang,

Haimin Luo,

Wenzheng Chen,

Lan Xu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Jiang_2023_CVPR, author = {Jiang, Suyi and Jiang, Haoran and Wang, Ziyu and Luo, Haimin and Chen, Wenzheng and Xu, Lan}, title = {HumanGen: Generating Human Radiance Fields With Explicit Priors}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12543-12554} }
Local Connectivity-Based Density Estimation for Face Clustering: Junho Shin,

Hyo-Jun Lee,

Hyunseop Kim,

Jong-Hyeon Baek,

Daehyun Kim,

Yeong Jun Koh; [pdf] [supp]
[bibtex]
@InProceedings{Shin_2023_CVPR, author = {Shin, Junho and Lee, Hyo-Jun and Kim, Hyunseop and Baek, Jong-Hyeon and Kim, Daehyun and Koh, Yeong Jun}, title = {Local Connectivity-Based Density Estimation for Face Clustering}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13621-13629} }
Adaptive Zone-Aware Hierarchical Planner for Vision-Language Navigation: Chen Gao,

Xingyu Peng,

Mi Yan,

He Wang,

Lirong Yang,

Haibing Ren,

Hongsheng Li,

Si Liu; [pdf]
[bibtex]
@InProceedings{Gao_2023_CVPR, author = {Gao, Chen and Peng, Xingyu and Yan, Mi and Wang, He and Yang, Lirong and Ren, Haibing and Li, Hongsheng and Liu, Si}, title = {Adaptive Zone-Aware Hierarchical Planner for Vision-Language Navigation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14911-14920} }
Memory-Friendly Scalable Super-Resolution via Rewinding Lottery Ticket Hypothesis: Jin Lin,

Xiaotong Luo,

Ming Hong,

Yanyun Qu,

Yuan Xie,

Zongze Wu; [pdf] [supp]
[bibtex]
@InProceedings{Lin_2023_CVPR, author = {Lin, Jin and Luo, Xiaotong and Hong, Ming and Qu, Yanyun and Xie, Yuan and Wu, Zongze}, title = {Memory-Friendly Scalable Super-Resolution via Rewinding Lottery Ticket Hypothesis}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14398-14407} }
Therbligs in Action: Video Understanding Through Motion Primitives: Eadom Dessalene,

Michael Maynord,

Cornelia Fermüller,

Yiannis Aloimonos; [pdf]
[bibtex]
@InProceedings{Dessalene_2023_CVPR, author = {Dessalene, Eadom and Maynord, Michael and Ferm\"uller, Cornelia and Aloimonos, Yiannis}, title = {Therbligs in Action: Video Understanding Through Motion Primitives}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10618-10626} }
SadTalker: Learning Realistic 3D Motion Coefficients for Stylized Audio-Driven Single Image Talking Face Animation: Wenxuan Zhang,

Xiaodong Cun,

Xuan Wang,

Yong Zhang,

Xi Shen,

Yu Guo,

Ying Shan,

Fei Wang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhang_2023_CVPR, author = {Zhang, Wenxuan and Cun, Xiaodong and Wang, Xuan and Zhang, Yong and Shen, Xi and Guo, Yu and Shan, Ying and Wang, Fei}, title = {SadTalker: Learning Realistic 3D Motion Coefficients for Stylized Audio-Driven Single Image Talking Face Animation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8652-8661} }
HAAV: Hierarchical Aggregation of Augmented Views for Image Captioning: Chia-Wen Kuo,

Zsolt Kira; [pdf] [supp]
[bibtex]
@InProceedings{Kuo_2023_CVPR, author = {Kuo, Chia-Wen and Kira, Zsolt}, title = {HAAV: Hierarchical Aggregation of Augmented Views for Image Captioning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11039-11049} }
Learning Sample Relationship for Exposure Correction: Jie Huang,

Feng Zhao,

Man Zhou,

Jie Xiao,

Naishan Zheng,

Kaiwen Zheng,

Zhiwei Xiong; [pdf]
[bibtex]
@InProceedings{Huang_2023_CVPR, author = {Huang, Jie and Zhao, Feng and Zhou, Man and Xiao, Jie and Zheng, Naishan and Zheng, Kaiwen and Xiong, Zhiwei}, title = {Learning Sample Relationship for Exposure Correction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9904-9913} }
TRACE: 5D Temporal Regression of Avatars With Dynamic Cameras in 3D Environments: Yu Sun,

Qian Bao,

Wu Liu,

Tao Mei,

Michael J. Black; [pdf] [supp]
[bibtex]
@InProceedings{Sun_2023_CVPR, author = {Sun, Yu and Bao, Qian and Liu, Wu and Mei, Tao and Black, Michael J.}, title = {TRACE: 5D Temporal Regression of Avatars With Dynamic Cameras in 3D Environments}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8856-8866} }
End-to-End 3D Dense Captioning With Vote2Cap-DETR: Sijin Chen,

Hongyuan Zhu,

Xin Chen,

Yinjie Lei,

Gang Yu,

Tao Chen; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chen_2023_CVPR, author = {Chen, Sijin and Zhu, Hongyuan and Chen, Xin and Lei, Yinjie and Yu, Gang and Chen, Tao}, title = {End-to-End 3D Dense Captioning With Vote2Cap-DETR}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11124-11133} }
Learned Two-Plane Perspective Prior Based Image Resampling for Efficient Object Detection: Anurag Ghosh,

N. Dinesh Reddy,

Christoph Mertz,

Srinivasa G. Narasimhan; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ghosh_2023_CVPR, author = {Ghosh, Anurag and Reddy, N. Dinesh and Mertz, Christoph and Narasimhan, Srinivasa G.}, title = {Learned Two-Plane Perspective Prior Based Image Resampling for Efficient Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13364-13373} }
Tell Me What Happened: Unifying Text-Guided Video Completion via Multimodal Masked Video Generation: Tsu-Jui Fu,

Licheng Yu,

Ning Zhang,

Cheng-Yang Fu,

Jong-Chyi Su,

William Yang Wang,

Sean Bell; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Fu_2023_CVPR, author = {Fu, Tsu-Jui and Yu, Licheng and Zhang, Ning and Fu, Cheng-Yang and Su, Jong-Chyi and Wang, William Yang and Bell, Sean}, title = {Tell Me What Happened: Unifying Text-Guided Video Completion via Multimodal Masked Video Generation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10681-10692} }
Tracking Through Containers and Occluders in the Wild: Basile Van Hoorick,

Pavel Tokmakov,

Simon Stent,

Jie Li,

Carl Vondrick; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Van_Hoorick_2023_CVPR, author = {Van Hoorick, Basile and Tokmakov, Pavel and Stent, Simon and Li, Jie and Vondrick, Carl}, title = {Tracking Through Containers and Occluders in the Wild}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13802-13812} }
Decompose, Adjust, Compose: Effective Normalization by Playing With Frequency for Domain Generalization: Sangrok Lee,

Jongseong Bae,

Ha Young Kim; [pdf] [arXiv]
[bibtex]
@InProceedings{Lee_2023_CVPR, author = {Lee, Sangrok and Bae, Jongseong and Kim, Ha Young}, title = {Decompose, Adjust, Compose: Effective Normalization by Playing With Frequency for Domain Generalization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11776-11785} }
Novel Class Discovery for 3D Point Cloud Semantic Segmentation: Luigi Riz,

Cristiano Saltori,

Elisa Ricci,

Fabio Poiesi; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Riz_2023_CVPR, author = {Riz, Luigi and Saltori, Cristiano and Ricci, Elisa and Poiesi, Fabio}, title = {Novel Class Discovery for 3D Point Cloud Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9393-9402} }
Learning 3D-Aware Image Synthesis With Unknown Pose Distribution: Zifan Shi,

Yujun Shen,

Yinghao Xu,

Sida Peng,

Yiyi Liao,

Sheng Guo,

Qifeng Chen,

Dit-Yan Yeung; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Shi_2023_CVPR, author = {Shi, Zifan and Shen, Yujun and Xu, Yinghao and Peng, Sida and Liao, Yiyi and Guo, Sheng and Chen, Qifeng and Yeung, Dit-Yan}, title = {Learning 3D-Aware Image Synthesis With Unknown Pose Distribution}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13062-13071} }
Train-Once-for-All Personalization: Hong-You Chen,

Yandong Li,

Yin Cui,

Mingda Zhang,

Wei-Lun Chao,

Li Zhang; [pdf] [supp]
[bibtex]
@InProceedings{Chen_2023_CVPR, author = {Chen, Hong-You and Li, Yandong and Cui, Yin and Zhang, Mingda and Chao, Wei-Lun and Zhang, Li}, title = {Train-Once-for-All Personalization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11818-11827} }
DIFu: Depth-Guided Implicit Function for Clothed Human Reconstruction: Dae-Young Song,

HeeKyung Lee,

Jeongil Seo,

Donghyeon Cho; [pdf] [supp]
[bibtex]
@InProceedings{Song_2023_CVPR, author = {Song, Dae-Young and Lee, HeeKyung and Seo, Jeongil and Cho, Donghyeon}, title = {DIFu: Depth-Guided Implicit Function for Clothed Human Reconstruction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8738-8747} }
Bi-LRFusion: Bi-Directional LiDAR-Radar Fusion for 3D Dynamic Object Detection: Yingjie Wang,

Jiajun Deng,

Yao Li,

Jinshui Hu,

Cong Liu,

Yu Zhang,

Jianmin Ji,

Wanli Ouyang,

Yanyong Zhang; [pdf] [supp]
[bibtex]
@InProceedings{Wang_2023_CVPR, author = {Wang, Yingjie and Deng, Jiajun and Li, Yao and Hu, Jinshui and Liu, Cong and Zhang, Yu and Ji, Jianmin and Ouyang, Wanli and Zhang, Yanyong}, title = {Bi-LRFusion: Bi-Directional LiDAR-Radar Fusion for 3D Dynamic Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13394-13403} }
LOCATE: Localize and Transfer Object Parts for Weakly Supervised Affordance Grounding: Gen Li,

Varun Jampani,

Deqing Sun,

Laura Sevilla-Lara; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Li_2023_CVPR, author = {Li, Gen and Jampani, Varun and Sun, Deqing and Sevilla-Lara, Laura}, title = {LOCATE: Localize and Transfer Object Parts for Weakly Supervised Affordance Grounding}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10922-10931} }
TokenHPE: Learning Orientation Tokens for Efficient Head Pose Estimation via Transformers: Cheng Zhang,

Hai Liu,

Yongjian Deng,

Bochen Xie,

Youfu Li; [pdf] [supp]
[bibtex]
@InProceedings{Zhang_2023_CVPR, author = {Zhang, Cheng and Liu, Hai and Deng, Yongjian and Xie, Bochen and Li, Youfu}, title = {TokenHPE: Learning Orientation Tokens for Efficient Head Pose Estimation via Transformers}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8897-8906} }
BioNet: A Biologically-Inspired Network for Face Recognition: Pengyu Li; [pdf] [supp]
[bibtex]
@InProceedings{Li_2023_CVPR, author = {Li, Pengyu}, title = {BioNet: A Biologically-Inspired Network for Face Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10344-10354} }
Scaling Up GANs for Text-to-Image Synthesis: Minguk Kang,

Jun-Yan Zhu,

Richard Zhang,

Jaesik Park,

Eli Shechtman,

Sylvain Paris,

Taesung Park; [pdf] [arXiv]
[bibtex]
@InProceedings{Kang_2023_CVPR, author = {Kang, Minguk and Zhu, Jun-Yan and Zhang, Richard and Park, Jaesik and Shechtman, Eli and Paris, Sylvain and Park, Taesung}, title = {Scaling Up GANs for Text-to-Image Synthesis}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10124-10134} }
DepGraph: Towards Any Structural Pruning: Gongfan Fang,

Xinyin Ma,

Mingli Song,

Michael Bi Mi,

Xinchao Wang; [pdf] [arXiv]
[bibtex]
@InProceedings{Fang_2023_CVPR, author = {Fang, Gongfan and Ma, Xinyin and Song, Mingli and Mi, Michael Bi and Wang, Xinchao}, title = {DepGraph: Towards Any Structural Pruning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16091-16101} }
Exploring Discontinuity for Video Frame Interpolation: Sangjin Lee,

Hyeongmin Lee,

Chajin Shin,

Hanbin Son,

Sangyoun Lee; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Lee_2023_CVPR, author = {Lee, Sangjin and Lee, Hyeongmin and Shin, Chajin and Son, Hanbin and Lee, Sangyoun}, title = {Exploring Discontinuity for Video Frame Interpolation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9791-9800} }
DynamicStereo: Consistent Dynamic Depth From Stereo Videos: Nikita Karaev,

Ignacio Rocco,

Benjamin Graham,

Natalia Neverova,

Andrea Vedaldi,

Christian Rupprecht; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Karaev_2023_CVPR, author = {Karaev, Nikita and Rocco, Ignacio and Graham, Benjamin and Neverova, Natalia and Vedaldi, Andrea and Rupprecht, Christian}, title = {DynamicStereo: Consistent Dynamic Depth From Stereo Videos}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13229-13239} }
Vid2Avatar: 3D Avatar Reconstruction From Videos in the Wild via Self-Supervised Scene Decomposition: Chen Guo,

Tianjian Jiang,

Xu Chen,

Jie Song,

Otmar Hilliges; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Guo_2023_CVPR, author = {Guo, Chen and Jiang, Tianjian and Chen, Xu and Song, Jie and Hilliges, Otmar}, title = {Vid2Avatar: 3D Avatar Reconstruction From Videos in the Wild via Self-Supervised Scene Decomposition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12858-12868} }
Task Residual for Tuning Vision-Language Models: Tao Yu,

Zhihe Lu,

Xin Jin,

Zhibo Chen,

Xinchao Wang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yu_2023_CVPR, author = {Yu, Tao and Lu, Zhihe and Jin, Xin and Chen, Zhibo and Wang, Xinchao}, title = {Task Residual for Tuning Vision-Language Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10899-10909} }
Hierarchical Prompt Learning for Multi-Task Learning: Yajing Liu,

Yuning Lu,

Hao Liu,

Yaozu An,

Zhuoran Xu,

Zhuokun Yao,

Baofeng Zhang,

Zhiwei Xiong,

Chenguang Gui; [pdf] [supp]
[bibtex]
@InProceedings{Liu_2023_CVPR, author = {Liu, Yajing and Lu, Yuning and Liu, Hao and An, Yaozu and Xu, Zhuoran and Yao, Zhuokun and Zhang, Baofeng and Xiong, Zhiwei and Gui, Chenguang}, title = {Hierarchical Prompt Learning for Multi-Task Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10888-10898} }
RIFormer: Keep Your Vision Backbone Effective but Removing Token Mixer: Jiahao Wang,

Songyang Zhang,

Yong Liu,

Taiqiang Wu,

Yujiu Yang,

Xihui Liu,

Kai Chen,

Ping Luo,

Dahua Lin; [pdf] [supp]
[bibtex]
@InProceedings{Wang_2023_CVPR, author = {Wang, Jiahao and Zhang, Songyang and Liu, Yong and Wu, Taiqiang and Yang, Yujiu and Liu, Xihui and Chen, Kai and Luo, Ping and Lin, Dahua}, title = {RIFormer: Keep Your Vision Backbone Effective but Removing Token Mixer}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14443-14452} }
Context-Based Trit-Plane Coding for Progressive Image Compression: Seungmin Jeon,

Kwang Pyo Choi,

Youngo Park,

Chang-Su Kim; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Jeon_2023_CVPR, author = {Jeon, Seungmin and Choi, Kwang Pyo and Park, Youngo and Kim, Chang-Su}, title = {Context-Based Trit-Plane Coding for Progressive Image Compression}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14348-14357} }
Recurrent Vision Transformers for Object Detection With Event Cameras: Mathias Gehrig,

Davide Scaramuzza; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Gehrig_2023_CVPR, author = {Gehrig, Mathias and Scaramuzza, Davide}, title = {Recurrent Vision Transformers for Object Detection With Event Cameras}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13884-13893} }
METransformer: Radiology Report Generation by Transformer With Multiple Learnable Expert Tokens: Zhanyu Wang,

Lingqiao Liu,

Lei Wang,

Luping Zhou; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2023_CVPR, author = {Wang, Zhanyu and Liu, Lingqiao and Wang, Lei and Zhou, Luping}, title = {METransformer: Radiology Report Generation by Transformer With Multiple Learnable Expert Tokens}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11558-11567} }
Revealing the Dark Secrets of Masked Image Modeling: Zhenda Xie,

Zigang Geng,

Jingcheng Hu,

Zheng Zhang,

Han Hu,

Yue Cao; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Xie_2023_CVPR, author = {Xie, Zhenda and Geng, Zigang and Hu, Jingcheng and Zhang, Zheng and Hu, Han and Cao, Yue}, title = {Revealing the Dark Secrets of Masked Image Modeling}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14475-14485} }
Fine-Grained Classification With Noisy Labels: Qi Wei,

Lei Feng,

Haoliang Sun,

Ren Wang,

Chenhui Guo,

Yilong Yin; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wei_2023_CVPR, author = {Wei, Qi and Feng, Lei and Sun, Haoliang and Wang, Ren and Guo, Chenhui and Yin, Yilong}, title = {Fine-Grained Classification With Noisy Labels}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11651-11660} }
CAP: Robust Point Cloud Classification via Semantic and Structural Modeling: Daizong Ding,

Erling Jiang,

Yuanmin Huang,

Mi Zhang,

Wenxuan Li,

Min Yang; [pdf] [supp]
[bibtex]
@InProceedings{Ding_2023_CVPR, author = {Ding, Daizong and Jiang, Erling and Huang, Yuanmin and Zhang, Mi and Li, Wenxuan and Yang, Min}, title = {CAP: Robust Point Cloud Classification via Semantic and Structural Modeling}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12260-12270} }
Visual-Tactile Sensing for In-Hand Object Reconstruction: Wenqiang Xu,

Zhenjun Yu,

Han Xue,

Ruolin Ye,

Siqiong Yao,

Cewu Lu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Xu_2023_CVPR, author = {Xu, Wenqiang and Yu, Zhenjun and Xue, Han and Ye, Ruolin and Yao, Siqiong and Lu, Cewu}, title = {Visual-Tactile Sensing for In-Hand Object Reconstruction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8803-8812} }
Local-to-Global Registration for Bundle-Adjusting Neural Radiance Fields: Yue Chen,

Xingyu Chen,

Xuan Wang,

Qi Zhang,

Yu Guo,

Ying Shan,

Fei Wang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chen_2023_CVPR, author = {Chen, Yue and Chen, Xingyu and Wang, Xuan and Zhang, Qi and Guo, Yu and Shan, Ying and Wang, Fei}, title = {Local-to-Global Registration for Bundle-Adjusting Neural Radiance Fields}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8264-8273} }
FJMP: Factorized Joint Multi-Agent Motion Prediction Over Learned Directed Acyclic Interaction Graphs: Luke Rowe,

Martin Ethier,

Eli-Henry Dykhne,

Krzysztof Czarnecki; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Rowe_2023_CVPR, author = {Rowe, Luke and Ethier, Martin and Dykhne, Eli-Henry and Czarnecki, Krzysztof}, title = {FJMP: Factorized Joint Multi-Agent Motion Prediction Over Learned Directed Acyclic Interaction Graphs}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13745-13755} }
Correlational Image Modeling for Self-Supervised Visual Pre-Training: Wei Li,

Jiahao Xie,

Chen Change Loy; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Li_2023_CVPR, author = {Li, Wei and Xie, Jiahao and Loy, Chen Change}, title = {Correlational Image Modeling for Self-Supervised Visual Pre-Training}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15105-15115} }
Self-Supervised Implicit Glyph Attention for Text Recognition: Tongkun Guan,

Chaochen Gu,

Jingzheng Tu,

Xue Yang,

Qi Feng,

Yudi Zhao,

Wei Shen; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Guan_2023_CVPR, author = {Guan, Tongkun and Gu, Chaochen and Tu, Jingzheng and Yang, Xue and Feng, Qi and Zhao, Yudi and Shen, Wei}, title = {Self-Supervised Implicit Glyph Attention for Text Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15285-15294} }
ACL-SPC: Adaptive Closed-Loop System for Self-Supervised Point Cloud Completion: Sangmin Hong,

Mohsen Yavartanoo,

Reyhaneh Neshatavar,

Kyoung Mu Lee; [pdf] [supp]
[bibtex]
@InProceedings{Hong_2023_CVPR, author = {Hong, Sangmin and Yavartanoo, Mohsen and Neshatavar, Reyhaneh and Lee, Kyoung Mu}, title = {ACL-SPC: Adaptive Closed-Loop System for Self-Supervised Point Cloud Completion}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9435-9444} }
Focus on Details: Online Multi-Object Tracking With Diverse Fine-Grained Representation: Hao Ren,

Shoudong Han,

Huilin Ding,

Ziwen Zhang,

Hongwei Wang,

Faquan Wang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ren_2023_CVPR, author = {Ren, Hao and Han, Shoudong and Ding, Huilin and Zhang, Ziwen and Wang, Hongwei and Wang, Faquan}, title = {Focus on Details: Online Multi-Object Tracking With Diverse Fine-Grained Representation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11289-11298} }
DiffPose: Toward More Reliable 3D Pose Estimation: Jia Gong,

Lin Geng Foo,

Zhipeng Fan,

Qiuhong Ke,

Hossein Rahmani,

Jun Liu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Gong_2023_CVPR, author = {Gong, Jia and Foo, Lin Geng and Fan, Zhipeng and Ke, Qiuhong and Rahmani, Hossein and Liu, Jun}, title = {DiffPose: Toward More Reliable 3D Pose Estimation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13041-13051} }
Learning Analytical Posterior Probability for Human Mesh Recovery: Qi Fang,

Kang Chen,

Yinghui Fan,

Qing Shuai,

Jiefeng Li,

Weidong Zhang; [pdf] [supp]
[bibtex]
@InProceedings{Fang_2023_CVPR, author = {Fang, Qi and Chen, Kang and Fan, Yinghui and Shuai, Qing and Li, Jiefeng and Zhang, Weidong}, title = {Learning Analytical Posterior Probability for Human Mesh Recovery}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8781-8791} }
Non-Contrastive Unsupervised Learning of Physiological Signals From Video: Jeremy Speth,

Nathan Vance,

Patrick Flynn,

Adam Czajka; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Speth_2023_CVPR, author = {Speth, Jeremy and Vance, Nathan and Flynn, Patrick and Czajka, Adam}, title = {Non-Contrastive Unsupervised Learning of Physiological Signals From Video}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14464-14474} }
FashionSAP: Symbols and Attributes Prompt for Fine-Grained Fashion Vision-Language Pre-Training: Yunpeng Han,

Lisai Zhang,

Qingcai Chen,

Zhijian Chen,

Zhonghua Li,

Jianxin Yang,

Zhao Cao; [pdf] [arXiv]
[bibtex]
@InProceedings{Han_2023_CVPR, author = {Han, Yunpeng and Zhang, Lisai and Chen, Qingcai and Chen, Zhijian and Li, Zhonghua and Yang, Jianxin and Cao, Zhao}, title = {FashionSAP: Symbols and Attributes Prompt for Fine-Grained Fashion Vision-Language Pre-Training}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15028-15038} }
Structure Aggregation for Cross-Spectral Stereo Image Guided Denoising: Zehua Sheng,

Zhu Yu,

Xiongwei Liu,

Si-Yuan Cao,

Yuqi Liu,

Hui-Liang Shen,

Huaqi Zhang; [pdf] [supp]
[bibtex]
@InProceedings{Sheng_2023_CVPR, author = {Sheng, Zehua and Yu, Zhu and Liu, Xiongwei and Cao, Si-Yuan and Liu, Yuqi and Shen, Hui-Liang and Zhang, Huaqi}, title = {Structure Aggregation for Cross-Spectral Stereo Image Guided Denoising}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13997-14006} }
RONO: Robust Discriminative Learning With Noisy Labels for 2D-3D Cross-Modal Retrieval: Yanglin Feng,

Hongyuan Zhu,

Dezhong Peng,

Xi Peng,

Peng Hu; [pdf] [supp]
[bibtex]
@InProceedings{Feng_2023_CVPR, author = {Feng, Yanglin and Zhu, Hongyuan and Peng, Dezhong and Peng, Xi and Hu, Peng}, title = {RONO: Robust Discriminative Learning With Noisy Labels for 2D-3D Cross-Modal Retrieval}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11610-11619} }
ConQueR: Query Contrast Voxel-DETR for 3D Object Detection: Benjin Zhu,

Zhe Wang,

Shaoshuai Shi,

Hang Xu,

Lanqing Hong,

Hongsheng Li; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhu_2023_CVPR, author = {Zhu, Benjin and Wang, Zhe and Shi, Shaoshuai and Xu, Hang and Hong, Lanqing and Li, Hongsheng}, title = {ConQueR: Query Contrast Voxel-DETR for 3D Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9296-9305} }
Robust Multiview Point Cloud Registration With Reliable Pose Graph Initialization and History Reweighting: Haiping Wang,

Yuan Liu,

Zhen Dong,

Yulan Guo,

Yu-Shen Liu,

Wenping Wang,

Bisheng Yang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2023_CVPR, author = {Wang, Haiping and Liu, Yuan and Dong, Zhen and Guo, Yulan and Liu, Yu-Shen and Wang, Wenping and Yang, Bisheng}, title = {Robust Multiview Point Cloud Registration With Reliable Pose Graph Initialization and History Reweighting}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9506-9515} }
OSRT: Omnidirectional Image Super-Resolution With Distortion-Aware Transformer: Fanghua Yu,

Xintao Wang,

Mingdeng Cao,

Gen Li,

Ying Shan,

Chao Dong; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yu_2023_CVPR, author = {Yu, Fanghua and Wang, Xintao and Cao, Mingdeng and Li, Gen and Shan, Ying and Dong, Chao}, title = {OSRT: Omnidirectional Image Super-Resolution With Distortion-Aware Transformer}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13283-13292} }
BEV@DC: Bird's-Eye View Assisted Training for Depth Completion: Wending Zhou,

Xu Yan,

Yinghong Liao,

Yuankai Lin,

Jin Huang,

Gangming Zhao,

Shuguang Cui,

Zhen Li; [pdf] [supp]
[bibtex]
@InProceedings{Zhou_2023_CVPR, author = {Zhou, Wending and Yan, Xu and Liao, Yinghong and Lin, Yuankai and Huang, Jin and Zhao, Gangming and Cui, Shuguang and Li, Zhen}, title = {BEV@DC: Bird's-Eye View Assisted Training for Depth Completion}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9233-9242} }
Large-Scale Training Data Search for Object Re-Identification: Yue Yao,

Tom Gedeon,

Liang Zheng; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yao_2023_CVPR, author = {Yao, Yue and Gedeon, Tom and Zheng, Liang}, title = {Large-Scale Training Data Search for Object Re-Identification}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15568-15578} }
SelfME: Self-Supervised Motion Learning for Micro-Expression Recognition: Xinqi Fan,

Xueli Chen,

Mingjie Jiang,

Ali Raza Shahid,

Hong Yan; [pdf]
[bibtex]
@InProceedings{Fan_2023_CVPR, author = {Fan, Xinqi and Chen, Xueli and Jiang, Mingjie and Shahid, Ali Raza and Yan, Hong}, title = {SelfME: Self-Supervised Motion Learning for Micro-Expression Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13834-13843} }
NewsNet: A Novel Dataset for Hierarchical Temporal Segmentation: Haoqian Wu,

Keyu Chen,

Haozhe Liu,

Mingchen Zhuge,

Bing Li,

Ruizhi Qiao,

Xiujun Shu,

Bei Gan,

Liangsheng Xu,

Bo Ren,

Mengmeng Xu,

Wentian Zhang,

Raghavendra Ramachandra,

Chia-Wen Lin,

Bernard Ghanem; [pdf] [supp]
[bibtex]
@InProceedings{Wu_2023_CVPR, author = {Wu, Haoqian and Chen, Keyu and Liu, Haozhe and Zhuge, Mingchen and Li, Bing and Qiao, Ruizhi and Shu, Xiujun and Gan, Bei and Xu, Liangsheng and Ren, Bo and Xu, Mengmeng and Zhang, Wentian and Ramachandra, Raghavendra and Lin, Chia-Wen and Ghanem, Bernard}, title = {NewsNet: A Novel Dataset for Hierarchical Temporal Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10669-10680} }
Uncertainty-Aware Unsupervised Image Deblurring With Deep Residual Prior: Xiaole Tang,

Xile Zhao,

Jun Liu,

Jianli Wang,

Yuchun Miao,

Tieyong Zeng; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Tang_2023_CVPR, author = {Tang, Xiaole and Zhao, Xile and Liu, Jun and Wang, Jianli and Miao, Yuchun and Zeng, Tieyong}, title = {Uncertainty-Aware Unsupervised Image Deblurring With Deep Residual Prior}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9883-9892} }
FedDM: Iterative Distribution Matching for Communication-Efficient Federated Learning: Yuanhao Xiong,

Ruochen Wang,

Minhao Cheng,

Felix Yu,

Cho-Jui Hsieh; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Xiong_2023_CVPR, author = {Xiong, Yuanhao and Wang, Ruochen and Cheng, Minhao and Yu, Felix and Hsieh, Cho-Jui}, title = {FedDM: Iterative Distribution Matching for Communication-Efficient Federated Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16323-16332} }
Bit-Shrinking: Limiting Instantaneous Sharpness for Improving Post-Training Quantization: Chen Lin,

Bo Peng,

Zheyang Li,

Wenming Tan,

Ye Ren,

Jun Xiao,

Shiliang Pu; [pdf]
[bibtex]
@InProceedings{Lin_2023_CVPR, author = {Lin, Chen and Peng, Bo and Li, Zheyang and Tan, Wenming and Ren, Ye and Xiao, Jun and Pu, Shiliang}, title = {Bit-Shrinking: Limiting Instantaneous Sharpness for Improving Post-Training Quantization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16196-16205} }
LSTFE-Net:Long Short-Term Feature Enhancement Network for Video Small Object Detection: Jinsheng Xiao,

Yuanxu Wu,

Yunhua Chen,

Shurui Wang,

Zhongyuan Wang,

Jiayi Ma; [pdf]
[bibtex]
@InProceedings{Xiao_2023_CVPR, author = {Xiao, Jinsheng and Wu, Yuanxu and Chen, Yunhua and Wang, Shurui and Wang, Zhongyuan and Ma, Jiayi}, title = {LSTFE-Net:Long Short-Term Feature Enhancement Network for Video Small Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14613-14622} }
MIC: Masked Image Consistency for Context-Enhanced Domain Adaptation: Lukas Hoyer,

Dengxin Dai,

Haoran Wang,

Luc Van Gool; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Hoyer_2023_CVPR, author = {Hoyer, Lukas and Dai, Dengxin and Wang, Haoran and Van Gool, Luc}, title = {MIC: Masked Image Consistency for Context-Enhanced Domain Adaptation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11721-11732} }
SkyEye: Self-Supervised Bird's-Eye-View Semantic Mapping Using Monocular Frontal View Images: Nikhil Gosala,

Kürsat Petek,

Paulo L. J. Drews-Jr,

Wolfram Burgard,

Abhinav Valada; [pdf] [supp]
[bibtex]
@InProceedings{Gosala_2023_CVPR, author = {Gosala, Nikhil and Petek, K\"ursat and Drews-Jr, Paulo L. J. and Burgard, Wolfram and Valada, Abhinav}, title = {SkyEye: Self-Supervised Bird's-Eye-View Semantic Mapping Using Monocular Frontal View Images}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14901-14910} }
VoxFormer: Sparse Voxel Transformer for Camera-Based 3D Semantic Scene Completion: Yiming Li,

Zhiding Yu,

Christopher Choy,

Chaowei Xiao,

Jose M. Alvarez,

Sanja Fidler,

Chen Feng,

Anima Anandkumar; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Li_2023_CVPR, author = {Li, Yiming and Yu, Zhiding and Choy, Christopher and Xiao, Chaowei and Alvarez, Jose M. and Fidler, Sanja and Feng, Chen and Anandkumar, Anima}, title = {VoxFormer: Sparse Voxel Transformer for Camera-Based 3D Semantic Scene Completion}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9087-9098} }
Joint Video Multi-Frame Interpolation and Deblurring Under Unknown Exposure Time: Wei Shang,

Dongwei Ren,

Yi Yang,

Hongzhi Zhang,

Kede Ma,

Wangmeng Zuo; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Shang_2023_CVPR, author = {Shang, Wei and Ren, Dongwei and Yang, Yi and Zhang, Hongzhi and Ma, Kede and Zuo, Wangmeng}, title = {Joint Video Multi-Frame Interpolation and Deblurring Under Unknown Exposure Time}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13935-13944} }
Dual-Bridging With Adversarial Noise Generation for Domain Adaptive rPPG Estimation: Jingda Du,

Si-Qi Liu,

Bochao Zhang,

Pong C. Yuen; [pdf]
[bibtex]
@InProceedings{Du_2023_CVPR, author = {Du, Jingda and Liu, Si-Qi and Zhang, Bochao and Yuen, Pong C.}, title = {Dual-Bridging With Adversarial Noise Generation for Domain Adaptive rPPG Estimation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10355-10364} }
NeuDA: Neural Deformable Anchor for High-Fidelity Implicit Surface Reconstruction: Bowen Cai,

Jinchi Huang,

Rongfei Jia,

Chengfei Lv,

Huan Fu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Cai_2023_CVPR, author = {Cai, Bowen and Huang, Jinchi and Jia, Rongfei and Lv, Chengfei and Fu, Huan}, title = {NeuDA: Neural Deformable Anchor for High-Fidelity Implicit Surface Reconstruction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8476-8485} }
Boosting Weakly-Supervised Temporal Action Localization With Text Information: Guozhang Li,

De Cheng,

Xinpeng Ding,

Nannan Wang,

Xiaoyu Wang,

Xinbo Gao; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Li_2023_CVPR, author = {Li, Guozhang and Cheng, De and Ding, Xinpeng and Wang, Nannan and Wang, Xiaoyu and Gao, Xinbo}, title = {Boosting Weakly-Supervised Temporal Action Localization With Text Information}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10648-10657} }
OpenMix: Exploring Outlier Samples for Misclassification Detection: Fei Zhu,

Zhen Cheng,

Xu-Yao Zhang,

Cheng-Lin Liu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhu_2023_CVPR, author = {Zhu, Fei and Cheng, Zhen and Zhang, Xu-Yao and Liu, Cheng-Lin}, title = {OpenMix: Exploring Outlier Samples for Misclassification Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12074-12083} }
Multivariate, Multi-Frequency and Multimodal: Rethinking Graph Neural Networks for Emotion Recognition in Conversation: Feiyu Chen,

Jie Shao,

Shuyuan Zhu,

Heng Tao Shen; [pdf] [supp]
[bibtex]
@InProceedings{Chen_2023_CVPR, author = {Chen, Feiyu and Shao, Jie and Zhu, Shuyuan and Shen, Heng Tao}, title = {Multivariate, Multi-Frequency and Multimodal: Rethinking Graph Neural Networks for Emotion Recognition in Conversation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10761-10770} }
Bridging Precision and Confidence: A Train-Time Loss for Calibrating Object Detection: Muhammad Akhtar Munir,

Muhammad Haris Khan,

Salman Khan,

Fahad Shahbaz Khan; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Munir_2023_CVPR, author = {Munir, Muhammad Akhtar and Khan, Muhammad Haris and Khan, Salman and Khan, Fahad Shahbaz}, title = {Bridging Precision and Confidence: A Train-Time Loss for Calibrating Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11474-11483} }
DyLiN: Making Light Field Networks Dynamic: Heng Yu,

Joel Julin,

Zoltán Á. Milacski,

Koichiro Niinuma,

László A. Jeni; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yu_2023_CVPR, author = {Yu, Heng and Julin, Joel and Milacski, Zolt\'an \'A. and Niinuma, Koichiro and Jeni, L\'aszl\'o A.}, title = {DyLiN: Making Light Field Networks Dynamic}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12397-12406} }
Human Guided Ground-Truth Generation for Realistic Image Super-Resolution: Du Chen,

Jie Liang,

Xindong Zhang,

Ming Liu,

Hui Zeng,

Lei Zhang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chen_2023_CVPR, author = {Chen, Du and Liang, Jie and Zhang, Xindong and Liu, Ming and Zeng, Hui and Zhang, Lei}, title = {Human Guided Ground-Truth Generation for Realistic Image Super-Resolution}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14082-14091} }
Align and Attend: Multimodal Summarization With Dual Contrastive Losses: Bo He,

Jun Wang,

Jielin Qiu,

Trung Bui,

Abhinav Shrivastava,

Zhaowen Wang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{He_2023_CVPR, author = {He, Bo and Wang, Jun and Qiu, Jielin and Bui, Trung and Shrivastava, Abhinav and Wang, Zhaowen}, title = {Align and Attend: Multimodal Summarization With Dual Contrastive Losses}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14867-14878} }
SinGRAF: Learning a 3D Generative Radiance Field for a Single Scene: Minjung Son,

Jeong Joon Park,

Leonidas Guibas,

Gordon Wetzstein; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Son_2023_CVPR, author = {Son, Minjung and Park, Jeong Joon and Guibas, Leonidas and Wetzstein, Gordon}, title = {SinGRAF: Learning a 3D Generative Radiance Field for a Single Scene}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8507-8517} }
Self-Supervised AutoFlow: Hsin-Ping Huang,

Charles Herrmann,

Junhwa Hur,

Erika Lu,

Kyle Sargent,

Austin Stone,

Ming-Hsuan Yang,

Deqing Sun; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Huang_2023_CVPR, author = {Huang, Hsin-Ping and Herrmann, Charles and Hur, Junhwa and Lu, Erika and Sargent, Kyle and Stone, Austin and Yang, Ming-Hsuan and Sun, Deqing}, title = {Self-Supervised AutoFlow}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11412-11421} }
Neuralangelo: High-Fidelity Neural Surface Reconstruction: Zhaoshuo Li,

Thomas Müller,

Alex Evans,

Russell H. Taylor,

Mathias Unberath,

Ming-Yu Liu,

Chen-Hsuan Lin; [pdf] [supp]
[bibtex]
@InProceedings{Li_2023_CVPR, author = {Li, Zhaoshuo and M\"uller, Thomas and Evans, Alex and Taylor, Russell H. and Unberath, Mathias and Liu, Ming-Yu and Lin, Chen-Hsuan}, title = {Neuralangelo: High-Fidelity Neural Surface Reconstruction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8456-8465} }
Re-GAN: Data-Efficient GANs Training via Architectural Reconfiguration: Divya Saxena,

Jiannong Cao,

Jiahao Xu,

Tarun Kulshrestha; [pdf] [supp]
[bibtex]
@InProceedings{Saxena_2023_CVPR, author = {Saxena, Divya and Cao, Jiannong and Xu, Jiahao and Kulshrestha, Tarun}, title = {Re-GAN: Data-Efficient GANs Training via Architectural Reconfiguration}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16230-16240} }
Dimensionality-Varying Diffusion Process: Han Zhang,

Ruili Feng,

Zhantao Yang,

Lianghua Huang,

Yu Liu,

Yifei Zhang,

Yujun Shen,

Deli Zhao,

Jingren Zhou,

Fan Cheng; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhang_2023_CVPR, author = {Zhang, Han and Feng, Ruili and Yang, Zhantao and Huang, Lianghua and Liu, Yu and Zhang, Yifei and Shen, Yujun and Zhao, Deli and Zhou, Jingren and Cheng, Fan}, title = {Dimensionality-Varying Diffusion Process}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14307-14316} }
RenderDiffusion: Image Diffusion for 3D Reconstruction, Inpainting and Generation: Titas Anciukevičius,

Zexiang Xu,

Matthew Fisher,

Paul Henderson,

Hakan Bilen,

Niloy J. Mitra,

Paul Guerrero; [pdf] [supp]
[bibtex]
@InProceedings{Anciukevicius_2023_CVPR, author = {Anciukevi\v{c}ius, Titas and Xu, Zexiang and Fisher, Matthew and Henderson, Paul and Bilen, Hakan and Mitra, Niloy J. and Guerrero, Paul}, title = {RenderDiffusion: Image Diffusion for 3D Reconstruction, Inpainting and Generation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12608-12618} }
Latent-NeRF for Shape-Guided Generation of 3D Shapes and Textures: Gal Metzer,

Elad Richardson,

Or Patashnik,

Raja Giryes,

Daniel Cohen-Or; [pdf] [arXiv]
[bibtex]
@InProceedings{Metzer_2023_CVPR, author = {Metzer, Gal and Richardson, Elad and Patashnik, Or and Giryes, Raja and Cohen-Or, Daniel}, title = {Latent-NeRF for Shape-Guided Generation of 3D Shapes and Textures}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12663-12673} }
Learning Generative Structure Prior for Blind Text Image Super-Resolution: Xiaoming Li,

Wangmeng Zuo,

Chen Change Loy; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Li_2023_CVPR, author = {Li, Xiaoming and Zuo, Wangmeng and Loy, Chen Change}, title = {Learning Generative Structure Prior for Blind Text Image Super-Resolution}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10103-10113} }
PEFAT: Boosting Semi-Supervised Medical Image Classification via Pseudo-Loss Estimation and Feature Adversarial Training: Qingjie Zeng,

Yutong Xie,

Zilin Lu,

Yong Xia; [pdf] [supp]
[bibtex]
@InProceedings{Zeng_2023_CVPR, author = {Zeng, Qingjie and Xie, Yutong and Lu, Zilin and Xia, Yong}, title = {PEFAT: Boosting Semi-Supervised Medical Image Classification via Pseudo-Loss Estimation and Feature Adversarial Training}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15671-15680} }
Ground-Truth Free Meta-Learning for Deep Compressive Sampling: Xinran Qin,

Yuhui Quan,

Tongyao Pang,

Hui Ji; [pdf] [supp]
[bibtex]
@InProceedings{Qin_2023_CVPR, author = {Qin, Xinran and Quan, Yuhui and Pang, Tongyao and Ji, Hui}, title = {Ground-Truth Free Meta-Learning for Deep Compressive Sampling}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9947-9956} }
SHS-Net: Learning Signed Hyper Surfaces for Oriented Normal Estimation of Point Clouds: Qing Li,

Huifang Feng,

Kanle Shi,

Yue Gao,

Yi Fang,

Yu-Shen Liu,

Zhizhong Han; [pdf] [supp]
[bibtex]
@InProceedings{Li_2023_CVPR, author = {Li, Qing and Feng, Huifang and Shi, Kanle and Gao, Yue and Fang, Yi and Liu, Yu-Shen and Han, Zhizhong}, title = {SHS-Net: Learning Signed Hyper Surfaces for Oriented Normal Estimation of Point Clouds}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13591-13600} }
DistractFlow: Improving Optical Flow Estimation via Realistic Distractions and Pseudo-Labeling: Jisoo Jeong,

Hong Cai,

Risheek Garrepalli,

Fatih Porikli; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Jeong_2023_CVPR, author = {Jeong, Jisoo and Cai, Hong and Garrepalli, Risheek and Porikli, Fatih}, title = {DistractFlow: Improving Optical Flow Estimation via Realistic Distractions and Pseudo-Labeling}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13691-13700} }
DSVT: Dynamic Sparse Voxel Transformer With Rotated Sets: Haiyang Wang,

Chen Shi,

Shaoshuai Shi,

Meng Lei,

Sen Wang,

Di He,

Bernt Schiele,

Liwei Wang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2023_CVPR, author = {Wang, Haiyang and Shi, Chen and Shi, Shaoshuai and Lei, Meng and Wang, Sen and He, Di and Schiele, Bernt and Wang, Liwei}, title = {DSVT: Dynamic Sparse Voxel Transformer With Rotated Sets}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13520-13529} }
Enhancing the Self-Universality for Transferable Targeted Attacks: Zhipeng Wei,

Jingjing Chen,

Zuxuan Wu,

Yu-Gang Jiang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wei_2023_CVPR, author = {Wei, Zhipeng and Chen, Jingjing and Wu, Zuxuan and Jiang, Yu-Gang}, title = {Enhancing the Self-Universality for Transferable Targeted Attacks}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12281-12290} }
EditableNeRF: Editing Topologically Varying Neural Radiance Fields by Key Points: Chengwei Zheng,

Wenbin Lin,

Feng Xu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zheng_2023_CVPR, author = {Zheng, Chengwei and Lin, Wenbin and Xu, Feng}, title = {EditableNeRF: Editing Topologically Varying Neural Radiance Fields by Key Points}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8317-8327} }
NeuralEditor: Editing Neural Radiance Fields via Manipulating Point Clouds: Jun-Kun Chen,

Jipeng Lyu,

Yu-Xiong Wang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chen_2023_CVPR, author = {Chen, Jun-Kun and Lyu, Jipeng and Wang, Yu-Xiong}, title = {NeuralEditor: Editing Neural Radiance Fields via Manipulating Point Clouds}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12439-12448} }
NIKI: Neural Inverse Kinematics With Invertible Neural Networks for 3D Human Pose and Shape Estimation: Jiefeng Li,

Siyuan Bian,

Qi Liu,

Jiasheng Tang,

Fan Wang,

Cewu Lu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Li_2023_CVPR, author = {Li, Jiefeng and Bian, Siyuan and Liu, Qi and Tang, Jiasheng and Wang, Fan and Lu, Cewu}, title = {NIKI: Neural Inverse Kinematics With Invertible Neural Networks for 3D Human Pose and Shape Estimation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12933-12942} }
Transfer4D: A Framework for Frugal Motion Capture and Deformation Transfer: Shubh Maheshwari,

Rahul Narain,

Ramya Hebbalaguppe; [pdf] [supp]
[bibtex]
@InProceedings{Maheshwari_2023_CVPR, author = {Maheshwari, Shubh and Narain, Rahul and Hebbalaguppe, Ramya}, title = {Transfer4D: A Framework for Frugal Motion Capture and Deformation Transfer}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12836-12846} }
Randomized Adversarial Training via Taylor Expansion: Gaojie Jin,

Xinping Yi,

Dengyu Wu,

Ronghui Mu,

Xiaowei Huang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Jin_2023_CVPR, author = {Jin, Gaojie and Yi, Xinping and Wu, Dengyu and Mu, Ronghui and Huang, Xiaowei}, title = {Randomized Adversarial Training via Taylor Expansion}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16447-16457} }
Learning To Measure the Point Cloud Reconstruction Loss in a Representation Space: Tianxin Huang,

Zhonggan Ding,

Jiangning Zhang,

Ying Tai,

Zhenyu Zhang,

Mingang Chen,

Chengjie Wang,

Yong Liu; [pdf] [supp]
[bibtex]
@InProceedings{Huang_2023_CVPR, author = {Huang, Tianxin and Ding, Zhonggan and Zhang, Jiangning and Tai, Ying and Zhang, Zhenyu and Chen, Mingang and Wang, Chengjie and Liu, Yong}, title = {Learning To Measure the Point Cloud Reconstruction Loss in a Representation Space}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12208-12217} }
Progressive Neighbor Consistency Mining for Correspondence Pruning: Xin Liu,

Jufeng Yang; [pdf]
[bibtex]
@InProceedings{Liu_2023_CVPR, author = {Liu, Xin and Yang, Jufeng}, title = {Progressive Neighbor Consistency Mining for Correspondence Pruning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9527-9537} }
Bootstrapping Objectness From Videos by Relaxed Common Fate and Visual Grouping: Long Lian,

Zhirong Wu,

Stella X. Yu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Lian_2023_CVPR, author = {Lian, Long and Wu, Zhirong and Yu, Stella X.}, title = {Bootstrapping Objectness From Videos by Relaxed Common Fate and Visual Grouping}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14582-14591} }
Semi-Supervised Hand Appearance Recovery via Structure Disentanglement and Dual Adversarial Discrimination: Zimeng Zhao,

Binghui Zuo,

Zhiyu Long,

Yangang Wang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhao_2023_CVPR, author = {Zhao, Zimeng and Zuo, Binghui and Long, Zhiyu and Wang, Yangang}, title = {Semi-Supervised Hand Appearance Recovery via Structure Disentanglement and Dual Adversarial Discrimination}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12125-12136} }
Back to the Source: Diffusion-Driven Adaptation To Test-Time Corruption: Jin Gao,

Jialing Zhang,

Xihui Liu,

Trevor Darrell,

Evan Shelhamer,

Dequan Wang; [pdf] [supp]
[bibtex]
@InProceedings{Gao_2023_CVPR, author = {Gao, Jin and Zhang, Jialing and Liu, Xihui and Darrell, Trevor and Shelhamer, Evan and Wang, Dequan}, title = {Back to the Source: Diffusion-Driven Adaptation To Test-Time Corruption}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11786-11796} }
LayoutDM: Discrete Diffusion Model for Controllable Layout Generation: Naoto Inoue,

Kotaro Kikuchi,

Edgar Simo-Serra,

Mayu Otani,

Kota Yamaguchi; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Inoue_2023_CVPR, author = {Inoue, Naoto and Kikuchi, Kotaro and Simo-Serra, Edgar and Otani, Mayu and Yamaguchi, Kota}, title = {LayoutDM: Discrete Diffusion Model for Controllable Layout Generation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10167-10176} }
ShapeTalk: A Language Dataset and Framework for 3D Shape Edits and Deformations: Panos Achlioptas,

Ian Huang,

Minhyuk Sung,

Sergey Tulyakov,

Leonidas Guibas; [pdf]
[bibtex]
@InProceedings{Achlioptas_2023_CVPR, author = {Achlioptas, Panos and Huang, Ian and Sung, Minhyuk and Tulyakov, Sergey and Guibas, Leonidas}, title = {ShapeTalk: A Language Dataset and Framework for 3D Shape Edits and Deformations}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12685-12694} }
RGBD2: Generative Scene Synthesis via Incremental View Inpainting Using RGBD Diffusion Models: Jiabao Lei,

Jiapeng Tang,

Kui Jia; [pdf] [arXiv]
[bibtex]
@InProceedings{Lei_2023_CVPR, author = {Lei, Jiabao and Tang, Jiapeng and Jia, Kui}, title = {RGBD2: Generative Scene Synthesis via Incremental View Inpainting Using RGBD Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8422-8434} }
System-Status-Aware Adaptive Network for Online Streaming Video Understanding: Lin Geng Foo,

Jia Gong,

Zhipeng Fan,

Jun Liu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Foo_2023_CVPR, author = {Foo, Lin Geng and Gong, Jia and Fan, Zhipeng and Liu, Jun}, title = {System-Status-Aware Adaptive Network for Online Streaming Video Understanding}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10514-10523} }
Local-Guided Global: Paired Similarity Representation for Visual Reinforcement Learning: Hyesong Choi,

Hunsang Lee,

Wonil Song,

Sangryul Jeon,

Kwanghoon Sohn,

Dongbo Min; [pdf] [supp]
[bibtex]
@InProceedings{Choi_2023_CVPR, author = {Choi, Hyesong and Lee, Hunsang and Song, Wonil and Jeon, Sangryul and Sohn, Kwanghoon and Min, Dongbo}, title = {Local-Guided Global: Paired Similarity Representation for Visual Reinforcement Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15072-15082} }
FFCV: Accelerating Training by Removing Data Bottlenecks: Guillaume Leclerc,

Andrew Ilyas,

Logan Engstrom,

Sung Min Park,

Hadi Salman,

Aleksander Mądry; [pdf] [supp]
[bibtex]
@InProceedings{Leclerc_2023_CVPR, author = {Leclerc, Guillaume and Ilyas, Andrew and Engstrom, Logan and Park, Sung Min and Salman, Hadi and M\k{a}dry, Aleksander}, title = {FFCV: Accelerating Training by Removing Data Bottlenecks}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12011-12020} }
Region-Aware Pretraining for Open-Vocabulary Object Detection With Vision Transformers: Dahun Kim,

Anelia Angelova,

Weicheng Kuo; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kim_2023_CVPR, author = {Kim, Dahun and Angelova, Anelia and Kuo, Weicheng}, title = {Region-Aware Pretraining for Open-Vocabulary Object Detection With Vision Transformers}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11144-11154} }
Towards Unsupervised Object Detection From LiDAR Point Clouds: Lunjun Zhang,

Anqi Joyce Yang,

Yuwen Xiong,

Sergio Casas,

Bin Yang,

Mengye Ren,

Raquel Urtasun; [pdf] [supp]
[bibtex]
@InProceedings{Zhang_2023_CVPR, author = {Zhang, Lunjun and Yang, Anqi Joyce and Xiong, Yuwen and Casas, Sergio and Yang, Bin and Ren, Mengye and Urtasun, Raquel}, title = {Towards Unsupervised Object Detection From LiDAR Point Clouds}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9317-9328} }
NeRF-DS: Neural Radiance Fields for Dynamic Specular Objects: Zhiwen Yan,

Chen Li,

Gim Hee Lee; [pdf] [supp]
[bibtex]
@InProceedings{Yan_2023_CVPR, author = {Yan, Zhiwen and Li, Chen and Lee, Gim Hee}, title = {NeRF-DS: Neural Radiance Fields for Dynamic Specular Objects}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8285-8295} }
M6Doc: A Large-Scale Multi-Format, Multi-Type, Multi-Layout, Multi-Language, Multi-Annotation Category Dataset for Modern Document Layout Analysis: Hiuyi Cheng,

Peirong Zhang,

Sihang Wu,

Jiaxin Zhang,

Qiyuan Zhu,

Zecheng Xie,

Jing Li,

Kai Ding,

Lianwen Jin; [pdf] [supp]
[bibtex]
@InProceedings{Cheng_2023_CVPR, author = {Cheng, Hiuyi and Zhang, Peirong and Wu, Sihang and Zhang, Jiaxin and Zhu, Qiyuan and Xie, Zecheng and Li, Jing and Ding, Kai and Jin, Lianwen}, title = {M6Doc: A Large-Scale Multi-Format, Multi-Type, Multi-Layout, Multi-Language, Multi-Annotation Category Dataset for Modern Document Layout Analysis}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15138-15147} }
RealFusion: 360deg Reconstruction of Any Object From a Single Image: Luke Melas-Kyriazi,

Iro Laina,

Christian Rupprecht,

Andrea Vedaldi; [pdf] [supp]
[bibtex]
@InProceedings{Melas-Kyriazi_2023_CVPR, author = {Melas-Kyriazi, Luke and Laina, Iro and Rupprecht, Christian and Vedaldi, Andrea}, title = {RealFusion: 360deg Reconstruction of Any Object From a Single Image}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8446-8455} }
LargeKernel3D: Scaling Up Kernels in 3D Sparse CNNs: Yukang Chen,

Jianhui Liu,

Xiangyu Zhang,

Xiaojuan Qi,

Jiaya Jia; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chen_2023_CVPR, author = {Chen, Yukang and Liu, Jianhui and Zhang, Xiangyu and Qi, Xiaojuan and Jia, Jiaya}, title = {LargeKernel3D: Scaling Up Kernels in 3D Sparse CNNs}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13488-13498} }
3D Concept Learning and Reasoning From Multi-View Images: Yining Hong,

Chunru Lin,

Yilun Du,

Zhenfang Chen,

Joshua B. Tenenbaum,

Chuang Gan; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Hong_2023_CVPR, author = {Hong, Yining and Lin, Chunru and Du, Yilun and Chen, Zhenfang and Tenenbaum, Joshua B. and Gan, Chuang}, title = {3D Concept Learning and Reasoning From Multi-View Images}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9202-9212} }
Soft Augmentation for Image Classification: Yang Liu,

Shen Yan,

Laura Leal-Taixé,

James Hays,

Deva Ramanan; [pdf] [supp]
[bibtex]
@InProceedings{Liu_2023_CVPR, author = {Liu, Yang and Yan, Shen and Leal-Taix\'e, Laura and Hays, James and Ramanan, Deva}, title = {Soft Augmentation for Image Classification}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16241-16250} }
PREIM3D: 3D Consistent Precise Image Attribute Editing From a Single Image: Jianhui Li,

Jianmin Li,

Haoji Zhang,

Shilong Liu,

Zhengyi Wang,

Zihao Xiao,

Kaiwen Zheng,

Jun Zhu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Li_2023_CVPR, author = {Li, Jianhui and Li, Jianmin and Zhang, Haoji and Liu, Shilong and Wang, Zhengyi and Xiao, Zihao and Zheng, Kaiwen and Zhu, Jun}, title = {PREIM3D: 3D Consistent Precise Image Attribute Editing From a Single Image}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8549-8558} }
Detecting Backdoors in Pre-Trained Encoders: Shiwei Feng,

Guanhong Tao,

Siyuan Cheng,

Guangyu Shen,

Xiangzhe Xu,

Yingqi Liu,

Kaiyuan Zhang,

Shiqing Ma,

Xiangyu Zhang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Feng_2023_CVPR, author = {Feng, Shiwei and Tao, Guanhong and Cheng, Siyuan and Shen, Guangyu and Xu, Xiangzhe and Liu, Yingqi and Zhang, Kaiyuan and Ma, Shiqing and Zhang, Xiangyu}, title = {Detecting Backdoors in Pre-Trained Encoders}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16352-16362} }
Primitive Generation and Semantic-Related Alignment for Universal Zero-Shot Segmentation: Shuting He,

Henghui Ding,

Wei Jiang; [pdf] [supp]
[bibtex]
@InProceedings{He_2023_CVPR, author = {He, Shuting and Ding, Henghui and Jiang, Wei}, title = {Primitive Generation and Semantic-Related Alignment for Universal Zero-Shot Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11238-11247} }
Long Range Pooling for 3D Large-Scale Scene Understanding: Xiang-Li Li,

Meng-Hao Guo,

Tai-Jiang Mu,

Ralph R. Martin,

Shi-Min Hu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Li_2023_CVPR, author = {Li, Xiang-Li and Guo, Meng-Hao and Mu, Tai-Jiang and Martin, Ralph R. and Hu, Shi-Min}, title = {Long Range Pooling for 3D Large-Scale Scene Understanding}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10300-10311} }
Causally-Aware Intraoperative Imputation for Overall Survival Time Prediction: Xiang Li,

Xuelin Qian,

Litian Liang,

Lingjie Kong,

Qiaole Dong,

Jiejun Chen,

Dingxia Liu,

Xiuzhong Yao,

Yanwei Fu; [pdf] [supp]
[bibtex]
@InProceedings{Li_2023_CVPR, author = {Li, Xiang and Qian, Xuelin and Liang, Litian and Kong, Lingjie and Dong, Qiaole and Chen, Jiejun and Liu, Dingxia and Yao, Xiuzhong and Fu, Yanwei}, title = {Causally-Aware Intraoperative Imputation for Overall Survival Time Prediction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15681-15690} }
Twin Contrastive Learning With Noisy Labels: Zhizhong Huang,

Junping Zhang,

Hongming Shan; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Huang_2023_CVPR, author = {Huang, Zhizhong and Zhang, Junping and Shan, Hongming}, title = {Twin Contrastive Learning With Noisy Labels}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11661-11670} }
Asymmetric Feature Fusion for Image Retrieval: Hui Wu,

Min Wang,

Wengang Zhou,

Zhenbo Lu,

Houqiang Li; [pdf] [supp]
[bibtex]
@InProceedings{Wu_2023_CVPR, author = {Wu, Hui and Wang, Min and Zhou, Wengang and Lu, Zhenbo and Li, Houqiang}, title = {Asymmetric Feature Fusion for Image Retrieval}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11082-11092} }
CREPE: Can Vision-Language Foundation Models Reason Compositionally?: Zixian Ma,

Jerry Hong,

Mustafa Omer Gul,

Mona Gandhi,

Irena Gao,

Ranjay Krishna; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ma_2023_CVPR, author = {Ma, Zixian and Hong, Jerry and Gul, Mustafa Omer and Gandhi, Mona and Gao, Irena and Krishna, Ranjay}, title = {CREPE: Can Vision-Language Foundation Models Reason Compositionally?}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10910-10921} }
PyramidFlow: High-Resolution Defect Contrastive Localization Using Pyramid Normalizing Flow: Jiarui Lei,

Xiaobo Hu,

Yue Wang,

Dong Liu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Lei_2023_CVPR, author = {Lei, Jiarui and Hu, Xiaobo and Wang, Yue and Liu, Dong}, title = {PyramidFlow: High-Resolution Defect Contrastive Localization Using Pyramid Normalizing Flow}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14143-14152} }
On-the-Fly Category Discovery: Ruoyi Du,

Dongliang Chang,

Kongming Liang,

Timothy Hospedales,

Yi-Zhe Song,

Zhanyu Ma; [pdf]
[bibtex]
@InProceedings{Du_2023_CVPR, author = {Du, Ruoyi and Chang, Dongliang and Liang, Kongming and Hospedales, Timothy and Song, Yi-Zhe and Ma, Zhanyu}, title = {On-the-Fly Category Discovery}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11691-11700} }
MAIR: Multi-View Attention Inverse Rendering With 3D Spatially-Varying Lighting Estimation: JunYong Choi,

SeokYeong Lee,

Haesol Park,

Seung-Won Jung,

Ig-Jae Kim,

Junghyun Cho; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Choi_2023_CVPR, author = {Choi, JunYong and Lee, SeokYeong and Park, Haesol and Jung, Seung-Won and Kim, Ig-Jae and Cho, Junghyun}, title = {MAIR: Multi-View Attention Inverse Rendering With 3D Spatially-Varying Lighting Estimation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8392-8401} }
DF-Platter: Multi-Face Heterogeneous Deepfake Dataset: Kartik Narayan,

Harsh Agarwal,

Kartik Thakral,

Surbhi Mittal,

Mayank Vatsa,

Richa Singh; [pdf] [supp]
[bibtex]
@InProceedings{Narayan_2023_CVPR, author = {Narayan, Kartik and Agarwal, Harsh and Thakral, Kartik and Mittal, Surbhi and Vatsa, Mayank and Singh, Richa}, title = {DF-Platter: Multi-Face Heterogeneous Deepfake Dataset}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9739-9748} }
Shifted Diffusion for Text-to-Image Generation: Yufan Zhou,

Bingchen Liu,

Yizhe Zhu,

Xiao Yang,

Changyou Chen,

Jinhui Xu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhou_2023_CVPR, author = {Zhou, Yufan and Liu, Bingchen and Zhu, Yizhe and Yang, Xiao and Chen, Changyou and Xu, Jinhui}, title = {Shifted Diffusion for Text-to-Image Generation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10157-10166} }
Boosting Detection in Crowd Analysis via Underutilized Output Features: Shaokai Wu,

Fengyu Yang; [pdf] [supp]
[bibtex]
@InProceedings{Wu_2023_CVPR, author = {Wu, Shaokai and Yang, Fengyu}, title = {Boosting Detection in Crowd Analysis via Underutilized Output Features}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15609-15618} }
K3DN: Disparity-Aware Kernel Estimation for Dual-Pixel Defocus Deblurring: Yan Yang,

Liyuan Pan,

Liu Liu,

Miaomiao Liu; [pdf] [supp]
[bibtex]
@InProceedings{Yang_2023_CVPR, author = {Yang, Yan and Pan, Liyuan and Liu, Liu and Liu, Miaomiao}, title = {K3DN: Disparity-Aware Kernel Estimation for Dual-Pixel Defocus Deblurring}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13263-13272} }
DartBlur: Privacy Preservation With Detection Artifact Suppression: Baowei Jiang,

Bing Bai,

Haozhe Lin,

Yu Wang,

Yuchen Guo,

Lu Fang; [pdf] [supp]
[bibtex]
@InProceedings{Jiang_2023_CVPR, author = {Jiang, Baowei and Bai, Bing and Lin, Haozhe and Wang, Yu and Guo, Yuchen and Fang, Lu}, title = {DartBlur: Privacy Preservation With Detection Artifact Suppression}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16479-16488} }
LipFormer: High-Fidelity and Generalizable Talking Face Generation With a Pre-Learned Facial Codebook: Jiayu Wang,

Kang Zhao,

Shiwei Zhang,

Yingya Zhang,

Yujun Shen,

Deli Zhao,

Jingren Zhou; [pdf] [supp]
[bibtex]
@InProceedings{Wang_2023_CVPR, author = {Wang, Jiayu and Zhao, Kang and Zhang, Shiwei and Zhang, Yingya and Shen, Yujun and Zhao, Deli and Zhou, Jingren}, title = {LipFormer: High-Fidelity and Generalizable Talking Face Generation With a Pre-Learned Facial Codebook}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13844-13853} }
Generalizable Local Feature Pre-Training for Deformable Shape Analysis: Souhaib Attaiki,

Lei Li,

Maks Ovsjanikov; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Attaiki_2023_CVPR, author = {Attaiki, Souhaib and Li, Lei and Ovsjanikov, Maks}, title = {Generalizable Local Feature Pre-Training for Deformable Shape Analysis}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13650-13661} }
Progressive Random Convolutions for Single Domain Generalization: Seokeon Choi,

Debasmit Das,

Sungha Choi,

Seunghan Yang,

Hyunsin Park,

Sungrack Yun; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Choi_2023_CVPR, author = {Choi, Seokeon and Das, Debasmit and Choi, Sungha and Yang, Seunghan and Park, Hyunsin and Yun, Sungrack}, title = {Progressive Random Convolutions for Single Domain Generalization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10312-10322} }
OPE-SR: Orthogonal Position Encoding for Designing a Parameter-Free Upsampling Module in Arbitrary-Scale Image Super-Resolution: Gaochao Song,

Qian Sun,

Luo Zhang,

Ran Su,

Jianfeng Shi,

Ying He; [pdf] [supp]
[bibtex]
@InProceedings{Song_2023_CVPR, author = {Song, Gaochao and Sun, Qian and Zhang, Luo and Su, Ran and Shi, Jianfeng and He, Ying}, title = {OPE-SR: Orthogonal Position Encoding for Designing a Parameter-Free Upsampling Module in Arbitrary-Scale Image Super-Resolution}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10009-10020} }
I2MVFormer: Large Language Model Generated Multi-View Document Supervision for Zero-Shot Image Classification: Muhammad Ferjad Naeem,

Muhammad Gul Zain Ali Khan,

Yongqin Xian,

Muhammad Zeshan Afzal,

Didier Stricker,

Luc Van Gool,

Federico Tombari; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Naeem_2023_CVPR, author = {Naeem, Muhammad Ferjad and Khan, Muhammad Gul Zain Ali and Xian, Yongqin and Afzal, Muhammad Zeshan and Stricker, Didier and Van Gool, Luc and Tombari, Federico}, title = {I2MVFormer: Large Language Model Generated Multi-View Document Supervision for Zero-Shot Image Classification}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15169-15179} }
MixSim: A Hierarchical Framework for Mixed Reality Traffic Simulation: Simon Suo,

Kelvin Wong,

Justin Xu,

James Tu,

Alexander Cui,

Sergio Casas,

Raquel Urtasun; [pdf] [supp]
[bibtex]
@InProceedings{Suo_2023_CVPR, author = {Suo, Simon and Wong, Kelvin and Xu, Justin and Tu, James and Cui, Alexander and Casas, Sergio and Urtasun, Raquel}, title = {MixSim: A Hierarchical Framework for Mixed Reality Traffic Simulation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9622-9631} }
Context-Aware Alignment and Mutual Masking for 3D-Language Pre-Training: Zhao Jin,

Munawar Hayat,

Yuwei Yang,

Yulan Guo,

Yinjie Lei; [pdf] [supp]
[bibtex]
@InProceedings{Jin_2023_CVPR, author = {Jin, Zhao and Hayat, Munawar and Yang, Yuwei and Guo, Yulan and Lei, Yinjie}, title = {Context-Aware Alignment and Mutual Masking for 3D-Language Pre-Training}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10984-10994} }
Generalized Decoding for Pixel, Image, and Language: Xueyan Zou,

Zi-Yi Dou,

Jianwei Yang,

Zhe Gan,

Linjie Li,

Chunyuan Li,

Xiyang Dai,

Harkirat Behl,

Jianfeng Wang,

Lu Yuan,

Nanyun Peng,

Lijuan Wang,

Yong Jae Lee,

Jianfeng Gao; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zou_2023_CVPR, author = {Zou, Xueyan and Dou, Zi-Yi and Yang, Jianwei and Gan, Zhe and Li, Linjie and Li, Chunyuan and Dai, Xiyang and Behl, Harkirat and Wang, Jianfeng and Yuan, Lu and Peng, Nanyun and Wang, Lijuan and Lee, Yong Jae and Gao, Jianfeng}, title = {Generalized Decoding for Pixel, Image, and Language}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15116-15127} }
Towards Unified Scene Text Spotting Based on Sequence Generation: Taeho Kil,

Seonghyeon Kim,

Sukmin Seo,

Yoonsik Kim,

Daehee Kim; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kil_2023_CVPR, author = {Kil, Taeho and Kim, Seonghyeon and Seo, Sukmin and Kim, Yoonsik and Kim, Daehee}, title = {Towards Unified Scene Text Spotting Based on Sequence Generation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15223-15232} }
X3KD: Knowledge Distillation Across Modalities, Tasks and Stages for Multi-Camera 3D Object Detection: Marvin Klingner,

Shubhankar Borse,

Varun Ravi Kumar,

Behnaz Rezaei,

Venkatraman Narayanan,

Senthil Yogamani,

Fatih Porikli; [pdf] [supp]
[bibtex]
@InProceedings{Klingner_2023_CVPR, author = {Klingner, Marvin and Borse, Shubhankar and Kumar, Varun Ravi and Rezaei, Behnaz and Narayanan, Venkatraman and Yogamani, Senthil and Porikli, Fatih}, title = {X3KD: Knowledge Distillation Across Modalities, Tasks and Stages for Multi-Camera 3D Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13343-13353} }
Rawgment: Noise-Accounted RAW Augmentation Enables Recognition in a Wide Variety of Environments: Masakazu Yoshimura,

Junji Otsuka,

Atsushi Irie,

Takeshi Ohashi; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yoshimura_2023_CVPR, author = {Yoshimura, Masakazu and Otsuka, Junji and Irie, Atsushi and Ohashi, Takeshi}, title = {Rawgment: Noise-Accounted RAW Augmentation Enables Recognition in a Wide Variety of Environments}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14007-14017} }
BITE: Beyond Priors for Improved Three-D Dog Pose Estimation: Nadine Rüegg,

Shashank Tripathi,

Konrad Schindler,

Michael J. Black,

Silvia Zuffi; [pdf] [supp]
[bibtex]
@InProceedings{Ruegg_2023_CVPR, author = {R\"uegg, Nadine and Tripathi, Shashank and Schindler, Konrad and Black, Michael J. and Zuffi, Silvia}, title = {BITE: Beyond Priors for Improved Three-D Dog Pose Estimation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8867-8876} }
Equivalent Transformation and Dual Stream Network Construction for Mobile Image Super-Resolution: Jiahao Chao,

Zhou Zhou,

Hongfan Gao,

Jiali Gong,

Zhengfeng Yang,

Zhenbing Zeng,

Lydia Dehbi; [pdf] [supp]
[bibtex]
@InProceedings{Chao_2023_CVPR, author = {Chao, Jiahao and Zhou, Zhou and Gao, Hongfan and Gong, Jiali and Yang, Zhengfeng and Zeng, Zhenbing and Dehbi, Lydia}, title = {Equivalent Transformation and Dual Stream Network Construction for Mobile Image Super-Resolution}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14102-14111} }
High-Resolution Image Reconstruction With Latent Diffusion Models From Human Brain Activity: Yu Takagi,

Shinji Nishimoto; [pdf] [supp]
[bibtex]
@InProceedings{Takagi_2023_CVPR, author = {Takagi, Yu and Nishimoto, Shinji}, title = {High-Resolution Image Reconstruction With Latent Diffusion Models From Human Brain Activity}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14453-14463} }
DARE-GRAM: Unsupervised Domain Adaptation Regression by Aligning Inverse Gram Matrices: Ismail Nejjar,

Qin Wang,

Olga Fink; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Nejjar_2023_CVPR, author = {Nejjar, Ismail and Wang, Qin and Fink, Olga}, title = {DARE-GRAM: Unsupervised Domain Adaptation Regression by Aligning Inverse Gram Matrices}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11744-11754} }
Bidirectional Copy-Paste for Semi-Supervised Medical Image Segmentation: Yunhao Bai,

Duowen Chen,

Qingli Li,

Wei Shen,

Yan Wang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Bai_2023_CVPR, author = {Bai, Yunhao and Chen, Duowen and Li, Qingli and Shen, Wei and Wang, Yan}, title = {Bidirectional Copy-Paste for Semi-Supervised Medical Image Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11514-11524} }
Learning Discriminative Representations for Skeleton Based Action Recognition: Huanyu Zhou,

Qingjie Liu,

Yunhong Wang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhou_2023_CVPR, author = {Zhou, Huanyu and Liu, Qingjie and Wang, Yunhong}, title = {Learning Discriminative Representations for Skeleton Based Action Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10608-10617} }
Few-Shot Non-Line-of-Sight Imaging With Signal-Surface Collaborative Regularization: Xintong Liu,

Jianyu Wang,

Leping Xiao,

Xing Fu,

Lingyun Qiu,

Zuoqiang Shi; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Liu_2023_CVPR, author = {Liu, Xintong and Wang, Jianyu and Xiao, Leping and Fu, Xing and Qiu, Lingyun and Shi, Zuoqiang}, title = {Few-Shot Non-Line-of-Sight Imaging With Signal-Surface Collaborative Regularization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13303-13312} }
Probabilistic Debiasing of Scene Graphs: Bashirul Azam Biswas,

Qiang Ji; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Biswas_2023_CVPR, author = {Biswas, Bashirul Azam and Ji, Qiang}, title = {Probabilistic Debiasing of Scene Graphs}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10429-10438} }
Depth Estimation From Camera Image and mmWave Radar Point Cloud: Akash Deep Singh,

Yunhao Ba,

Ankur Sarker,

Howard Zhang,

Achuta Kadambi,

Stefano Soatto,

Mani Srivastava,

Alex Wong; [pdf] [supp]
[bibtex]
@InProceedings{Singh_2023_CVPR, author = {Singh, Akash Deep and Ba, Yunhao and Sarker, Ankur and Zhang, Howard and Kadambi, Achuta and Soatto, Stefano and Srivastava, Mani and Wong, Alex}, title = {Depth Estimation From Camera Image and mmWave Radar Point Cloud}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9275-9285} }
Learning Event Guided High Dynamic Range Video Reconstruction: Yixin Yang,

Jin Han,

Jinxiu Liang,

Imari Sato,

Boxin Shi; [pdf] [supp]
[bibtex]
@InProceedings{Yang_2023_CVPR, author = {Yang, Yixin and Han, Jin and Liang, Jinxiu and Sato, Imari and Shi, Boxin}, title = {Learning Event Guided High Dynamic Range Video Reconstruction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13924-13934} }
Prototypical Residual Networks for Anomaly Detection and Localization: Hui Zhang,

Zuxuan Wu,

Zheng Wang,

Zhineng Chen,

Yu-Gang Jiang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhang_2023_CVPR, author = {Zhang, Hui and Wu, Zuxuan and Wang, Zheng and Chen, Zhineng and Jiang, Yu-Gang}, title = {Prototypical Residual Networks for Anomaly Detection and Localization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16281-16291} }
Ultrahigh Resolution Image/Video Matting With Spatio-Temporal Sparsity: Yanan Sun,

Chi-Keung Tang,

Yu-Wing Tai; [pdf] [supp]
[bibtex]
@InProceedings{Sun_2023_CVPR, author = {Sun, Yanan and Tang, Chi-Keung and Tai, Yu-Wing}, title = {Ultrahigh Resolution Image/Video Matting With Spatio-Temporal Sparsity}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14112-14121} }
Zero-Shot Noise2Noise: Efficient Image Denoising Without Any Data: Youssef Mansour,

Reinhard Heckel; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Mansour_2023_CVPR, author = {Mansour, Youssef and Heckel, Reinhard}, title = {Zero-Shot Noise2Noise: Efficient Image Denoising Without Any Data}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14018-14027} }
FIANCEE: Faster Inference of Adversarial Networks via Conditional Early Exits: Polina Karpikova,

Ekaterina Radionova,

Anastasia Yaschenko,

Andrei Spiridonov,

Leonid Kostyushko,

Riccardo Fabbricatore,

Aleksei Ivakhnenko; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Karpikova_2023_CVPR, author = {Karpikova, Polina and Radionova, Ekaterina and Yaschenko, Anastasia and Spiridonov, Andrei and Kostyushko, Leonid and Fabbricatore, Riccardo and Ivakhnenko, Aleksei}, title = {FIANCEE: Faster Inference of Adversarial Networks via Conditional Early Exits}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12032-12043} }
Simultaneously Short- and Long-Term Temporal Modeling for Semi-Supervised Video Semantic Segmentation: Jiangwei Lao,

Weixiang Hong,

Xin Guo,

Yingying Zhang,

Jian Wang,

Jingdong Chen,

Wei Chu; [pdf] [supp]
[bibtex]
@InProceedings{Lao_2023_CVPR, author = {Lao, Jiangwei and Hong, Weixiang and Guo, Xin and Zhang, Yingying and Wang, Jian and Chen, Jingdong and Chu, Wei}, title = {Simultaneously Short- and Long-Term Temporal Modeling for Semi-Supervised Video Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14763-14772} }
Learning To Generate Text-Grounded Mask for Open-World Semantic Segmentation From Only Image-Text Pairs: Junbum Cha,

Jonghwan Mun,

Byungseok Roh; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Cha_2023_CVPR, author = {Cha, Junbum and Mun, Jonghwan and Roh, Byungseok}, title = {Learning To Generate Text-Grounded Mask for Open-World Semantic Segmentation From Only Image-Text Pairs}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11165-11174} }
Shakes on a Plane: Unsupervised Depth Estimation From Unstabilized Photography: Ilya Chugunov,

Yuxuan Zhang,

Felix Heide; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chugunov_2023_CVPR, author = {Chugunov, Ilya and Zhang, Yuxuan and Heide, Felix}, title = {Shakes on a Plane: Unsupervised Depth Estimation From Unstabilized Photography}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13240-13251} }
Learning Correspondence Uncertainty via Differentiable Nonlinear Least Squares: Dominik Muhle,

Lukas Koestler,

Krishna Murthy Jatavallabhula,

Daniel Cremers; [pdf] [supp]
[bibtex]
@InProceedings{Muhle_2023_CVPR, author = {Muhle, Dominik and Koestler, Lukas and Jatavallabhula, Krishna Murthy and Cremers, Daniel}, title = {Learning Correspondence Uncertainty via Differentiable Nonlinear Least Squares}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13102-13112} }
Towards Effective Visual Representations for Partial-Label Learning: Shiyu Xia,

Jiaqi Lv,

Ning Xu,

Gang Niu,

Xin Geng; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Xia_2023_CVPR, author = {Xia, Shiyu and Lv, Jiaqi and Xu, Ning and Niu, Gang and Geng, Xin}, title = {Towards Effective Visual Representations for Partial-Label Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15589-15598} }
MaskCLIP: Masked Self-Distillation Advances Contrastive Language-Image Pretraining: Xiaoyi Dong,

Jianmin Bao,

Yinglin Zheng,

Ting Zhang,

Dongdong Chen,

Hao Yang,

Ming Zeng,

Weiming Zhang,

Lu Yuan,

Dong Chen,

Fang Wen,

Nenghai Yu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Dong_2023_CVPR, author = {Dong, Xiaoyi and Bao, Jianmin and Zheng, Yinglin and Zhang, Ting and Chen, Dongdong and Yang, Hao and Zeng, Ming and Zhang, Weiming and Yuan, Lu and Chen, Dong and Wen, Fang and Yu, Nenghai}, title = {MaskCLIP: Masked Self-Distillation Advances Contrastive Language-Image Pretraining}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10995-11005} }
Inferring and Leveraging Parts From Object Shape for Improving Semantic Image Synthesis: Yuxiang Wei,

Zhilong Ji,

Xiaohe Wu,

Jinfeng Bai,

Lei Zhang,

Wangmeng Zuo; [pdf] [supp]
[bibtex]
@InProceedings{Wei_2023_CVPR, author = {Wei, Yuxiang and Ji, Zhilong and Wu, Xiaohe and Bai, Jinfeng and Zhang, Lei and Zuo, Wangmeng}, title = {Inferring and Leveraging Parts From Object Shape for Improving Semantic Image Synthesis}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11248-11258} }
MIME: Human-Aware 3D Scene Generation: Hongwei Yi,

Chun-Hao P. Huang,

Shashank Tripathi,

Lea Hering,

Justus Thies,

Michael J. Black; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yi_2023_CVPR, author = {Yi, Hongwei and Huang, Chun-Hao P. and Tripathi, Shashank and Hering, Lea and Thies, Justus and Black, Michael J.}, title = {MIME: Human-Aware 3D Scene Generation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12965-12976} }
NerVE: Neural Volumetric Edges for Parametric Curve Extraction From Point Cloud: Xiangyu Zhu,

Dong Du,

Weikai Chen,

Zhiyou Zhao,

Yinyu Nie,

Xiaoguang Han; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhu_2023_CVPR, author = {Zhu, Xiangyu and Du, Dong and Chen, Weikai and Zhao, Zhiyou and Nie, Yinyu and Han, Xiaoguang}, title = {NerVE: Neural Volumetric Edges for Parametric Curve Extraction From Point Cloud}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13601-13610} }
ShapeClipper: Scalable 3D Shape Learning From Single-View Images via Geometric and CLIP-Based Consistency: Zixuan Huang,

Varun Jampani,

Anh Thai,

Yuanzhen Li,

Stefan Stojanov,

James M. Rehg; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Huang_2023_CVPR, author = {Huang, Zixuan and Jampani, Varun and Thai, Anh and Li, Yuanzhen and Stojanov, Stefan and Rehg, James M.}, title = {ShapeClipper: Scalable 3D Shape Learning From Single-View Images via Geometric and CLIP-Based Consistency}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12912-12922} }
Backdoor Attacks Against Deep Image Compression via Adaptive Frequency Trigger: Yi Yu,

Yufei Wang,

Wenhan Yang,

Shijian Lu,

Yap-Peng Tan,

Alex C. Kot; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yu_2023_CVPR, author = {Yu, Yi and Wang, Yufei and Yang, Wenhan and Lu, Shijian and Tan, Yap-Peng and Kot, Alex C.}, title = {Backdoor Attacks Against Deep Image Compression via Adaptive Frequency Trigger}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12250-12259} }
A New Path: Scaling Vision-and-Language Navigation With Synthetic Instructions and Imitation Learning: Aishwarya Kamath,

Peter Anderson,

Su Wang,

Jing Yu Koh,

Alexander Ku,

Austin Waters,

Yinfei Yang,

Jason Baldridge,

Zarana Parekh; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kamath_2023_CVPR, author = {Kamath, Aishwarya and Anderson, Peter and Wang, Su and Koh, Jing Yu and Ku, Alexander and Waters, Austin and Yang, Yinfei and Baldridge, Jason and Parekh, Zarana}, title = {A New Path: Scaling Vision-and-Language Navigation With Synthetic Instructions and Imitation Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10813-10823} }
Layout-Based Causal Inference for Object Navigation: Sixian Zhang,

Xinhang Song,

Weijie Li,

Yubing Bai,

Xinyao Yu,

Shuqiang Jiang; [pdf] [supp]
[bibtex]
@InProceedings{Zhang_2023_CVPR, author = {Zhang, Sixian and Song, Xinhang and Li, Weijie and Bai, Yubing and Yu, Xinyao and Jiang, Shuqiang}, title = {Layout-Based Causal Inference for Object Navigation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10792-10802} }
Pose-Disentangled Contrastive Learning for Self-Supervised Facial Representation: Yuanyuan Liu,

Wenbin Wang,

Yibing Zhan,

Shaoze Feng,

Kejun Liu,

Zhe Chen; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Liu_2023_CVPR, author = {Liu, Yuanyuan and Wang, Wenbin and Zhan, Yibing and Feng, Shaoze and Liu, Kejun and Chen, Zhe}, title = {Pose-Disentangled Contrastive Learning for Self-Supervised Facial Representation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9717-9728} }
Inverse Rendering of Translucent Objects Using Physical and Neural Renderers: Chenhao Li,

Trung Thanh Ngo,

Hajime Nagahara; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Li_2023_CVPR, author = {Li, Chenhao and Ngo, Trung Thanh and Nagahara, Hajime}, title = {Inverse Rendering of Translucent Objects Using Physical and Neural Renderers}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12510-12520} }
Towards Building Self-Aware Object Detectors via Reliable Uncertainty Quantification and Calibration: Kemal Oksuz,

Tom Joy,

Puneet K. Dokania; [pdf] [supp]
[bibtex]
@InProceedings{Oksuz_2023_CVPR, author = {Oksuz, Kemal and Joy, Tom and Dokania, Puneet K.}, title = {Towards Building Self-Aware Object Detectors via Reliable Uncertainty Quantification and Calibration}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9263-9274} }
Source-Free Video Domain Adaptation With Spatial-Temporal-Historical Consistency Learning: Kai Li,

Deep Patel,

Erik Kruus,

Martin Renqiang Min; [pdf] [supp]
[bibtex]
@InProceedings{Li_2023_CVPR, author = {Li, Kai and Patel, Deep and Kruus, Erik and Min, Martin Renqiang}, title = {Source-Free Video Domain Adaptation With Spatial-Temporal-Historical Consistency Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14643-14652} }
Fusing Pre-Trained Language Models With Multimodal Prompts Through Reinforcement Learning: Youngjae Yu,

Jiwan Chung,

Heeseung Yun,

Jack Hessel,

Jae Sung Park,

Ximing Lu,

Rowan Zellers,

Prithviraj Ammanabrolu,

Ronan Le Bras,

Gunhee Kim,

Yejin Choi; [pdf] [supp]
[bibtex]
@InProceedings{Yu_2023_CVPR, author = {Yu, Youngjae and Chung, Jiwan and Yun, Heeseung and Hessel, Jack and Park, Jae Sung and Lu, Ximing and Zellers, Rowan and Ammanabrolu, Prithviraj and Le Bras, Ronan and Kim, Gunhee and Choi, Yejin}, title = {Fusing Pre-Trained Language Models With Multimodal Prompts Through Reinforcement Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10845-10856} }
Dense Network Expansion for Class Incremental Learning: Zhiyuan Hu,

Yunsheng Li,

Jiancheng Lyu,

Dashan Gao,

Nuno Vasconcelos; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Hu_2023_CVPR, author = {Hu, Zhiyuan and Li, Yunsheng and Lyu, Jiancheng and Gao, Dashan and Vasconcelos, Nuno}, title = {Dense Network Expansion for Class Incremental Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11858-11867} }
Regularize Implicit Neural Representation by Itself: Zhemin Li,

Hongxia Wang,

Deyu Meng; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Li_2023_CVPR, author = {Li, Zhemin and Wang, Hongxia and Meng, Deyu}, title = {Regularize Implicit Neural Representation by Itself}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10280-10288} }
Ambiguous Medical Image Segmentation Using Diffusion Models: Aimon Rahman,

Jeya Maria Jose Valanarasu,

Ilker Hacihaliloglu,

Vishal M. Patel; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Rahman_2023_CVPR, author = {Rahman, Aimon and Valanarasu, Jeya Maria Jose and Hacihaliloglu, Ilker and Patel, Vishal M.}, title = {Ambiguous Medical Image Segmentation Using Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11536-11546} }
DANI-Net: Uncalibrated Photometric Stereo by Differentiable Shadow Handling, Anisotropic Reflectance Modeling, and Neural Inverse Rendering: Zongrui Li,

Qian Zheng,

Boxin Shi,

Gang Pan,

Xudong Jiang; [pdf] [supp]
[bibtex]
@InProceedings{Li_2023_CVPR, author = {Li, Zongrui and Zheng, Qian and Shi, Boxin and Pan, Gang and Jiang, Xudong}, title = {DANI-Net: Uncalibrated Photometric Stereo by Differentiable Shadow Handling, Anisotropic Reflectance Modeling, and Neural Inverse Rendering}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8381-8391} }
Towards Better Stability and Adaptability: Improve Online Self-Training for Model Adaptation in Semantic Segmentation: Dong Zhao,

Shuang Wang,

Qi Zang,

Dou Quan,

Xiutiao Ye,

Licheng Jiao; [pdf]
[bibtex]
@InProceedings{Zhao_2023_CVPR, author = {Zhao, Dong and Wang, Shuang and Zang, Qi and Quan, Dou and Ye, Xiutiao and Jiao, Licheng}, title = {Towards Better Stability and Adaptability: Improve Online Self-Training for Model Adaptation in Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11733-11743} }
Ranking Regularization for Critical Rare Classes: Minimizing False Positives at a High True Positive Rate: Kiarash Mohammadi,

He Zhao,

Mengyao Zhai,

Frederick Tung; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Mohammadi_2023_CVPR, author = {Mohammadi, Kiarash and Zhao, He and Zhai, Mengyao and Tung, Frederick}, title = {Ranking Regularization for Critical Rare Classes: Minimizing False Positives at a High True Positive Rate}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15783-15792} }
Joint HDR Denoising and Fusion: A Real-World Mobile HDR Image Dataset: Shuaizheng Liu,

Xindong Zhang,

Lingchen Sun,

Zhetong Liang,

Hui Zeng,

Lei Zhang; [pdf] [supp]
[bibtex]
@InProceedings{Liu_2023_CVPR, author = {Liu, Shuaizheng and Zhang, Xindong and Sun, Lingchen and Liang, Zhetong and Zeng, Hui and Zhang, Lei}, title = {Joint HDR Denoising and Fusion: A Real-World Mobile HDR Image Dataset}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13966-13975} }
MIST: Multi-Modal Iterative Spatial-Temporal Transformer for Long-Form Video Question Answering: Difei Gao,

Luowei Zhou,

Lei Ji,

Linchao Zhu,

Yi Yang,

Mike Zheng Shou; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Gao_2023_CVPR, author = {Gao, Difei and Zhou, Luowei and Ji, Lei and Zhu, Linchao and Yang, Yi and Shou, Mike Zheng}, title = {MIST: Multi-Modal Iterative Spatial-Temporal Transformer for Long-Form Video Question Answering}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14773-14783} }
Privacy-Preserving Representations Are Not Enough: Recovering Scene Content From Camera Poses: Kunal Chelani,

Torsten Sattler,

Fredrik Kahl,

Zuzana Kukelova; [pdf] [supp]
[bibtex]
@InProceedings{Chelani_2023_CVPR, author = {Chelani, Kunal and Sattler, Torsten and Kahl, Fredrik and Kukelova, Zuzana}, title = {Privacy-Preserving Representations Are Not Enough: Recovering Scene Content From Camera Poses}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13132-13141} }
A New Dataset Based on Images Taken by Blind People for Testing the Robustness of Image Classification Models Trained for ImageNet Categories: Reza Akbarian Bafghi,

Danna Gurari; [pdf] [supp]
[bibtex]
@InProceedings{Bafghi_2023_CVPR, author = {Bafghi, Reza Akbarian and Gurari, Danna}, title = {A New Dataset Based on Images Taken by Blind People for Testing the Robustness of Image Classification Models Trained for ImageNet Categories}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16261-16270} }
Detecting Backdoors During the Inference Stage Based on Corruption Robustness Consistency: Xiaogeng Liu,

Minghui Li,

Haoyu Wang,

Shengshan Hu,

Dengpan Ye,

Hai Jin,

Libing Wu,

Chaowei Xiao; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Liu_2023_CVPR, author = {Liu, Xiaogeng and Li, Minghui and Wang, Haoyu and Hu, Shengshan and Ye, Dengpan and Jin, Hai and Wu, Libing and Xiao, Chaowei}, title = {Detecting Backdoors During the Inference Stage Based on Corruption Robustness Consistency}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16363-16372} }
Black-Box Sparse Adversarial Attack via Multi-Objective Optimisation: Phoenix Neale Williams,

Ke Li; [pdf] [supp]
[bibtex]
@InProceedings{Williams_2023_CVPR, author = {Williams, Phoenix Neale and Li, Ke}, title = {Black-Box Sparse Adversarial Attack via Multi-Objective Optimisation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12291-12301} }
Renderable Neural Radiance Map for Visual Navigation: Obin Kwon,

Jeongho Park,

Songhwai Oh; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kwon_2023_CVPR, author = {Kwon, Obin and Park, Jeongho and Oh, Songhwai}, title = {Renderable Neural Radiance Map for Visual Navigation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9099-9108} }
Learning Orthogonal Prototypes for Generalized Few-Shot Semantic Segmentation: Sun-Ao Liu,

Yiheng Zhang,

Zhaofan Qiu,

Hongtao Xie,

Yongdong Zhang,

Ting Yao; [pdf]
[bibtex]
@InProceedings{Liu_2023_CVPR, author = {Liu, Sun-Ao and Zhang, Yiheng and Qiu, Zhaofan and Xie, Hongtao and Zhang, Yongdong and Yao, Ting}, title = {Learning Orthogonal Prototypes for Generalized Few-Shot Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11319-11328} }
Are Deep Neural Networks SMARTer Than Second Graders?: Anoop Cherian,

Kuan-Chuan Peng,

Suhas Lohit,

Kevin A. Smith,

Joshua B. Tenenbaum; [pdf] [arXiv]
[bibtex]
@InProceedings{Cherian_2023_CVPR, author = {Cherian, Anoop and Peng, Kuan-Chuan and Lohit, Suhas and Smith, Kevin A. and Tenenbaum, Joshua B.}, title = {Are Deep Neural Networks SMARTer Than Second Graders?}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10834-10844} }
Bi-Level Meta-Learning for Few-Shot Domain Generalization: Xiaorong Qin,

Xinhang Song,

Shuqiang Jiang; [pdf] [supp]
[bibtex]
@InProceedings{Qin_2023_CVPR, author = {Qin, Xiaorong and Song, Xinhang and Jiang, Shuqiang}, title = {Bi-Level Meta-Learning for Few-Shot Domain Generalization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15900-15910} }
Multi-Modal Learning With Missing Modality via Shared-Specific Feature Modelling: Hu Wang,

Yuanhong Chen,

Congbo Ma,

Jodie Avery,

Louise Hull,

Gustavo Carneiro; [pdf]
[bibtex]
@InProceedings{Wang_2023_CVPR, author = {Wang, Hu and Chen, Yuanhong and Ma, Congbo and Avery, Jodie and Hull, Louise and Carneiro, Gustavo}, title = {Multi-Modal Learning With Missing Modality via Shared-Specific Feature Modelling}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15878-15887} }
DisWOT: Student Architecture Search for Distillation WithOut Training: Peijie Dong,

Lujun Li,

Zimian Wei; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Dong_2023_CVPR, author = {Dong, Peijie and Li, Lujun and Wei, Zimian}, title = {DisWOT: Student Architecture Search for Distillation WithOut Training}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11898-11908} }
Logical Consistency and Greater Descriptive Power for Facial Hair Attribute Learning: Haiyu Wu,

Grace Bezold,

Aman Bhatta,

Kevin W. Bowyer; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wu_2023_CVPR, author = {Wu, Haiyu and Bezold, Grace and Bhatta, Aman and Bowyer, Kevin W.}, title = {Logical Consistency and Greater Descriptive Power for Facial Hair Attribute Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8588-8597} }
Spatio-Temporal Pixel-Level Contrastive Learning-Based Source-Free Domain Adaptation for Video Semantic Segmentation: Shao-Yuan Lo,

Poojan Oza,

Sumanth Chennupati,

Alejandro Galindo,

Vishal M. Patel; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Lo_2023_CVPR, author = {Lo, Shao-Yuan and Oza, Poojan and Chennupati, Sumanth and Galindo, Alejandro and Patel, Vishal M.}, title = {Spatio-Temporal Pixel-Level Contrastive Learning-Based Source-Free Domain Adaptation for Video Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10534-10543} }
InternImage: Exploring Large-Scale Vision Foundation Models With Deformable Convolutions: Wenhai Wang,

Jifeng Dai,

Zhe Chen,

Zhenhang Huang,

Zhiqi Li,

Xizhou Zhu,

Xiaowei Hu,

Tong Lu,

Lewei Lu,

Hongsheng Li,

Xiaogang Wang,

Yu Qiao; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2023_CVPR, author = {Wang, Wenhai and Dai, Jifeng and Chen, Zhe and Huang, Zhenhang and Li, Zhiqi and Zhu, Xizhou and Hu, Xiaowei and Lu, Tong and Lu, Lewei and Li, Hongsheng and Wang, Xiaogang and Qiao, Yu}, title = {InternImage: Exploring Large-Scale Vision Foundation Models With Deformable Convolutions}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14408-14419} }
DAA: A Delta Age AdaIN Operation for Age Estimation via Binary Code Transformer: Ping Chen,

Xingpeng Zhang,

Ye Li,

Ju Tao,

Bin Xiao,

Bing Wang,

Zongjie Jiang; [pdf] [arXiv]
[bibtex]
@InProceedings{Chen_2023_CVPR, author = {Chen, Ping and Zhang, Xingpeng and Li, Ye and Tao, Ju and Xiao, Bin and Wang, Bing and Jiang, Zongjie}, title = {DAA: A Delta Age AdaIN Operation for Age Estimation via Binary Code Transformer}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15836-15845} }
Mind the Label Shift of Augmentation-Based Graph OOD Generalization: Junchi Yu,

Jian Liang,

Ran He; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yu_2023_CVPR, author = {Yu, Junchi and Liang, Jian and He, Ran}, title = {Mind the Label Shift of Augmentation-Based Graph OOD Generalization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11620-11630} }
Unsupervised Intrinsic Image Decomposition With LiDAR Intensity: Shogo Sato,

Yasuhiro Yao,

Taiga Yoshida,

Takuhiro Kaneko,

Shingo Ando,

Jun Shimamura; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Sato_2023_CVPR, author = {Sato, Shogo and Yao, Yasuhiro and Yoshida, Taiga and Kaneko, Takuhiro and Ando, Shingo and Shimamura, Jun}, title = {Unsupervised Intrinsic Image Decomposition With LiDAR Intensity}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13466-13475} }
PET-NeuS: Positional Encoding Tri-Planes for Neural Surfaces: Yiqun Wang,

Ivan Skorokhodov,

Peter Wonka; [pdf] [supp]
[bibtex]
@InProceedings{Wang_2023_CVPR, author = {Wang, Yiqun and Skorokhodov, Ivan and Wonka, Peter}, title = {PET-NeuS: Positional Encoding Tri-Planes for Neural Surfaces}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12598-12607} }
ZegCLIP: Towards Adapting CLIP for Zero-Shot Semantic Segmentation: Ziqin Zhou,

Yinjie Lei,

Bowen Zhang,

Lingqiao Liu,

Yifan Liu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhou_2023_CVPR, author = {Zhou, Ziqin and Lei, Yinjie and Zhang, Bowen and Liu, Lingqiao and Liu, Yifan}, title = {ZegCLIP: Towards Adapting CLIP for Zero-Shot Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11175-11185} }
AdaptiveMix: Improving GAN Training via Feature Space Shrinkage: Haozhe Liu,

Wentian Zhang,

Bing Li,

Haoqian Wu,

Nanjun He,

Yawen Huang,

Yuexiang Li,

Bernard Ghanem,

Yefeng Zheng; [pdf] [supp]
[bibtex]
@InProceedings{Liu_2023_CVPR, author = {Liu, Haozhe and Zhang, Wentian and Li, Bing and Wu, Haoqian and He, Nanjun and Huang, Yawen and Li, Yuexiang and Ghanem, Bernard and Zheng, Yefeng}, title = {AdaptiveMix: Improving GAN Training via Feature Space Shrinkage}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16219-16229} }
Specialist Diffusion: Plug-and-Play Sample-Efficient Fine-Tuning of Text-to-Image Diffusion Models To Learn Any Unseen Style: Haoming Lu,

Hazarapet Tunanyan,

Kai Wang,

Shant Navasardyan,

Zhangyang Wang,

Humphrey Shi; [pdf] [supp]
[bibtex]
@InProceedings{Lu_2023_CVPR, author = {Lu, Haoming and Tunanyan, Hazarapet and Wang, Kai and Navasardyan, Shant and Wang, Zhangyang and Shi, Humphrey}, title = {Specialist Diffusion: Plug-and-Play Sample-Efficient Fine-Tuning of Text-to-Image Diffusion Models To Learn Any Unseen Style}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14267-14276} }
HyperCUT: Video Sequence From a Single Blurry Image Using Unsupervised Ordering: Bang-Dang Pham,

Phong Tran,

Anh Tran,

Cuong Pham,

Rang Nguyen,

Minh Hoai; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Pham_2023_CVPR, author = {Pham, Bang-Dang and Tran, Phong and Tran, Anh and Pham, Cuong and Nguyen, Rang and Hoai, Minh}, title = {HyperCUT: Video Sequence From a Single Blurry Image Using Unsupervised Ordering}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9843-9852} }
Can't Steal? Cont-Steal! Contrastive Stealing Attacks Against Image Encoders: Zeyang Sha,

Xinlei He,

Ning Yu,

Michael Backes,

Yang Zhang; [pdf] [supp]
[bibtex]
@InProceedings{Sha_2023_CVPR, author = {Sha, Zeyang and He, Xinlei and Yu, Ning and Backes, Michael and Zhang, Yang}, title = {Can't Steal? Cont-Steal! Contrastive Stealing Attacks Against Image Encoders}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16373-16383} }
Nerflets: Local Radiance Fields for Efficient Structure-Aware 3D Scene Representation From 2D Supervision: Xiaoshuai Zhang,

Abhijit Kundu,

Thomas Funkhouser,

Leonidas Guibas,

Hao Su,

Kyle Genova; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhang_2023_CVPR, author = {Zhang, Xiaoshuai and Kundu, Abhijit and Funkhouser, Thomas and Guibas, Leonidas and Su, Hao and Genova, Kyle}, title = {Nerflets: Local Radiance Fields for Efficient Structure-Aware 3D Scene Representation From 2D Supervision}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8274-8284} }
CLIP Is Also an Efficient Segmenter: A Text-Driven Approach for Weakly Supervised Semantic Segmentation: Yuqi Lin,

Minghao Chen,

Wenxiao Wang,

Boxi Wu,

Ke Li,

Binbin Lin,

Haifeng Liu,

Xiaofei He; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Lin_2023_CVPR, author = {Lin, Yuqi and Chen, Minghao and Wang, Wenxiao and Wu, Boxi and Li, Ke and Lin, Binbin and Liu, Haifeng and He, Xiaofei}, title = {CLIP Is Also an Efficient Segmenter: A Text-Driven Approach for Weakly Supervised Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15305-15314} }
Spatially Adaptive Self-Supervised Learning for Real-World Image Denoising: Junyi Li,

Zhilu Zhang,

Xiaoyu Liu,

Chaoyu Feng,

Xiaotao Wang,

Lei Lei,

Wangmeng Zuo; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Li_2023_CVPR, author = {Li, Junyi and Zhang, Zhilu and Liu, Xiaoyu and Feng, Chaoyu and Wang, Xiaotao and Lei, Lei and Zuo, Wangmeng}, title = {Spatially Adaptive Self-Supervised Learning for Real-World Image Denoising}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9914-9924} }
From Images to Textual Prompts: Zero-Shot Visual Question Answering With Frozen Large Language Models: Jiaxian Guo,

Junnan Li,

Dongxu Li,

Anthony Meng Huat Tiong,

Boyang Li,

Dacheng Tao,

Steven Hoi; [pdf] [supp]
[bibtex]
@InProceedings{Guo_2023_CVPR, author = {Guo, Jiaxian and Li, Junnan and Li, Dongxu and Tiong, Anthony Meng Huat and Li, Boyang and Tao, Dacheng and Hoi, Steven}, title = {From Images to Textual Prompts: Zero-Shot Visual Question Answering With Frozen Large Language Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10867-10877} }
Observation-Centric SORT: Rethinking SORT for Robust Multi-Object Tracking: Jinkun Cao,

Jiangmiao Pang,

Xinshuo Weng,

Rawal Khirodkar,

Kris Kitani; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Cao_2023_CVPR, author = {Cao, Jinkun and Pang, Jiangmiao and Weng, Xinshuo and Khirodkar, Rawal and Kitani, Kris}, title = {Observation-Centric SORT: Rethinking SORT for Robust Multi-Object Tracking}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9686-9696} }
Transformer-Based Learned Optimization: Erik Gärtner,

Luke Metz,

Mykhaylo Andriluka,

C. Daniel Freeman,

Cristian Sminchisescu; [pdf] [supp]
[bibtex]
@InProceedings{Gartner_2023_CVPR, author = {G\"artner, Erik and Metz, Luke and Andriluka, Mykhaylo and Freeman, C. Daniel and Sminchisescu, Cristian}, title = {Transformer-Based Learned Optimization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11970-11979} }
Quantum-Inspired Spectral-Spatial Pyramid Network for Hyperspectral Image Classification: Jie Zhang,

Yongshan Zhang,

Yicong Zhou; [pdf]
[bibtex]
@InProceedings{Zhang_2023_CVPR, author = {Zhang, Jie and Zhang, Yongshan and Zhou, Yicong}, title = {Quantum-Inspired Spectral-Spatial Pyramid Network for Hyperspectral Image Classification}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9925-9934} }
Towards Benchmarking and Assessing Visual Naturalness of Physical World Adversarial Attacks: Simin Li,

Shuning Zhang,

Gujun Chen,

Dong Wang,

Pu Feng,

Jiakai Wang,

Aishan Liu,

Xin Yi,

Xianglong Liu; [pdf] [supp]
[bibtex]
@InProceedings{Li_2023_CVPR, author = {Li, Simin and Zhang, Shuning and Chen, Gujun and Wang, Dong and Feng, Pu and Wang, Jiakai and Liu, Aishan and Yi, Xin and Liu, Xianglong}, title = {Towards Benchmarking and Assessing Visual Naturalness of Physical World Adversarial Attacks}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12324-12333} }
Visual Prompt Multi-Modal Tracking: Jiawen Zhu,

Simiao Lai,

Xin Chen,

Dong Wang,

Huchuan Lu; [pdf] [arXiv]
[bibtex]
@InProceedings{Zhu_2023_CVPR, author = {Zhu, Jiawen and Lai, Simiao and Chen, Xin and Wang, Dong and Lu, Huchuan}, title = {Visual Prompt Multi-Modal Tracking}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9516-9526} }
Dealing With Cross-Task Class Discrimination in Online Continual Learning: Yiduo Guo,

Bing Liu,

Dongyan Zhao; [pdf] [supp]
[bibtex]
@InProceedings{Guo_2023_CVPR, author = {Guo, Yiduo and Liu, Bing and Zhao, Dongyan}, title = {Dealing With Cross-Task Class Discrimination in Online Continual Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11878-11887} }
GIVL: Improving Geographical Inclusivity of Vision-Language Models With Pre-Training Methods: Da Yin,

Feng Gao,

Govind Thattai,

Michael Johnston,

Kai-Wei Chang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yin_2023_CVPR, author = {Yin, Da and Gao, Feng and Thattai, Govind and Johnston, Michael and Chang, Kai-Wei}, title = {GIVL: Improving Geographical Inclusivity of Vision-Language Models With Pre-Training Methods}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10951-10961} }
Bi3D: Bi-Domain Active Learning for Cross-Domain 3D Object Detection: Jiakang Yuan,

Bo Zhang,

Xiangchao Yan,

Tao Chen,

Botian Shi,

Yikang Li,

Yu Qiao; [pdf] [arXiv]
[bibtex]
@InProceedings{Yuan_2023_CVPR, author = {Yuan, Jiakang and Zhang, Bo and Yan, Xiangchao and Chen, Tao and Shi, Botian and Li, Yikang and Qiao, Yu}, title = {Bi3D: Bi-Domain Active Learning for Cross-Domain 3D Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15599-15608} }
Towards Fast Adaptation of Pretrained Contrastive Models for Multi-Channel Video-Language Retrieval: Xudong Lin,

Simran Tiwari,

Shiyuan Huang,

Manling Li,

Mike Zheng Shou,

Heng Ji,

Shih-Fu Chang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Lin_2023_CVPR, author = {Lin, Xudong and Tiwari, Simran and Huang, Shiyuan and Li, Manling and Shou, Mike Zheng and Ji, Heng and Chang, Shih-Fu}, title = {Towards Fast Adaptation of Pretrained Contrastive Models for Multi-Channel Video-Language Retrieval}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14846-14855} }
Crowd3D: Towards Hundreds of People Reconstruction From a Single Image: Hao Wen,

Jing Huang,

Huili Cui,

Haozhe Lin,

Yu-Kun Lai,

Lu Fang,

Kun Li; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wen_2023_CVPR, author = {Wen, Hao and Huang, Jing and Cui, Huili and Lin, Haozhe and Lai, Yu-Kun and Fang, Lu and Li, Kun}, title = {Crowd3D: Towards Hundreds of People Reconstruction From a Single Image}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8937-8946} }
Highly Confident Local Structure Based Consensus Graph Learning for Incomplete Multi-View Clustering: Jie Wen,

Chengliang Liu,

Gehui Xu,

Zhihao Wu,

Chao Huang,

Lunke Fei,

Yong Xu; [pdf] [supp]
[bibtex]
@InProceedings{Wen_2023_CVPR, author = {Wen, Jie and Liu, Chengliang and Xu, Gehui and Wu, Zhihao and Huang, Chao and Fei, Lunke and Xu, Yong}, title = {Highly Confident Local Structure Based Consensus Graph Learning for Incomplete Multi-View Clustering}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15712-15721} }
Humans As Light Bulbs: 3D Human Reconstruction From Thermal Reflection: Ruoshi Liu,

Carl Vondrick; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Liu_2023_CVPR, author = {Liu, Ruoshi and Vondrick, Carl}, title = {Humans As Light Bulbs: 3D Human Reconstruction From Thermal Reflection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12531-12542} }
CafeBoost: Causal Feature Boost To Eliminate Task-Induced Bias for Class Incremental Learning: Benliu Qiu,

Hongliang Li,

Haitao Wen,

Heqian Qiu,

Lanxiao Wang,

Fanman Meng,

Qingbo Wu,

Lili Pan; [pdf] [supp]
[bibtex]
@InProceedings{Qiu_2023_CVPR, author = {Qiu, Benliu and Li, Hongliang and Wen, Haitao and Qiu, Heqian and Wang, Lanxiao and Meng, Fanman and Wu, Qingbo and Pan, Lili}, title = {CafeBoost: Causal Feature Boost To Eliminate Task-Induced Bias for Class Incremental Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16016-16025} }
A-La-Carte Prompt Tuning (APT): Combining Distinct Data via Composable Prompting: Benjamin Bowman,

Alessandro Achille,

Luca Zancato,

Matthew Trager,

Pramuditha Perera,

Giovanni Paolini,

Stefano Soatto; [pdf] [supp]
[bibtex]
@InProceedings{Bowman_2023_CVPR, author = {Bowman, Benjamin and Achille, Alessandro and Zancato, Luca and Trager, Matthew and Perera, Pramuditha and Paolini, Giovanni and Soatto, Stefano}, title = {A-La-Carte Prompt Tuning (APT): Combining Distinct Data via Composable Prompting}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14984-14993} }
ViLEM: Visual-Language Error Modeling for Image-Text Retrieval: Yuxin Chen,

Zongyang Ma,

Ziqi Zhang,

Zhongang Qi,

Chunfeng Yuan,

Ying Shan,

Bing Li,

Weiming Hu,

Xiaohu Qie,

Jianping Wu; [pdf] [supp]
[bibtex]
@InProceedings{Chen_2023_CVPR, author = {Chen, Yuxin and Ma, Zongyang and Zhang, Ziqi and Qi, Zhongang and Yuan, Chunfeng and Shan, Ying and Li, Bing and Hu, Weiming and Qie, Xiaohu and Wu, Jianping}, title = {ViLEM: Visual-Language Error Modeling for Image-Text Retrieval}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11018-11027} }
Egocentric Auditory Attention Localization in Conversations: Fiona Ryan,

Hao Jiang,

Abhinav Shukla,

James M. Rehg,

Vamsi Krishna Ithapu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ryan_2023_CVPR, author = {Ryan, Fiona and Jiang, Hao and Shukla, Abhinav and Rehg, James M. and Ithapu, Vamsi Krishna}, title = {Egocentric Auditory Attention Localization in Conversations}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14663-14674} }
Open-World Multi-Task Control Through Goal-Aware Representation Learning and Adaptive Horizon Prediction: Shaofei Cai,

Zihao Wang,

Xiaojian Ma,

Anji Liu,

Yitao Liang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Cai_2023_CVPR, author = {Cai, Shaofei and Wang, Zihao and Ma, Xiaojian and Liu, Anji and Liang, Yitao}, title = {Open-World Multi-Task Control Through Goal-Aware Representation Learning and Adaptive Horizon Prediction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13734-13744} }
MoDi: Unconditional Motion Synthesis From Diverse Data: Sigal Raab,

Inbal Leibovitch,

Peizhuo Li,

Kfir Aberman,

Olga Sorkine-Hornung,

Daniel Cohen-Or; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Raab_2023_CVPR, author = {Raab, Sigal and Leibovitch, Inbal and Li, Peizhuo and Aberman, Kfir and Sorkine-Hornung, Olga and Cohen-Or, Daniel}, title = {MoDi: Unconditional Motion Synthesis From Diverse Data}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13873-13883} }
Visual Localization Using Imperfect 3D Models From the Internet: Vojtech Panek,

Zuzana Kukelova,

Torsten Sattler; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Panek_2023_CVPR, author = {Panek, Vojtech and Kukelova, Zuzana and Sattler, Torsten}, title = {Visual Localization Using Imperfect 3D Models From the Internet}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13175-13186} }
PVO: Panoptic Visual Odometry: Weicai Ye,

Xinyue Lan,

Shuo Chen,

Yuhang Ming,

Xingyuan Yu,

Hujun Bao,

Zhaopeng Cui,

Guofeng Zhang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ye_2023_CVPR, author = {Ye, Weicai and Lan, Xinyue and Chen, Shuo and Ming, Yuhang and Yu, Xingyuan and Bao, Hujun and Cui, Zhaopeng and Zhang, Guofeng}, title = {PVO: Panoptic Visual Odometry}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9579-9589} }
Generative Diffusion Prior for Unified Image Restoration and Enhancement: Ben Fei,

Zhaoyang Lyu,

Liang Pan,

Junzhe Zhang,

Weidong Yang,

Tianyue Luo,

Bo Zhang,

Bo Dai; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Fei_2023_CVPR, author = {Fei, Ben and Lyu, Zhaoyang and Pan, Liang and Zhang, Junzhe and Yang, Weidong and Luo, Tianyue and Zhang, Bo and Dai, Bo}, title = {Generative Diffusion Prior for Unified Image Restoration and Enhancement}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9935-9946} }
Real-Time Controllable Denoising for Image and Video: Zhaoyang Zhang,

Yitong Jiang,

Wenqi Shao,

Xiaogang Wang,

Ping Luo,

Kaimo Lin,

Jinwei Gu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhang_2023_CVPR, author = {Zhang, Zhaoyang and Jiang, Yitong and Shao, Wenqi and Wang, Xiaogang and Luo, Ping and Lin, Kaimo and Gu, Jinwei}, title = {Real-Time Controllable Denoising for Image and Video}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14028-14038} }
ISBNet: A 3D Point Cloud Instance Segmentation Network With Instance-Aware Sampling and Box-Aware Dynamic Convolution: Tuan Duc Ngo,

Binh-Son Hua,

Khoi Nguyen; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ngo_2023_CVPR, author = {Ngo, Tuan Duc and Hua, Binh-Son and Nguyen, Khoi}, title = {ISBNet: A 3D Point Cloud Instance Segmentation Network With Instance-Aware Sampling and Box-Aware Dynamic Convolution}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13550-13559} }
IterativePFN: True Iterative Point Cloud Filtering: Dasith de Silva Edirimuni,

Xuequan Lu,

Zhiwen Shao,

Gang Li,

Antonio Robles-Kelly,

Ying He; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{de_Silva_Edirimuni_2023_CVPR, author = {de Silva Edirimuni, Dasith and Lu, Xuequan and Shao, Zhiwen and Li, Gang and Robles-Kelly, Antonio and He, Ying}, title = {IterativePFN: True Iterative Point Cloud Filtering}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13530-13539} }
CLIP-S4: Language-Guided Self-Supervised Semantic Segmentation: Wenbin He,

Suphanut Jamonnak,

Liang Gou,

Liu Ren; [pdf] [supp]
[bibtex]
@InProceedings{He_2023_CVPR, author = {He, Wenbin and Jamonnak, Suphanut and Gou, Liang and Ren, Liu}, title = {CLIP-S4: Language-Guided Self-Supervised Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11207-11216} }
Deep Incomplete Multi-View Clustering With Cross-View Partial Sample and Prototype Alignment: Jiaqi Jin,

Siwei Wang,

Zhibin Dong,

Xinwang Liu,

En Zhu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Jin_2023_CVPR, author = {Jin, Jiaqi and Wang, Siwei and Dong, Zhibin and Liu, Xinwang and Zhu, En}, title = {Deep Incomplete Multi-View Clustering With Cross-View Partial Sample and Prototype Alignment}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11600-11609} }
Revisiting Multimodal Representation in Contrastive Learning: From Patch and Token Embeddings to Finite Discrete Tokens: Yuxiao Chen,

Jianbo Yuan,

Yu Tian,

Shijie Geng,

Xinyu Li,

Ding Zhou,

Dimitris N. Metaxas,

Hongxia Yang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chen_2023_CVPR, author = {Chen, Yuxiao and Yuan, Jianbo and Tian, Yu and Geng, Shijie and Li, Xinyu and Zhou, Ding and Metaxas, Dimitris N. and Yang, Hongxia}, title = {Revisiting Multimodal Representation in Contrastive Learning: From Patch and Token Embeddings to Finite Discrete Tokens}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15095-15104} }
Heterogeneous Continual Learning: Divyam Madaan,

Hongxu Yin,

Wonmin Byeon,

Jan Kautz,

Pavlo Molchanov; [pdf] [supp]
[bibtex]
@InProceedings{Madaan_2023_CVPR, author = {Madaan, Divyam and Yin, Hongxu and Byeon, Wonmin and Kautz, Jan and Molchanov, Pavlo}, title = {Heterogeneous Continual Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15985-15995} }
Object Pose Estimation With Statistical Guarantees: Conformal Keypoint Detection and Geometric Uncertainty Propagation: Heng Yang,

Marco Pavone; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yang_2023_CVPR, author = {Yang, Heng and Pavone, Marco}, title = {Object Pose Estimation With Statistical Guarantees: Conformal Keypoint Detection and Geometric Uncertainty Propagation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8947-8958} }
3D-Aware Multi-Class Image-to-Image Translation With NeRFs: Senmao Li,

Joost van de Weijer,

Yaxing Wang,

Fahad Shahbaz Khan,

Meiqin Liu,

Jian Yang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Li_2023_CVPR, author = {Li, Senmao and van de Weijer, Joost and Wang, Yaxing and Khan, Fahad Shahbaz and Liu, Meiqin and Yang, Jian}, title = {3D-Aware Multi-Class Image-to-Image Translation With NeRFs}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12652-12662} }
Unsupervised Visible-Infrared Person Re-Identification via Progressive Graph Matching and Alternate Learning: Zesen Wu,

Mang Ye; [pdf] [supp]
[bibtex]
@InProceedings{Wu_2023_CVPR, author = {Wu, Zesen and Ye, Mang}, title = {Unsupervised Visible-Infrared Person Re-Identification via Progressive Graph Matching and Alternate Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9548-9558} }
Hierarchical B-Frame Video Coding Using Two-Layer CANF Without Motion Coding: David Alexandre,

Hsueh-Ming Hang,

Wen-Hsiao Peng; [pdf] [supp]
[bibtex]
@InProceedings{Alexandre_2023_CVPR, author = {Alexandre, David and Hang, Hsueh-Ming and Peng, Wen-Hsiao}, title = {Hierarchical B-Frame Video Coding Using Two-Layer CANF Without Motion Coding}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10249-10258} }
Seeing Through the Glass: Neural 3D Reconstruction of Object Inside a Transparent Container: Jinguang Tong,

Sundaram Muthu,

Fahira Afzal Maken,

Chuong Nguyen,

Hongdong Li; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Tong_2023_CVPR, author = {Tong, Jinguang and Muthu, Sundaram and Maken, Fahira Afzal and Nguyen, Chuong and Li, Hongdong}, title = {Seeing Through the Glass: Neural 3D Reconstruction of Object Inside a Transparent Container}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12555-12564} }
Neural Voting Field for Camera-Space 3D Hand Pose Estimation: Lin Huang,

Chung-Ching Lin,

Kevin Lin,

Lin Liang,

Lijuan Wang,

Junsong Yuan,

Zicheng Liu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Huang_2023_CVPR, author = {Huang, Lin and Lin, Chung-Ching and Lin, Kevin and Liang, Lin and Wang, Lijuan and Yuan, Junsong and Liu, Zicheng}, title = {Neural Voting Field for Camera-Space 3D Hand Pose Estimation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8969-8978} }
Visual Recognition-Driven Image Restoration for Multiple Degradation With Intrinsic Semantics Recovery: Zizheng Yang,

Jie Huang,

Jiahao Chang,

Man Zhou,

Hu Yu,

Jinghao Zhang,

Feng Zhao; [pdf] [supp]
[bibtex]
@InProceedings{Yang_2023_CVPR, author = {Yang, Zizheng and Huang, Jie and Chang, Jiahao and Zhou, Man and Yu, Hu and Zhang, Jinghao and Zhao, Feng}, title = {Visual Recognition-Driven Image Restoration for Multiple Degradation With Intrinsic Semantics Recovery}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14059-14070} }
Knowledge Combination To Learn Rotated Detection Without Rotated Annotation: Tianyu Zhu,

Bryce Ferenczi,

Pulak Purkait,

Tom Drummond,

Hamid Rezatofighi,

Anton van den Hengel; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhu_2023_CVPR, author = {Zhu, Tianyu and Ferenczi, Bryce and Purkait, Pulak and Drummond, Tom and Rezatofighi, Hamid and van den Hengel, Anton}, title = {Knowledge Combination To Learn Rotated Detection Without Rotated Annotation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15518-15527} }
Pointersect: Neural Rendering With Cloud-Ray Intersection: Jen-Hao Rick Chang,

Wei-Yu Chen,

Anurag Ranjan,

Kwang Moo Yi,

Oncel Tuzel; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chang_2023_CVPR, author = {Chang, Jen-Hao Rick and Chen, Wei-Yu and Ranjan, Anurag and Yi, Kwang Moo and Tuzel, Oncel}, title = {Pointersect: Neural Rendering With Cloud-Ray Intersection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8359-8369} }
Beyond Attentive Tokens: Incorporating Token Importance and Diversity for Efficient Vision Transformers: Sifan Long,

Zhen Zhao,

Jimin Pi,

Shengsheng Wang,

Jingdong Wang; [pdf] [arXiv]
[bibtex]
@InProceedings{Long_2023_CVPR, author = {Long, Sifan and Zhao, Zhen and Pi, Jimin and Wang, Shengsheng and Wang, Jingdong}, title = {Beyond Attentive Tokens: Incorporating Token Importance and Diversity for Efficient Vision Transformers}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10334-10343} }
STDLens: Model Hijacking-Resilient Federated Learning for Object Detection: Ka-Ho Chow,

Ling Liu,

Wenqi Wei,

Fatih Ilhan,

Yanzhao Wu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chow_2023_CVPR, author = {Chow, Ka-Ho and Liu, Ling and Wei, Wenqi and Ilhan, Fatih and Wu, Yanzhao}, title = {STDLens: Model Hijacking-Resilient Federated Learning for Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16343-16351} }
MagicPony: Learning Articulated 3D Animals in the Wild: Shangzhe Wu,

Ruining Li,

Tomas Jakab,

Christian Rupprecht,

Andrea Vedaldi; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wu_2023_CVPR, author = {Wu, Shangzhe and Li, Ruining and Jakab, Tomas and Rupprecht, Christian and Vedaldi, Andrea}, title = {MagicPony: Learning Articulated 3D Animals in the Wild}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8792-8802} }
Affordances From Human Videos as a Versatile Representation for Robotics: Shikhar Bahl,

Russell Mendonca,

Lili Chen,

Unnat Jain,

Deepak Pathak; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Bahl_2023_CVPR, author = {Bahl, Shikhar and Mendonca, Russell and Chen, Lili and Jain, Unnat and Pathak, Deepak}, title = {Affordances From Human Videos as a Versatile Representation for Robotics}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13778-13790} }
AMT: All-Pairs Multi-Field Transforms for Efficient Frame Interpolation: Zhen Li,

Zuo-Liang Zhu,

Ling-Hao Han,

Qibin Hou,

Chun-Le Guo,

Ming-Ming Cheng; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Li_2023_CVPR, author = {Li, Zhen and Zhu, Zuo-Liang and Han, Ling-Hao and Hou, Qibin and Guo, Chun-Le and Cheng, Ming-Ming}, title = {AMT: All-Pairs Multi-Field Transforms for Efficient Frame Interpolation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9801-9810} }
Toward RAW Object Detection: A New Benchmark and a New Model: Ruikang Xu,

Chang Chen,

Jingyang Peng,

Cheng Li,

Yibin Huang,

Fenglong Song,

Youliang Yan,

Zhiwei Xiong; [pdf] [supp]
[bibtex]
@InProceedings{Xu_2023_CVPR, author = {Xu, Ruikang and Chen, Chang and Peng, Jingyang and Li, Cheng and Huang, Yibin and Song, Fenglong and Yan, Youliang and Xiong, Zhiwei}, title = {Toward RAW Object Detection: A New Benchmark and a New Model}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13384-13393} }
Music-Driven Group Choreography: Nhat Le,

Thang Pham,

Tuong Do,

Erman Tjiputra,

Quang D. Tran,

Anh Nguyen; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Le_2023_CVPR, author = {Le, Nhat and Pham, Thang and Do, Tuong and Tjiputra, Erman and Tran, Quang D. and Nguyen, Anh}, title = {Music-Driven Group Choreography}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8673-8682} }
Cascade Evidential Learning for Open-World Weakly-Supervised Temporal Action Localization: Mengyuan Chen,

Junyu Gao,

Changsheng Xu; [pdf]
[bibtex]
@InProceedings{Chen_2023_CVPR, author = {Chen, Mengyuan and Gao, Junyu and Xu, Changsheng}, title = {Cascade Evidential Learning for Open-World Weakly-Supervised Temporal Action Localization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14741-14750} }
STAR Loss: Reducing Semantic Ambiguity in Facial Landmark Detection: Zhenglin Zhou,

Huaxia Li,

Hong Liu,

Nanyang Wang,

Gang Yu,

Rongrong Ji; [pdf] [supp]
[bibtex]
@InProceedings{Zhou_2023_CVPR, author = {Zhou, Zhenglin and Li, Huaxia and Liu, Hong and Wang, Nanyang and Yu, Gang and Ji, Rongrong}, title = {STAR Loss: Reducing Semantic Ambiguity in Facial Landmark Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15475-15484} }
Seeing What You Said: Talking Face Generation Guided by a Lip Reading Expert: Jiadong Wang,

Xinyuan Qian,

Malu Zhang,

Robby T. Tan,

Haizhou Li; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2023_CVPR, author = {Wang, Jiadong and Qian, Xinyuan and Zhang, Malu and Tan, Robby T. and Li, Haizhou}, title = {Seeing What You Said: Talking Face Generation Guided by a Lip Reading Expert}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14653-14662} }
SimpSON: Simplifying Photo Cleanup With Single-Click Distracting Object Segmentation Network: Chuong Huynh,

Yuqian Zhou,

Zhe Lin,

Connelly Barnes,

Eli Shechtman,

Sohrab Amirghodsi,

Abhinav Shrivastava; [pdf] [supp]
[bibtex]
@InProceedings{Huynh_2023_CVPR, author = {Huynh, Chuong and Zhou, Yuqian and Lin, Zhe and Barnes, Connelly and Shechtman, Eli and Amirghodsi, Sohrab and Shrivastava, Abhinav}, title = {SimpSON: Simplifying Photo Cleanup With Single-Click Distracting Object Segmentation Network}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14518-14527} }
Learning Neural Duplex Radiance Fields for Real-Time View Synthesis: Ziyu Wan,

Christian Richardt,

Aljaž Božič,

Chao Li,

Vijay Rengarajan,

Seonghyeon Nam,

Xiaoyu Xiang,

Tuotuo Li,

Bo Zhu,

Rakesh Ranjan,

Jing Liao; [pdf] [supp]
[bibtex]
@InProceedings{Wan_2023_CVPR, author = {Wan, Ziyu and Richardt, Christian and Bo\v{z}i\v{c}, Alja\v{z} and Li, Chao and Rengarajan, Vijay and Nam, Seonghyeon and Xiang, Xiaoyu and Li, Tuotuo and Zhu, Bo and Ranjan, Rakesh and Liao, Jing}, title = {Learning Neural Duplex Radiance Fields for Real-Time View Synthesis}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8307-8316} }
Towards Modality-Agnostic Person Re-Identification With Descriptive Query: Cuiqun Chen,

Mang Ye,

Ding Jiang; [pdf]
[bibtex]
@InProceedings{Chen_2023_CVPR, author = {Chen, Cuiqun and Ye, Mang and Jiang, Ding}, title = {Towards Modality-Agnostic Person Re-Identification With Descriptive Query}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15128-15137} }
An In-Depth Exploration of Person Re-Identification and Gait Recognition in Cloth-Changing Conditions: Weijia Li,

Saihui Hou,

Chunjie Zhang,

Chunshui Cao,

Xu Liu,

Yongzhen Huang,

Yao Zhao; [pdf]
[bibtex]
@InProceedings{Li_2023_CVPR, author = {Li, Weijia and Hou, Saihui and Zhang, Chunjie and Cao, Chunshui and Liu, Xu and Huang, Yongzhen and Zhao, Yao}, title = {An In-Depth Exploration of Person Re-Identification and Gait Recognition in Cloth-Changing Conditions}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13824-13833} }
Visual Exemplar Driven Task-Prompting for Unified Perception in Autonomous Driving: Xiwen Liang,

Minzhe Niu,

Jianhua Han,

Hang Xu,

Chunjing Xu,

Xiaodan Liang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Liang_2023_CVPR, author = {Liang, Xiwen and Niu, Minzhe and Han, Jianhua and Xu, Hang and Xu, Chunjing and Liang, Xiaodan}, title = {Visual Exemplar Driven Task-Prompting for Unified Perception in Autonomous Driving}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9611-9621} }
Toward Verifiable and Reproducible Human Evaluation for Text-to-Image Generation: Mayu Otani,

Riku Togashi,

Yu Sawai,

Ryosuke Ishigami,

Yuta Nakashima,

Esa Rahtu,

Janne Heikkilä,

Shin’ichi Satoh; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Otani_2023_CVPR, author = {Otani, Mayu and Togashi, Riku and Sawai, Yu and Ishigami, Ryosuke and Nakashima, Yuta and Rahtu, Esa and Heikkil\"a, Janne and Satoh, Shin{\textquoteright}ichi}, title = {Toward Verifiable and Reproducible Human Evaluation for Text-to-Image Generation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14277-14286} }
Learning a 3D Morphable Face Reflectance Model From Low-Cost Data: Yuxuan Han,

Zhibo Wang,

Feng Xu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Han_2023_CVPR, author = {Han, Yuxuan and Wang, Zhibo and Xu, Feng}, title = {Learning a 3D Morphable Face Reflectance Model From Low-Cost Data}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8598-8608} }
Recurrent Homography Estimation Using Homography-Guided Image Warping and Focus Transformer: Si-Yuan Cao,

Runmin Zhang,

Lun Luo,

Beinan Yu,

Zehua Sheng,

Junwei Li,

Hui-Liang Shen; [pdf] [supp]
[bibtex]
@InProceedings{Cao_2023_CVPR, author = {Cao, Si-Yuan and Zhang, Runmin and Luo, Lun and Yu, Beinan and Sheng, Zehua and Li, Junwei and Shen, Hui-Liang}, title = {Recurrent Homography Estimation Using Homography-Guided Image Warping and Focus Transformer}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9833-9842} }
I2-SDF: Intrinsic Indoor Scene Reconstruction and Editing via Raytracing in Neural SDFs: Jingsen Zhu,

Yuchi Huo,

Qi Ye,

Fujun Luan,

Jifan Li,

Dianbing Xi,

Lisha Wang,

Rui Tang,

Wei Hua,

Hujun Bao,

Rui Wang; [pdf] [supp]
[bibtex]
@InProceedings{Zhu_2023_CVPR, author = {Zhu, Jingsen and Huo, Yuchi and Ye, Qi and Luan, Fujun and Li, Jifan and Xi, Dianbing and Wang, Lisha and Tang, Rui and Hua, Wei and Bao, Hujun and Wang, Rui}, title = {I2-SDF: Intrinsic Indoor Scene Reconstruction and Editing via Raytracing in Neural SDFs}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12489-12498} }
DLBD: A Self-Supervised Direct-Learned Binary Descriptor: Bin Xiao,

Yang Hu,

Bo Liu,

Xiuli Bi,

Weisheng Li,

Xinbo Gao; [pdf]
[bibtex]
@InProceedings{Xiao_2023_CVPR, author = {Xiao, Bin and Hu, Yang and Liu, Bo and Bi, Xiuli and Li, Weisheng and Gao, Xinbo}, title = {DLBD: A Self-Supervised Direct-Learned Binary Descriptor}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15846-15855} }
Fuzzy Positive Learning for Semi-Supervised Semantic Segmentation: Pengchong Qiao,

Zhidan Wei,

Yu Wang,

Zhennan Wang,

Guoli Song,

Fan Xu,

Xiangyang Ji,

Chang Liu,

Jie Chen; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Qiao_2023_CVPR, author = {Qiao, Pengchong and Wei, Zhidan and Wang, Yu and Wang, Zhennan and Song, Guoli and Xu, Fan and Ji, Xiangyang and Liu, Chang and Chen, Jie}, title = {Fuzzy Positive Learning for Semi-Supervised Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15465-15474} }
Multi-View Inverse Rendering for Large-Scale Real-World Indoor Scenes: Zhen Li,

Lingli Wang,

Mofang Cheng,

Cihui Pan,

Jiaqi Yang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Li_2023_CVPR, author = {Li, Zhen and Wang, Lingli and Cheng, Mofang and Pan, Cihui and Yang, Jiaqi}, title = {Multi-View Inverse Rendering for Large-Scale Real-World Indoor Scenes}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12499-12509} }
Boosting Transductive Few-Shot Fine-Tuning With Margin-Based Uncertainty Weighting and Probability Regularization: Ran Tao,

Hao Chen,

Marios Savvides; [pdf] [supp]
[bibtex]
@InProceedings{Tao_2023_CVPR, author = {Tao, Ran and Chen, Hao and Savvides, Marios}, title = {Boosting Transductive Few-Shot Fine-Tuning With Margin-Based Uncertainty Weighting and Probability Regularization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15752-15761} }
SMPConv: Self-Moving Point Representations for Continuous Convolution: Sanghyeon Kim,

Eunbyung Park; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kim_2023_CVPR, author = {Kim, Sanghyeon and Park, Eunbyung}, title = {SMPConv: Self-Moving Point Representations for Continuous Convolution}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10289-10299} }
PRISE: Demystifying Deep Lucas-Kanade With Strongly Star-Convex Constraints for Multimodel Image Alignment: Yiqing Zhang,

Xinming Huang,

Ziming Zhang; [pdf] [arXiv]
[bibtex]
@InProceedings{Zhang_2023_CVPR, author = {Zhang, Yiqing and Huang, Xinming and Zhang, Ziming}, title = {PRISE: Demystifying Deep Lucas-Kanade With Strongly Star-Convex Constraints for Multimodel Image Alignment}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13187-13197} }
Learning To Exploit Temporal Structure for Biomedical Vision-Language Processing: Shruthi Bannur,

Stephanie Hyland,

Qianchu Liu,

Fernando Pérez-García,

Maximilian Ilse,

Daniel C. Castro,

Benedikt Boecking,

Harshita Sharma,

Kenza Bouzid,

Anja Thieme,

Anton Schwaighofer,

Maria Wetscherek,

Matthew P. Lungren,

Aditya Nori,

Javier Alvarez-Valle,

Ozan Oktay; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Bannur_2023_CVPR, author = {Bannur, Shruthi and Hyland, Stephanie and Liu, Qianchu and P\'erez-Garc{\'\i}a, Fernando and Ilse, Maximilian and Castro, Daniel C. and Boecking, Benedikt and Sharma, Harshita and Bouzid, Kenza and Thieme, Anja and Schwaighofer, Anton and Wetscherek, Maria and Lungren, Matthew P. and Nori, Aditya and Alvarez-Valle, Javier and Oktay, Ozan}, title = {Learning To Exploit Temporal Structure for Biomedical Vision-Language Processing}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15016-15027} }
Simple Cues Lead to a Strong Multi-Object Tracker: Jenny Seidenschwarz,

Guillem Brasó,

Víctor Castro Serrano,

Ismail Elezi,

Laura Leal-Taixé; [pdf] [supp]
[bibtex]
@InProceedings{Seidenschwarz_2023_CVPR, author = {Seidenschwarz, Jenny and Bras\'o, Guillem and Serrano, V{\'\i}ctor Castro and Elezi, Ismail and Leal-Taix\'e, Laura}, title = {Simple Cues Lead to a Strong Multi-Object Tracker}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13813-13823} }
Marching-Primitives: Shape Abstraction From Signed Distance Function: Weixiao Liu,

Yuwei Wu,

Sipu Ruan,

Gregory S. Chirikjian; [pdf] [supp]
[bibtex]
@InProceedings{Liu_2023_CVPR, author = {Liu, Weixiao and Wu, Yuwei and Ruan, Sipu and Chirikjian, Gregory S.}, title = {Marching-Primitives: Shape Abstraction From Signed Distance Function}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8771-8780} }
PointVector: A Vector Representation in Point Cloud Analysis: Xin Deng,

WenYu Zhang,

Qing Ding,

XinMing Zhang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Deng_2023_CVPR, author = {Deng, Xin and Zhang, WenYu and Ding, Qing and Zhang, XinMing}, title = {PointVector: A Vector Representation in Point Cloud Analysis}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9455-9465} }
BAEFormer: Bi-Directional and Early Interaction Transformers for Bird's Eye View Semantic Segmentation: Cong Pan,

Yonghao He,

Junran Peng,

Qian Zhang,

Wei Sui,

Zhaoxiang Zhang; [pdf]
[bibtex]
@InProceedings{Pan_2023_CVPR, author = {Pan, Cong and He, Yonghao and Peng, Junran and Zhang, Qian and Sui, Wei and Zhang, Zhaoxiang}, title = {BAEFormer: Bi-Directional and Early Interaction Transformers for Bird's Eye View Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9590-9599} }
Generic-to-Specific Distillation of Masked Autoencoders: Wei Huang,

Zhiliang Peng,

Li Dong,

Furu Wei,

Jianbin Jiao,

Qixiang Ye; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Huang_2023_CVPR, author = {Huang, Wei and Peng, Zhiliang and Dong, Li and Wei, Furu and Jiao, Jianbin and Ye, Qixiang}, title = {Generic-to-Specific Distillation of Masked Autoencoders}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15996-16005} }
Combining Implicit-Explicit View Correlation for Light Field Semantic Segmentation: Ruixuan Cong,

Da Yang,

Rongshan Chen,

Sizhe Wang,

Zhenglong Cui,

Hao Sheng; [pdf]
[bibtex]
@InProceedings{Cong_2023_CVPR, author = {Cong, Ruixuan and Yang, Da and Chen, Rongshan and Wang, Sizhe and Cui, Zhenglong and Sheng, Hao}, title = {Combining Implicit-Explicit View Correlation for Light Field Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9172-9181} }
SOOD: Towards Semi-Supervised Oriented Object Detection: Wei Hua,

Dingkang Liang,

Jingyu Li,

Xiaolong Liu,

Zhikang Zou,

Xiaoqing Ye,

Xiang Bai; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Hua_2023_CVPR, author = {Hua, Wei and Liang, Dingkang and Li, Jingyu and Liu, Xiaolong and Zou, Zhikang and Ye, Xiaoqing and Bai, Xiang}, title = {SOOD: Towards Semi-Supervised Oriented Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15558-15567} }
Beyond mAP: Towards Better Evaluation of Instance Segmentation: Rohit Jena,

Lukas Zhornyak,

Nehal Doiphode,

Pratik Chaudhari,

Vivek Buch,

James Gee,

Jianbo Shi; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Jena_2023_CVPR, author = {Jena, Rohit and Zhornyak, Lukas and Doiphode, Nehal and Chaudhari, Pratik and Buch, Vivek and Gee, James and Shi, Jianbo}, title = {Beyond mAP: Towards Better Evaluation of Instance Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11309-11318} }
BASiS: Batch Aligned Spectral Embedding Space: Or Streicher,

Ido Cohen,

Guy Gilboa; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Streicher_2023_CVPR, author = {Streicher, Or and Cohen, Ido and Gilboa, Guy}, title = {BASiS: Batch Aligned Spectral Embedding Space}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10396-10405} }
DCFace: Synthetic Face Generation With Dual Condition Diffusion Model: Minchul Kim,

Feng Liu,

Anil Jain,

Xiaoming Liu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kim_2023_CVPR, author = {Kim, Minchul and Liu, Feng and Jain, Anil and Liu, Xiaoming}, title = {DCFace: Synthetic Face Generation With Dual Condition Diffusion Model}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12715-12725} }
Infinite Photorealistic Worlds Using Procedural Generation: Alexander Raistrick,

Lahav Lipson,

Zeyu Ma,

Lingjie Mei,

Mingzhe Wang,

Yiming Zuo,

Karhan Kayan,

Hongyu Wen,

Beining Han,

Yihan Wang,

Alejandro Newell,

Hei Law,

Ankit Goyal,

Kaiyu Yang,

Jia Deng; [pdf] [supp]
[bibtex]
@InProceedings{Raistrick_2023_CVPR, author = {Raistrick, Alexander and Lipson, Lahav and Ma, Zeyu and Mei, Lingjie and Wang, Mingzhe and Zuo, Yiming and Kayan, Karhan and Wen, Hongyu and Han, Beining and Wang, Yihan and Newell, Alejandro and Law, Hei and Goyal, Ankit and Yang, Kaiyu and Deng, Jia}, title = {Infinite Photorealistic Worlds Using Procedural Generation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12630-12641} }
Diversity-Measurable Anomaly Detection: Wenrui Liu,

Hong Chang,

Bingpeng Ma,

Shiguang Shan,

Xilin Chen; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Liu_2023_CVPR, author = {Liu, Wenrui and Chang, Hong and Ma, Bingpeng and Shan, Shiguang and Chen, Xilin}, title = {Diversity-Measurable Anomaly Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12147-12156} }
A Large-Scale Robustness Analysis of Video Action Recognition Models: Madeline Chantry Schiappa,

Naman Biyani,

Prudvi Kamtam,

Shruti Vyas,

Hamid Palangi,

Vibhav Vineet,

Yogesh S. Rawat; [pdf] [supp]
[bibtex]
@InProceedings{Schiappa_2023_CVPR, author = {Schiappa, Madeline Chantry and Biyani, Naman and Kamtam, Prudvi and Vyas, Shruti and Palangi, Hamid and Vineet, Vibhav and Rawat, Yogesh S.}, title = {A Large-Scale Robustness Analysis of Video Action Recognition Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14698-14708} }
Blind Video Deflickering by Neural Filtering With a Flawed Atlas: Chenyang Lei,

Xuanchi Ren,

Zhaoxiang Zhang,

Qifeng Chen; [pdf] [arXiv]
[bibtex]
@InProceedings{Lei_2023_CVPR, author = {Lei, Chenyang and Ren, Xuanchi and Zhang, Zhaoxiang and Chen, Qifeng}, title = {Blind Video Deflickering by Neural Filtering With a Flawed Atlas}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10439-10448} }
Grid-Guided Neural Radiance Fields for Large Urban Scenes: Linning Xu,

Yuanbo Xiangli,

Sida Peng,

Xingang Pan,

Nanxuan Zhao,

Christian Theobalt,

Bo Dai,

Dahua Lin; [pdf] [arXiv]
[bibtex]
@InProceedings{Xu_2023_CVPR, author = {Xu, Linning and Xiangli, Yuanbo and Peng, Sida and Pan, Xingang and Zhao, Nanxuan and Theobalt, Christian and Dai, Bo and Lin, Dahua}, title = {Grid-Guided Neural Radiance Fields for Large Urban Scenes}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8296-8306} }
FreeNeRF: Improving Few-Shot Neural Rendering With Free Frequency Regularization: Jiawei Yang,

Marco Pavone,

Yue Wang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yang_2023_CVPR, author = {Yang, Jiawei and Pavone, Marco and Wang, Yue}, title = {FreeNeRF: Improving Few-Shot Neural Rendering With Free Frequency Regularization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8254-8263} }
NeuWigs: A Neural Dynamic Model for Volumetric Hair Capture and Animation: Ziyan Wang,

Giljoo Nam,

Tuur Stuyck,

Stephen Lombardi,

Chen Cao,

Jason Saragih,

Michael Zollhöfer,

Jessica Hodgins,

Christoph Lassner; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2023_CVPR, author = {Wang, Ziyan and Nam, Giljoo and Stuyck, Tuur and Lombardi, Stephen and Cao, Chen and Saragih, Jason and Zollh\"ofer, Michael and Hodgins, Jessica and Lassner, Christoph}, title = {NeuWigs: A Neural Dynamic Model for Volumetric Hair Capture and Animation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8641-8651} }
CLIP2: Contrastive Language-Image-Point Pretraining From Real-World Point Cloud Data: Yihan Zeng,

Chenhan Jiang,

Jiageng Mao,

Jianhua Han,

Chaoqiang Ye,

Qingqiu Huang,

Dit-Yan Yeung,

Zhen Yang,

Xiaodan Liang,

Hang Xu; [pdf] [supp]
[bibtex]
@InProceedings{Zeng_2023_CVPR, author = {Zeng, Yihan and Jiang, Chenhan and Mao, Jiageng and Han, Jianhua and Ye, Chaoqiang and Huang, Qingqiu and Yeung, Dit-Yan and Yang, Zhen and Liang, Xiaodan and Xu, Hang}, title = {CLIP2: Contrastive Language-Image-Point Pretraining From Real-World Point Cloud Data}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15244-15253} }
HNeRV: A Hybrid Neural Representation for Videos: Hao Chen,

Matthew Gwilliam,

Ser-Nam Lim,

Abhinav Shrivastava; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chen_2023_CVPR, author = {Chen, Hao and Gwilliam, Matthew and Lim, Ser-Nam and Shrivastava, Abhinav}, title = {HNeRV: A Hybrid Neural Representation for Videos}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10270-10279} }
Model-Agnostic Gender Debiased Image Captioning: Yusuke Hirota,

Yuta Nakashima,

Noa Garcia; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Hirota_2023_CVPR, author = {Hirota, Yusuke and Nakashima, Yuta and Garcia, Noa}, title = {Model-Agnostic Gender Debiased Image Captioning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15191-15200} }
FitMe: Deep Photorealistic 3D Morphable Model Avatars: Alexandros Lattas,

Stylianos Moschoglou,

Stylianos Ploumpis,

Baris Gecer,

Jiankang Deng,

Stefanos Zafeiriou; [pdf] [supp]
[bibtex]
@InProceedings{Lattas_2023_CVPR, author = {Lattas, Alexandros and Moschoglou, Stylianos and Ploumpis, Stylianos and Gecer, Baris and Deng, Jiankang and Zafeiriou, Stefanos}, title = {FitMe: Deep Photorealistic 3D Morphable Model Avatars}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8629-8640} }
CLIPPO: Image-and-Language Understanding From Pixels Only: Michael Tschannen,

Basil Mustafa,

Neil Houlsby; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Tschannen_2023_CVPR, author = {Tschannen, Michael and Mustafa, Basil and Houlsby, Neil}, title = {CLIPPO: Image-and-Language Understanding From Pixels Only}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11006-11017} }
DETR With Additional Global Aggregation for Cross-Domain Weakly Supervised Object Detection: Zongheng Tang,

Yifan Sun,

Si Liu,

Yi Yang; [pdf] [arXiv]
[bibtex]
@InProceedings{Tang_2023_CVPR, author = {Tang, Zongheng and Sun, Yifan and Liu, Si and Yang, Yi}, title = {DETR With Additional Global Aggregation for Cross-Domain Weakly Supervised Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11422-11432} }
Towards Bridging the Performance Gaps of Joint Energy-Based Models: Xiulong Yang,

Qing Su,

Shihao Ji; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yang_2023_CVPR, author = {Yang, Xiulong and Su, Qing and Ji, Shihao}, title = {Towards Bridging the Performance Gaps of Joint Energy-Based Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15732-15741} }
expOSE: Accurate Initialization-Free Projective Factorization Using Exponential Regularization: José Pedro Iglesias,

Amanda Nilsson,

Carl Olsson; [pdf] [supp]
[bibtex]
@InProceedings{Iglesias_2023_CVPR, author = {Iglesias, Jos\'e Pedro and Nilsson, Amanda and Olsson, Carl}, title = {expOSE: Accurate Initialization-Free Projective Factorization Using Exponential Regularization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8959-8968} }
OpenGait: Revisiting Gait Recognition Towards Better Practicality: Chao Fan,

Junhao Liang,

Chuanfu Shen,

Saihui Hou,

Yongzhen Huang,

Shiqi Yu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Fan_2023_CVPR, author = {Fan, Chao and Liang, Junhao and Shen, Chuanfu and Hou, Saihui and Huang, Yongzhen and Yu, Shiqi}, title = {OpenGait: Revisiting Gait Recognition Towards Better Practicality}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9707-9716} }
DATID-3D: Diversity-Preserved Domain Adaptation Using Text-to-Image Diffusion for 3D Generative Model: Gwanghyun Kim,

Se Young Chun; [pdf] [supp]
[bibtex]
@InProceedings{Kim_2023_CVPR, author = {Kim, Gwanghyun and Chun, Se Young}, title = {DATID-3D: Diversity-Preserved Domain Adaptation Using Text-to-Image Diffusion for 3D Generative Model}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14203-14213} }
Learning Neural Volumetric Representations of Dynamic Humans in Minutes: Chen Geng,

Sida Peng,

Zhen Xu,

Hujun Bao,

Xiaowei Zhou; [pdf] [arXiv]
[bibtex]
@InProceedings{Geng_2023_CVPR, author = {Geng, Chen and Peng, Sida and Xu, Zhen and Bao, Hujun and Zhou, Xiaowei}, title = {Learning Neural Volumetric Representations of Dynamic Humans in Minutes}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8759-8770} }
Streaming Video Model: Yucheng Zhao,

Chong Luo,

Chuanxin Tang,

Dongdong Chen,

Noel Codella,

Zheng-Jun Zha; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhao_2023_CVPR, author = {Zhao, Yucheng and Luo, Chong and Tang, Chuanxin and Chen, Dongdong and Codella, Noel and Zha, Zheng-Jun}, title = {Streaming Video Model}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14602-14612} }
CapDet: Unifying Dense Captioning and Open-World Detection Pretraining: Yanxin Long,

Youpeng Wen,

Jianhua Han,

Hang Xu,

Pengzhen Ren,

Wei Zhang,

Shen Zhao,

Xiaodan Liang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Long_2023_CVPR, author = {Long, Yanxin and Wen, Youpeng and Han, Jianhua and Xu, Hang and Ren, Pengzhen and Zhang, Wei and Zhao, Shen and Liang, Xiaodan}, title = {CapDet: Unifying Dense Captioning and Open-World Detection Pretraining}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15233-15243} }
Bayesian Posterior Approximation With Stochastic Ensembles: Oleksandr Balabanov,

Bernhard Mehlig,

Hampus Linander; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Balabanov_2023_CVPR, author = {Balabanov, Oleksandr and Mehlig, Bernhard and Linander, Hampus}, title = {Bayesian Posterior Approximation With Stochastic Ensembles}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13701-13711} }
Symmetric Shape-Preserving Autoencoder for Unsupervised Real Scene Point Cloud Completion: Changfeng Ma,

Yinuo Chen,

Pengxiao Guo,

Jie Guo,

Chongjun Wang,

Yanwen Guo; [pdf] [supp]
[bibtex]
@InProceedings{Ma_2023_CVPR, author = {Ma, Changfeng and Chen, Yinuo and Guo, Pengxiao and Guo, Jie and Wang, Chongjun and Guo, Yanwen}, title = {Symmetric Shape-Preserving Autoencoder for Unsupervised Real Scene Point Cloud Completion}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13560-13569} }
Comprehensive and Delicate: An Efficient Transformer for Image Restoration: Haiyu Zhao,

Yuanbiao Gou,

Boyun Li,

Dezhong Peng,

Jiancheng Lv,

Xi Peng; [pdf] [supp]
[bibtex]
@InProceedings{Zhao_2023_CVPR, author = {Zhao, Haiyu and Gou, Yuanbiao and Li, Boyun and Peng, Dezhong and Lv, Jiancheng and Peng, Xi}, title = {Comprehensive and Delicate: An Efficient Transformer for Image Restoration}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14122-14132} }
Zero-Shot Model Diagnosis: Jinqi Luo,

Zhaoning Wang,

Chen Henry Wu,

Dong Huang,

Fernando De la Torre; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Luo_2023_CVPR, author = {Luo, Jinqi and Wang, Zhaoning and Wu, Chen Henry and Huang, Dong and De la Torre, Fernando}, title = {Zero-Shot Model Diagnosis}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11631-11640} }
ShadowDiffusion: When Degradation Prior Meets Diffusion Model for Shadow Removal: Lanqing Guo,

Chong Wang,

Wenhan Yang,

Siyu Huang,

Yufei Wang,

Hanspeter Pfister,

Bihan Wen; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Guo_2023_CVPR, author = {Guo, Lanqing and Wang, Chong and Yang, Wenhan and Huang, Siyu and Wang, Yufei and Pfister, Hanspeter and Wen, Bihan}, title = {ShadowDiffusion: When Degradation Prior Meets Diffusion Model for Shadow Removal}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14049-14058} }
Pruning Parameterization With Bi-Level Optimization for Efficient Semantic Segmentation on the Edge: Changdi Yang,

Pu Zhao,

Yanyu Li,

Wei Niu,

Jiexiong Guan,

Hao Tang,

Minghai Qin,

Bin Ren,

Xue Lin,

Yanzhi Wang; [pdf] [supp]
[bibtex]
@InProceedings{Yang_2023_CVPR, author = {Yang, Changdi and Zhao, Pu and Li, Yanyu and Niu, Wei and Guan, Jiexiong and Tang, Hao and Qin, Minghai and Ren, Bin and Lin, Xue and Wang, Yanzhi}, title = {Pruning Parameterization With Bi-Level Optimization for Efficient Semantic Segmentation on the Edge}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15402-15412} }
NLOST: Non-Line-of-Sight Imaging With Transformer: Yue Li,

Jiayong Peng,

Juntian Ye,

Yueyi Zhang,

Feihu Xu,

Zhiwei Xiong; [pdf] [supp]
[bibtex]
@InProceedings{Li_2023_CVPR, author = {Li, Yue and Peng, Jiayong and Ye, Juntian and Zhang, Yueyi and Xu, Feihu and Xiong, Zhiwei}, title = {NLOST: Non-Line-of-Sight Imaging With Transformer}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13313-13322} }
Text-Visual Prompting for Efficient 2D Temporal Video Grounding: Yimeng Zhang,

Xin Chen,

Jinghan Jia,

Sijia Liu,

Ke Ding; [pdf] [arXiv]
[bibtex]
@InProceedings{Zhang_2023_CVPR, author = {Zhang, Yimeng and Chen, Xin and Jia, Jinghan and Liu, Sijia and Ding, Ke}, title = {Text-Visual Prompting for Efficient 2D Temporal Video Grounding}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14794-14804} }
NEF: Neural Edge Fields for 3D Parametric Curve Reconstruction From Multi-View Images: Yunfan Ye,

Renjiao Yi,

Zhirui Gao,

Chenyang Zhu,

Zhiping Cai,

Kai Xu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ye_2023_CVPR, author = {Ye, Yunfan and Yi, Renjiao and Gao, Zhirui and Zhu, Chenyang and Cai, Zhiping and Xu, Kai}, title = {NEF: Neural Edge Fields for 3D Parametric Curve Reconstruction From Multi-View Images}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8486-8495} }
Geometric Visual Similarity Learning in 3D Medical Image Self-Supervised Pre-Training: Yuting He,

Guanyu Yang,

Rongjun Ge,

Yang Chen,

Jean-Louis Coatrieux,

Boyu Wang,

Shuo Li; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{He_2023_CVPR, author = {He, Yuting and Yang, Guanyu and Ge, Rongjun and Chen, Yang and Coatrieux, Jean-Louis and Wang, Boyu and Li, Shuo}, title = {Geometric Visual Similarity Learning in 3D Medical Image Self-Supervised Pre-Training}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9538-9547} }
Less Is More: Reducing Task and Model Complexity for 3D Point Cloud Semantic Segmentation: Li Li,

Hubert P. H. Shum,

Toby P. Breckon; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Li_2023_CVPR, author = {Li, Li and Shum, Hubert P. H. and Breckon, Toby P.}, title = {Less Is More: Reducing Task and Model Complexity for 3D Point Cloud Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9361-9371} }
AdaMAE: Adaptive Masking for Efficient Spatiotemporal Learning With Masked Autoencoders: Wele Gedara Chaminda Bandara,

Naman Patel,

Ali Gholami,

Mehdi Nikkhah,

Motilal Agrawal,

Vishal M. Patel; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Bandara_2023_CVPR, author = {Bandara, Wele Gedara Chaminda and Patel, Naman and Gholami, Ali and Nikkhah, Mehdi and Agrawal, Motilal and Patel, Vishal M.}, title = {AdaMAE: Adaptive Masking for Efficient Spatiotemporal Learning With Masked Autoencoders}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14507-14517} }
Directional Connectivity-Based Segmentation of Medical Images: Ziyun Yang,

Sina Farsiu; [pdf] [arXiv]
[bibtex]
@InProceedings{Yang_2023_CVPR, author = {Yang, Ziyun and Farsiu, Sina}, title = {Directional Connectivity-Based Segmentation of Medical Images}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11525-11535} }
Towards Flexible Multi-Modal Document Models: Naoto Inoue,

Kotaro Kikuchi,

Edgar Simo-Serra,

Mayu Otani,

Kota Yamaguchi; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Inoue_2023_CVPR, author = {Inoue, Naoto and Kikuchi, Kotaro and Simo-Serra, Edgar and Otani, Mayu and Yamaguchi, Kota}, title = {Towards Flexible Multi-Modal Document Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14287-14296} }
LiDAR-in-the-Loop Hyperparameter Optimization: Félix Goudreault,

Dominik Scheuble,

Mario Bijelic,

Nicolas Robidoux,

Felix Heide; [pdf] [supp]
[bibtex]
@InProceedings{Goudreault_2023_CVPR, author = {Goudreault, F\'elix and Scheuble, Dominik and Bijelic, Mario and Robidoux, Nicolas and Heide, Felix}, title = {LiDAR-in-the-Loop Hyperparameter Optimization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13404-13414} }
Local 3D Editing via 3D Distillation of CLIP Knowledge: Junha Hyung,

Sungwon Hwang,

Daejin Kim,

Hyunji Lee,

Jaegul Choo; [pdf] [supp]
[bibtex]
@InProceedings{Hyung_2023_CVPR, author = {Hyung, Junha and Hwang, Sungwon and Kim, Daejin and Lee, Hyunji and Choo, Jaegul}, title = {Local 3D Editing via 3D Distillation of CLIP Knowledge}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12674-12684} }
Human Body Shape Completion With Implicit Shape and Flow Learning: Boyao Zhou,

Di Meng,

Jean-Sébastien Franco,

Edmond Boyer; [pdf] [supp]
[bibtex]
@InProceedings{Zhou_2023_CVPR, author = {Zhou, Boyao and Meng, Di and Franco, Jean-S\'ebastien and Boyer, Edmond}, title = {Human Body Shape Completion With Implicit Shape and Flow Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12901-12911} }
Modular Memorability: Tiered Representations for Video Memorability Prediction: Théo Dumont,

Juan Segundo Hevia,

Camilo L. Fosco; [pdf] [supp]
[bibtex]
@InProceedings{Dumont_2023_CVPR, author = {Dumont, Th\'eo and Hevia, Juan Segundo and Fosco, Camilo L.}, title = {Modular Memorability: Tiered Representations for Video Memorability Prediction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10751-10760} }
Weakly-Supervised Domain Adaptive Semantic Segmentation With Prototypical Contrastive Learning: Anurag Das,

Yongqin Xian,

Dengxin Dai,

Bernt Schiele; [pdf] [supp]
[bibtex]
@InProceedings{Das_2023_CVPR, author = {Das, Anurag and Xian, Yongqin and Dai, Dengxin and Schiele, Bernt}, title = {Weakly-Supervised Domain Adaptive Semantic Segmentation With Prototypical Contrastive Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15434-15443} }
Language-Guided Music Recommendation for Video via Prompt Analogies: Daniel McKee,

Justin Salamon,

Josef Sivic,

Bryan Russell; [pdf] [supp]
[bibtex]
@InProceedings{McKee_2023_CVPR, author = {McKee, Daniel and Salamon, Justin and Sivic, Josef and Russell, Bryan}, title = {Language-Guided Music Recommendation for Video via Prompt Analogies}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14784-14793} }
Re2TAL: Rewiring Pretrained Video Backbones for Reversible Temporal Action Localization: Chen Zhao,

Shuming Liu,

Karttikeya Mangalam,

Bernard Ghanem; [pdf] [supp]
[bibtex]
@InProceedings{Zhao_2023_CVPR, author = {Zhao, Chen and Liu, Shuming and Mangalam, Karttikeya and Ghanem, Bernard}, title = {Re2TAL: Rewiring Pretrained Video Backbones for Reversible Temporal Action Localization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10637-10647} }
NeRFLight: Fast and Light Neural Radiance Fields Using a Shared Feature Grid: Fernando Rivas-Manzaneque,

Jorge Sierra-Acosta,

Adrian Penate-Sanchez,

Francesc Moreno-Noguer,

Angela Ribeiro; [pdf] [supp]
[bibtex]
@InProceedings{Rivas-Manzaneque_2023_CVPR, author = {Rivas-Manzaneque, Fernando and Sierra-Acosta, Jorge and Penate-Sanchez, Adrian and Moreno-Noguer, Francesc and Ribeiro, Angela}, title = {NeRFLight: Fast and Light Neural Radiance Fields Using a Shared Feature Grid}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12417-12427} }
MVImgNet: A Large-Scale Dataset of Multi-View Images: Xianggang Yu,

Mutian Xu,

Yidan Zhang,

Haolin Liu,

Chongjie Ye,

Yushuang Wu,

Zizheng Yan,

Chenming Zhu,

Zhangyang Xiong,

Tianyou Liang,

Guanying Chen,

Shuguang Cui,

Xiaoguang Han; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yu_2023_CVPR, author = {Yu, Xianggang and Xu, Mutian and Zhang, Yidan and Liu, Haolin and Ye, Chongjie and Wu, Yushuang and Yan, Zizheng and Zhu, Chenming and Xiong, Zhangyang and Liang, Tianyou and Chen, Guanying and Cui, Shuguang and Han, Xiaoguang}, title = {MVImgNet: A Large-Scale Dataset of Multi-View Images}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9150-9161} }
A New Benchmark: On the Utility of Synthetic Data With Blender for Bare Supervised Learning and Downstream Domain Adaptation: Hui Tang,

Kui Jia; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Tang_2023_CVPR, author = {Tang, Hui and Jia, Kui}, title = {A New Benchmark: On the Utility of Synthetic Data With Blender for Bare Supervised Learning and Downstream Domain Adaptation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15954-15964} }
Autoregressive Visual Tracking: Xing Wei,

Yifan Bai,

Yongchao Zheng,

Dahu Shi,

Yihong Gong; [pdf]
[bibtex]
@InProceedings{Wei_2023_CVPR, author = {Wei, Xing and Bai, Yifan and Zheng, Yongchao and Shi, Dahu and Gong, Yihong}, title = {Autoregressive Visual Tracking}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9697-9706} }
Unsupervised Domain Adaption With Pixel-Level Discriminator for Image-Aware Layout Generation: Chenchen Xu,

Min Zhou,

Tiezheng Ge,

Yuning Jiang,

Weiwei Xu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Xu_2023_CVPR, author = {Xu, Chenchen and Zhou, Min and Ge, Tiezheng and Jiang, Yuning and Xu, Weiwei}, title = {Unsupervised Domain Adaption With Pixel-Level Discriminator for Image-Aware Layout Generation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10114-10123} }
Real-Time 6K Image Rescaling With Rate-Distortion Optimization: Chenyang Qi,

Xin Yang,

Ka Leong Cheng,

Ying-Cong Chen,

Qifeng Chen; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Qi_2023_CVPR, author = {Qi, Chenyang and Yang, Xin and Cheng, Ka Leong and Chen, Ying-Cong and Chen, Qifeng}, title = {Real-Time 6K Image Rescaling With Rate-Distortion Optimization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14092-14101} }
Gated Stereo: Joint Depth Estimation From Gated and Wide-Baseline Active Stereo Cues: Stefanie Walz,

Mario Bijelic,

Andrea Ramazzina,

Amanpreet Walia,

Fahim Mannan,

Felix Heide; [pdf] [supp]
[bibtex]
@InProceedings{Walz_2023_CVPR, author = {Walz, Stefanie and Bijelic, Mario and Ramazzina, Andrea and Walia, Amanpreet and Mannan, Fahim and Heide, Felix}, title = {Gated Stereo: Joint Depth Estimation From Gated and Wide-Baseline Active Stereo Cues}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13252-13262} }
MammalNet: A Large-Scale Video Benchmark for Mammal Recognition and Behavior Understanding: Jun Chen,

Ming Hu,

Darren J. Coker,

Michael L. Berumen,

Blair Costelloe,

Sara Beery,

Anna Rohrbach,

Mohamed Elhoseiny; [pdf] [supp]
[bibtex]
@InProceedings{Chen_2023_CVPR, author = {Chen, Jun and Hu, Ming and Coker, Darren J. and Berumen, Michael L. and Costelloe, Blair and Beery, Sara and Rohrbach, Anna and Elhoseiny, Mohamed}, title = {MammalNet: A Large-Scale Video Benchmark for Mammal Recognition and Behavior Understanding}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13052-13061} }
Hand Avatar: Free-Pose Hand Animation and Rendering From Monocular Video: Xingyu Chen,

Baoyuan Wang,

Heung-Yeung Shum; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chen_2023_CVPR, author = {Chen, Xingyu and Wang, Baoyuan and Shum, Heung-Yeung}, title = {Hand Avatar: Free-Pose Hand Animation and Rendering From Monocular Video}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8683-8693} }
VindLU: A Recipe for Effective Video-and-Language Pretraining: Feng Cheng,

Xizi Wang,

Jie Lei,

David Crandall,

Mohit Bansal,

Gedas Bertasius; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Cheng_2023_CVPR, author = {Cheng, Feng and Wang, Xizi and Lei, Jie and Crandall, David and Bansal, Mohit and Bertasius, Gedas}, title = {VindLU: A Recipe for Effective Video-and-Language Pretraining}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10739-10750} }
OmniAvatar: Geometry-Guided Controllable 3D Head Synthesis: Hongyi Xu,

Guoxian Song,

Zihang Jiang,

Jianfeng Zhang,

Yichun Shi,

Jing Liu,

Wanchun Ma,

Jiashi Feng,

Linjie Luo; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Xu_2023_CVPR, author = {Xu, Hongyi and Song, Guoxian and Jiang, Zihang and Zhang, Jianfeng and Shi, Yichun and Liu, Jing and Ma, Wanchun and Feng, Jiashi and Luo, Linjie}, title = {OmniAvatar: Geometry-Guided Controllable 3D Head Synthesis}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12814-12824} }
SUDS: Scalable Urban Dynamic Scenes: Haithem Turki,

Jason Y. Zhang,

Francesco Ferroni,

Deva Ramanan; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Turki_2023_CVPR, author = {Turki, Haithem and Zhang, Jason Y. and Ferroni, Francesco and Ramanan, Deva}, title = {SUDS: Scalable Urban Dynamic Scenes}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12375-12385} }
Cloud-Device Collaborative Adaptation to Continual Changing Environments in the Real-World: Yulu Gan,

Mingjie Pan,

Rongyu Zhang,

Zijian Ling,

Lingran Zhao,

Jiaming Liu,

Shanghang Zhang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Gan_2023_CVPR, author = {Gan, Yulu and Pan, Mingjie and Zhang, Rongyu and Ling, Zijian and Zhao, Lingran and Liu, Jiaming and Zhang, Shanghang}, title = {Cloud-Device Collaborative Adaptation to Continual Changing Environments in the Real-World}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12157-12166} }
Seasoning Model Soups for Robustness to Adversarial and Natural Distribution Shifts: Francesco Croce,

Sylvestre-Alvise Rebuffi,

Evan Shelhamer,

Sven Gowal; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Croce_2023_CVPR, author = {Croce, Francesco and Rebuffi, Sylvestre-Alvise and Shelhamer, Evan and Gowal, Sven}, title = {Seasoning Model Soups for Robustness to Adversarial and Natural Distribution Shifts}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12313-12323} }
How To Prevent the Continuous Damage of Noises To Model Training?: Xiaotian Yu,

Yang Jiang,

Tianqi Shi,

Zunlei Feng,

Yuexuan Wang,

Mingli Song,

Li Sun; [pdf] [supp]
[bibtex]
@InProceedings{Yu_2023_CVPR, author = {Yu, Xiaotian and Jiang, Yang and Shi, Tianqi and Feng, Zunlei and Wang, Yuexuan and Song, Mingli and Sun, Li}, title = {How To Prevent the Continuous Damage of Noises To Model Training?}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12054-12063} }
Skinned Motion Retargeting With Residual Perception of Motion Semantics & Geometry: Jiaxu Zhang,

Junwu Weng,

Di Kang,

Fang Zhao,

Shaoli Huang,

Xuefei Zhe,

Linchao Bao,

Ying Shan,

Jue Wang,

Zhigang Tu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhang_2023_CVPR, author = {Zhang, Jiaxu and Weng, Junwu and Kang, Di and Zhao, Fang and Huang, Shaoli and Zhe, Xuefei and Bao, Linchao and Shan, Ying and Wang, Jue and Tu, Zhigang}, title = {Skinned Motion Retargeting With Residual Perception of Motion Semantics \& Geometry}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13864-13872} }
Weakly-Supervised Single-View Image Relighting: Renjiao Yi,

Chenyang Zhu,

Kai Xu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yi_2023_CVPR, author = {Yi, Renjiao and Zhu, Chenyang and Xu, Kai}, title = {Weakly-Supervised Single-View Image Relighting}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8402-8411} }
DualVector: Unsupervised Vector Font Synthesis With Dual-Part Representation: Ying-Tian Liu,

Zhifei Zhang,

Yuan-Chen Guo,

Matthew Fisher,

Zhaowen Wang,

Song-Hai Zhang; [pdf] [supp]
[bibtex]
@InProceedings{Liu_2023_CVPR, author = {Liu, Ying-Tian and Zhang, Zhifei and Guo, Yuan-Chen and Fisher, Matthew and Wang, Zhaowen and Zhang, Song-Hai}, title = {DualVector: Unsupervised Vector Font Synthesis With Dual-Part Representation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14193-14202} }
ReasonNet: End-to-End Driving With Temporal and Global Reasoning: Hao Shao,

Letian Wang,

Ruobing Chen,

Steven L. Waslander,

Hongsheng Li,

Yu Liu; [pdf] [supp]
[bibtex]
@InProceedings{Shao_2023_CVPR, author = {Shao, Hao and Wang, Letian and Chen, Ruobing and Waslander, Steven L. and Li, Hongsheng and Liu, Yu}, title = {ReasonNet: End-to-End Driving With Temporal and Global Reasoning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13723-13733} }
Learning Situation Hyper-Graphs for Video Question Answering: Aisha Urooj,

Hilde Kuehne,

Bo Wu,

Kim Chheu,

Walid Bousselham,

Chuang Gan,

Niels Lobo,

Mubarak Shah; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Urooj_2023_CVPR, author = {Urooj, Aisha and Kuehne, Hilde and Wu, Bo and Chheu, Kim and Bousselham, Walid and Gan, Chuang and Lobo, Niels and Shah, Mubarak}, title = {Learning Situation Hyper-Graphs for Video Question Answering}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14879-14889} }
GazeNeRF: 3D-Aware Gaze Redirection With Neural Radiance Fields: Alessandro Ruzzi,

Xiangwei Shi,

Xi Wang,

Gengyan Li,

Shalini De Mello,

Hyung Jin Chang,

Xucong Zhang,

Otmar Hilliges; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ruzzi_2023_CVPR, author = {Ruzzi, Alessandro and Shi, Xiangwei and Wang, Xi and Li, Gengyan and De Mello, Shalini and Chang, Hyung Jin and Zhang, Xucong and Hilliges, Otmar}, title = {GazeNeRF: 3D-Aware Gaze Redirection With Neural Radiance Fields}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9676-9685} }
SegLoc: Learning Segmentation-Based Representations for Privacy-Preserving Visual Localization: Maxime Pietrantoni,

Martin Humenberger,

Torsten Sattler,

Gabriela Csurka; [pdf] [supp]
[bibtex]
@InProceedings{Pietrantoni_2023_CVPR, author = {Pietrantoni, Maxime and Humenberger, Martin and Sattler, Torsten and Csurka, Gabriela}, title = {SegLoc: Learning Segmentation-Based Representations for Privacy-Preserving Visual Localization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15380-15391} }
Efficient Hierarchical Entropy Model for Learned Point Cloud Compression: Rui Song,

Chunyang Fu,

Shan Liu,

Ge Li; [pdf] [supp]
[bibtex]
@InProceedings{Song_2023_CVPR, author = {Song, Rui and Fu, Chunyang and Liu, Shan and Li, Ge}, title = {Efficient Hierarchical Entropy Model for Learned Point Cloud Compression}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14368-14377} }
Image Cropping With Spatial-Aware Feature and Rank Consistency: Chao Wang,

Li Niu,

Bo Zhang,

Liqing Zhang; [pdf] [supp]
[bibtex]
@InProceedings{Wang_2023_CVPR, author = {Wang, Chao and Niu, Li and Zhang, Bo and Zhang, Liqing}, title = {Image Cropping With Spatial-Aware Feature and Rank Consistency}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10052-10061} }
SVGformer: Representation Learning for Continuous Vector Graphics Using Transformers: Defu Cao,

Zhaowen Wang,

Jose Echevarria,

Yan Liu; [pdf] [supp]
[bibtex]
@InProceedings{Cao_2023_CVPR, author = {Cao, Defu and Wang, Zhaowen and Echevarria, Jose and Liu, Yan}, title = {SVGformer: Representation Learning for Continuous Vector Graphics Using Transformers}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10093-10102} }
Learning Attribute and Class-Specific Representation Duet for Fine-Grained Fashion Analysis: Yang Jiao,

Yan Gao,

Jingjing Meng,

Jin Shang,

Yi Sun; [pdf] [supp]
[bibtex]
@InProceedings{Jiao_2023_CVPR, author = {Jiao, Yang and Gao, Yan and Meng, Jingjing and Shang, Jin and Sun, Yi}, title = {Learning Attribute and Class-Specific Representation Duet for Fine-Grained Fashion Analysis}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11050-11059} }
Pixels, Regions, and Objects: Multiple Enhancement for Salient Object Detection: Yi Wang,

Ruili Wang,

Xin Fan,

Tianzhu Wang,

Xiangjian He; [pdf] [supp]
[bibtex]
@InProceedings{Wang_2023_CVPR, author = {Wang, Yi and Wang, Ruili and Fan, Xin and Wang, Tianzhu and He, Xiangjian}, title = {Pixels, Regions, and Objects: Multiple Enhancement for Salient Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10031-10040} }
Leveraging Temporal Context in Low Representational Power Regimes: Camilo L. Fosco,

SouYoung Jin,

Emilie Josephs,

Aude Oliva; [pdf] [supp]
[bibtex]
@InProceedings{Fosco_2023_CVPR, author = {Fosco, Camilo L. and Jin, SouYoung and Josephs, Emilie and Oliva, Aude}, title = {Leveraging Temporal Context in Low Representational Power Regimes}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10693-10703} }
Omni3D: A Large Benchmark and Model for 3D Object Detection in the Wild: Garrick Brazil,

Abhinav Kumar,

Julian Straub,

Nikhila Ravi,

Justin Johnson,

Georgia Gkioxari; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Brazil_2023_CVPR, author = {Brazil, Garrick and Kumar, Abhinav and Straub, Julian and Ravi, Nikhila and Johnson, Justin and Gkioxari, Georgia}, title = {Omni3D: A Large Benchmark and Model for 3D Object Detection in the Wild}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13154-13164} }
OT-Filter: An Optimal Transport Filter for Learning With Noisy Labels: Chuanwen Feng,

Yilong Ren,

Xike Xie; [pdf]
[bibtex]
@InProceedings{Feng_2023_CVPR, author = {Feng, Chuanwen and Ren, Yilong and Xie, Xike}, title = {OT-Filter: An Optimal Transport Filter for Learning With Noisy Labels}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16164-16174} }
Rigidity-Aware Detection for 6D Object Pose Estimation: Yang Hai,

Rui Song,

Jiaojiao Li,

Mathieu Salzmann,

Yinlin Hu; [pdf] [arXiv]
[bibtex]
@InProceedings{Hai_2023_CVPR, author = {Hai, Yang and Song, Rui and Li, Jiaojiao and Salzmann, Mathieu and Hu, Yinlin}, title = {Rigidity-Aware Detection for 6D Object Pose Estimation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8927-8936} }
Clover: Towards a Unified Video-Language Alignment and Fusion Model: Jingjia Huang,

Yinan Li,

Jiashi Feng,

Xinglong Wu,

Xiaoshuai Sun,

Rongrong Ji; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Huang_2023_CVPR, author = {Huang, Jingjia and Li, Yinan and Feng, Jiashi and Wu, Xinglong and Sun, Xiaoshuai and Ji, Rongrong}, title = {Clover: Towards a Unified Video-Language Alignment and Fusion Model}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14856-14866} }
Self-Supervised Learning From Images With a Joint-Embedding Predictive Architecture: Mahmoud Assran,

Quentin Duval,

Ishan Misra,

Piotr Bojanowski,

Pascal Vincent,

Michael Rabbat,

Yann LeCun,

Nicolas Ballas; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Assran_2023_CVPR, author = {Assran, Mahmoud and Duval, Quentin and Misra, Ishan and Bojanowski, Piotr and Vincent, Pascal and Rabbat, Michael and LeCun, Yann and Ballas, Nicolas}, title = {Self-Supervised Learning From Images With a Joint-Embedding Predictive Architecture}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15619-15629} }
A2J-Transformer: Anchor-to-Joint Transformer Network for 3D Interacting Hand Pose Estimation From a Single RGB Image: Changlong Jiang,

Yang Xiao,

Cunlin Wu,

Mingyang Zhang,

Jinghong Zheng,

Zhiguo Cao,

Joey Tianyi Zhou; [pdf]
[bibtex]
@InProceedings{Jiang_2023_CVPR, author = {Jiang, Changlong and Xiao, Yang and Wu, Cunlin and Zhang, Mingyang and Zheng, Jinghong and Cao, Zhiguo and Zhou, Joey Tianyi}, title = {A2J-Transformer: Anchor-to-Joint Transformer Network for 3D Interacting Hand Pose Estimation From a Single RGB Image}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8846-8855} }
The Treasure Beneath Multiple Annotations: An Uncertainty-Aware Edge Detector: Caixia Zhou,

Yaping Huang,

Mengyang Pu,

Qingji Guan,

Li Huang,

Haibin Ling; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhou_2023_CVPR, author = {Zhou, Caixia and Huang, Yaping and Pu, Mengyang and Guan, Qingji and Huang, Li and Ling, Haibin}, title = {The Treasure Beneath Multiple Annotations: An Uncertainty-Aware Edge Detector}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15507-15517} }
DP-NeRF: Deblurred Neural Radiance Field With Physical Scene Priors: Dogyoon Lee,

Minhyeok Lee,

Chajin Shin,

Sangyoun Lee; [pdf] [supp]
[bibtex]
@InProceedings{Lee_2023_CVPR, author = {Lee, Dogyoon and Lee, Minhyeok and Shin, Chajin and Lee, Sangyoun}, title = {DP-NeRF: Deblurred Neural Radiance Field With Physical Scene Priors}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12386-12396} }
Self-Supervised Blind Motion Deblurring With Deep Expectation Maximization: Ji Li,

Weixi Wang,

Yuesong Nan,

Hui Ji; [pdf] [supp]
[bibtex]
@InProceedings{Li_2023_CVPR, author = {Li, Ji and Wang, Weixi and Nan, Yuesong and Ji, Hui}, title = {Self-Supervised Blind Motion Deblurring With Deep Expectation Maximization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13986-13996} }
Grounding Counterfactual Explanation of Image Classifiers to Textual Concept Space: Siwon Kim,

Jinoh Oh,

Sungjin Lee,

Seunghak Yu,

Jaeyoung Do,

Tara Taghavi; [pdf] [supp]
[bibtex]
@InProceedings{Kim_2023_CVPR, author = {Kim, Siwon and Oh, Jinoh and Lee, Sungjin and Yu, Seunghak and Do, Jaeyoung and Taghavi, Tara}, title = {Grounding Counterfactual Explanation of Image Classifiers to Textual Concept Space}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10942-10950} }
SemiCVT: Semi-Supervised Convolutional Vision Transformer for Semantic Segmentation: Huimin Huang,

Shiao Xie,

Lanfen Lin,

Ruofeng Tong,

Yen-Wei Chen,

Yuexiang Li,

Hong Wang,

Yawen Huang,

Yefeng Zheng; [pdf]
[bibtex]
@InProceedings{Huang_2023_CVPR, author = {Huang, Huimin and Xie, Shiao and Lin, Lanfen and Tong, Ruofeng and Chen, Yen-Wei and Li, Yuexiang and Wang, Hong and Huang, Yawen and Zheng, Yefeng}, title = {SemiCVT: Semi-Supervised Convolutional Vision Transformer for Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11340-11349} }
Towards Open-World Segmentation of Parts: Tai-Yu Pan,

Qing Liu,

Wei-Lun Chao,

Brian Price; [pdf] [supp]
[bibtex]
@InProceedings{Pan_2023_CVPR, author = {Pan, Tai-Yu and Liu, Qing and Chao, Wei-Lun and Price, Brian}, title = {Towards Open-World Segmentation of Parts}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15392-15401} }
Stitchable Neural Networks: Zizheng Pan,

Jianfei Cai,

Bohan Zhuang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Pan_2023_CVPR, author = {Pan, Zizheng and Cai, Jianfei and Zhuang, Bohan}, title = {Stitchable Neural Networks}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16102-16112} }
Audio-Visual Grouping Network for Sound Localization From Mixtures: Shentong Mo,

Yapeng Tian; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Mo_2023_CVPR, author = {Mo, Shentong and Tian, Yapeng}, title = {Audio-Visual Grouping Network for Sound Localization From Mixtures}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10565-10574} }
Fair Federated Medical Image Segmentation via Client Contribution Estimation: Meirui Jiang,

Holger R. Roth,

Wenqi Li,

Dong Yang,

Can Zhao,

Vishwesh Nath,

Daguang Xu,

Qi Dou,

Ziyue Xu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Jiang_2023_CVPR, author = {Jiang, Meirui and Roth, Holger R. and Li, Wenqi and Yang, Dong and Zhao, Can and Nath, Vishwesh and Xu, Daguang and Dou, Qi and Xu, Ziyue}, title = {Fair Federated Medical Image Segmentation via Client Contribution Estimation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16302-16311} }
Dynamic Generative Targeted Attacks With Pattern Injection: Weiwei Feng,

Nanqing Xu,

Tianzhu Zhang,

Yongdong Zhang; [pdf] [supp]
[bibtex]
@InProceedings{Feng_2023_CVPR, author = {Feng, Weiwei and Xu, Nanqing and Zhang, Tianzhu and Zhang, Yongdong}, title = {Dynamic Generative Targeted Attacks With Pattern Injection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16404-16414} }
Visual Recognition by Request: Chufeng Tang,

Lingxi Xie,

Xiaopeng Zhang,

Xiaolin Hu,

Qi Tian; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Tang_2023_CVPR, author = {Tang, Chufeng and Xie, Lingxi and Zhang, Xiaopeng and Hu, Xiaolin and Tian, Qi}, title = {Visual Recognition by Request}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15265-15274} }
PointCert: Point Cloud Classification With Deterministic Certified Robustness Guarantees: Jinghuai Zhang,

Jinyuan Jia,

Hongbin Liu,

Neil Zhenqiang Gong; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhang_2023_CVPR, author = {Zhang, Jinghuai and Jia, Jinyuan and Liu, Hongbin and Gong, Neil Zhenqiang}, title = {PointCert: Point Cloud Classification With Deterministic Certified Robustness Guarantees}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9496-9505} }
Cap4Video: What Can Auxiliary Captions Do for Text-Video Retrieval?: Wenhao Wu,

Haipeng Luo,

Bo Fang,

Jingdong Wang,

Wanli Ouyang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wu_2023_CVPR, author = {Wu, Wenhao and Luo, Haipeng and Fang, Bo and Wang, Jingdong and Ouyang, Wanli}, title = {Cap4Video: What Can Auxiliary Captions Do for Text-Video Retrieval?}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10704-10713} }
Progressive Semantic-Visual Mutual Adaption for Generalized Zero-Shot Learning: Man Liu,

Feng Li,

Chunjie Zhang,

Yunchao Wei,

Huihui Bai,

Yao Zhao; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Liu_2023_CVPR, author = {Liu, Man and Li, Feng and Zhang, Chunjie and Wei, Yunchao and Bai, Huihui and Zhao, Yao}, title = {Progressive Semantic-Visual Mutual Adaption for Generalized Zero-Shot Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15337-15346} }
Block Selection Method for Using Feature Norm in Out-of-Distribution Detection: Yeonguk Yu,

Sungho Shin,

Seongju Lee,

Changhyun Jun,

Kyoobin Lee; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yu_2023_CVPR, author = {Yu, Yeonguk and Shin, Sungho and Lee, Seongju and Jun, Changhyun and Lee, Kyoobin}, title = {Block Selection Method for Using Feature Norm in Out-of-Distribution Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15701-15711} }
Four-View Geometry With Unknown Radial Distortion: Petr Hruby,

Viktor Korotynskiy,

Timothy Duff,

Luke Oeding,

Marc Pollefeys,

Tomas Pajdla,

Viktor Larsson; [pdf] [supp]
[bibtex]
@InProceedings{Hruby_2023_CVPR, author = {Hruby, Petr and Korotynskiy, Viktor and Duff, Timothy and Oeding, Luke and Pollefeys, Marc and Pajdla, Tomas and Larsson, Viktor}, title = {Four-View Geometry With Unknown Radial Distortion}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8990-9000} }
How To Prevent the Poor Performance Clients for Personalized Federated Learning?: Zhe Qu,

Xingyu Li,

Xiao Han,

Rui Duan,

Chengchao Shen,

Lixing Chen; [pdf] [supp]
[bibtex]
@InProceedings{Qu_2023_CVPR, author = {Qu, Zhe and Li, Xingyu and Han, Xiao and Duan, Rui and Shen, Chengchao and Chen, Lixing}, title = {How To Prevent the Poor Performance Clients for Personalized Federated Learning?}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12167-12176} }
Galactic: Scaling End-to-End Reinforcement Learning for Rearrangement at 100k Steps-per-Second: Vincent-Pierre Berges,

Andrew Szot,

Devendra Singh Chaplot,

Aaron Gokaslan,

Roozbeh Mottaghi,

Dhruv Batra,

Eric Undersander; [pdf] [supp]
[bibtex]
@InProceedings{Berges_2023_CVPR, author = {Berges, Vincent-Pierre and Szot, Andrew and Chaplot, Devendra Singh and Gokaslan, Aaron and Mottaghi, Roozbeh and Batra, Dhruv and Undersander, Eric}, title = {Galactic: Scaling End-to-End Reinforcement Learning for Rearrangement at 100k Steps-per-Second}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13767-13777} }
Learning on Gradients: Generalized Artifacts Representation for GAN-Generated Images Detection: Chuangchuang Tan,

Yao Zhao,

Shikui Wei,

Guanghua Gu,

Yunchao Wei; [pdf]
[bibtex]
@InProceedings{Tan_2023_CVPR, author = {Tan, Chuangchuang and Zhao, Yao and Wei, Shikui and Gu, Guanghua and Wei, Yunchao}, title = {Learning on Gradients: Generalized Artifacts Representation for GAN-Generated Images Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12105-12114} }
Don't Lie to Me! Robust and Efficient Explainability With Verified Perturbation Analysis: Thomas Fel,

Melanie Ducoffe,

David Vigouroux,

Rémi Cadène,

Mikaël Capelle,

Claire Nicodème,

Thomas Serre; [pdf] [supp]
[bibtex]
@InProceedings{Fel_2023_CVPR, author = {Fel, Thomas and Ducoffe, Melanie and Vigouroux, David and Cad\`ene, R\'emi and Capelle, Mika\"el and Nicod\`eme, Claire and Serre, Thomas}, title = {Don't Lie to Me! Robust and Efficient Explainability With Verified Perturbation Analysis}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16153-16163} }
Defending Against Patch-Based Backdoor Attacks on Self-Supervised Learning: Ajinkya Tejankar,

Maziar Sanjabi,

Qifan Wang,

Sinong Wang,

Hamed Firooz,

Hamed Pirsiavash,

Liang Tan; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Tejankar_2023_CVPR, author = {Tejankar, Ajinkya and Sanjabi, Maziar and Wang, Qifan and Wang, Sinong and Firooz, Hamed and Pirsiavash, Hamed and Tan, Liang}, title = {Defending Against Patch-Based Backdoor Attacks on Self-Supervised Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12239-12249} }
GeoNet: Benchmarking Unsupervised Adaptation Across Geographies: Tarun Kalluri,

Wangdong Xu,

Manmohan Chandraker; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kalluri_2023_CVPR, author = {Kalluri, Tarun and Xu, Wangdong and Chandraker, Manmohan}, title = {GeoNet: Benchmarking Unsupervised Adaptation Across Geographies}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15368-15379} }
Learning Transformation-Predictive Representations for Detection and Description of Local Features: Zihao Wang,

Chunxu Wu,

Yifei Yang,

Zhen Li; [pdf] [supp]
[bibtex]
@InProceedings{Wang_2023_CVPR, author = {Wang, Zihao and Wu, Chunxu and Yang, Yifei and Li, Zhen}, title = {Learning Transformation-Predictive Representations for Detection and Description of Local Features}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11464-11473} }
Dionysus: Recovering Scene Structures by Dividing Into Semantic Pieces: Likang Wang,

Lei Chen; [pdf]
[bibtex]
@InProceedings{Wang_2023_CVPR, author = {Wang, Likang and Chen, Lei}, title = {Dionysus: Recovering Scene Structures by Dividing Into Semantic Pieces}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12576-12587} }
Advancing Visual Grounding With Scene Knowledge: Benchmark and Method: Zhihong Chen,

Ruifei Zhang,

Yibing Song,

Xiang Wan,

Guanbin Li; [pdf]
[bibtex]
@InProceedings{Chen_2023_CVPR, author = {Chen, Zhihong and Zhang, Ruifei and Song, Yibing and Wan, Xiang and Li, Guanbin}, title = {Advancing Visual Grounding With Scene Knowledge: Benchmark and Method}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15039-15049} }
Multiview Compressive Coding for 3D Reconstruction: Chao-Yuan Wu,

Justin Johnson,

Jitendra Malik,

Christoph Feichtenhofer,

Georgia Gkioxari; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wu_2023_CVPR, author = {Wu, Chao-Yuan and Johnson, Justin and Malik, Jitendra and Feichtenhofer, Christoph and Gkioxari, Georgia}, title = {Multiview Compressive Coding for 3D Reconstruction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9065-9075} }
Modeling Entities As Semantic Points for Visual Information Extraction in the Wild: Zhibo Yang,

Rujiao Long,

Pengfei Wang,

Sibo Song,

Humen Zhong,

Wenqing Cheng,

Xiang Bai,

Cong Yao; [pdf] [arXiv]
[bibtex]
@InProceedings{Yang_2023_CVPR, author = {Yang, Zhibo and Long, Rujiao and Wang, Pengfei and Song, Sibo and Zhong, Humen and Cheng, Wenqing and Bai, Xiang and Yao, Cong}, title = {Modeling Entities As Semantic Points for Visual Information Extraction in the Wild}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15358-15367} }
MobileVOS: Real-Time Video Object Segmentation Contrastive Learning Meets Knowledge Distillation: Roy Miles,

Mehmet Kerim Yucel,

Bruno Manganelli,

Albert Saà-Garriga; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Miles_2023_CVPR, author = {Miles, Roy and Yucel, Mehmet Kerim and Manganelli, Bruno and Sa\`a-Garriga, Albert}, title = {MobileVOS: Real-Time Video Object Segmentation Contrastive Learning Meets Knowledge Distillation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10480-10490} }
Pose Synchronization Under Multiple Pair-Wise Relative Poses: Yifan Sun,

Qixing Huang; [pdf] [supp]
[bibtex]
@InProceedings{Sun_2023_CVPR, author = {Sun, Yifan and Huang, Qixing}, title = {Pose Synchronization Under Multiple Pair-Wise Relative Poses}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13072-13081} }
Controllable Light Diffusion for Portraits: David Futschik,

Kelvin Ritland,

James Vecore,

Sean Fanello,

Sergio Orts-Escolano,

Brian Curless,

Daniel Sýkora,

Rohit Pandey; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Futschik_2023_CVPR, author = {Futschik, David and Ritland, Kelvin and Vecore, James and Fanello, Sean and Orts-Escolano, Sergio and Curless, Brian and S\'ykora, Daniel and Pandey, Rohit}, title = {Controllable Light Diffusion for Portraits}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8412-8421} }
Boosting Low-Data Instance Segmentation by Unsupervised Pre-Training With Saliency Prompt: Hao Li,

Dingwen Zhang,

Nian Liu,

Lechao Cheng,

Yalun Dai,

Chao Zhang,

Xinggang Wang,

Junwei Han; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Li_2023_CVPR, author = {Li, Hao and Zhang, Dingwen and Liu, Nian and Cheng, Lechao and Dai, Yalun and Zhang, Chao and Wang, Xinggang and Han, Junwei}, title = {Boosting Low-Data Instance Segmentation by Unsupervised Pre-Training With Saliency Prompt}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15485-15494} }
Virtual Occlusions Through Implicit Depth: Jamie Watson,

Mohamed Sayed,

Zawar Qureshi,

Gabriel J. Brostow,

Sara Vicente,

Oisin Mac Aodha,

Michael Firman; [pdf] [arXiv]
[bibtex]
@InProceedings{Watson_2023_CVPR, author = {Watson, Jamie and Sayed, Mohamed and Qureshi, Zawar and Brostow, Gabriel J. and Vicente, Sara and Mac Aodha, Oisin and Firman, Michael}, title = {Virtual Occlusions Through Implicit Depth}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9053-9064} }
DiGA: Distil To Generalize and Then Adapt for Domain Adaptive Semantic Segmentation: Fengyi Shen,

Akhil Gurram,

Ziyuan Liu,

He Wang,

Alois Knoll; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Shen_2023_CVPR, author = {Shen, Fengyi and Gurram, Akhil and Liu, Ziyuan and Wang, He and Knoll, Alois}, title = {DiGA: Distil To Generalize and Then Adapt for Domain Adaptive Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15866-15877} }
DiffSwap: High-Fidelity and Controllable Face Swapping via 3D-Aware Masked Diffusion: Wenliang Zhao,

Yongming Rao,

Weikang Shi,

Zuyan Liu,

Jie Zhou,

Jiwen Lu; [pdf]
[bibtex]
@InProceedings{Zhao_2023_CVPR, author = {Zhao, Wenliang and Rao, Yongming and Shi, Weikang and Liu, Zuyan and Zhou, Jie and Lu, Jiwen}, title = {DiffSwap: High-Fidelity and Controllable Face Swapping via 3D-Aware Masked Diffusion}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8568-8577} }
Learned Image Compression With Mixed Transformer-CNN Architectures: Jinming Liu,

Heming Sun,

Jiro Katto; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Liu_2023_CVPR, author = {Liu, Jinming and Sun, Heming and Katto, Jiro}, title = {Learned Image Compression With Mixed Transformer-CNN Architectures}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14388-14397} }
Quantum Multi-Model Fitting: Matteo Farina,

Luca Magri,

Willi Menapace,

Elisa Ricci,

Vladislav Golyanik,

Federica Arrigoni; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Farina_2023_CVPR, author = {Farina, Matteo and Magri, Luca and Menapace, Willi and Ricci, Elisa and Golyanik, Vladislav and Arrigoni, Federica}, title = {Quantum Multi-Model Fitting}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13640-13649} }
PermutoSDF: Fast Multi-View Reconstruction With Implicit Surfaces Using Permutohedral Lattices: Radu Alexandru Rosu,

Sven Behnke; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Rosu_2023_CVPR, author = {Rosu, Radu Alexandru and Behnke, Sven}, title = {PermutoSDF: Fast Multi-View Reconstruction With Implicit Surfaces Using Permutohedral Lattices}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8466-8475} }
Detection Hub: Unifying Object Detection Datasets via Query Adaptation on Language Embedding: Lingchen Meng,

Xiyang Dai,

Yinpeng Chen,

Pengchuan Zhang,

Dongdong Chen,

Mengchen Liu,

Jianfeng Wang,

Zuxuan Wu,

Lu Yuan,

Yu-Gang Jiang; [pdf] [arXiv]
[bibtex]
@InProceedings{Meng_2023_CVPR, author = {Meng, Lingchen and Dai, Xiyang and Chen, Yinpeng and Zhang, Pengchuan and Chen, Dongdong and Liu, Mengchen and Wang, Jianfeng and Wu, Zuxuan and Yuan, Lu and Jiang, Yu-Gang}, title = {Detection Hub: Unifying Object Detection Datasets via Query Adaptation on Language Embedding}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11402-11411} }
Adversarial Normalization: I Can Visualize Everything (ICE): Hoyoung Choi,

Seungwan Jin,

Kyungsik Han; [pdf]
[bibtex]
@InProceedings{Choi_2023_CVPR, author = {Choi, Hoyoung and Jin, Seungwan and Han, Kyungsik}, title = {Adversarial Normalization: I Can Visualize Everything (ICE)}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12115-12124} }
Referring Multi-Object Tracking: Dongming Wu,

Wencheng Han,

Tiancai Wang,

Xingping Dong,

Xiangyu Zhang,

Jianbing Shen; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wu_2023_CVPR, author = {Wu, Dongming and Han, Wencheng and Wang, Tiancai and Dong, Xingping and Zhang, Xiangyu and Shen, Jianbing}, title = {Referring Multi-Object Tracking}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14633-14642} }
Hint-Aug: Drawing Hints From Foundation Vision Transformers Towards Boosted Few-Shot Parameter-Efficient Tuning: Zhongzhi Yu,

Shang Wu,

Yonggan Fu,

Shunyao Zhang,

Yingyan (Celine) Lin; [pdf]
[bibtex]
@InProceedings{Yu_2023_CVPR, author = {Yu, Zhongzhi and Wu, Shang and Fu, Yonggan and Zhang, Shunyao and Lin, Yingyan (Celine)}, title = {Hint-Aug: Drawing Hints From Foundation Vision Transformers Towards Boosted Few-Shot Parameter-Efficient Tuning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11102-11112} }
A Strong Baseline for Generalized Few-Shot Semantic Segmentation: Sina Hajimiri,

Malik Boudiaf,

Ismail Ben Ayed,

Jose Dolz; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Hajimiri_2023_CVPR, author = {Hajimiri, Sina and Boudiaf, Malik and Ben Ayed, Ismail and Dolz, Jose}, title = {A Strong Baseline for Generalized Few-Shot Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11269-11278} }
DynaFed: Tackling Client Data Heterogeneity With Global Dynamics: Renjie Pi,

Weizhong Zhang,

Yueqi Xie,

Jiahui Gao,

Xiaoyu Wang,

Sunghun Kim,

Qifeng Chen; [pdf] [arXiv]
[bibtex]
@InProceedings{Pi_2023_CVPR, author = {Pi, Renjie and Zhang, Weizhong and Xie, Yueqi and Gao, Jiahui and Wang, Xiaoyu and Kim, Sunghun and Chen, Qifeng}, title = {DynaFed: Tackling Client Data Heterogeneity With Global Dynamics}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12177-12186} }
CUF: Continuous Upsampling Filters: Cristina N. Vasconcelos,

Cengiz Oztireli,

Mark Matthews,

Milad Hashemi,

Kevin Swersky,

Andrea Tagliasacchi; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Vasconcelos_2023_CVPR, author = {Vasconcelos, Cristina N. and Oztireli, Cengiz and Matthews, Mark and Hashemi, Milad and Swersky, Kevin and Tagliasacchi, Andrea}, title = {CUF: Continuous Upsampling Filters}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9999-10008} }
Quantitative Manipulation of Custom Attributes on 3D-Aware Image Synthesis: Hoseok Do,

EunKyung Yoo,

Taehyeong Kim,

Chul Lee,

Jin Young Choi; [pdf] [supp]
[bibtex]
@InProceedings{Do_2023_CVPR, author = {Do, Hoseok and Yoo, EunKyung and Kim, Taehyeong and Lee, Chul and Choi, Jin Young}, title = {Quantitative Manipulation of Custom Attributes on 3D-Aware Image Synthesis}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8529-8538} }
HOTNAS: Hierarchical Optimal Transport for Neural Architecture Search: Jiechao Yang,

Yong Liu,

Hongteng Xu; [pdf] [supp]
[bibtex]
@InProceedings{Yang_2023_CVPR, author = {Yang, Jiechao and Liu, Yong and Xu, Hongteng}, title = {HOTNAS: Hierarchical Optimal Transport for Neural Architecture Search}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11990-12000} }
Neural Fields Meet Explicit Geometric Representations for Inverse Rendering of Urban Scenes: Zian Wang,

Tianchang Shen,

Jun Gao,

Shengyu Huang,

Jacob Munkberg,

Jon Hasselgren,

Zan Gojcic,

Wenzheng Chen,

Sanja Fidler; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2023_CVPR, author = {Wang, Zian and Shen, Tianchang and Gao, Jun and Huang, Shengyu and Munkberg, Jacob and Hasselgren, Jon and Gojcic, Zan and Chen, Wenzheng and Fidler, Sanja}, title = {Neural Fields Meet Explicit Geometric Representations for Inverse Rendering of Urban Scenes}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8370-8380} }
Cross-Image-Attention for Conditional Embeddings in Deep Metric Learning: Dmytro Kotovenko,

Pingchuan Ma,

Timo Milbich,

Björn Ommer; [pdf] [supp]
[bibtex]
@InProceedings{Kotovenko_2023_CVPR, author = {Kotovenko, Dmytro and Ma, Pingchuan and Milbich, Timo and Ommer, Bj\"orn}, title = {Cross-Image-Attention for Conditional Embeddings in Deep Metric Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11070-11081} }
Enhanced Multimodal Representation Learning With Cross-Modal KD: Mengxi Chen,

Linyu Xing,

Yu Wang,

Ya Zhang; [pdf] [supp]
[bibtex]
@InProceedings{Chen_2023_CVPR, author = {Chen, Mengxi and Xing, Linyu and Wang, Yu and Zhang, Ya}, title = {Enhanced Multimodal Representation Learning With Cross-Modal KD}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11766-11775} }
Learning a Depth Covariance Function: Eric Dexheimer,

Andrew J. Davison; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Dexheimer_2023_CVPR, author = {Dexheimer, Eric and Davison, Andrew J.}, title = {Learning a Depth Covariance Function}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13122-13131} }
Evading DeepFake Detectors via Adversarial Statistical Consistency: Yang Hou,

Qing Guo,

Yihao Huang,

Xiaofei Xie,

Lei Ma,

Jianjun Zhao; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Hou_2023_CVPR, author = {Hou, Yang and Guo, Qing and Huang, Yihao and Xie, Xiaofei and Ma, Lei and Zhao, Jianjun}, title = {Evading DeepFake Detectors via Adversarial Statistical Consistency}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12271-12280} }
V2V4Real: A Real-World Large-Scale Dataset for Vehicle-to-Vehicle Cooperative Perception: Runsheng Xu,

Xin Xia,

Jinlong Li,

Hanzhao Li,

Shuo Zhang,

Zhengzhong Tu,

Zonglin Meng,

Hao Xiang,

Xiaoyu Dong,

Rui Song,

Hongkai Yu,

Bolei Zhou,

Jiaqi Ma; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Xu_2023_CVPR, author = {Xu, Runsheng and Xia, Xin and Li, Jinlong and Li, Hanzhao and Zhang, Shuo and Tu, Zhengzhong and Meng, Zonglin and Xiang, Hao and Dong, Xiaoyu and Song, Rui and Yu, Hongkai and Zhou, Bolei and Ma, Jiaqi}, title = {V2V4Real: A Real-World Large-Scale Dataset for Vehicle-to-Vehicle Cooperative Perception}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13712-13722} }
RMLVQA: A Margin Loss Approach for Visual Question Answering With Language Biases: Abhipsa Basu,

Sravanti Addepalli,

R. Venkatesh Babu; [pdf] [supp]
[bibtex]
@InProceedings{Basu_2023_CVPR, author = {Basu, Abhipsa and Addepalli, Sravanti and Babu, R. Venkatesh}, title = {RMLVQA: A Margin Loss Approach for Visual Question Answering With Language Biases}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11671-11680} }
Adaptive Sparse Convolutional Networks With Global Context Enhancement for Faster Object Detection on Drone Images: Bowei Du,

Yecheng Huang,

Jiaxin Chen,

Di Huang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Du_2023_CVPR, author = {Du, Bowei and Huang, Yecheng and Chen, Jiaxin and Huang, Di}, title = {Adaptive Sparse Convolutional Networks With Global Context Enhancement for Faster Object Detection on Drone Images}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13435-13444} }
Command-Driven Articulated Object Understanding and Manipulation: Ruihang Chu,

Zhengzhe Liu,

Xiaoqing Ye,

Xiao Tan,

Xiaojuan Qi,

Chi-Wing Fu,

Jiaya Jia; [pdf] [supp]
[bibtex]
@InProceedings{Chu_2023_CVPR, author = {Chu, Ruihang and Liu, Zhengzhe and Ye, Xiaoqing and Tan, Xiao and Qi, Xiaojuan and Fu, Chi-Wing and Jia, Jiaya}, title = {Command-Driven Articulated Object Understanding and Manipulation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8813-8823} }
ConStruct-VL: Data-Free Continual Structured VL Concepts Learning: James Seale Smith,

Paola Cascante-Bonilla,

Assaf Arbelle,

Donghyun Kim,

Rameswar Panda,

David Cox,

Diyi Yang,

Zsolt Kira,

Rogerio Feris,

Leonid Karlinsky; [pdf] [supp]
[bibtex]
@InProceedings{Smith_2023_CVPR, author = {Smith, James Seale and Cascante-Bonilla, Paola and Arbelle, Assaf and Kim, Donghyun and Panda, Rameswar and Cox, David and Yang, Diyi and Kira, Zsolt and Feris, Rogerio and Karlinsky, Leonid}, title = {ConStruct-VL: Data-Free Continual Structured VL Concepts Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14994-15004} }
HelixSurf: A Robust and Efficient Neural Implicit Surface Learning of Indoor Scenes With Iterative Intertwined Regularization: Zhihao Liang,

Zhangjin Huang,

Changxing Ding,

Kui Jia; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Liang_2023_CVPR, author = {Liang, Zhihao and Huang, Zhangjin and Ding, Changxing and Jia, Kui}, title = {HelixSurf: A Robust and Efficient Neural Implicit Surface Learning of Indoor Scenes With Iterative Intertwined Regularization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13165-13174} }
Towards a Smaller Student: Capacity Dynamic Distillation for Efficient Image Retrieval: Yi Xie,

Huaidong Zhang,

Xuemiao Xu,

Jianqing Zhu,

Shengfeng He; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Xie_2023_CVPR, author = {Xie, Yi and Zhang, Huaidong and Xu, Xuemiao and Zhu, Jianqing and He, Shengfeng}, title = {Towards a Smaller Student: Capacity Dynamic Distillation for Efficient Image Retrieval}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16006-16015} }
3D-Aware Facial Landmark Detection via Multi-View Consistent Training on Synthetic Data: Libing Zeng,

Lele Chen,

Wentao Bao,

Zhong Li,

Yi Xu,

Junsong Yuan,

Nima Khademi Kalantari; [pdf] [supp]
[bibtex]
@InProceedings{Zeng_2023_CVPR, author = {Zeng, Libing and Chen, Lele and Bao, Wentao and Li, Zhong and Xu, Yi and Yuan, Junsong and Kalantari, Nima Khademi}, title = {3D-Aware Facial Landmark Detection via Multi-View Consistent Training on Synthetic Data}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12747-12758} }
PC2: Projection-Conditioned Point Cloud Diffusion for Single-Image 3D Reconstruction: Luke Melas-Kyriazi,

Christian Rupprecht,

Andrea Vedaldi; [pdf] [supp]
[bibtex]
@InProceedings{Melas-Kyriazi_2023_CVPR, author = {Melas-Kyriazi, Luke and Rupprecht, Christian and Vedaldi, Andrea}, title = {PC2: Projection-Conditioned Point Cloud Diffusion for Single-Image 3D Reconstruction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12923-12932} }
Gradient-Based Uncertainty Attribution for Explainable Bayesian Deep Learning: Hanjing Wang,

Dhiraj Joshi,

Shiqiang Wang,

Qiang Ji; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2023_CVPR, author = {Wang, Hanjing and Joshi, Dhiraj and Wang, Shiqiang and Ji, Qiang}, title = {Gradient-Based Uncertainty Attribution for Explainable Bayesian Deep Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12044-12053} }
Manipulating Transfer Learning for Property Inference: Yulong Tian,

Fnu Suya,

Anshuman Suri,

Fengyuan Xu,

David Evans; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Tian_2023_CVPR, author = {Tian, Yulong and Suya, Fnu and Suri, Anshuman and Xu, Fengyuan and Evans, David}, title = {Manipulating Transfer Learning for Property Inference}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15975-15984} }
Class Adaptive Network Calibration: Bingyuan Liu,

Jérôme Rony,

Adrian Galdran,

Jose Dolz,

Ismail Ben Ayed; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Liu_2023_CVPR, author = {Liu, Bingyuan and Rony, J\'er\^ome and Galdran, Adrian and Dolz, Jose and Ben Ayed, Ismail}, title = {Class Adaptive Network Calibration}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16070-16079} }
Evading Forensic Classifiers With Attribute-Conditioned Adversarial Faces: Fahad Shamshad,

Koushik Srivatsan,

Karthik Nandakumar; [pdf] [supp]
[bibtex]
@InProceedings{Shamshad_2023_CVPR, author = {Shamshad, Fahad and Srivatsan, Koushik and Nandakumar, Karthik}, title = {Evading Forensic Classifiers With Attribute-Conditioned Adversarial Faces}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16469-16478} }
OCTET: Object-Aware Counterfactual Explanations: Mehdi Zemni,

Mickaël Chen,

Éloi Zablocki,

Hédi Ben-Younes,

Patrick Pérez,

Matthieu Cord; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zemni_2023_CVPR, author = {Zemni, Mehdi and Chen, Micka\"el and Zablocki, \'Eloi and Ben-Younes, H\'edi and P\'erez, Patrick and Cord, Matthieu}, title = {OCTET: Object-Aware Counterfactual Explanations}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15062-15071} }
Polarized Color Image Denoising: Zhuoxiao Li,

Haiyang Jiang,

Mingdeng Cao,

Yinqiang Zheng; [pdf] [supp]
[bibtex]
@InProceedings{Li_2023_CVPR, author = {Li, Zhuoxiao and Jiang, Haiyang and Cao, Mingdeng and Zheng, Yinqiang}, title = {Polarized Color Image Denoising}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9873-9882} }
UniDAformer: Unified Domain Adaptive Panoptic Segmentation Transformer via Hierarchical Mask Calibration: Jingyi Zhang,

Jiaxing Huang,

Xiaoqin Zhang,

Shijian Lu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhang_2023_CVPR, author = {Zhang, Jingyi and Huang, Jiaxing and Zhang, Xiaoqin and Lu, Shijian}, title = {UniDAformer: Unified Domain Adaptive Panoptic Segmentation Transformer via Hierarchical Mask Calibration}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11227-11237} }
Non-Contrastive Learning Meets Language-Image Pre-Training: Jinghao Zhou,

Li Dong,

Zhe Gan,

Lijuan Wang,

Furu Wei; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhou_2023_CVPR, author = {Zhou, Jinghao and Dong, Li and Gan, Zhe and Wang, Lijuan and Wei, Furu}, title = {Non-Contrastive Learning Meets Language-Image Pre-Training}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11028-11038} }
Switchable Representation Learning Framework With Self-Compatibility: Shengsen Wu,

Yan Bai,

Yihang Lou,

Xiongkun Linghu,

Jianzhong He,

Ling-Yu Duan; [pdf] [arXiv]
[bibtex]
@InProceedings{Wu_2023_CVPR, author = {Wu, Shengsen and Bai, Yan and Lou, Yihang and Linghu, Xiongkun and He, Jianzhong and Duan, Ling-Yu}, title = {Switchable Representation Learning Framework With Self-Compatibility}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15943-15953} }
Zero-Shot Dual-Lens Super-Resolution: Ruikang Xu,

Mingde Yao,

Zhiwei Xiong; [pdf] [supp]
[bibtex]
@InProceedings{Xu_2023_CVPR, author = {Xu, Ruikang and Yao, Mingde and Xiong, Zhiwei}, title = {Zero-Shot Dual-Lens Super-Resolution}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9130-9139} }
Improving Vision-and-Language Navigation by Generating Future-View Image Semantics: Jialu Li,

Mohit Bansal; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Li_2023_CVPR, author = {Li, Jialu and Bansal, Mohit}, title = {Improving Vision-and-Language Navigation by Generating Future-View Image Semantics}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10803-10812} }
gSDF: Geometry-Driven Signed Distance Functions for 3D Hand-Object Reconstruction: Zerui Chen,

Shizhe Chen,

Cordelia Schmid,

Ivan Laptev; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chen_2023_CVPR, author = {Chen, Zerui and Chen, Shizhe and Schmid, Cordelia and Laptev, Ivan}, title = {gSDF: Geometry-Driven Signed Distance Functions for 3D Hand-Object Reconstruction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12890-12900} }
CIMI4D: A Large Multimodal Climbing Motion Dataset Under Human-Scene Interactions: Ming Yan,

Xin Wang,

Yudi Dai,

Siqi Shen,

Chenglu Wen,

Lan Xu,

Yuexin Ma,

Cheng Wang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yan_2023_CVPR, author = {Yan, Ming and Wang, Xin and Dai, Yudi and Shen, Siqi and Wen, Chenglu and Xu, Lan and Ma, Yuexin and Wang, Cheng}, title = {CIMI4D: A Large Multimodal Climbing Motion Dataset Under Human-Scene Interactions}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12977-12988} }
Modernizing Old Photos Using Multiple References via Photorealistic Style Transfer: Agus Gunawan,

Soo Ye Kim,

Hyeonjun Sim,

Jae-Ho Lee,

Munchurl Kim; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Gunawan_2023_CVPR, author = {Gunawan, Agus and Kim, Soo Ye and Sim, Hyeonjun and Lee, Jae-Ho and Kim, Munchurl}, title = {Modernizing Old Photos Using Multiple References via Photorealistic Style Transfer}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12460-12469} }
Curvature-Balanced Feature Manifold Learning for Long-Tailed Classification: Yanbiao Ma,

Licheng Jiao,

Fang Liu,

Shuyuan Yang,

Xu Liu,

Lingling Li; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ma_2023_CVPR, author = {Ma, Yanbiao and Jiao, Licheng and Liu, Fang and Yang, Shuyuan and Liu, Xu and Li, Lingling}, title = {Curvature-Balanced Feature Manifold Learning for Long-Tailed Classification}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15824-15835} }; Back