CVPR 2022 Open Access Repository

Papers

Back
Dual Cross-Attention Learning for Fine-Grained Visual Categorization and Object Re-Identification: Haowei Zhu,

Wenjing Ke,

Dong Li,

Ji Liu,

Lu Tian,

Yi Shan; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhu_2022_CVPR, author = {Zhu, Haowei and Ke, Wenjing and Li, Dong and Liu, Ji and Tian, Lu and Shan, Yi}, title = {Dual Cross-Attention Learning for Fine-Grained Visual Categorization and Object Re-Identification}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {4692-4702} }
SimAN: Exploring Self-Supervised Representation Learning of Scene Text via Similarity-Aware Normalization: Canjie Luo,

Lianwen Jin,

Jingdong Chen; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Luo_2022_CVPR, author = {Luo, Canjie and Jin, Lianwen and Chen, Jingdong}, title = {SimAN: Exploring Self-Supervised Representation Learning of Scene Text via Similarity-Aware Normalization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {1039-1048} }
Weakly Supervised Semantic Segmentation by Pixel-to-Prototype Contrast: Ye Du,

Zehua Fu,

Qingjie Liu,

Yunhong Wang; [pdf] [arXiv]
[bibtex]
@InProceedings{Du_2022_CVPR, author = {Du, Ye and Fu, Zehua and Liu, Qingjie and Wang, Yunhong}, title = {Weakly Supervised Semantic Segmentation by Pixel-to-Prototype Contrast}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {4320-4329} }
Controllable Animation of Fluid Elements in Still Images: Aniruddha Mahapatra,

Kuldeep Kulkarni; [pdf] [arXiv]
[bibtex]
@InProceedings{Mahapatra_2022_CVPR, author = {Mahapatra, Aniruddha and Kulkarni, Kuldeep}, title = {Controllable Animation of Fluid Elements in Still Images}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {3667-3676} }
Recurrent Dynamic Embedding for Video Object Segmentation: Mingxing Li,

Li Hu,

Zhiwei Xiong,

Bang Zhang,

Pan Pan,

Dong Liu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Li_2022_CVPR, author = {Li, Mingxing and Hu, Li and Xiong, Zhiwei and Zhang, Bang and Pan, Pan and Liu, Dong}, title = {Recurrent Dynamic Embedding for Video Object Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {1332-1341} }
Deep Hierarchical Semantic Segmentation: Liulei Li,

Tianfei Zhou,

Wenguan Wang,

Jianwu Li,

Yi Yang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Li_2022_CVPR, author = {Li, Liulei and Zhou, Tianfei and Wang, Wenguan and Li, Jianwu and Yang, Yi}, title = {Deep Hierarchical Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {1246-1257} }
f-SfT: Shape-From-Template With a Physics-Based Deformation Model: Navami Kairanda,

Edith Tretschk,

Mohamed Elgharib,

Christian Theobalt,

Vladislav Golyanik; [pdf] [supp]
[bibtex]
@InProceedings{Kairanda_2022_CVPR, author = {Kairanda, Navami and Tretschk, Edith and Elgharib, Mohamed and Theobalt, Christian and Golyanik, Vladislav}, title = {f-SfT: Shape-From-Template With a Physics-Based Deformation Model}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {3948-3958} }
TWIST: Two-Way Inter-Label Self-Training for Semi-Supervised 3D Instance Segmentation: Ruihang Chu,

Xiaoqing Ye,

Zhengzhe Liu,

Xiao Tan,

Xiaojuan Qi,

Chi-Wing Fu,

Jiaya Jia; [pdf] [supp]
[bibtex]
@InProceedings{Chu_2022_CVPR, author = {Chu, Ruihang and Ye, Xiaoqing and Liu, Zhengzhe and Tan, Xiao and Qi, Xiaojuan and Fu, Chi-Wing and Jia, Jiaya}, title = {TWIST: Two-Way Inter-Label Self-Training for Semi-Supervised 3D Instance Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {1100-1109} }
Do Learned Representations Respect Causal Relationships?: Lan Wang,

Vishnu Naresh Boddeti; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2022_CVPR, author = {Wang, Lan and Boddeti, Vishnu Naresh}, title = {Do Learned Representations Respect Causal Relationships?}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {264-274} }
Multi-Class Token Transformer for Weakly Supervised Semantic Segmentation: Lian Xu,

Wanli Ouyang,

Mohammed Bennamoun,

Farid Boussaid,

Dan Xu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Xu_2022_CVPR, author = {Xu, Lian and Ouyang, Wanli and Bennamoun, Mohammed and Boussaid, Farid and Xu, Dan}, title = {Multi-Class Token Transformer for Weakly Supervised Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {4310-4319} }
3D Moments From Near-Duplicate Photos: Qianqian Wang,

Zhengqi Li,

David Salesin,

Noah Snavely,

Brian Curless,

Janne Kontkanen; [pdf] [arXiv]
[bibtex]
@InProceedings{Wang_2022_CVPR, author = {Wang, Qianqian and Li, Zhengqi and Salesin, David and Snavely, Noah and Curless, Brian and Kontkanen, Janne}, title = {3D Moments From Near-Duplicate Photos}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {3906-3915} }
Blind2Unblind: Self-Supervised Image Denoising With Visible Blind Spots: Zejin Wang,

Jiazheng Liu,

Guoqing Li,

Hua Han; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2022_CVPR, author = {Wang, Zejin and Liu, Jiazheng and Li, Guoqing and Han, Hua}, title = {Blind2Unblind: Self-Supervised Image Denoising With Visible Blind Spots}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {2027-2036} }
CLRNet: Cross Layer Refinement Network for Lane Detection: Tu Zheng,

Yifei Huang,

Yang Liu,

Wenjian Tang,

Zheng Yang,

Deng Cai,

Xiaofei He; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zheng_2022_CVPR, author = {Zheng, Tu and Huang, Yifei and Liu, Yang and Tang, Wenjian and Yang, Zheng and Cai, Deng and He, Xiaofei}, title = {CLRNet: Cross Layer Refinement Network for Lane Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {898-907} }
Pointly-Supervised Instance Segmentation: Bowen Cheng,

Omkar Parkhi,

Alexander Kirillov; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Cheng_2022_CVPR, author = {Cheng, Bowen and Parkhi, Omkar and Kirillov, Alexander}, title = {Pointly-Supervised Instance Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {2617-2626} }
LGT-Net: Indoor Panoramic Room Layout Estimation With Geometry-Aware Transformer Network: Zhigang Jiang,

Zhongzheng Xiang,

Jinhua Xu,

Ming Zhao; [pdf] [supp]
[bibtex]
@InProceedings{Jiang_2022_CVPR, author = {Jiang, Zhigang and Xiang, Zhongzheng and Xu, Jinhua and Zhao, Ming}, title = {LGT-Net: Indoor Panoramic Room Layout Estimation With Geometry-Aware Transformer Network}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {1654-1663} }
Sparse Local Patch Transformer for Robust Face Alignment and Landmarks Inherent Relation Learning: Jiahao Xia,

Weiwei Qu,

Wenjian Huang,

Jianguo Zhang,

Xi Wang,

Min Xu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Xia_2022_CVPR, author = {Xia, Jiahao and Qu, Weiwei and Huang, Wenjian and Zhang, Jianguo and Wang, Xi and Xu, Min}, title = {Sparse Local Patch Transformer for Robust Face Alignment and Landmarks Inherent Relation Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {4052-4061} }
Rotationally Equivariant 3D Object Detection: Hong-Xing Yu,

Jiajun Wu,

Li Yi; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yu_2022_CVPR, author = {Yu, Hong-Xing and Wu, Jiajun and Yi, Li}, title = {Rotationally Equivariant 3D Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {1456-1464} }
Accelerating DETR Convergence via Semantic-Aligned Matching: Gongjie Zhang,

Zhipeng Luo,

Yingchen Yu,

Kaiwen Cui,

Shijian Lu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhang_2022_CVPR, author = {Zhang, Gongjie and Luo, Zhipeng and Yu, Yingchen and Cui, Kaiwen and Lu, Shijian}, title = {Accelerating DETR Convergence via Semantic-Aligned Matching}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {949-958} }
Vision Transformer With Deformable Attention: Zhuofan Xia,

Xuran Pan,

Shiji Song,

Li Erran Li,

Gao Huang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Xia_2022_CVPR, author = {Xia, Zhuofan and Pan, Xuran and Song, Shiji and Li, Li Erran and Huang, Gao}, title = {Vision Transformer With Deformable Attention}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {4794-4803} }
RM-Depth: Unsupervised Learning of Recurrent Monocular Depth in Dynamic Scenes: Tak-Wai Hui; [pdf]
[bibtex]
@InProceedings{Hui_2022_CVPR, author = {Hui, Tak-Wai}, title = {RM-Depth: Unsupervised Learning of Recurrent Monocular Depth in Dynamic Scenes}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {1675-1684} }
Cloning Outfits From Real-World Images to 3D Characters for Generalizable Person Re-Identification: Yanan Wang,

Xuezhi Liang,

Shengcai Liao; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2022_CVPR, author = {Wang, Yanan and Liang, Xuezhi and Liao, Shengcai}, title = {Cloning Outfits From Real-World Images to 3D Characters for Generalizable Person Re-Identification}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {4900-4909} }
ABPN: Adaptive Blend Pyramid Network for Real-Time Local Retouching of Ultra High-Resolution Photo: Biwen Lei,

Xiefan Guo,

Hongyu Yang,

Miaomiao Cui,

Xuansong Xie,

Di Huang; [pdf] [supp]
[bibtex]
@InProceedings{Lei_2022_CVPR, author = {Lei, Biwen and Guo, Xiefan and Yang, Hongyu and Cui, Miaomiao and Xie, Xuansong and Huang, Di}, title = {ABPN: Adaptive Blend Pyramid Network for Real-Time Local Retouching of Ultra High-Resolution Photo}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {2108-2117} }
Portrait Eyeglasses and Shadow Removal by Leveraging 3D Synthetic Data: Junfeng Lyu,

Zhibo Wang,

Feng Xu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Lyu_2022_CVPR, author = {Lyu, Junfeng and Wang, Zhibo and Xu, Feng}, title = {Portrait Eyeglasses and Shadow Removal by Leveraging 3D Synthetic Data}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {3429-3439} }
Open-World Instance Segmentation: Exploiting Pseudo Ground Truth From Learned Pairwise Affinity: Weiyao Wang,

Matt Feiszli,

Heng Wang,

Jitendra Malik,

Du Tran; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2022_CVPR, author = {Wang, Weiyao and Feiszli, Matt and Wang, Heng and Malik, Jitendra and Tran, Du}, title = {Open-World Instance Segmentation: Exploiting Pseudo Ground Truth From Learned Pairwise Affinity}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {4422-4432} }
HandOccNet: Occlusion-Robust 3D Hand Mesh Estimation Network: JoonKyu Park,

Yeonguk Oh,

Gyeongsik Moon,

Hongsuk Choi,

Kyoung Mu Lee; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Park_2022_CVPR, author = {Park, JoonKyu and Oh, Yeonguk and Moon, Gyeongsik and Choi, Hongsuk and Lee, Kyoung Mu}, title = {HandOccNet: Occlusion-Robust 3D Hand Mesh Estimation Network}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {1496-1505} }
Modular Action Concept Grounding in Semantic Video Prediction: Wei Yu,

Wenxin Chen,

Songheng Yin,

Steve Easterbrook,

Animesh Garg; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yu_2022_CVPR, author = {Yu, Wei and Chen, Wenxin and Yin, Songheng and Easterbrook, Steve and Garg, Animesh}, title = {Modular Action Concept Grounding in Semantic Video Prediction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {3605-3614} }
Sub-Word Level Lip Reading With Visual Attention: K R Prajwal,

Triantafyllos Afouras,

Andrew Zisserman; [pdf] [arXiv]
[bibtex]
@InProceedings{Prajwal_2022_CVPR, author = {Prajwal, K R and Afouras, Triantafyllos and Zisserman, Andrew}, title = {Sub-Word Level Lip Reading With Visual Attention}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {5162-5172} }
Weakly Supervised High-Fidelity Clothing Model Generation: Ruili Feng,

Cheng Ma,

Chengji Shen,

Xin Gao,

Zhenjiang Liu,

Xiaobo Li,

Kairi Ou,

Deli Zhao,

Zheng-Jun Zha; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Feng_2022_CVPR, author = {Feng, Ruili and Ma, Cheng and Shen, Chengji and Gao, Xin and Liu, Zhenjiang and Li, Xiaobo and Ou, Kairi and Zhao, Deli and Zha, Zheng-Jun}, title = {Weakly Supervised High-Fidelity Clothing Model Generation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {3440-3449} }
Knowledge Mining With Scene Text for Fine-Grained Recognition: Hao Wang,

Junchao Liao,

Tianheng Cheng,

Zewen Gao,

Hao Liu,

Bo Ren,

Xiang Bai,

Wenyu Liu; [pdf] [arXiv]
[bibtex]
@InProceedings{Wang_2022_CVPR, author = {Wang, Hao and Liao, Junchao and Cheng, Tianheng and Gao, Zewen and Liu, Hao and Ren, Bo and Bai, Xiang and Liu, Wenyu}, title = {Knowledge Mining With Scene Text for Fine-Grained Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {4624-4633} }
TransGeo: Transformer Is All You Need for Cross-View Image Geo-Localization: Sijie Zhu,

Mubarak Shah,

Chen Chen; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhu_2022_CVPR, author = {Zhu, Sijie and Shah, Mubarak and Chen, Chen}, title = {TransGeo: Transformer Is All You Need for Cross-View Image Geo-Localization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {1162-1171} }
R(Det)2: Randomized Decision Routing for Object Detection: Yali Li,

Shengjin Wang; [pdf] [supp]
[bibtex]
@InProceedings{Li_2022_CVPR, author = {Li, Yali and Wang, Shengjin}, title = {R(Det)2: Randomized Decision Routing for Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {4825-4834} }
SASIC: Stereo Image Compression With Latent Shifts and Stereo Attention: Matthias Wödlinger,

Jan Kotera,

Jan Xu,

Robert Sablatnig; [pdf] [supp]
[bibtex]
@InProceedings{Wodlinger_2022_CVPR, author = {W\"odlinger, Matthias and Kotera, Jan and Xu, Jan and Sablatnig, Robert}, title = {SASIC: Stereo Image Compression With Latent Shifts and Stereo Attention}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {661-670} }
CVNet: Contour Vibration Network for Building Extraction: Ziqiang Xu,

Chunyan Xu,

Zhen Cui,

Xiangwei Zheng,

Jian Yang; [pdf]
[bibtex]
@InProceedings{Xu_2022_CVPR, author = {Xu, Ziqiang and Xu, Chunyan and Cui, Zhen and Zheng, Xiangwei and Yang, Jian}, title = {CVNet: Contour Vibration Network for Building Extraction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {1383-1391} }
Hyperbolic Image Segmentation: Mina Ghadimi Atigh,

Julian Schoep,

Erman Acar,

Nanne van Noord,

Pascal Mettes; [pdf] [supp]
[bibtex]
@InProceedings{Atigh_2022_CVPR, author = {Atigh, Mina Ghadimi and Schoep, Julian and Acar, Erman and van Noord, Nanne and Mettes, Pascal}, title = {Hyperbolic Image Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {4453-4462} }
CLIMS: Cross Language Image Matching for Weakly Supervised Semantic Segmentation: Jinheng Xie,

Xianxu Hou,

Kai Ye,

Linlin Shen; [pdf] [supp]
[bibtex]
@InProceedings{Xie_2022_CVPR, author = {Xie, Jinheng and Hou, Xianxu and Ye, Kai and Shen, Linlin}, title = {CLIMS: Cross Language Image Matching for Weakly Supervised Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {4483-4492} }
TransRank: Self-Supervised Video Representation Learning via Ranking-Based Transformation Recognition: Haodong Duan,

Nanxuan Zhao,

Kai Chen,

Dahua Lin; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Duan_2022_CVPR, author = {Duan, Haodong and Zhao, Nanxuan and Chen, Kai and Lin, Dahua}, title = {TransRank: Self-Supervised Video Representation Learning via Ranking-Based Transformation Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {3000-3010} }
Invariant Grounding for Video Question Answering: Yicong Li,

Xiang Wang,

Junbin Xiao,

Wei Ji,

Tat-Seng Chua; [pdf] [supp]
[bibtex]
@InProceedings{Li_2022_CVPR, author = {Li, Yicong and Wang, Xiang and Xiao, Junbin and Ji, Wei and Chua, Tat-Seng}, title = {Invariant Grounding for Video Question Answering}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {2928-2937} }
Prompt Distribution Learning: Yuning Lu,

Jianzhuang Liu,

Yonggang Zhang,

Yajing Liu,

Xinmei Tian; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Lu_2022_CVPR, author = {Lu, Yuning and Liu, Jianzhuang and Zhang, Yonggang and Liu, Yajing and Tian, Xinmei}, title = {Prompt Distribution Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {5206-5215} }
Temporal Alignment Networks for Long-Term Video: Tengda Han,

Weidi Xie,

Andrew Zisserman; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Han_2022_CVPR, author = {Han, Tengda and Xie, Weidi and Zisserman, Andrew}, title = {Temporal Alignment Networks for Long-Term Video}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {2906-2916} }
LAR-SR: A Local Autoregressive Model for Image Super-Resolution: Baisong Guo,

Xiaoyun Zhang,

Haoning Wu,

Yu Wang,

Ya Zhang,

Yan-Feng Wang; [pdf] [supp]
[bibtex]
@InProceedings{Guo_2022_CVPR, author = {Guo, Baisong and Zhang, Xiaoyun and Wu, Haoning and Wang, Yu and Zhang, Ya and Wang, Yan-Feng}, title = {LAR-SR: A Local Autoregressive Model for Image Super-Resolution}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {1909-1918} }
Democracy Does Matter: Comprehensive Feature Mining for Co-Salient Object Detection: Siyue Yu,

Jimin Xiao,

Bingfeng Zhang,

Eng Gee Lim; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yu_2022_CVPR, author = {Yu, Siyue and Xiao, Jimin and Zhang, Bingfeng and Lim, Eng Gee}, title = {Democracy Does Matter: Comprehensive Feature Mining for Co-Salient Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {979-988} }
Doodle It Yourself: Class Incremental Learning by Drawing a Few Sketches: Ayan Kumar Bhunia,

Viswanatha Reddy Gajjala,

Subhadeep Koley,

Rohit Kundu,

Aneeshan Sain,

Tao Xiang,

Yi-Zhe Song; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Bhunia_2022_CVPR, author = {Bhunia, Ayan Kumar and Gajjala, Viswanatha Reddy and Koley, Subhadeep and Kundu, Rohit and Sain, Aneeshan and Xiang, Tao and Song, Yi-Zhe}, title = {Doodle It Yourself: Class Incremental Learning by Drawing a Few Sketches}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {2293-2302} }
Comparing Correspondences: Video Prediction With Correspondence-Wise Losses: Daniel Geng,

Max Hamilton,

Andrew Owens; [pdf] [arXiv]
[bibtex]
@InProceedings{Geng_2022_CVPR, author = {Geng, Daniel and Hamilton, Max and Owens, Andrew}, title = {Comparing Correspondences: Video Prediction With Correspondence-Wise Losses}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {3365-3376} }
Non-Iterative Recovery From Nonlinear Observations Using Generative Models: Jiulong Liu,

Zhaoqiang Liu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Liu_2022_CVPR, author = {Liu, Jiulong and Liu, Zhaoqiang}, title = {Non-Iterative Recovery From Nonlinear Observations Using Generative Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {233-243} }
Partially Does It: Towards Scene-Level FG-SBIR With Partial Input: Pinaki Nath Chowdhury,

Ayan Kumar Bhunia,

Viswanatha Reddy Gajjala,

Aneeshan Sain,

Tao Xiang,

Yi-Zhe Song; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chowdhury_2022_CVPR, author = {Chowdhury, Pinaki Nath and Bhunia, Ayan Kumar and Gajjala, Viswanatha Reddy and Sain, Aneeshan and Xiang, Tao and Song, Yi-Zhe}, title = {Partially Does It: Towards Scene-Level FG-SBIR With Partial Input}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {2395-2405} }
Density-Preserving Deep Point Cloud Compression: Yun He,

Xinlin Ren,

Danhang Tang,

Yinda Zhang,

Xiangyang Xue,

Yanwei Fu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{He_2022_CVPR, author = {He, Yun and Ren, Xinlin and Tang, Danhang and Zhang, Yinda and Xue, Xiangyang and Fu, Yanwei}, title = {Density-Preserving Deep Point Cloud Compression}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {2333-2342} }
Fast and Unsupervised Action Boundary Detection for Action Segmentation: Zexing Du,

Xue Wang,

Guoqing Zhou,

Qing Wang; [pdf]
[bibtex]
@InProceedings{Du_2022_CVPR, author = {Du, Zexing and Wang, Xue and Zhou, Guoqing and Wang, Qing}, title = {Fast and Unsupervised Action Boundary Detection for Action Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {3323-3332} }
Robust Optimization As Data Augmentation for Large-Scale Graphs: Kezhi Kong,

Guohao Li,

Mucong Ding,

Zuxuan Wu,

Chen Zhu,

Bernard Ghanem,

Gavin Taylor,

Tom Goldstein; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kong_2022_CVPR, author = {Kong, Kezhi and Li, Guohao and Ding, Mucong and Wu, Zuxuan and Zhu, Chen and Ghanem, Bernard and Taylor, Gavin and Goldstein, Tom}, title = {Robust Optimization As Data Augmentation for Large-Scale Graphs}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {60-69} }
360MonoDepth: High-Resolution 360deg Monocular Depth Estimation: Manuel Rey-Area,

Mingze Yuan,

Christian Richardt; [pdf] [supp]
[bibtex]
@InProceedings{Rey-Area_2022_CVPR, author = {Rey-Area, Manuel and Yuan, Mingze and Richardt, Christian}, title = {360MonoDepth: High-Resolution 360deg Monocular Depth Estimation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {3762-3772} }
MUSE-VAE: Multi-Scale VAE for Environment-Aware Long Term Trajectory Prediction: Mihee Lee,

Samuel S. Sohn,

Seonghyeon Moon,

Sejong Yoon,

Mubbasir Kapadia,

Vladimir Pavlovic; [pdf] [supp]
[bibtex]
@InProceedings{Lee_2022_CVPR, author = {Lee, Mihee and Sohn, Samuel S. and Moon, Seonghyeon and Yoon, Sejong and Kapadia, Mubbasir and Pavlovic, Vladimir}, title = {MUSE-VAE: Multi-Scale VAE for Environment-Aware Long Term Trajectory Prediction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {2221-2230} }
GazeOnce: Real-Time Multi-Person Gaze Estimation: Mingfang Zhang,

Yunfei Liu,

Feng Lu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhang_2022_CVPR, author = {Zhang, Mingfang and Liu, Yunfei and Lu, Feng}, title = {GazeOnce: Real-Time Multi-Person Gaze Estimation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {4197-4206} }
Depth-Aware Generative Adversarial Network for Talking Head Video Generation: Fa-Ting Hong,

Longhao Zhang,

Li Shen,

Dan Xu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Hong_2022_CVPR, author = {Hong, Fa-Ting and Zhang, Longhao and Shen, Li and Xu, Dan}, title = {Depth-Aware Generative Adversarial Network for Talking Head Video Generation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {3397-3406} }
Clipped Hyperbolic Classifiers Are Super-Hyperbolic Classifiers: Yunhui Guo,

Xudong Wang,

Yubei Chen,

Stella X. Yu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Guo_2022_CVPR, author = {Guo, Yunhui and Wang, Xudong and Chen, Yubei and Yu, Stella X.}, title = {Clipped Hyperbolic Classifiers Are Super-Hyperbolic Classifiers}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {11-20} }
Implicit Feature Decoupling With Depthwise Quantization: Iordanis Fostiropoulos,

Barry Boehm; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Fostiropoulos_2022_CVPR, author = {Fostiropoulos, Iordanis and Boehm, Barry}, title = {Implicit Feature Decoupling With Depthwise Quantization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {396-405} }
Graph-Context Attention Networks for Size-Varied Deep Graph Matching: Zheheng Jiang,

Hossein Rahmani,

Plamen Angelov,

Sue Black,

Bryan M. Williams; [pdf] [supp]
[bibtex]
@InProceedings{Jiang_2022_CVPR, author = {Jiang, Zheheng and Rahmani, Hossein and Angelov, Plamen and Black, Sue and Williams, Bryan M.}, title = {Graph-Context Attention Networks for Size-Varied Deep Graph Matching}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {2343-2352} }
Measuring Compositional Consistency for Video Question Answering: Mona Gandhi,

Mustafa Omer Gul,

Eva Prakash,

Madeleine Grunde-McLaughlin,

Ranjay Krishna,

Maneesh Agrawala; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Gandhi_2022_CVPR, author = {Gandhi, Mona and Gul, Mustafa Omer and Prakash, Eva and Grunde-McLaughlin, Madeleine and Krishna, Ranjay and Agrawala, Maneesh}, title = {Measuring Compositional Consistency for Video Question Answering}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {5046-5055} }
Category Contrast for Unsupervised Domain Adaptation in Visual Tasks: Jiaxing Huang,

Dayan Guan,

Aoran Xiao,

Shijian Lu,

Ling Shao; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Huang_2022_CVPR, author = {Huang, Jiaxing and Guan, Dayan and Xiao, Aoran and Lu, Shijian and Shao, Ling}, title = {Category Contrast for Unsupervised Domain Adaptation in Visual Tasks}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {1203-1214} }
SwapMix: Diagnosing and Regularizing the Over-Reliance on Visual Context in Visual Question Answering: Vipul Gupta,

Zhuowan Li,

Adam Kortylewski,

Chenyu Zhang,

Yingwei Li,

Alan Yuille; [pdf] [arXiv]
[bibtex]
@InProceedings{Gupta_2022_CVPR, author = {Gupta, Vipul and Li, Zhuowan and Kortylewski, Adam and Zhang, Chenyu and Li, Yingwei and Yuille, Alan}, title = {SwapMix: Diagnosing and Regularizing the Over-Reliance on Visual Context in Visual Question Answering}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {5078-5088} }
Mutual Information-Driven Pan-Sharpening: Man Zhou,

Keyu Yan,

Jie Huang,

Zihe Yang,

Xueyang Fu,

Feng Zhao; [pdf]
[bibtex]
@InProceedings{Zhou_2022_CVPR, author = {Zhou, Man and Yan, Keyu and Huang, Jie and Yang, Zihe and Fu, Xueyang and Zhao, Feng}, title = {Mutual Information-Driven Pan-Sharpening}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {1798-1808} }
FLOAT: Factorized Learning of Object Attributes for Improved Multi-Object Multi-Part Scene Parsing: Rishubh Singh,

Pranav Gupta,

Pradeep Shenoy,

Ravikiran Sarvadevabhatla; [pdf] [arXiv]
[bibtex]
@InProceedings{Singh_2022_CVPR, author = {Singh, Rishubh and Gupta, Pranav and Shenoy, Pradeep and Sarvadevabhatla, Ravikiran}, title = {FLOAT: Factorized Learning of Object Attributes for Improved Multi-Object Multi-Part Scene Parsing}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {1445-1455} }
FocusCut: Diving Into a Focus View in Interactive Segmentation: Zheng Lin,

Zheng-Peng Duan,

Zhao Zhang,

Chun-Le Guo,

Ming-Ming Cheng; [pdf]
[bibtex]
@InProceedings{Lin_2022_CVPR, author = {Lin, Zheng and Duan, Zheng-Peng and Zhang, Zhao and Guo, Chun-Le and Cheng, Ming-Ming}, title = {FocusCut: Diving Into a Focus View in Interactive Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {2637-2646} }
Medial Spectral Coordinates for 3D Shape Analysis: Morteza Rezanejad,

Mohammad Khodadad,

Hamidreza Mahyar,

Herve Lombaert,

Michael Gruninger,

Dirk Walther,

Kaleem Siddiqi; [pdf] [arXiv]
[bibtex]
@InProceedings{Rezanejad_2022_CVPR, author = {Rezanejad, Morteza and Khodadad, Mohammad and Mahyar, Hamidreza and Lombaert, Herve and Gruninger, Michael and Walther, Dirk and Siddiqi, Kaleem}, title = {Medial Spectral Coordinates for 3D Shape Analysis}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {2686-2696} }
Dressing in the Wild by Watching Dance Videos: Xin Dong,

Fuwei Zhao,

Zhenyu Xie,

Xijin Zhang,

Daniel K. Du,

Min Zheng,

Xiang Long,

Xiaodan Liang,

Jianchao Yang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Dong_2022_CVPR, author = {Dong, Xin and Zhao, Fuwei and Xie, Zhenyu and Zhang, Xijin and Du, Daniel K. and Zheng, Min and Long, Xiang and Liang, Xiaodan and Yang, Jianchao}, title = {Dressing in the Wild by Watching Dance Videos}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {3480-3489} }
SeeThroughNet: Resurrection of Auxiliary Loss by Preserving Class Probability Information: Dasol Han,

Jaewook Yoo,

Dokwan Oh; [pdf] [supp]
[bibtex]
@InProceedings{Han_2022_CVPR, author = {Han, Dasol and Yoo, Jaewook and Oh, Dokwan}, title = {SeeThroughNet: Resurrection of Auxiliary Loss by Preserving Class Probability Information}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {4463-4472} }
Learning To Restore 3D Face From In-the-Wild Degraded Images: Zhenyu Zhang,

Yanhao Ge,

Ying Tai,

Xiaoming Huang,

Chengjie Wang,

Hao Tang,

Dongjin Huang,

Zhifeng Xie; [pdf] [supp]
[bibtex]
@InProceedings{Zhang_2022_CVPR, author = {Zhang, Zhenyu and Ge, Yanhao and Tai, Ying and Huang, Xiaoming and Wang, Chengjie and Tang, Hao and Huang, Dongjin and Xie, Zhifeng}, title = {Learning To Restore 3D Face From In-the-Wild Degraded Images}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {4237-4247} }
SmartAdapt: Multi-Branch Object Detection Framework for Videos on Mobiles: Ran Xu,

Fangzhou Mu,

Jayoung Lee,

Preeti Mukherjee,

Somali Chaterji,

Saurabh Bagchi,

Yin Li; [pdf] [supp]
[bibtex]
@InProceedings{Xu_2022_CVPR, author = {Xu, Ran and Mu, Fangzhou and Lee, Jayoung and Mukherjee, Preeti and Chaterji, Somali and Bagchi, Saurabh and Li, Yin}, title = {SmartAdapt: Multi-Branch Object Detection Framework for Videos on Mobiles}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {2528-2538} }
VL-Adapter: Parameter-Efficient Transfer Learning for Vision-and-Language Tasks: Yi-Lin Sung,

Jaemin Cho,

Mohit Bansal; [pdf] [supp]
[bibtex]
@InProceedings{Sung_2022_CVPR, author = {Sung, Yi-Lin and Cho, Jaemin and Bansal, Mohit}, title = {VL-Adapter: Parameter-Efficient Transfer Learning for Vision-and-Language Tasks}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {5227-5237} }
Deep Hybrid Models for Out-of-Distribution Detection: Senqi Cao,

Zhongfei Zhang; [pdf] [supp]
[bibtex]
@InProceedings{Cao_2022_CVPR, author = {Cao, Senqi and Zhang, Zhongfei}, title = {Deep Hybrid Models for Out-of-Distribution Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {4733-4743} }
Accelerating Video Object Segmentation With Compressed Video: Kai Xu,

Angela Yao; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Xu_2022_CVPR, author = {Xu, Kai and Yao, Angela}, title = {Accelerating Video Object Segmentation With Compressed Video}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {1342-1351} }
FastDOG: Fast Discrete Optimization on GPU: Ahmed Abbas,

Paul Swoboda; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Abbas_2022_CVPR, author = {Abbas, Ahmed and Swoboda, Paul}, title = {FastDOG: Fast Discrete Optimization on GPU}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {439-449} }
Self-Supervised Equivariant Learning for Oriented Keypoint Detection: Jongmin Lee,

Byungjin Kim,

Minsu Cho; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Lee_2022_CVPR, author = {Lee, Jongmin and Kim, Byungjin and Cho, Minsu}, title = {Self-Supervised Equivariant Learning for Oriented Keypoint Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {4847-4857} }
Focal and Global Knowledge Distillation for Detectors: Zhendong Yang,

Zhe Li,

Xiaohu Jiang,

Yuan Gong,

Zehuan Yuan,

Danpei Zhao,

Chun Yuan; [pdf] [arXiv]
[bibtex]
@InProceedings{Yang_2022_CVPR, author = {Yang, Zhendong and Li, Zhe and Jiang, Xiaohu and Gong, Yuan and Yuan, Zehuan and Zhao, Danpei and Yuan, Chun}, title = {Focal and Global Knowledge Distillation for Detectors}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {4643-4652} }
Learning To Prompt for Continual Learning: Zifeng Wang,

Zizhao Zhang,

Chen-Yu Lee,

Han Zhang,

Ruoxi Sun,

Xiaoqi Ren,

Guolong Su,

Vincent Perot,

Jennifer Dy,

Tomas Pfister; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2022_CVPR, author = {Wang, Zifeng and Zhang, Zizhao and Lee, Chen-Yu and Zhang, Han and Sun, Ruoxi and Ren, Xiaoqi and Su, Guolong and Perot, Vincent and Dy, Jennifer and Pfister, Tomas}, title = {Learning To Prompt for Continual Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {139-149} }
Human Mesh Recovery From Multiple Shots: Georgios Pavlakos,

Jitendra Malik,

Angjoo Kanazawa; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Pavlakos_2022_CVPR, author = {Pavlakos, Georgios and Malik, Jitendra and Kanazawa, Angjoo}, title = {Human Mesh Recovery From Multiple Shots}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {1485-1495} }
GANSeg: Learning To Segment by Unsupervised Hierarchical Image Generation: Xingzhe He,

Bastian Wandt,

Helge Rhodin; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{He_2022_CVPR, author = {He, Xingzhe and Wandt, Bastian and Rhodin, Helge}, title = {GANSeg: Learning To Segment by Unsupervised Hierarchical Image Generation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {1225-1235} }
Dense Learning Based Semi-Supervised Object Detection: Binghui Chen,

Pengyu Li,

Xiang Chen,

Biao Wang,

Lei Zhang,

Xian-Sheng Hua; [pdf] [arXiv]
[bibtex]
@InProceedings{Chen_2022_CVPR, author = {Chen, Binghui and Li, Pengyu and Chen, Xiang and Wang, Biao and Zhang, Lei and Hua, Xian-Sheng}, title = {Dense Learning Based Semi-Supervised Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {4815-4824} }
Fixing Malfunctional Objects With Learned Physical Simulation and Functional Prediction: Yining Hong,

Kaichun Mo,

Li Yi,

Leonidas J. Guibas,

Antonio Torralba,

Joshua B. Tenenbaum,

Chuang Gan; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Hong_2022_CVPR, author = {Hong, Yining and Mo, Kaichun and Yi, Li and Guibas, Leonidas J. and Torralba, Antonio and Tenenbaum, Joshua B. and Gan, Chuang}, title = {Fixing Malfunctional Objects With Learned Physical Simulation and Functional Prediction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {1413-1423} }
Convolution of Convolution: Let Kernels Spatially Collaborate: Rongzhen Zhao,

Jian Li,

Zhenzhi Wu; [pdf]
[bibtex]
@InProceedings{Zhao_2022_CVPR, author = {Zhao, Rongzhen and Li, Jian and Wu, Zhenzhi}, title = {Convolution of Convolution: Let Kernels Spatially Collaborate}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {651-660} }
Video-Text Representation Learning via Differentiable Weak Temporal Alignment: Dohwan Ko,

Joonmyung Choi,

Juyeon Ko,

Shinyeong Noh,

Kyoung-Woon On,

Eun-Sol Kim,

Hyunwoo J. Kim; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ko_2022_CVPR, author = {Ko, Dohwan and Choi, Joonmyung and Ko, Juyeon and Noh, Shinyeong and On, Kyoung-Woon and Kim, Eun-Sol and Kim, Hyunwoo J.}, title = {Video-Text Representation Learning via Differentiable Weak Temporal Alignment}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {5016-5025} }
Progressive Minimal Path Method With Embedded CNN: Wei Liao; [pdf] [arXiv]
[bibtex]
@InProceedings{Liao_2022_CVPR, author = {Liao, Wei}, title = {Progressive Minimal Path Method With Embedded CNN}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {4514-4522} }
3D Human Tongue Reconstruction From Single "In-the-Wild" Images: Stylianos Ploumpis,

Stylianos Moschoglou,

Vasileios Triantafyllou,

Stefanos Zafeiriou; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ploumpis_2022_CVPR, author = {Ploumpis, Stylianos and Moschoglou, Stylianos and Triantafyllou, Vasileios and Zafeiriou, Stefanos}, title = {3D Human Tongue Reconstruction From Single ''In-the-Wild'' Images}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {2771-2780} }
A Simple Multi-Modality Transfer Learning Baseline for Sign Language Translation: Yutong Chen,

Fangyun Wei,

Xiao Sun,

Zhirong Wu,

Stephen Lin; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chen_2022_CVPR, author = {Chen, Yutong and Wei, Fangyun and Sun, Xiao and Wu, Zhirong and Lin, Stephen}, title = {A Simple Multi-Modality Transfer Learning Baseline for Sign Language Translation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {5120-5130} }
MonoDTR: Monocular 3D Object Detection With Depth-Aware Transformer: Kuan-Chih Huang,

Tsung-Han Wu,

Hung-Ting Su,

Winston H. Hsu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Huang_2022_CVPR, author = {Huang, Kuan-Chih and Wu, Tsung-Han and Su, Hung-Ting and Hsu, Winston H.}, title = {MonoDTR: Monocular 3D Object Detection With Depth-Aware Transformer}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {4012-4021} }
Learning Graph Regularisation for Guided Super-Resolution: Riccardo de Lutio,

Alexander Becker,

Stefano D'Aronco,

Stefania Russo,

Jan D. Wegner,

Konrad Schindler; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{de_Lutio_2022_CVPR, author = {de Lutio, Riccardo and Becker, Alexander and D'Aronco, Stefano and Russo, Stefania and Wegner, Jan D. and Schindler, Konrad}, title = {Learning Graph Regularisation for Guided Super-Resolution}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {1979-1988} }
Voxel Field Fusion for 3D Object Detection: Yanwei Li,

Xiaojuan Qi,

Yukang Chen,

Liwei Wang,

Zeming Li,

Jian Sun,

Jiaya Jia; [pdf] [arXiv]
[bibtex]
@InProceedings{Li_2022_CVPR, author = {Li, Yanwei and Qi, Xiaojuan and Chen, Yukang and Wang, Liwei and Li, Zeming and Sun, Jian and Jia, Jiaya}, title = {Voxel Field Fusion for 3D Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {1120-1129} }
Fast Algorithm for Low-Rank Tensor Completion in Delay-Embedded Space: Ryuki Yamamoto,

Hidekata Hontani,

Akira Imakura,

Tatsuya Yokota; [pdf]
[bibtex]
@InProceedings{Yamamoto_2022_CVPR, author = {Yamamoto, Ryuki and Hontani, Hidekata and Imakura, Akira and Yokota, Tatsuya}, title = {Fast Algorithm for Low-Rank Tensor Completion in Delay-Embedded Space}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {2058-2066} }
Panoptic, Instance and Semantic Relations: A Relational Context Encoder To Enhance Panoptic Segmentation: Shubhankar Borse,

Hyojin Park,

Hong Cai,

Debasmit Das,

Risheek Garrepalli,

Fatih Porikli; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Borse_2022_CVPR, author = {Borse, Shubhankar and Park, Hyojin and Cai, Hong and Das, Debasmit and Garrepalli, Risheek and Porikli, Fatih}, title = {Panoptic, Instance and Semantic Relations: A Relational Context Encoder To Enhance Panoptic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {1269-1279} }
ETHSeg: An Amodel Instance Segmentation Network and a Real-World Dataset for X-Ray Waste Inspection: Lingteng Qiu,

Zhangyang Xiong,

Xuhao Wang,

Kenkun Liu,

Yihan Li,

Guanying Chen,

Xiaoguang Han,

Shuguang Cui; [pdf] [supp]
[bibtex]
@InProceedings{Qiu_2022_CVPR, author = {Qiu, Lingteng and Xiong, Zhangyang and Wang, Xuhao and Liu, Kenkun and Li, Yihan and Chen, Guanying and Han, Xiaoguang and Cui, Shuguang}, title = {ETHSeg: An Amodel Instance Segmentation Network and a Real-World Dataset for X-Ray Waste Inspection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {2283-2292} }
Killing Two Birds With One Stone: Efficient and Robust Training of Face Recognition CNNs by Partial FC: Xiang An,

Jiankang Deng,

Jia Guo,

Ziyong Feng,

XuHan Zhu,

Jing Yang,

Tongliang Liu; [pdf] [arXiv]
[bibtex]
@InProceedings{An_2022_CVPR, author = {An, Xiang and Deng, Jiankang and Guo, Jia and Feng, Ziyong and Zhu, XuHan and Yang, Jing and Liu, Tongliang}, title = {Killing Two Birds With One Stone: Efficient and Robust Training of Face Recognition CNNs by Partial FC}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {4042-4051} }
FineDiving: A Fine-Grained Dataset for Procedure-Aware Action Quality Assessment: Jinglin Xu,

Yongming Rao,

Xumin Yu,

Guangyi Chen,

Jie Zhou,

Jiwen Lu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Xu_2022_CVPR, author = {Xu, Jinglin and Rao, Yongming and Yu, Xumin and Chen, Guangyi and Zhou, Jie and Lu, Jiwen}, title = {FineDiving: A Fine-Grained Dataset for Procedure-Aware Action Quality Assessment}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {2949-2958} }
HEAT: Holistic Edge Attention Transformer for Structured Reconstruction: Jiacheng Chen,

Yiming Qian,

Yasutaka Furukawa; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chen_2022_CVPR, author = {Chen, Jiacheng and Qian, Yiming and Furukawa, Yasutaka}, title = {HEAT: Holistic Edge Attention Transformer for Structured Reconstruction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {3866-3875} }
Exploiting Pseudo Labels in a Self-Supervised Learning Framework for Improved Monocular Depth Estimation: Andra Petrovai,

Sergiu Nedevschi; [pdf] [supp]
[bibtex]
@InProceedings{Petrovai_2022_CVPR, author = {Petrovai, Andra and Nedevschi, Sergiu}, title = {Exploiting Pseudo Labels in a Self-Supervised Learning Framework for Improved Monocular Depth Estimation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {1578-1588} }
VideoINR: Learning Video Implicit Neural Representation for Continuous Space-Time Super-Resolution: Zeyuan Chen,

Yinbo Chen,

Jingwen Liu,

Xingqian Xu,

Vidit Goel,

Zhangyang Wang,

Humphrey Shi,

Xiaolong Wang; [pdf] [supp]
[bibtex]
@InProceedings{Chen_2022_CVPR, author = {Chen, Zeyuan and Chen, Yinbo and Liu, Jingwen and Xu, Xingqian and Goel, Vidit and Wang, Zhangyang and Shi, Humphrey and Wang, Xiaolong}, title = {VideoINR: Learning Video Implicit Neural Representation for Continuous Space-Time Super-Resolution}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {2047-2057} }
Towards End-to-End Unified Scene Text Detection and Layout Analysis: Shangbang Long,

Siyang Qin,

Dmitry Panteleev,

Alessandro Bissacco,

Yasuhisa Fujii,

Michalis Raptis; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Long_2022_CVPR, author = {Long, Shangbang and Qin, Siyang and Panteleev, Dmitry and Bissacco, Alessandro and Fujii, Yasuhisa and Raptis, Michalis}, title = {Towards End-to-End Unified Scene Text Detection and Layout Analysis}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {1049-1059} }
AutoSDF: Shape Priors for 3D Completion, Reconstruction and Generation: Paritosh Mittal,

Yen-Chi Cheng,

Maneesh Singh,

Shubham Tulsiani; [pdf] [arXiv]
[bibtex]
@InProceedings{Mittal_2022_CVPR, author = {Mittal, Paritosh and Cheng, Yen-Chi and Singh, Maneesh and Tulsiani, Shubham}, title = {AutoSDF: Shape Priors for 3D Completion, Reconstruction and Generation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {306-315} }
ISNAS-DIP: Image-Specific Neural Architecture Search for Deep Image Prior: Metin Ersin Arican,

Ozgur Kara,

Gustav Bredell,

Ender Konukoglu; [pdf] [supp]
[bibtex]
@InProceedings{Arican_2022_CVPR, author = {Arican, Metin Ersin and Kara, Ozgur and Bredell, Gustav and Konukoglu, Ender}, title = {ISNAS-DIP: Image-Specific Neural Architecture Search for Deep Image Prior}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {1960-1968} }
End-to-End Referring Video Object Segmentation With Multimodal Transformers: Adam Botach,

Evgenii Zheltonozhskii,

Chaim Baskin; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Botach_2022_CVPR, author = {Botach, Adam and Zheltonozhskii, Evgenii and Baskin, Chaim}, title = {End-to-End Referring Video Object Segmentation With Multimodal Transformers}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {4985-4995} }
Unpaired Cartoon Image Synthesis via Gated Cycle Mapping: Yifang Men,

Yuan Yao,

Miaomiao Cui,

Zhouhui Lian,

Xuansong Xie,

Xian-Sheng Hua; [pdf] [supp]
[bibtex]
@InProceedings{Men_2022_CVPR, author = {Men, Yifang and Yao, Yuan and Cui, Miaomiao and Lian, Zhouhui and Xie, Xuansong and Hua, Xian-Sheng}, title = {Unpaired Cartoon Image Synthesis via Gated Cycle Mapping}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {3501-3510} }
Detecting Camouflaged Object in Frequency Domain: Yijie Zhong,

Bo Li,

Lv Tang,

Senyun Kuang,

Shuang Wu,

Shouhong Ding; [pdf] [supp]
[bibtex]
@InProceedings{Zhong_2022_CVPR, author = {Zhong, Yijie and Li, Bo and Tang, Lv and Kuang, Senyun and Wu, Shuang and Ding, Shouhong}, title = {Detecting Camouflaged Object in Frequency Domain}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {4504-4513} }
Style-Based Global Appearance Flow for Virtual Try-On: Sen He,

Yi-Zhe Song,

Tao Xiang; [pdf] [arXiv]
[bibtex]
@InProceedings{He_2022_CVPR, author = {He, Sen and Song, Yi-Zhe and Xiang, Tao}, title = {Style-Based Global Appearance Flow for Virtual Try-On}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {3470-3479} }
Active Learning for Open-Set Annotation: Kun-Peng Ning,

Xun Zhao,

Yu Li,

Sheng-Jun Huang; [pdf] [arXiv]
[bibtex]
@InProceedings{Ning_2022_CVPR, author = {Ning, Kun-Peng and Zhao, Xun and Li, Yu and Huang, Sheng-Jun}, title = {Active Learning for Open-Set Annotation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {41-49} }
Semi-Supervised Video Semantic Segmentation With Inter-Frame Feature Reconstruction: Jiafan Zhuang,

Zilei Wang,

Yuan Gao; [pdf]
[bibtex]
@InProceedings{Zhuang_2022_CVPR, author = {Zhuang, Jiafan and Wang, Zilei and Gao, Yuan}, title = {Semi-Supervised Video Semantic Segmentation With Inter-Frame Feature Reconstruction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {3263-3271} }
GenDR: A Generalized Differentiable Renderer: Felix Petersen,

Bastian Goldluecke,

Christian Borgelt,

Oliver Deussen; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Petersen_2022_CVPR, author = {Petersen, Felix and Goldluecke, Bastian and Borgelt, Christian and Deussen, Oliver}, title = {GenDR: A Generalized Differentiable Renderer}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {4002-4011} }
XYLayoutLM: Towards Layout-Aware Multimodal Networks for Visually-Rich Document Understanding: Zhangxuan Gu,

Changhua Meng,

Ke Wang,

Jun Lan,

Weiqiang Wang,

Ming Gu,

Liqing Zhang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Gu_2022_CVPR, author = {Gu, Zhangxuan and Meng, Changhua and Wang, Ke and Lan, Jun and Wang, Weiqiang and Gu, Ming and Zhang, Liqing}, title = {XYLayoutLM: Towards Layout-Aware Multimodal Networks for Visually-Rich Document Understanding}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {4583-4592} }
Amodal Segmentation Through Out-of-Task and Out-of-Distribution Generalization With a Bayesian Model: Yihong Sun,

Adam Kortylewski,

Alan Yuille; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Sun_2022_CVPR, author = {Sun, Yihong and Kortylewski, Adam and Yuille, Alan}, title = {Amodal Segmentation Through Out-of-Task and Out-of-Distribution Generalization With a Bayesian Model}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {1215-1224} }
Canonical Voting: Towards Robust Oriented Bounding Box Detection in 3D Scenes: Yang You,

Zelin Ye,

Yujing Lou,

Chengkun Li,

Yong-Lu Li,

Lizhuang Ma,

Weiming Wang,

Cewu Lu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{You_2022_CVPR, author = {You, Yang and Ye, Zelin and Lou, Yujing and Li, Chengkun and Li, Yong-Lu and Ma, Lizhuang and Wang, Weiming and Lu, Cewu}, title = {Canonical Voting: Towards Robust Oriented Bounding Box Detection in 3D Scenes}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {1193-1202} }
Object-Aware Video-Language Pre-Training for Retrieval: Jinpeng Wang,

Yixiao Ge,

Guanyu Cai,

Rui Yan,

Xudong Lin,

Ying Shan,

Xiaohu Qie,

Mike Zheng Shou; [pdf] [arXiv]
[bibtex]
@InProceedings{Wang_2022_CVPR, author = {Wang, Jinpeng and Ge, Yixiao and Cai, Guanyu and Yan, Rui and Lin, Xudong and Shan, Ying and Qie, Xiaohu and Shou, Mike Zheng}, title = {Object-Aware Video-Language Pre-Training for Retrieval}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {3313-3322} }
OSKDet: Orientation-Sensitive Keypoint Localization for Rotated Object Detection: Dongchen Lu,

Dongmei Li,

Yali Li,

Shengjin Wang; [pdf]
[bibtex]
@InProceedings{Lu_2022_CVPR, author = {Lu, Dongchen and Li, Dongmei and Li, Yali and Wang, Shengjin}, title = {OSKDet: Orientation-Sensitive Keypoint Localization for Rotated Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {1182-1192} }
Exploring Geometric Consistency for Monocular 3D Object Detection: Qing Lian,

Botao Ye,

Ruijia Xu,

Weilong Yao,

Tong Zhang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Lian_2022_CVPR, author = {Lian, Qing and Ye, Botao and Xu, Ruijia and Yao, Weilong and Zhang, Tong}, title = {Exploring Geometric Consistency for Monocular 3D Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {1685-1694} }
Neural Window Fully-Connected CRFs for Monocular Depth Estimation: Weihao Yuan,

Xiaodong Gu,

Zuozhuo Dai,

Siyu Zhu,

Ping Tan; [pdf] [arXiv]
[bibtex]
@InProceedings{Yuan_2022_CVPR, author = {Yuan, Weihao and Gu, Xiaodong and Dai, Zuozhuo and Zhu, Siyu and Tan, Ping}, title = {Neural Window Fully-Connected CRFs for Monocular Depth Estimation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {3916-3925} }
CodedVTR: Codebook-Based Sparse Voxel Transformer With Geometric Guidance: Tianchen Zhao,

Niansong Zhang,

Xuefei Ning,

He Wang,

Li Yi,

Yu Wang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhao_2022_CVPR, author = {Zhao, Tianchen and Zhang, Niansong and Ning, Xuefei and Wang, He and Yi, Li and Wang, Yu}, title = {CodedVTR: Codebook-Based Sparse Voxel Transformer With Geometric Guidance}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {1435-1444} }
Coherent Point Drift Revisited for Non-Rigid Shape Matching and Registration: Aoxiang Fan,

Jiayi Ma,

Xin Tian,

Xiaoguang Mei,

Wei Liu; [pdf]
[bibtex]
@InProceedings{Fan_2022_CVPR, author = {Fan, Aoxiang and Ma, Jiayi and Tian, Xin and Mei, Xiaoguang and Liu, Wei}, title = {Coherent Point Drift Revisited for Non-Rigid Shape Matching and Registration}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {1424-1434} }
Align and Prompt: Video-and-Language Pre-Training With Entity Prompts: Dongxu Li,

Junnan Li,

Hongdong Li,

Juan Carlos Niebles,

Steven C.H. Hoi; [pdf] [arXiv]
[bibtex]
@InProceedings{Li_2022_CVPR, author = {Li, Dongxu and Li, Junnan and Li, Hongdong and Niebles, Juan Carlos and Hoi, Steven C.H.}, title = {Align and Prompt: Video-and-Language Pre-Training With Entity Prompts}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {4953-4963} }
It's About Time: Analog Clock Reading in the Wild: Charig Yang,

Weidi Xie,

Andrew Zisserman; [pdf] [supp]
[bibtex]
@InProceedings{Yang_2022_CVPR, author = {Yang, Charig and Xie, Weidi and Zisserman, Andrew}, title = {It's About Time: Analog Clock Reading in the Wild}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {2508-2517} }
Cross Modal Retrieval With Querybank Normalisation: Simion-Vlad Bogolin,

Ioana Croitoru,

Hailin Jin,

Yang Liu,

Samuel Albanie; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Bogolin_2022_CVPR, author = {Bogolin, Simion-Vlad and Croitoru, Ioana and Jin, Hailin and Liu, Yang and Albanie, Samuel}, title = {Cross Modal Retrieval With Querybank Normalisation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {5194-5205} }
Hire-MLP: Vision MLP via Hierarchical Rearrangement: Jianyuan Guo,

Yehui Tang,

Kai Han,

Xinghao Chen,

Han Wu,

Chao Xu,

Chang Xu,

Yunhe Wang; [pdf] [supp]
[bibtex]
@InProceedings{Guo_2022_CVPR, author = {Guo, Jianyuan and Tang, Yehui and Han, Kai and Chen, Xinghao and Wu, Han and Xu, Chao and Xu, Chang and Wang, Yunhe}, title = {Hire-MLP: Vision MLP via Hierarchical Rearrangement}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {826-836} }
Occluded Human Mesh Recovery: Rawal Khirodkar,

Shashank Tripathi,

Kris Kitani; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Khirodkar_2022_CVPR, author = {Khirodkar, Rawal and Tripathi, Shashank and Kitani, Kris}, title = {Occluded Human Mesh Recovery}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {1715-1725} }
MAD: A Scalable Dataset for Language Grounding in Videos From Movie Audio Descriptions: Mattia Soldan,

Alejandro Pardo,

Juan León Alcázar,

Fabian Caba,

Chen Zhao,

Silvio Giancola,

Bernard Ghanem; [pdf] [supp]
[bibtex]
@InProceedings{Soldan_2022_CVPR, author = {Soldan, Mattia and Pardo, Alejandro and Alc\'azar, Juan Le\'on and Caba, Fabian and Zhao, Chen and Giancola, Silvio and Ghanem, Bernard}, title = {MAD: A Scalable Dataset for Language Grounding in Videos From Movie Audio Descriptions}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {5026-5035} }
ArtiBoost: Boosting Articulated 3D Hand-Object Pose Estimation via Online Exploration and Synthesis: Lixin Yang,

Kailin Li,

Xinyu Zhan,

Jun Lv,

Wenqiang Xu,

Jiefeng Li,

Cewu Lu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yang_2022_CVPR, author = {Yang, Lixin and Li, Kailin and Zhan, Xinyu and Lv, Jun and Xu, Wenqiang and Li, Jiefeng and Lu, Cewu}, title = {ArtiBoost: Boosting Articulated 3D Hand-Object Pose Estimation via Online Exploration and Synthesis}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {2750-2760} }
Disentangled3D: Learning a 3D Generative Model With Disentangled Geometry and Appearance From Monocular Images: Ayush Tewari,

Mallikarjun B R,

Xingang Pan,

Ohad Fried,

Maneesh Agrawala,

Christian Theobalt; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Tewari_2022_CVPR, author = {Tewari, Ayush and R, Mallikarjun B and Pan, Xingang and Fried, Ohad and Agrawala, Maneesh and Theobalt, Christian}, title = {Disentangled3D: Learning a 3D Generative Model With Disentangled Geometry and Appearance From Monocular Images}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {1516-1525} }
Revisiting Random Channel Pruning for Neural Network Compression: Yawei Li,

Kamil Adamczewski,

Wen Li,

Shuhang Gu,

Radu Timofte,

Luc Van Gool; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Li_2022_CVPR, author = {Li, Yawei and Adamczewski, Kamil and Li, Wen and Gu, Shuhang and Timofte, Radu and Van Gool, Luc}, title = {Revisiting Random Channel Pruning for Neural Network Compression}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {191-201} }
Does Text Attract Attention on E-Commerce Images: A Novel Saliency Prediction Dataset and Method: Lai Jiang,

Yifei Li,

Shengxi Li,

Mai Xu,

Se Lei,

Yichen Guo,

Bo Huang; [pdf]
[bibtex]
@InProceedings{Jiang_2022_CVPR, author = {Jiang, Lai and Li, Yifei and Li, Shengxi and Xu, Mai and Lei, Se and Guo, Yichen and Huang, Bo}, title = {Does Text Attract Attention on E-Commerce Images: A Novel Saliency Prediction Dataset and Method}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {2088-2097} }
Topologically-Aware Deformation Fields for Single-View 3D Reconstruction: Shivam Duggal,

Deepak Pathak; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Duggal_2022_CVPR, author = {Duggal, Shivam and Pathak, Deepak}, title = {Topologically-Aware Deformation Fields for Single-View 3D Reconstruction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {1536-1546} }
Sparse Non-Local CRF: Olga Veksler,

Yuri Boykov; [pdf] [supp]
[bibtex]
@InProceedings{Veksler_2022_CVPR, author = {Veksler, Olga and Boykov, Yuri}, title = {Sparse Non-Local CRF}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {4493-4503} }
EPro-PnP: Generalized End-to-End Probabilistic Perspective-N-Points for Monocular Object Pose Estimation: Hansheng Chen,

Pichao Wang,

Fan Wang,

Wei Tian,

Lu Xiong,

Hao Li; [pdf] [supp]
[bibtex]
@InProceedings{Chen_2022_CVPR, author = {Chen, Hansheng and Wang, Pichao and Wang, Fan and Tian, Wei and Xiong, Lu and Li, Hao}, title = {EPro-PnP: Generalized End-to-End Probabilistic Perspective-N-Points for Monocular Object Pose Estimation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {2781-2790} }
Generating Diverse and Natural 3D Human Motions From Text: Chuan Guo,

Shihao Zou,

Xinxin Zuo,

Sen Wang,

Wei Ji,

Xingyu Li,

Li Cheng; [pdf] [supp]
[bibtex]
@InProceedings{Guo_2022_CVPR, author = {Guo, Chuan and Zou, Shihao and Zuo, Xinxin and Wang, Sen and Ji, Wei and Li, Xingyu and Cheng, Li}, title = {Generating Diverse and Natural 3D Human Motions From Text}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {5152-5161} }
Multi-Frame Self-Supervised Depth With Transformers: Vitor Guizilini,

Rareș Ambruș,

Dian Chen,

Sergey Zakharov,

Adrien Gaidon; [pdf] [supp]
[bibtex]
@InProceedings{Guizilini_2022_CVPR, author = {Guizilini, Vitor and Ambruș, Rareș and Chen, Dian and Zakharov, Sergey and Gaidon, Adrien}, title = {Multi-Frame Self-Supervised Depth With Transformers}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {160-170} }
Self-Supervised Keypoint Discovery in Behavioral Videos: Jennifer J. Sun,

Serim Ryou,

Roni H. Goldshmid,

Brandon Weissbourd,

John O. Dabiri,

David J. Anderson,

Ann Kennedy,

Yisong Yue,

Pietro Perona; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Sun_2022_CVPR, author = {Sun, Jennifer J. and Ryou, Serim and Goldshmid, Roni H. and Weissbourd, Brandon and Dabiri, John O. and Anderson, David J. and Kennedy, Ann and Yue, Yisong and Perona, Pietro}, title = {Self-Supervised Keypoint Discovery in Behavioral Videos}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {2171-2180} }
IRISformer: Dense Vision Transformers for Single-Image Inverse Rendering in Indoor Scenes: Rui Zhu,

Zhengqin Li,

Janarbek Matai,

Fatih Porikli,

Manmohan Chandraker; [pdf] [supp]
[bibtex]
@InProceedings{Zhu_2022_CVPR, author = {Zhu, Rui and Li, Zhengqin and Matai, Janarbek and Porikli, Fatih and Chandraker, Manmohan}, title = {IRISformer: Dense Vision Transformers for Single-Image Inverse Rendering in Indoor Scenes}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {2822-2831} }
Connecting the Complementary-View Videos: Joint Camera Identification and Subject Association: Ruize Han,

Yiyang Gan,

Jiacheng Li,

Feifan Wang,

Wei Feng,

Song Wang; [pdf] [supp]
[bibtex]
@InProceedings{Han_2022_CVPR, author = {Han, Ruize and Gan, Yiyang and Li, Jiacheng and Wang, Feifan and Feng, Wei and Wang, Song}, title = {Connecting the Complementary-View Videos: Joint Camera Identification and Subject Association}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {2416-2425} }
End-to-End Trajectory Distribution Prediction Based on Occupancy Grid Maps: Ke Guo,

Wenxi Liu,

Jia Pan; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Guo_2022_CVPR, author = {Guo, Ke and Liu, Wenxi and Pan, Jia}, title = {End-to-End Trajectory Distribution Prediction Based on Occupancy Grid Maps}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {2242-2251} }
Weakly Supervised Temporal Action Localization via Representative Snippet Knowledge Propagation: Linjiang Huang,

Liang Wang,

Hongsheng Li; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Huang_2022_CVPR, author = {Huang, Linjiang and Wang, Liang and Li, Hongsheng}, title = {Weakly Supervised Temporal Action Localization via Representative Snippet Knowledge Propagation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {3272-3281} }
E2EC: An End-to-End Contour-Based Method for High-Quality High-Speed Instance Segmentation: Tao Zhang,

Shiqing Wei,

Shunping Ji; [pdf] [arXiv]
[bibtex]
@InProceedings{Zhang_2022_CVPR, author = {Zhang, Tao and Wei, Shiqing and Ji, Shunping}, title = {E2EC: An End-to-End Contour-Based Method for High-Quality High-Speed Instance Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {4443-4452} }
Self-Supervised Image-Specific Prototype Exploration for Weakly Supervised Semantic Segmentation: Qi Chen,

Lingxiao Yang,

Jian-Huang Lai,

Xiaohua Xie; [pdf] [arXiv]
[bibtex]
@InProceedings{Chen_2022_CVPR, author = {Chen, Qi and Yang, Lingxiao and Lai, Jian-Huang and Xie, Xiaohua}, title = {Self-Supervised Image-Specific Prototype Exploration for Weakly Supervised Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {4288-4298} }
Clothes-Changing Person Re-Identification With RGB Modality Only: Xinqian Gu,

Hong Chang,

Bingpeng Ma,

Shutao Bai,

Shiguang Shan,

Xilin Chen; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Gu_2022_CVPR, author = {Gu, Xinqian and Chang, Hong and Ma, Bingpeng and Bai, Shutao and Shan, Shiguang and Chen, Xilin}, title = {Clothes-Changing Person Re-Identification With RGB Modality Only}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {1060-1069} }
Chitransformer: Towards Reliable Stereo From Cues: Qing Su,

Shihao Ji; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Su_2022_CVPR, author = {Su, Qing and Ji, Shihao}, title = {Chitransformer: Towards Reliable Stereo From Cues}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {1939-1949} }
Modality-Agnostic Learning for Radar-Lidar Fusion in Vehicle Detection: Yu-Jhe Li,

Jinhyung Park,

Matthew O'Toole,

Kris Kitani; [pdf]
[bibtex]
@InProceedings{Li_2022_CVPR, author = {Li, Yu-Jhe and Park, Jinhyung and O'Toole, Matthew and Kitani, Kris}, title = {Modality-Agnostic Learning for Radar-Lidar Fusion in Vehicle Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {918-927} }
A Re-Balancing Strategy for Class-Imbalanced Classification Based on Instance Difficulty: Sihao Yu,

Jiafeng Guo,

Ruqing Zhang,

Yixing Fan,

Zizhen Wang,

Xueqi Cheng; [pdf] [supp]
[bibtex]
@InProceedings{Yu_2022_CVPR, author = {Yu, Sihao and Guo, Jiafeng and Zhang, Ruqing and Fan, Yixing and Wang, Zizhen and Cheng, Xueqi}, title = {A Re-Balancing Strategy for Class-Imbalanced Classification Based on Instance Difficulty}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {70-79} }
Tracking People by Predicting 3D Appearance, Location and Pose: Jathushan Rajasegaran,

Georgios Pavlakos,

Angjoo Kanazawa,

Jitendra Malik; [pdf] [supp]
[bibtex]
@InProceedings{Rajasegaran_2022_CVPR, author = {Rajasegaran, Jathushan and Pavlakos, Georgios and Kanazawa, Angjoo and Malik, Jitendra}, title = {Tracking People by Predicting 3D Appearance, Location and Pose}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {2740-2749} }
Tencent-MVSE: A Large-Scale Benchmark Dataset for Multi-Modal Video Similarity Evaluation: Zhaoyang Zeng,

Yongsheng Luo,

Zhenhua Liu,

Fengyun Rao,

Dian Li,

Weidong Guo,

Zhen Wen; [pdf]
[bibtex]
@InProceedings{Zeng_2022_CVPR, author = {Zeng, Zhaoyang and Luo, Yongsheng and Liu, Zhenhua and Rao, Fengyun and Li, Dian and Guo, Weidong and Wen, Zhen}, title = {Tencent-MVSE: A Large-Scale Benchmark Dataset for Multi-Modal Video Similarity Evaluation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {3138-3147} }
Deep Orientation-Aware Functional Maps: Tackling Symmetry Issues in Shape Matching: Nicolas Donati,

Etienne Corman,

Maks Ovsjanikov; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Donati_2022_CVPR, author = {Donati, Nicolas and Corman, Etienne and Ovsjanikov, Maks}, title = {Deep Orientation-Aware Functional Maps: Tackling Symmetry Issues in Shape Matching}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {742-751} }
Video Shadow Detection via Spatio-Temporal Interpolation Consistency Training: Xiao Lu,

Yihong Cao,

Sheng Liu,

Chengjiang Long,

Zipei Chen,

Xuanyu Zhou,

Yimin Yang,

Chunxia Xiao; [pdf] [supp]
[bibtex]
@InProceedings{Lu_2022_CVPR, author = {Lu, Xiao and Cao, Yihong and Liu, Sheng and Long, Chengjiang and Chen, Zipei and Zhou, Xuanyu and Yang, Yimin and Xiao, Chunxia}, title = {Video Shadow Detection via Spatio-Temporal Interpolation Consistency Training}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {3116-3125} }
Robust and Accurate Superquadric Recovery: A Probabilistic Approach: Weixiao Liu,

Yuwei Wu,

Sipu Ruan,

Gregory S. Chirikjian; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Liu_2022_CVPR, author = {Liu, Weixiao and Wu, Yuwei and Ruan, Sipu and Chirikjian, Gregory S.}, title = {Robust and Accurate Superquadric Recovery: A Probabilistic Approach}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {2676-2685} }
Zero-Shot Text-Guided Object Generation With Dream Fields: Ajay Jain,

Ben Mildenhall,

Jonathan T. Barron,

Pieter Abbeel,

Ben Poole; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Jain_2022_CVPR, author = {Jain, Ajay and Mildenhall, Ben and Barron, Jonathan T. and Abbeel, Pieter and Poole, Ben}, title = {Zero-Shot Text-Guided Object Generation With Dream Fields}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {867-876} }
Sparse Instance Activation for Real-Time Instance Segmentation: Tianheng Cheng,

Xinggang Wang,

Shaoyu Chen,

Wenqiang Zhang,

Qian Zhang,

Chang Huang,

Zhaoxiang Zhang,

Wenyu Liu; [pdf] [arXiv]
[bibtex]
@InProceedings{Cheng_2022_CVPR, author = {Cheng, Tianheng and Wang, Xinggang and Chen, Shaoyu and Zhang, Wenqiang and Zhang, Qian and Huang, Chang and Zhang, Zhaoxiang and Liu, Wenyu}, title = {Sparse Instance Activation for Real-Time Instance Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {4433-4442} }
Can You Spot the Chameleon? Adversarially Camouflaging Images From Co-Salient Object Detection: Ruijun Gao,

Qing Guo,

Felix Juefei-Xu,

Hongkai Yu,

Huazhu Fu,

Wei Feng,

Yang Liu,

Song Wang; [pdf]
[bibtex]
@InProceedings{Gao_2022_CVPR, author = {Gao, Ruijun and Guo, Qing and Juefei-Xu, Felix and Yu, Hongkai and Fu, Huazhu and Feng, Wei and Liu, Yang and Wang, Song}, title = {Can You Spot the Chameleon? Adversarially Camouflaging Images From Co-Salient Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {2150-2159} }
Learning From Temporal Gradient for Semi-Supervised Action Recognition: Junfei Xiao,

Longlong Jing,

Lin Zhang,

Ju He,

Qi She,

Zongwei Zhou,

Alan Yuille,

Yingwei Li; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Xiao_2022_CVPR, author = {Xiao, Junfei and Jing, Longlong and Zhang, Lin and He, Ju and She, Qi and Zhou, Zongwei and Yuille, Alan and Li, Yingwei}, title = {Learning From Temporal Gradient for Semi-Supervised Action Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {3252-3262} }
Audio-Driven Neural Gesture Reenactment With Video Motion Graphs: Yang Zhou,

Jimei Yang,

Dingzeyu Li,

Jun Saito,

Deepali Aneja,

Evangelos Kalogerakis; [pdf] [supp]
[bibtex]
@InProceedings{Zhou_2022_CVPR, author = {Zhou, Yang and Yang, Jimei and Li, Dingzeyu and Saito, Jun and Aneja, Deepali and Kalogerakis, Evangelos}, title = {Audio-Driven Neural Gesture Reenactment With Video Motion Graphs}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {3418-3428} }
SoftCollage: A Differentiable Probabilistic Tree Generator for Image Collage: Jiahao Yu,

Li Chen,

Mingrui Zhang,

Mading Li; [pdf] [supp]
[bibtex]
@InProceedings{Yu_2022_CVPR, author = {Yu, Jiahao and Chen, Li and Zhang, Mingrui and Li, Mading}, title = {SoftCollage: A Differentiable Probabilistic Tree Generator for Image Collage}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {3729-3738} }
A Unified Framework for Implicit Sinkhorn Differentiation: Marvin Eisenberger,

Aysim Toker,

Laura Leal-Taixé,

Florian Bernard,

Daniel Cremers; [pdf] [supp]
[bibtex]
@InProceedings{Eisenberger_2022_CVPR, author = {Eisenberger, Marvin and Toker, Aysim and Leal-Taix\'e, Laura and Bernard, Florian and Cremers, Daniel}, title = {A Unified Framework for Implicit Sinkhorn Differentiation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {509-518} }
DGECN: A Depth-Guided Edge Convolutional Network for End-to-End 6D Pose Estimation: Tuo Cao,

Fei Luo,

Yanping Fu,

Wenxiao Zhang,

Shengjie Zheng,

Chunxia Xiao; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Cao_2022_CVPR, author = {Cao, Tuo and Luo, Fei and Fu, Yanping and Zhang, Wenxiao and Zheng, Shengjie and Xiao, Chunxia}, title = {DGECN: A Depth-Guided Edge Convolutional Network for End-to-End 6D Pose Estimation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {3783-3792} }
Winoground: Probing Vision and Language Models for Visio-Linguistic Compositionality: Tristan Thrush,

Ryan Jiang,

Max Bartolo,

Amanpreet Singh,

Adina Williams,

Douwe Kiela,

Candace Ross; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Thrush_2022_CVPR, author = {Thrush, Tristan and Jiang, Ryan and Bartolo, Max and Singh, Amanpreet and Williams, Adina and Kiela, Douwe and Ross, Candace}, title = {Winoground: Probing Vision and Language Models for Visio-Linguistic Compositionality}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {5238-5248} }
Progressive Attention on Multi-Level Dense Difference Maps for Generic Event Boundary Detection: Jiaqi Tang,

Zhaoyang Liu,

Chen Qian,

Wayne Wu,

Limin Wang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Tang_2022_CVPR, author = {Tang, Jiaqi and Liu, Zhaoyang and Qian, Chen and Wu, Wayne and Wang, Limin}, title = {Progressive Attention on Multi-Level Dense Difference Maps for Generic Event Boundary Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {3355-3364} }
3D Scene Painting via Semantic Image Synthesis: Jaebong Jeong,

Janghun Jo,

Sunghyun Cho,

Jaesik Park; [pdf] [supp]
[bibtex]
@InProceedings{Jeong_2022_CVPR, author = {Jeong, Jaebong and Jo, Janghun and Cho, Sunghyun and Park, Jaesik}, title = {3D Scene Painting via Semantic Image Synthesis}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {2262-2272} }
Revisiting Weakly Supervised Pre-Training of Visual Perception Models: Mannat Singh,

Laura Gustafson,

Aaron Adcock,

Vinicius de Freitas Reis,

Bugra Gedik,

Raj Prateek Kosaraju,

Dhruv Mahajan,

Ross Girshick,

Piotr Dollár,

Laurens van der Maaten; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Singh_2022_CVPR, author = {Singh, Mannat and Gustafson, Laura and Adcock, Aaron and de Freitas Reis, Vinicius and Gedik, Bugra and Kosaraju, Raj Prateek and Mahajan, Dhruv and Girshick, Ross and Doll\'ar, Piotr and van der Maaten, Laurens}, title = {Revisiting Weakly Supervised Pre-Training of Visual Perception Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {804-814} }
Meta Convolutional Neural Networks for Single Domain Generalization: Chaoqun Wan,

Xu Shen,

Yonggang Zhang,

Zhiheng Yin,

Xinmei Tian,

Feng Gao,

Jianqiang Huang,

Xian-Sheng Hua; [pdf] [supp]
[bibtex]
@InProceedings{Wan_2022_CVPR, author = {Wan, Chaoqun and Shen, Xu and Zhang, Yonggang and Yin, Zhiheng and Tian, Xinmei and Gao, Feng and Huang, Jianqiang and Hua, Xian-Sheng}, title = {Meta Convolutional Neural Networks for Single Domain Generalization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {4682-4691} }
Generalizing Gaze Estimation With Rotation Consistency: Yiwei Bao,

Yunfei Liu,

Haofei Wang,

Feng Lu; [pdf]
[bibtex]
@InProceedings{Bao_2022_CVPR, author = {Bao, Yiwei and Liu, Yunfei and Wang, Haofei and Lu, Feng}, title = {Generalizing Gaze Estimation With Rotation Consistency}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {4207-4216} }
Accelerating Neural Network Optimization Through an Automated Control Theory Lens: Jiahao Wang,

Baoyuan Wu,

Rui Su,

Mingdeng Cao,

Shuwei Shi,

Wanli Ouyang,

Yujiu Yang; [pdf] [supp]
[bibtex]
@InProceedings{Wang_2022_CVPR, author = {Wang, Jiahao and Wu, Baoyuan and Su, Rui and Cao, Mingdeng and Shi, Shuwei and Ouyang, Wanli and Yang, Yujiu}, title = {Accelerating Neural Network Optimization Through an Automated Control Theory Lens}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {490-499} }
Learning To Learn Across Diverse Data Biases in Deep Face Recognition: Chang Liu,

Xiang Yu,

Yi-Hsuan Tsai,

Masoud Faraki,

Ramin Moslemi,

Manmohan Chandraker,

Yun Fu; [pdf] [supp]
[bibtex]
@InProceedings{Liu_2022_CVPR, author = {Liu, Chang and Yu, Xiang and Tsai, Yi-Hsuan and Faraki, Masoud and Moslemi, Ramin and Chandraker, Manmohan and Fu, Yun}, title = {Learning To Learn Across Diverse Data Biases in Deep Face Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {4072-4082} }
Online Convolutional Re-Parameterization: Mu Hu,

Junyi Feng,

Jiashen Hua,

Baisheng Lai,

Jianqiang Huang,

Xiaojin Gong,

Xian-Sheng Hua; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Hu_2022_CVPR, author = {Hu, Mu and Feng, Junyi and Hua, Jiashen and Lai, Baisheng and Huang, Jianqiang and Gong, Xiaojin and Hua, Xian-Sheng}, title = {Online Convolutional Re-Parameterization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {568-577} }
Smooth Maximum Unit: Smooth Activation Function for Deep Networks Using Smoothing Maximum Technique: Koushik Biswas,

Sandeep Kumar,

Shilpak Banerjee,

Ashish Kumar Pandey; [pdf] [supp]
[bibtex]
@InProceedings{Biswas_2022_CVPR, author = {Biswas, Koushik and Kumar, Sandeep and Banerjee, Shilpak and Pandey, Ashish Kumar}, title = {Smooth Maximum Unit: Smooth Activation Function for Deep Networks Using Smoothing Maximum Technique}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {794-803} }
Learning Invisible Markers for Hidden Codes in Offline-to-Online Photography: Jun Jia,

Zhongpai Gao,

Dandan Zhu,

Xiongkuo Min,

Guangtao Zhai,

Xiaokang Yang; [pdf] [supp]
[bibtex]
@InProceedings{Jia_2022_CVPR, author = {Jia, Jun and Gao, Zhongpai and Zhu, Dandan and Min, Xiongkuo and Zhai, Guangtao and Yang, Xiaokang}, title = {Learning Invisible Markers for Hidden Codes in Offline-to-Online Photography}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {2273-2282} }
Noise Is Also Useful: Negative Correlation-Steered Latent Contrastive Learning: Jiexi Yan,

Lei Luo,

Chenghao Xu,

Cheng Deng,

Heng Huang; [pdf]
[bibtex]
@InProceedings{Yan_2022_CVPR, author = {Yan, Jiexi and Luo, Lei and Xu, Chenghao and Deng, Cheng and Huang, Heng}, title = {Noise Is Also Useful: Negative Correlation-Steered Latent Contrastive Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {31-40} }
Decoupled Multi-Task Learning With Cyclical Self-Regulation for Face Parsing: Qingping Zheng,

Jiankang Deng,

Zheng Zhu,

Ying Li,

Stefanos Zafeiriou; [pdf] [arXiv]
[bibtex]
@InProceedings{Zheng_2022_CVPR, author = {Zheng, Qingping and Deng, Jiankang and Zhu, Zheng and Li, Ying and Zafeiriou, Stefanos}, title = {Decoupled Multi-Task Learning With Cyclical Self-Regulation for Face Parsing}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {4156-4165} }
AUV-Net: Learning Aligned UV Maps for Texture Transfer and Synthesis: Zhiqin Chen,

Kangxue Yin,

Sanja Fidler; [pdf]
[bibtex]
@InProceedings{Chen_2022_CVPR, author = {Chen, Zhiqin and Yin, Kangxue and Fidler, Sanja}, title = {AUV-Net: Learning Aligned UV Maps for Texture Transfer and Synthesis}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {1465-1474} }
Eigencontours: Novel Contour Descriptors Based on Low-Rank Approximation: Wonhui Park,

Dongkwon Jin,

Chang-Su Kim; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Park_2022_CVPR, author = {Park, Wonhui and Jin, Dongkwon and Kim, Chang-Su}, title = {Eigencontours: Novel Contour Descriptors Based on Low-Rank Approximation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {2667-2675} }
Efficient Deep Embedded Subspace Clustering: Jinyu Cai,

Jicong Fan,

Wenzhong Guo,

Shiping Wang,

Yunhe Zhang,

Zhao Zhang; [pdf] [supp]
[bibtex]
@InProceedings{Cai_2022_CVPR, author = {Cai, Jinyu and Fan, Jicong and Guo, Wenzhong and Wang, Shiping and Zhang, Yunhe and Zhang, Zhao}, title = {Efficient Deep Embedded Subspace Clustering}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {1-10} }
Spatial-Temporal Space Hand-in-Hand: Spatial-Temporal Video Super-Resolution via Cycle-Projected Mutual Learning: Mengshun Hu,

Kui Jiang,

Liang Liao,

Jing Xiao,

Junjun Jiang,

Zheng Wang; [pdf]
[bibtex]
@InProceedings{Hu_2022_CVPR, author = {Hu, Mengshun and Jiang, Kui and Liao, Liang and Xiao, Jing and Jiang, Junjun and Wang, Zheng}, title = {Spatial-Temporal Space Hand-in-Hand: Spatial-Temporal Video Super-Resolution via Cycle-Projected Mutual Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {3574-3583} }
Revisiting Near/Remote Sensing With Geospatial Attention: Scott Workman,

M. Usman Rafique,

Hunter Blanton,

Nathan Jacobs; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Workman_2022_CVPR, author = {Workman, Scott and Rafique, M. Usman and Blanton, Hunter and Jacobs, Nathan}, title = {Revisiting Near/Remote Sensing With Geospatial Attention}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {1778-1787} }
Slot-VPS: Object-Centric Representation Learning for Video Panoptic Segmentation: Yi Zhou,

Hui Zhang,

Hana Lee,

Shuyang Sun,

Pingjun Li,

Yangguang Zhu,

ByungIn Yoo,

Xiaojuan Qi,

Jae-Joon Han; [pdf] [supp]
[bibtex]
@InProceedings{Zhou_2022_CVPR, author = {Zhou, Yi and Zhang, Hui and Lee, Hana and Sun, Shuyang and Li, Pingjun and Zhu, Yangguang and Yoo, ByungIn and Qi, Xiaojuan and Han, Jae-Joon}, title = {Slot-VPS: Object-Centric Representation Learning for Video Panoptic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {3093-3103} }
Efficient Video Instance Segmentation via Tracklet Query and Proposal: Jialian Wu,

Sudhir Yarram,

Hui Liang,

Tian Lan,

Junsong Yuan,

Jayan Eledath,

Gérard Medioni; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wu_2022_CVPR, author = {Wu, Jialian and Yarram, Sudhir and Liang, Hui and Lan, Tian and Yuan, Junsong and Eledath, Jayan and Medioni, G\'erard}, title = {Efficient Video Instance Segmentation via Tracklet Query and Proposal}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {959-968} }
NeuralHDHair: Automatic High-Fidelity Hair Modeling From a Single Image Using Implicit Neural Representations: Keyu Wu,

Yifan Ye,

Lingchen Yang,

Hongbo Fu,

Kun Zhou,

Youyi Zheng; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wu_2022_CVPR, author = {Wu, Keyu and Ye, Yifan and Yang, Lingchen and Fu, Hongbo and Zhou, Kun and Zheng, Youyi}, title = {NeuralHDHair: Automatic High-Fidelity Hair Modeling From a Single Image Using Implicit Neural Representations}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {1526-1535} }
Exploring Frequency Adversarial Attacks for Face Forgery Detection: Shuai Jia,

Chao Ma,

Taiping Yao,

Bangjie Yin,

Shouhong Ding,

Xiaokang Yang; [pdf] [arXiv]
[bibtex]
@InProceedings{Jia_2022_CVPR, author = {Jia, Shuai and Ma, Chao and Yao, Taiping and Yin, Bangjie and Ding, Shouhong and Yang, Xiaokang}, title = {Exploring Frequency Adversarial Attacks for Face Forgery Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {4103-4112} }
Signing at Scale: Learning to Co-Articulate Signs for Large-Scale Photo-Realistic Sign Language Production: Ben Saunders,

Necati Cihan Camgoz,

Richard Bowden; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Saunders_2022_CVPR, author = {Saunders, Ben and Camgoz, Necati Cihan and Bowden, Richard}, title = {Signing at Scale: Learning to Co-Articulate Signs for Large-Scale Photo-Realistic Sign Language Production}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {5141-5151} }
Explore Spatio-Temporal Aggregation for Insubstantial Object Detection: Benchmark Dataset and Baseline: Kailai Zhou,

Yibo Wang,

Tao Lv,

Yunqian Li,

Linsen Chen,

Qiu Shen,

Xun Cao; [pdf]
[bibtex]
@InProceedings{Zhou_2022_CVPR, author = {Zhou, Kailai and Wang, Yibo and Lv, Tao and Li, Yunqian and Chen, Linsen and Shen, Qiu and Cao, Xun}, title = {Explore Spatio-Temporal Aggregation for Insubstantial Object Detection: Benchmark Dataset and Baseline}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {3104-3115} }
Learning Bayesian Sparse Networks With Full Experience Replay for Continual Learning: Qingsen Yan,

Dong Gong,

Yuhang Liu,

Anton van den Hengel,

Javen Qinfeng Shi; [pdf] [arXiv]
[bibtex]
@InProceedings{Yan_2022_CVPR, author = {Yan, Qingsen and Gong, Dong and Liu, Yuhang and van den Hengel, Anton and Shi, Javen Qinfeng}, title = {Learning Bayesian Sparse Networks With Full Experience Replay for Continual Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {109-118} }
Graph-Based Spatial Transformer With Memory Replay for Multi-Future Pedestrian Trajectory Prediction: Lihuan Li,

Maurice Pagnucco,

Yang Song; [pdf]
[bibtex]
@InProceedings{Li_2022_CVPR, author = {Li, Lihuan and Pagnucco, Maurice and Song, Yang}, title = {Graph-Based Spatial Transformer With Memory Replay for Multi-Future Pedestrian Trajectory Prediction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {2231-2241} }
TableFormer: Table Structure Understanding With Transformers: Ahmed Nassar,

Nikolaos Livathinos,

Maksym Lysak,

Peter Staar; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Nassar_2022_CVPR, author = {Nassar, Ahmed and Livathinos, Nikolaos and Lysak, Maksym and Staar, Peter}, title = {TableFormer: Table Structure Understanding With Transformers}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {4614-4623} }
Exemplar-Based Pattern Synthesis With Implicit Periodic Field Network: Haiwei Chen,

Jiayi Liu,

Weikai Chen,

Shichen Liu,

Yajie Zhao; [pdf] [arXiv]
[bibtex]
@InProceedings{Chen_2022_CVPR, author = {Chen, Haiwei and Liu, Jiayi and Chen, Weikai and Liu, Shichen and Zhao, Yajie}, title = {Exemplar-Based Pattern Synthesis With Implicit Periodic Field Network}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {3708-3717} }
Generating 3D Bio-Printable Patches Using Wound Segmentation and Reconstruction To Treat Diabetic Foot Ulcers: Han Joo Chae,

Seunghwan Lee,

Hyewon Son,

Seungyeob Han,

Taebin Lim; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chae_2022_CVPR, author = {Chae, Han Joo and Lee, Seunghwan and Son, Hyewon and Han, Seungyeob and Lim, Taebin}, title = {Generating 3D Bio-Printable Patches Using Wound Segmentation and Reconstruction To Treat Diabetic Foot Ulcers}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {2539-2549} }
OmniFusion: 360 Monocular Depth Estimation via Geometry-Aware Fusion: Yuyan Li,

Yuliang Guo,

Zhixin Yan,

Xinyu Huang,

Ye Duan,

Liu Ren; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Li_2022_CVPR, author = {Li, Yuyan and Guo, Yuliang and Yan, Zhixin and Huang, Xinyu and Duan, Ye and Ren, Liu}, title = {OmniFusion: 360 Monocular Depth Estimation via Geometry-Aware Fusion}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {2801-2810} }
Semi-Weakly-Supervised Learning of Complex Actions From Instructional Task Videos: Yuhan Shen,

Ehsan Elhamifar; [pdf] [supp]
[bibtex]
@InProceedings{Shen_2022_CVPR, author = {Shen, Yuhan and Elhamifar, Ehsan}, title = {Semi-Weakly-Supervised Learning of Complex Actions From Instructional Task Videos}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {3344-3354} }
VALHALLA: Visual Hallucination for Machine Translation: Yi Li,

Rameswar Panda,

Yoon Kim,

Chun-Fu (Richard) Chen,

Rogerio S. Feris,

David Cox,

Nuno Vasconcelos; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Li_2022_CVPR, author = {Li, Yi and Panda, Rameswar and Kim, Yoon and Chen, Chun-Fu (Richard) and Feris, Rogerio S. and Cox, David and Vasconcelos, Nuno}, title = {VALHALLA: Visual Hallucination for Machine Translation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {5216-5226} }
Advancing High-Resolution Video-Language Representation With Large-Scale Video Transcriptions: Hongwei Xue,

Tiankai Hang,

Yanhong Zeng,

Yuchong Sun,

Bei Liu,

Huan Yang,

Jianlong Fu,

Baining Guo; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Xue_2022_CVPR, author = {Xue, Hongwei and Hang, Tiankai and Zeng, Yanhong and Sun, Yuchong and Liu, Bei and Yang, Huan and Fu, Jianlong and Guo, Baining}, title = {Advancing High-Resolution Video-Language Representation With Large-Scale Video Transcriptions}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {5036-5045} }
Neural Face Identification in a 2D Wireframe Projection of a Manifold Object: Kehan Wang,

Jia Zheng,

Zihan Zhou; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2022_CVPR, author = {Wang, Kehan and Zheng, Jia and Zhou, Zihan}, title = {Neural Face Identification in a 2D Wireframe Projection of a Manifold Object}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {1622-1631} }
Nonuniform-to-Uniform Quantization: Towards Accurate Quantization via Generalized Straight-Through Estimation: Zechun Liu,

Kwang-Ting Cheng,

Dong Huang,

Eric P. Xing,

Zhiqiang Shen; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Liu_2022_CVPR, author = {Liu, Zechun and Cheng, Kwang-Ting and Huang, Dong and Xing, Eric P. and Shen, Zhiqiang}, title = {Nonuniform-to-Uniform Quantization: Towards Accurate Quantization via Generalized Straight-Through Estimation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {4942-4952} }
Learning 3D Object Shape and Layout Without 3D Supervision: Georgia Gkioxari,

Nikhila Ravi,

Justin Johnson; [pdf] [supp]
[bibtex]
@InProceedings{Gkioxari_2022_CVPR, author = {Gkioxari, Georgia and Ravi, Nikhila and Johnson, Justin}, title = {Learning 3D Object Shape and Layout Without 3D Supervision}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {1695-1704} }
SimVP: Simpler Yet Better Video Prediction: Zhangyang Gao,

Cheng Tan,

Lirong Wu,

Stan Z. Li; [pdf] [supp]
[bibtex]
@InProceedings{Gao_2022_CVPR, author = {Gao, Zhangyang and Tan, Cheng and Wu, Lirong and Li, Stan Z.}, title = {SimVP: Simpler Yet Better Video Prediction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {3170-3180} }
Object Localization Under Single Coarse Point Supervision: Xuehui Yu,

Pengfei Chen,

Di Wu,

Najmul Hassan,

Guorong Li,

Junchi Yan,

Humphrey Shi,

Qixiang Ye,

Zhenjun Han; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yu_2022_CVPR, author = {Yu, Xuehui and Chen, Pengfei and Wu, Di and Hassan, Najmul and Li, Guorong and Yan, Junchi and Shi, Humphrey and Ye, Qixiang and Han, Zhenjun}, title = {Object Localization Under Single Coarse Point Supervision}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {4868-4877} }
Bayesian Nonparametric Submodular Video Partition for Robust Anomaly Detection: Hitesh Sapkota,

Qi Yu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Sapkota_2022_CVPR, author = {Sapkota, Hitesh and Yu, Qi}, title = {Bayesian Nonparametric Submodular Video Partition for Robust Anomaly Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {3212-3221} }
FocalClick: Towards Practical Interactive Image Segmentation: Xi Chen,

Zhiyan Zhao,

Yilei Zhang,

Manni Duan,

Donglian Qi,

Hengshuang Zhao; [pdf] [arXiv]
[bibtex]
@InProceedings{Chen_2022_CVPR, author = {Chen, Xi and Zhao, Zhiyan and Zhang, Yilei and Duan, Manni and Qi, Donglian and Zhao, Hengshuang}, title = {FocalClick: Towards Practical Interactive Image Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {1300-1309} }
ISDNet: Integrating Shallow and Deep Networks for Efficient Ultra-High Resolution Segmentation: Shaohua Guo,

Liang Liu,

Zhenye Gan,

Yabiao Wang,

Wuhao Zhang,

Chengjie Wang,

Guannan Jiang,

Wei Zhang,

Ran Yi,

Lizhuang Ma,

Ke Xu; [pdf] [supp]
[bibtex]
@InProceedings{Guo_2022_CVPR, author = {Guo, Shaohua and Liu, Liang and Gan, Zhenye and Wang, Yabiao and Zhang, Wuhao and Wang, Chengjie and Jiang, Guannan and Zhang, Wei and Yi, Ran and Ma, Lizhuang and Xu, Ke}, title = {ISDNet: Integrating Shallow and Deep Networks for Efficient Ultra-High Resolution Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {4361-4370} }
Understanding Uncertainty Maps in Vision With Statistical Testing: Jurijs Nazarovs,

Zhichun Huang,

Songwong Tasneeyapant,

Rudrasis Chakraborty,

Vikas Singh; [pdf] [supp]
[bibtex]
@InProceedings{Nazarovs_2022_CVPR, author = {Nazarovs, Jurijs and Huang, Zhichun and Tasneeyapant, Songwong and Chakraborty, Rudrasis and Singh, Vikas}, title = {Understanding Uncertainty Maps in Vision With Statistical Testing}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {406-416} }
A Variational Bayesian Method for Similarity Learning in Non-Rigid Image Registration: Daniel Grzech,

Mohammad Farid Azampour,

Ben Glocker,

Julia Schnabel,

Nassir Navab,

Bernhard Kainz,

Loïc Le Folgoc; [pdf]
[bibtex]
@InProceedings{Grzech_2022_CVPR, author = {Grzech, Daniel and Azampour, Mohammad Farid and Glocker, Ben and Schnabel, Julia and Navab, Nassir and Kainz, Bernhard and Le Folgoc, Lo{\"\i}c}, title = {A Variational Bayesian Method for Similarity Learning in Non-Rigid Image Registration}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {119-128} }
Quarantine: Sparsity Can Uncover the Trojan Attack Trigger for Free: Tianlong Chen,

Zhenyu Zhang,

Yihua Zhang,

Shiyu Chang,

Sijia Liu,

Zhangyang Wang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chen_2022_CVPR, author = {Chen, Tianlong and Zhang, Zhenyu and Zhang, Yihua and Chang, Shiyu and Liu, Sijia and Wang, Zhangyang}, title = {Quarantine: Sparsity Can Uncover the Trojan Attack Trigger for Free}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {598-609} }
Why Discard if You Can Recycle?: A Recycling Max Pooling Module for 3D Point Cloud Analysis: Jiajing Chen,

Burak Kakillioglu,

Huantao Ren,

Senem Velipasalar; [pdf] [supp]
[bibtex]
@InProceedings{Chen_2022_CVPR, author = {Chen, Jiajing and Kakillioglu, Burak and Ren, Huantao and Velipasalar, Senem}, title = {Why Discard if You Can Recycle?: A Recycling Max Pooling Module for 3D Point Cloud Analysis}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {559-567} }
Learning From Pixel-Level Noisy Label: A New Perspective for Light Field Saliency Detection: Mingtao Feng,

Kendong Liu,

Liang Zhang,

Hongshan Yu,

Yaonan Wang,

Ajmal Mian; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Feng_2022_CVPR, author = {Feng, Mingtao and Liu, Kendong and Zhang, Liang and Yu, Hongshan and Wang, Yaonan and Mian, Ajmal}, title = {Learning From Pixel-Level Noisy Label: A New Perspective for Light Field Saliency Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {1756-1766} }
Multi-View Depth Estimation by Fusing Single-View Depth Probability With Multi-View Geometry: Gwangbin Bae,

Ignas Budvytis,

Roberto Cipolla; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Bae_2022_CVPR, author = {Bae, Gwangbin and Budvytis, Ignas and Cipolla, Roberto}, title = {Multi-View Depth Estimation by Fusing Single-View Depth Probability With Multi-View Geometry}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {2842-2851} }
CLIP-NeRF: Text-and-Image Driven Manipulation of Neural Radiance Fields: Can Wang,

Menglei Chai,

Mingming He,

Dongdong Chen,

Jing Liao; [pdf] [supp]
[bibtex]
@InProceedings{Wang_2022_CVPR, author = {Wang, Can and Chai, Menglei and He, Mingming and Chen, Dongdong and Liao, Jing}, title = {CLIP-NeRF: Text-and-Image Driven Manipulation of Neural Radiance Fields}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {3835-3844} }
Homography Loss for Monocular 3D Object Detection: Jiaqi Gu,

Bojian Wu,

Lubin Fan,

Jianqiang Huang,

Shen Cao,

Zhiyu Xiang,

Xian-Sheng Hua; [pdf] [arXiv]
[bibtex]
@InProceedings{Gu_2022_CVPR, author = {Gu, Jiaqi and Wu, Bojian and Fan, Lubin and Huang, Jianqiang and Cao, Shen and Xiang, Zhiyu and Hua, Xian-Sheng}, title = {Homography Loss for Monocular 3D Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {1080-1089} }
Dynamic Sparse R-CNN: Qinghang Hong,

Fengming Liu,

Dong Li,

Ji Liu,

Lu Tian,

Yi Shan; [pdf]
[bibtex]
@InProceedings{Hong_2022_CVPR, author = {Hong, Qinghang and Liu, Fengming and Li, Dong and Liu, Ji and Tian, Lu and Shan, Yi}, title = {Dynamic Sparse R-CNN}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {4723-4732} }
Stable Long-Term Recurrent Video Super-Resolution: Benjamin Naoto Chiche,

Arnaud Woiselle,

Joana Frontera-Pons,

Jean-Luc Starck; [pdf] [supp]
[bibtex]
@InProceedings{Chiche_2022_CVPR, author = {Chiche, Benjamin Naoto and Woiselle, Arnaud and Frontera-Pons, Joana and Starck, Jean-Luc}, title = {Stable Long-Term Recurrent Video Super-Resolution}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {837-846} }
Dual-Generator Face Reenactment: Gee-Sern Hsu,

Chun-Hung Tsai,

Hung-Yi Wu; [pdf]
[bibtex]
@InProceedings{Hsu_2022_CVPR, author = {Hsu, Gee-Sern and Tsai, Chun-Hung and Wu, Hung-Yi}, title = {Dual-Generator Face Reenactment}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {642-650} }
A Hybrid Quantum-Classical Algorithm for Robust Fitting: Anh-Dzung Doan,

Michele Sasdelli,

David Suter,

Tat-Jun Chin; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Doan_2022_CVPR, author = {Doan, Anh-Dzung and Sasdelli, Michele and Suter, David and Chin, Tat-Jun}, title = {A Hybrid Quantum-Classical Algorithm for Robust Fitting}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {417-427} }
Human Instance Matting via Mutual Guidance and Multi-Instance Refinement: Yanan Sun,

Chi-Keung Tang,

Yu-Wing Tai; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Sun_2022_CVPR, author = {Sun, Yanan and Tang, Chi-Keung and Tai, Yu-Wing}, title = {Human Instance Matting via Mutual Guidance and Multi-Instance Refinement}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {2647-2656} }
SwinTextSpotter: Scene Text Spotting via Better Synergy Between Text Detection and Text Recognition: Mingxin Huang,

Yuliang Liu,

Zhenghao Peng,

Chongyu Liu,

Dahua Lin,

Shenggao Zhu,

Nicholas Yuan,

Kai Ding,

Lianwen Jin; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Huang_2022_CVPR, author = {Huang, Mingxin and Liu, Yuliang and Peng, Zhenghao and Liu, Chongyu and Lin, Dahua and Zhu, Shenggao and Yuan, Nicholas and Ding, Kai and Jin, Lianwen}, title = {SwinTextSpotter: Scene Text Spotting via Better Synergy Between Text Detection and Text Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {4593-4603} }
Video Frame Interpolation With Transformer: Liying Lu,

Ruizheng Wu,

Huaijia Lin,

Jiangbo Lu,

Jiaya Jia; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Lu_2022_CVPR, author = {Lu, Liying and Wu, Ruizheng and Lin, Huaijia and Lu, Jiangbo and Jia, Jiaya}, title = {Video Frame Interpolation With Transformer}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {3532-3542} }
TemporalUV: Capturing Loose Clothing With Temporally Coherent UV Coordinates: You Xie,

Huiqi Mao,

Angela Yao,

Nils Thuerey; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Xie_2022_CVPR, author = {Xie, You and Mao, Huiqi and Yao, Angela and Thuerey, Nils}, title = {TemporalUV: Capturing Loose Clothing With Temporally Coherent UV Coordinates}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {3450-3459} }
An Iterative Quantum Approach for Transformation Estimation From Point Sets: Natacha Kuete Meli,

Florian Mannel,

Jan Lellmann; [pdf] [supp]
[bibtex]
@InProceedings{Meli_2022_CVPR, author = {Meli, Natacha Kuete and Mannel, Florian and Lellmann, Jan}, title = {An Iterative Quantum Approach for Transformation Estimation From Point Sets}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {529-537} }
PhysFormer: Facial Video-Based Physiological Measurement With Temporal Difference Transformer: Zitong Yu,

Yuming Shen,

Jingang Shi,

Hengshuang Zhao,

Philip H.S. Torr,

Guoying Zhao; [pdf] [arXiv]
[bibtex]
@InProceedings{Yu_2022_CVPR, author = {Yu, Zitong and Shen, Yuming and Shi, Jingang and Zhao, Hengshuang and Torr, Philip H.S. and Zhao, Guoying}, title = {PhysFormer: Facial Video-Based Physiological Measurement With Temporal Difference Transformer}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {4186-4196} }
Dimension Embeddings for Monocular 3D Object Detection: Yunpeng Zhang,

Wenzhao Zheng,

Zheng Zhu,

Guan Huang,

Dalong Du,

Jie Zhou,

Jiwen Lu; [pdf]
[bibtex]
@InProceedings{Zhang_2022_CVPR, author = {Zhang, Yunpeng and Zheng, Wenzhao and Zhu, Zheng and Huang, Guan and Du, Dalong and Zhou, Jie and Lu, Jiwen}, title = {Dimension Embeddings for Monocular 3D Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {1589-1598} }
Blind Image Super-Resolution With Elaborate Degradation Modeling on Noise and Kernel: Zongsheng Yue,

Qian Zhao,

Jianwen Xie,

Lei Zhang,

Deyu Meng,

Kwan-Yee K. Wong; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yue_2022_CVPR, author = {Yue, Zongsheng and Zhao, Qian and Xie, Jianwen and Zhang, Lei and Meng, Deyu and Wong, Kwan-Yee K.}, title = {Blind Image Super-Resolution With Elaborate Degradation Modeling on Noise and Kernel}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {2128-2138} }
Progressive End-to-End Object Detection in Crowded Scenes: Anlin Zheng,

Yuang Zhang,

Xiangyu Zhang,

Xiaojuan Qi,

Jian Sun; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zheng_2022_CVPR, author = {Zheng, Anlin and Zhang, Yuang and Zhang, Xiangyu and Qi, Xiaojuan and Sun, Jian}, title = {Progressive End-to-End Object Detection in Crowded Scenes}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {857-866} }
Robust Combination of Distributed Gradients Under Adversarial Perturbations: Kwang In Kim; [pdf] [supp]
[bibtex]
@InProceedings{Kim_2022_CVPR, author = {Kim, Kwang In}, title = {Robust Combination of Distributed Gradients Under Adversarial Perturbations}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {254-263} }
Automatic Synthesis of Diverse Weak Supervision Sources for Behavior Analysis: Albert Tseng,

Jennifer J. Sun,

Yisong Yue; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Tseng_2022_CVPR, author = {Tseng, Albert and Sun, Jennifer J. and Yue, Yisong}, title = {Automatic Synthesis of Diverse Weak Supervision Sources for Behavior Analysis}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {2211-2220} }
Habitat-Web: Learning Embodied Object-Search Strategies From Human Demonstrations at Scale: Ram Ramrakhya,

Eric Undersander,

Dhruv Batra,

Abhishek Das; [pdf] [supp]
[bibtex]
@InProceedings{Ramrakhya_2022_CVPR, author = {Ramrakhya, Ram and Undersander, Eric and Batra, Dhruv and Das, Abhishek}, title = {Habitat-Web: Learning Embodied Object-Search Strategies From Human Demonstrations at Scale}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {5173-5183} }
The Probabilistic Normal Epipolar Constraint for Frame-to-Frame Rotation Optimization Under Uncertain Feature Positions: Dominik Muhle,

Lukas Koestler,

Nikolaus Demmel,

Florian Bernard,

Daniel Cremers; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Muhle_2022_CVPR, author = {Muhle, Dominik and Koestler, Lukas and Demmel, Nikolaus and Bernard, Florian and Cremers, Daniel}, title = {The Probabilistic Normal Epipolar Constraint for Frame-to-Frame Rotation Optimization Under Uncertain Feature Positions}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {1819-1828} }
DyRep: Bootstrapping Training With Dynamic Re-Parameterization: Tao Huang,

Shan You,

Bohan Zhang,

Yuxuan Du,

Fei Wang,

Chen Qian,

Chang Xu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Huang_2022_CVPR, author = {Huang, Tao and You, Shan and Zhang, Bohan and Du, Yuxuan and Wang, Fei and Qian, Chen and Xu, Chang}, title = {DyRep: Bootstrapping Training With Dynamic Re-Parameterization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {588-597} }
CDGNet: Class Distribution Guided Network for Human Parsing: Kunliang Liu,

Ouk Choi,

Jianming Wang,

Wonjun Hwang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Liu_2022_CVPR, author = {Liu, Kunliang and Choi, Ouk and Wang, Jianming and Hwang, Wonjun}, title = {CDGNet: Class Distribution Guided Network for Human Parsing}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {4473-4482} }
Deep Safe Multi-View Clustering: Reducing the Risk of Clustering Performance Degradation Caused by View Increase: Huayi Tang,

Yong Liu; [pdf] [supp]
[bibtex]
@InProceedings{Tang_2022_CVPR, author = {Tang, Huayi and Liu, Yong}, title = {Deep Safe Multi-View Clustering: Reducing the Risk of Clustering Performance Degradation Caused by View Increase}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {202-211} }
HP-Capsule: Unsupervised Face Part Discovery by Hierarchical Parsing Capsule Network: Chang Yu,

Xiangyu Zhu,

Xiaomei Zhang,

Zidu Wang,

Zhaoxiang Zhang,

Zhen Lei; [pdf] [supp]
[bibtex]
@InProceedings{Yu_2022_CVPR, author = {Yu, Chang and Zhu, Xiangyu and Zhang, Xiaomei and Wang, Zidu and Zhang, Zhaoxiang and Lei, Zhen}, title = {HP-Capsule: Unsupervised Face Part Discovery by Hierarchical Parsing Capsule Network}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {4032-4041} }
MuKEA: Multimodal Knowledge Extraction and Accumulation for Knowledge-Based Visual Question Answering: Yang Ding,

Jing Yu,

Bang Liu,

Yue Hu,

Mingxin Cui,

Qi Wu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ding_2022_CVPR, author = {Ding, Yang and Yu, Jing and Liu, Bang and Hu, Yue and Cui, Mingxin and Wu, Qi}, title = {MuKEA: Multimodal Knowledge Extraction and Accumulation for Knowledge-Based Visual Question Answering}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {5089-5098} }
Transform-Retrieve-Generate: Natural Language-Centric Outside-Knowledge Visual Question Answering: Feng Gao,

Qing Ping,

Govind Thattai,

Aishwarya Reganti,

Ying Nian Wu,

Prem Natarajan; [pdf] [supp]
[bibtex]
@InProceedings{Gao_2022_CVPR, author = {Gao, Feng and Ping, Qing and Thattai, Govind and Reganti, Aishwarya and Wu, Ying Nian and Natarajan, Prem}, title = {Transform-Retrieve-Generate: Natural Language-Centric Outside-Knowledge Visual Question Answering}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {5067-5077} }
Nested Hyperbolic Spaces for Dimensionality Reduction and Hyperbolic NN Design: Xiran Fan,

Chun-Hao Yang,

Baba C. Vemuri; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Fan_2022_CVPR, author = {Fan, Xiran and Yang, Chun-Hao and Vemuri, Baba C.}, title = {Nested Hyperbolic Spaces for Dimensionality Reduction and Hyperbolic NN Design}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {356-365} }
BNUDC: A Two-Branched Deep Neural Network for Restoring Images From Under-Display Cameras: Jaihyun Koh,

Jangho Lee,

Sungroh Yoon; [pdf] [supp]
[bibtex]
@InProceedings{Koh_2022_CVPR, author = {Koh, Jaihyun and Lee, Jangho and Yoon, Sungroh}, title = {BNUDC: A Two-Branched Deep Neural Network for Restoring Images From Under-Display Cameras}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {1950-1959} }
Training Object Detectors From Scratch: An Empirical Study in the Era of Vision Transformer: Weixiang Hong,

Jiangwei Lao,

Wang Ren,

Jian Wang,

Jingdong Chen,

Wei Chu; [pdf]
[bibtex]
@InProceedings{Hong_2022_CVPR, author = {Hong, Weixiang and Lao, Jiangwei and Ren, Wang and Wang, Jian and Chen, Jingdong and Chu, Wei}, title = {Training Object Detectors From Scratch: An Empirical Study in the Era of Vision Transformer}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {4662-4671} }
C2SLR: Consistency-Enhanced Continuous Sign Language Recognition: Ronglai Zuo,

Brian Mak; [pdf] [supp]
[bibtex]
@InProceedings{Zuo_2022_CVPR, author = {Zuo, Ronglai and Mak, Brian}, title = {C2SLR: Consistency-Enhanced Continuous Sign Language Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {5131-5140} }
Label Relation Graphs Enhanced Hierarchical Residual Network for Hierarchical Multi-Granularity Classification: Jingzhou Chen,

Peng Wang,

Jian Liu,

Yuntao Qian; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chen_2022_CVPR, author = {Chen, Jingzhou and Wang, Peng and Liu, Jian and Qian, Yuntao}, title = {Label Relation Graphs Enhanced Hierarchical Residual Network for Hierarchical Multi-Granularity Classification}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {4858-4867} }
Enhancing Face Recognition With Self-Supervised 3D Reconstruction: Mingjie He,

Jie Zhang,

Shiguang Shan,

Xilin Chen; [pdf]
[bibtex]
@InProceedings{He_2022_CVPR, author = {He, Mingjie and Zhang, Jie and Shan, Shiguang and Chen, Xilin}, title = {Enhancing Face Recognition With Self-Supervised 3D Reconstruction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {4062-4071} }
FvOR: Robust Joint Shape and Pose Optimization for Few-View Object Reconstruction: Zhenpei Yang,

Zhile Ren,

Miguel Angel Bautista,

Zaiwei Zhang,

Qi Shan,

Qixing Huang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yang_2022_CVPR, author = {Yang, Zhenpei and Ren, Zhile and Bautista, Miguel Angel and Zhang, Zaiwei and Shan, Qi and Huang, Qixing}, title = {FvOR: Robust Joint Shape and Pose Optimization for Few-View Object Reconstruction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {2497-2507} }
Few Could Be Better Than All: Feature Sampling and Grouping for Scene Text Detection: Jingqun Tang,

Wenqing Zhang,

Hongye Liu,

MingKun Yang,

Bo Jiang,

Guanglong Hu,

Xiang Bai; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Tang_2022_CVPR, author = {Tang, Jingqun and Zhang, Wenqing and Liu, Hongye and Yang, MingKun and Jiang, Bo and Hu, Guanglong and Bai, Xiang}, title = {Few Could Be Better Than All: Feature Sampling and Grouping for Scene Text Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {4563-4572} }
IDR: Self-Supervised Image Denoising via Iterative Data Refinement: Yi Zhang,

Dasong Li,

Ka Lung Law,

Xiaogang Wang,

Hongwei Qin,

Hongsheng Li; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhang_2022_CVPR, author = {Zhang, Yi and Li, Dasong and Law, Ka Lung and Wang, Xiaogang and Qin, Hongwei and Li, Hongsheng}, title = {IDR: Self-Supervised Image Denoising via Iterative Data Refinement}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {2098-2107} }
MogFace: Towards a Deeper Appreciation on Face Detection: Yang Liu,

Fei Wang,

Jiankang Deng,

Zhipeng Zhou,

Baigui Sun,

Hao Li; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Liu_2022_CVPR, author = {Liu, Yang and Wang, Fei and Deng, Jiankang and Zhou, Zhipeng and Sun, Baigui and Li, Hao}, title = {MogFace: Towards a Deeper Appreciation on Face Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {4093-4102} }
Multi-Label Iterated Learning for Image Classification With Label Ambiguity: Sai Rajeswar,

Pau Rodríguez,

Soumye Singhal,

David Vazquez,

Aaron Courville; [pdf] [supp]
[bibtex]
@InProceedings{Rajeswar_2022_CVPR, author = {Rajeswar, Sai and Rodr{\'\i}guez, Pau and Singhal, Soumye and Vazquez, David and Courville, Aaron}, title = {Multi-Label Iterated Learning for Image Classification With Label Ambiguity}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {4783-4793} }
Pushing the Envelope of Gradient Boosting Forests via Globally-Optimized Oblique Trees: Magzhan Gabidolla,

Miguel Á. Carreira-Perpiñán; [pdf] [supp]
[bibtex]
@InProceedings{Gabidolla_2022_CVPR, author = {Gabidolla, Magzhan and Carreira-Perpi\~n\'an, Miguel \'A.}, title = {Pushing the Envelope of Gradient Boosting Forests via Globally-Optimized Oblique Trees}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {285-294} }
Deformable Sprites for Unsupervised Video Decomposition: Vickie Ye,

Zhengqi Li,

Richard Tucker,

Angjoo Kanazawa,

Noah Snavely; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ye_2022_CVPR, author = {Ye, Vickie and Li, Zhengqi and Tucker, Richard and Kanazawa, Angjoo and Snavely, Noah}, title = {Deformable Sprites for Unsupervised Video Decomposition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {2657-2666} }
Learning To Detect Mobile Objects From LiDAR Scans Without Labels: Yurong You,

Katie Luo,

Cheng Perng Phoo,

Wei-Lun Chao,

Wen Sun,

Bharath Hariharan,

Mark Campbell,

Kilian Q. Weinberger; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{You_2022_CVPR, author = {You, Yurong and Luo, Katie and Phoo, Cheng Perng and Chao, Wei-Lun and Sun, Wen and Hariharan, Bharath and Campbell, Mark and Weinberger, Kilian Q.}, title = {Learning To Detect Mobile Objects From LiDAR Scans Without Labels}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {1130-1140} }
Time3D: End-to-End Joint Monocular 3D Object Detection and Tracking for Autonomous Driving: Peixuan Li,

Jieyu Jin; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Li_2022_CVPR, author = {Li, Peixuan and Jin, Jieyu}, title = {Time3D: End-to-End Joint Monocular 3D Object Detection and Tracking for Autonomous Driving}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {3885-3894} }
MonoJSG: Joint Semantic and Geometric Cost Volume for Monocular 3D Object Detection: Qing Lian,

Peiliang Li,

Xiaozhi Chen; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Lian_2022_CVPR, author = {Lian, Qing and Li, Peiliang and Chen, Xiaozhi}, title = {MonoJSG: Joint Semantic and Geometric Cost Volume for Monocular 3D Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {1070-1079} }
Efficient Classification of Very Large Images With Tiny Objects: Fanjie Kong,

Ricardo Henao; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kong_2022_CVPR, author = {Kong, Fanjie and Henao, Ricardo}, title = {Efficient Classification of Very Large Images With Tiny Objects}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {2384-2394} }
SWEM: Towards Real-Time Video Object Segmentation With Sequential Weighted Expectation-Maximization: Zhihui Lin,

Tianyu Yang,

Maomao Li,

Ziyu Wang,

Chun Yuan,

Wenhao Jiang,

Wei Liu; [pdf] [supp]
[bibtex]
@InProceedings{Lin_2022_CVPR, author = {Lin, Zhihui and Yang, Tianyu and Li, Maomao and Wang, Ziyu and Yuan, Chun and Jiang, Wenhao and Liu, Wei}, title = {SWEM: Towards Real-Time Video Object Segmentation With Sequential Weighted Expectation-Maximization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {1362-1372} }
Generating Diverse 3D Reconstructions From a Single Occluded Face Image: Rahul Dey,

Vishnu Naresh Boddeti; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Dey_2022_CVPR, author = {Dey, Rahul and Boddeti, Vishnu Naresh}, title = {Generating Diverse 3D Reconstructions From a Single Occluded Face Image}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {1547-1557} }
RBGNet: Ray-Based Grouping for 3D Object Detection: Haiyang Wang,

Shaoshuai Shi,

Ze Yang,

Rongyao Fang,

Qi Qian,

Hongsheng Li,

Bernt Schiele,

Liwei Wang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2022_CVPR, author = {Wang, Haiyang and Shi, Shaoshuai and Yang, Ze and Fang, Rongyao and Qian, Qi and Li, Hongsheng and Schiele, Bernt and Wang, Liwei}, title = {RBGNet: Ray-Based Grouping for 3D Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {1110-1119} }
Stand-Alone Inter-Frame Attention in Video Models: Fuchen Long,

Zhaofan Qiu,

Yingwei Pan,

Ting Yao,

Jiebo Luo,

Tao Mei; [pdf]
[bibtex]
@InProceedings{Long_2022_CVPR, author = {Long, Fuchen and Qiu, Zhaofan and Pan, Yingwei and Yao, Ting and Luo, Jiebo and Mei, Tao}, title = {Stand-Alone Inter-Frame Attention in Video Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {3192-3201} }
Memory-Augmented Deep Conditional Unfolding Network for Pan-Sharpening: Gang Yang,

Man Zhou,

Keyu Yan,

Aiping Liu,

Xueyang Fu,

Fan Wang; [pdf]
[bibtex]
@InProceedings{Yang_2022_CVPR, author = {Yang, Gang and Zhou, Man and Yan, Keyu and Liu, Aiping and Fu, Xueyang and Wang, Fan}, title = {Memory-Augmented Deep Conditional Unfolding Network for Pan-Sharpening}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {1788-1797} }
Large-Scale Pre-Training for Person Re-Identification With Noisy Labels: Dengpan Fu,

Dongdong Chen,

Hao Yang,

Jianmin Bao,

Lu Yuan,

Lei Zhang,

Houqiang Li,

Fang Wen,

Dong Chen; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Fu_2022_CVPR, author = {Fu, Dengpan and Chen, Dongdong and Yang, Hao and Bao, Jianmin and Yuan, Lu and Zhang, Lei and Li, Houqiang and Wen, Fang and Chen, Dong}, title = {Large-Scale Pre-Training for Person Re-Identification With Noisy Labels}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {2476-2486} }
Feature Erasing and Diffusion Network for Occluded Person Re-Identification: Zhikang Wang,

Feng Zhu,

Shixiang Tang,

Rui Zhao,

Lihuo He,

Jiangning Song; [pdf] [arXiv]
[bibtex]
@InProceedings{Wang_2022_CVPR, author = {Wang, Zhikang and Zhu, Feng and Tang, Shixiang and Zhao, Rui and He, Lihuo and Song, Jiangning}, title = {Feature Erasing and Diffusion Network for Occluded Person Re-Identification}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {4754-4763} }
Semantic Segmentation by Early Region Proxy: Yifan Zhang,

Bo Pang,

Cewu Lu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhang_2022_CVPR, author = {Zhang, Yifan and Pang, Bo and Lu, Cewu}, title = {Semantic Segmentation by Early Region Proxy}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {1258-1268} }
GIQE: Generic Image Quality Enhancement via Nth Order Iterative Degradation: Pranjay Shyam,

Kyung-Soo Kim,

Kuk-Jin Yoon; [pdf] [supp]
[bibtex]
@InProceedings{Shyam_2022_CVPR, author = {Shyam, Pranjay and Kim, Kyung-Soo and Yoon, Kuk-Jin}, title = {GIQE: Generic Image Quality Enhancement via Nth Order Iterative Degradation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {2077-2087} }
Instance Segmentation With Mask-Supervised Polygonal Boundary Transformers: Justin Lazarow,

Weijian Xu,

Zhuowen Tu; [pdf]
[bibtex]
@InProceedings{Lazarow_2022_CVPR, author = {Lazarow, Justin and Xu, Weijian and Tu, Zhuowen}, title = {Instance Segmentation With Mask-Supervised Polygonal Boundary Transformers}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {4382-4391} }
Single-Stage 3D Geometry-Preserving Depth Estimation Model Training on Dataset Mixtures With Uncalibrated Stereo Data: Nikolay Patakin,

Anna Vorontsova,

Mikhail Artemyev,

Anton Konushin; [pdf] [supp]
[bibtex]
@InProceedings{Patakin_2022_CVPR, author = {Patakin, Nikolay and Vorontsova, Anna and Artemyev, Mikhail and Konushin, Anton}, title = {Single-Stage 3D Geometry-Preserving Depth Estimation Model Training on Dataset Mixtures With Uncalibrated Stereo Data}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {1705-1714} }
LD-ConGR: A Large RGB-D Video Dataset for Long-Distance Continuous Gesture Recognition: Dan Liu,

Libo Zhang,

Yanjun Wu; [pdf] [supp]
[bibtex]
@InProceedings{Liu_2022_CVPR, author = {Liu, Dan and Zhang, Libo and Wu, Yanjun}, title = {LD-ConGR: A Large RGB-D Video Dataset for Long-Distance Continuous Gesture Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {3304-3312} }
SimVQA: Exploring Simulated Environments for Visual Question Answering: Paola Cascante-Bonilla,

Hui Wu,

Letao Wang,

Rogerio S. Feris,

Vicente Ordonez; [pdf] [supp]
[bibtex]
@InProceedings{Cascante-Bonilla_2022_CVPR, author = {Cascante-Bonilla, Paola and Wu, Hui and Wang, Letao and Feris, Rogerio S. and Ordonez, Vicente}, title = {SimVQA: Exploring Simulated Environments for Visual Question Answering}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {5056-5066} }
Thin-Plate Spline Motion Model for Image Animation: Jian Zhao,

Hui Zhang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhao_2022_CVPR, author = {Zhao, Jian and Zhang, Hui}, title = {Thin-Plate Spline Motion Model for Image Animation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {3657-3666} }
Learning Local Displacements for Point Cloud Completion: Yida Wang,

David Joseph Tan,

Nassir Navab,

Federico Tombari; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2022_CVPR, author = {Wang, Yida and Tan, David Joseph and Navab, Nassir and Tombari, Federico}, title = {Learning Local Displacements for Point Cloud Completion}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {1568-1577} }
Human Hands As Probes for Interactive Object Understanding: Mohit Goyal,

Sahil Modi,

Rishabh Goyal,

Saurabh Gupta; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Goyal_2022_CVPR, author = {Goyal, Mohit and Modi, Sahil and Goyal, Rishabh and Gupta, Saurabh}, title = {Human Hands As Probes for Interactive Object Understanding}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {3293-3303} }
Understanding and Increasing Efficiency of Frank-Wolfe Adversarial Training: Theodoros Tsiligkaridis,

Jay Roberts; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Tsiligkaridis_2022_CVPR, author = {Tsiligkaridis, Theodoros and Roberts, Jay}, title = {Understanding and Increasing Efficiency of Frank-Wolfe Adversarial Training}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {50-59} }
RADU: Ray-Aligned Depth Update Convolutions for ToF Data Denoising: Michael Schelling,

Pedro Hermosilla,

Timo Ropinski; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Schelling_2022_CVPR, author = {Schelling, Michael and Hermosilla, Pedro and Ropinski, Timo}, title = {RADU: Ray-Aligned Depth Update Convolutions for ToF Data Denoising}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {671-680} }
Rethinking Visual Geo-Localization for Large-Scale Applications: Gabriele Berton,

Carlo Masone,

Barbara Caputo; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Berton_2022_CVPR, author = {Berton, Gabriele and Masone, Carlo and Caputo, Barbara}, title = {Rethinking Visual Geo-Localization for Large-Scale Applications}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {4878-4888} }
ViM: Out-of-Distribution With Virtual-Logit Matching: Haoqi Wang,

Zhizhong Li,

Litong Feng,

Wayne Zhang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2022_CVPR, author = {Wang, Haoqi and Li, Zhizhong and Feng, Litong and Zhang, Wayne}, title = {ViM: Out-of-Distribution With Virtual-Logit Matching}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {4921-4930} }
Towards Accurate Facial Landmark Detection via Cascaded Transformers: Hui Li,

Zidong Guo,

Seon-Min Rhee,

Seungju Han,

Jae-Joon Han; [pdf] [supp]
[bibtex]
@InProceedings{Li_2022_CVPR, author = {Li, Hui and Guo, Zidong and Rhee, Seon-Min and Han, Seungju and Han, Jae-Joon}, title = {Towards Accurate Facial Landmark Detection via Cascaded Transformers}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {4176-4185} }
Long-Term Visual Map Sparsification With Heterogeneous GNN: Ming-Fang Chang,

Yipu Zhao,

Rajvi Shah,

Jakob J. Engel,

Michael Kaess,

Simon Lucey; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chang_2022_CVPR, author = {Chang, Ming-Fang and Zhao, Yipu and Shah, Rajvi and Engel, Jakob J. and Kaess, Michael and Lucey, Simon}, title = {Long-Term Visual Map Sparsification With Heterogeneous GNN}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {2406-2415} }
Dual-AI: Dual-Path Actor Interaction Learning for Group Activity Recognition: Mingfei Han,

David Junhao Zhang,

Yali Wang,

Rui Yan,

Lina Yao,

Xiaojun Chang,

Yu Qiao; [pdf] [supp]
[bibtex]
@InProceedings{Han_2022_CVPR, author = {Han, Mingfei and Zhang, David Junhao and Wang, Yali and Yan, Rui and Yao, Lina and Chang, Xiaojun and Qiao, Yu}, title = {Dual-AI: Dual-Path Actor Interaction Learning for Group Activity Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {2990-2999} }
A Brand New Dance Partner: Music-Conditioned Pluralistic Dancing Controlled by Multiple Dance Genres: Jinwoo Kim,

Heeseok Oh,

Seongjean Kim,

Hoseok Tong,

Sanghoon Lee; [pdf] [supp]
[bibtex]
@InProceedings{Kim_2022_CVPR, author = {Kim, Jinwoo and Oh, Heeseok and Kim, Seongjean and Tong, Hoseok and Lee, Sanghoon}, title = {A Brand New Dance Partner: Music-Conditioned Pluralistic Dancing Controlled by Multiple Dance Genres}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {3490-3500} }
Adaptive Early-Learning Correction for Segmentation From Noisy Annotations: Sheng Liu,

Kangning Liu,

Weicheng Zhu,

Yiqiu Shen,

Carlos Fernandez-Granda; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Liu_2022_CVPR, author = {Liu, Sheng and Liu, Kangning and Zhu, Weicheng and Shen, Yiqiu and Fernandez-Granda, Carlos}, title = {Adaptive Early-Learning Correction for Segmentation From Noisy Annotations}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {2606-2616} }
Multi-Scale Memory-Based Video Deblurring: Bo Ji,

Angela Yao; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ji_2022_CVPR, author = {Ji, Bo and Yao, Angela}, title = {Multi-Scale Memory-Based Video Deblurring}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {1919-1928} }
A Scalable Combinatorial Solver for Elastic Geometrically Consistent 3D Shape Matching: Paul Roetzer,

Paul Swoboda,

Daniel Cremers,

Florian Bernard; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Roetzer_2022_CVPR, author = {Roetzer, Paul and Swoboda, Paul and Cremers, Daniel and Bernard, Florian}, title = {A Scalable Combinatorial Solver for Elastic Geometrically Consistent 3D Shape Matching}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {428-438} }
Geometric Structure Preserving Warp for Natural Image Stitching: Peng Du,

Jifeng Ning,

Jiguang Cui,

Shaoli Huang,

Xinchao Wang,

Jiaxin Wang; [pdf] [supp]
[bibtex]
@InProceedings{Du_2022_CVPR, author = {Du, Peng and Ning, Jifeng and Cui, Jiguang and Huang, Shaoli and Wang, Xinchao and Wang, Jiaxin}, title = {Geometric Structure Preserving Warp for Natural Image Stitching}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {3688-3696} }
Focal Length and Object Pose Estimation via Render and Compare: Georgy Ponimatkin,

Yann Labbé,

Bryan Russell,

Mathieu Aubry,

Josef Sivic; [pdf] [supp]
[bibtex]
@InProceedings{Ponimatkin_2022_CVPR, author = {Ponimatkin, Georgy and Labb\'e, Yann and Russell, Bryan and Aubry, Mathieu and Sivic, Josef}, title = {Focal Length and Object Pose Estimation via Render and Compare}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {3825-3834} }
Dynamic 3D Gaze From Afar: Deep Gaze Estimation From Temporal Eye-Head-Body Coordination: Soma Nonaka,

Shohei Nobuhara,

Ko Nishino; [pdf] [supp]
[bibtex]
@InProceedings{Nonaka_2022_CVPR, author = {Nonaka, Soma and Nobuhara, Shohei and Nishino, Ko}, title = {Dynamic 3D Gaze From Afar: Deep Gaze Estimation From Temporal Eye-Head-Body Coordination}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {2192-2201} }
Expressive Talking Head Generation With Granular Audio-Visual Control: Borong Liang,

Yan Pan,

Zhizhi Guo,

Hang Zhou,

Zhibin Hong,

Xiaoguang Han,

Junyu Han,

Jingtuo Liu,

Errui Ding,

Jingdong Wang; [pdf] [supp]
[bibtex]
@InProceedings{Liang_2022_CVPR, author = {Liang, Borong and Pan, Yan and Guo, Zhizhi and Zhou, Hang and Hong, Zhibin and Han, Xiaoguang and Han, Junyu and Liu, Jingtuo and Ding, Errui and Wang, Jingdong}, title = {Expressive Talking Head Generation With Granular Audio-Visual Control}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {3387-3396} }
HairMapper: Removing Hair From Portraits Using GANs: Yiqian Wu,

Yong-Liang Yang,

Xiaogang Jin; [pdf] [supp]
[bibtex]
@InProceedings{Wu_2022_CVPR, author = {Wu, Yiqian and Yang, Yong-Liang and Jin, Xiaogang}, title = {HairMapper: Removing Hair From Portraits Using GANs}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {4227-4236} }
Out-of-Distribution Generalization With Causal Invariant Transformations: Ruoyu Wang,

Mingyang Yi,

Zhitang Chen,

Shengyu Zhu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2022_CVPR, author = {Wang, Ruoyu and Yi, Mingyang and Chen, Zhitang and Zhu, Shengyu}, title = {Out-of-Distribution Generalization With Causal Invariant Transformations}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {375-385} }
Learning Motion-Dependent Appearance for High-Fidelity Rendering of Dynamic Humans From a Single Camera: Jae Shin Yoon,

Duygu Ceylan,

Tuanfeng Y. Wang,

Jingwan Lu,

Jimei Yang,

Zhixin Shu,

Hyun Soo Park; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yoon_2022_CVPR, author = {Yoon, Jae Shin and Ceylan, Duygu and Wang, Tuanfeng Y. and Lu, Jingwan and Yang, Jimei and Shu, Zhixin and Park, Hyun Soo}, title = {Learning Motion-Dependent Appearance for High-Fidelity Rendering of Dynamic Humans From a Single Camera}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {3407-3417} }
Perturbed and Strict Mean Teachers for Semi-Supervised Semantic Segmentation: Yuyuan Liu,

Yu Tian,

Yuanhong Chen,

Fengbei Liu,

Vasileios Belagiannis,

Gustavo Carneiro; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Liu_2022_CVPR, author = {Liu, Yuyuan and Tian, Yu and Chen, Yuanhong and Liu, Fengbei and Belagiannis, Vasileios and Carneiro, Gustavo}, title = {Perturbed and Strict Mean Teachers for Semi-Supervised Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {4258-4267} }
IFRNet: Intermediate Feature Refine Network for Efficient Frame Interpolation: Lingtong Kong,

Boyuan Jiang,

Donghao Luo,

Wenqing Chu,

Xiaoming Huang,

Ying Tai,

Chengjie Wang,

Jie Yang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kong_2022_CVPR, author = {Kong, Lingtong and Jiang, Boyuan and Luo, Donghao and Chu, Wenqing and Huang, Xiaoming and Tai, Ying and Wang, Chengjie and Yang, Jie}, title = {IFRNet: Intermediate Feature Refine Network for Efficient Frame Interpolation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {1969-1978} }
Toward Practical Monocular Indoor Depth Estimation: Cho-Ying Wu,

Jialiang Wang,

Michael Hall,

Ulrich Neumann,

Shuochen Su; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wu_2022_CVPR, author = {Wu, Cho-Ying and Wang, Jialiang and Hall, Michael and Neumann, Ulrich and Su, Shuochen}, title = {Toward Practical Monocular Indoor Depth Estimation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {3814-3824} }
Speed Up Object Detection on Gigapixel-Level Images With Patch Arrangement: Jiahao Fan,

Huabin Liu,

Wenjie Yang,

John See,

Aixin Zhang,

Weiyao Lin; [pdf]
[bibtex]
@InProceedings{Fan_2022_CVPR, author = {Fan, Jiahao and Liu, Huabin and Yang, Wenjie and See, John and Zhang, Aixin and Lin, Weiyao}, title = {Speed Up Object Detection on Gigapixel-Level Images With Patch Arrangement}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {4653-4661} }
Neural Recognition of Dashed Curves With Gestalt Law of Continuity: Hanyuan Liu,

Chengze Li,

Xueting Liu,

Tien-Tsin Wong; [pdf] [supp]
[bibtex]
@InProceedings{Liu_2022_CVPR, author = {Liu, Hanyuan and Li, Chengze and Liu, Xueting and Wong, Tien-Tsin}, title = {Neural Recognition of Dashed Curves With Gestalt Law of Continuity}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {1373-1382} }
HODOR: High-Level Object Descriptors for Object Re-Segmentation in Video Learned From Static Images: Ali Athar,

Jonathon Luiten,

Alexander Hermans,

Deva Ramanan,

Bastian Leibe; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Athar_2022_CVPR, author = {Athar, Ali and Luiten, Jonathon and Hermans, Alexander and Ramanan, Deva and Leibe, Bastian}, title = {HODOR: High-Level Object Descriptors for Object Re-Segmentation in Video Learned From Static Images}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {3022-3031} }
MLSLT: Towards Multilingual Sign Language Translation: Aoxiong Yin,

Zhou Zhao,

Weike Jin,

Meng Zhang,

Xingshan Zeng,

Xiaofei He; [pdf] [supp]
[bibtex]
@InProceedings{Yin_2022_CVPR, author = {Yin, Aoxiong and Zhao, Zhou and Jin, Weike and Zhang, Meng and Zeng, Xingshan and He, Xiaofei}, title = {MLSLT: Towards Multilingual Sign Language Translation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {5109-5119} }
Contrastive Test-Time Adaptation: Dian Chen,

Dequan Wang,

Trevor Darrell,

Sayna Ebrahimi; [pdf] [arXiv]
[bibtex]
@InProceedings{Chen_2022_CVPR, author = {Chen, Dian and Wang, Dequan and Darrell, Trevor and Ebrahimi, Sayna}, title = {Contrastive Test-Time Adaptation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {295-305} }
Collaborative Learning for Hand and Object Reconstruction With Attention-Guided Graph Convolution: Tze Ho Elden Tse,

Kwang In Kim,

Ales̆ Leonardis,

Hyung Jin Chang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Tse_2022_CVPR, author = {Tse, Tze Ho Elden and Kim, Kwang In and Leonardis, Ales̆ and Chang, Hyung Jin}, title = {Collaborative Learning for Hand and Object Reconstruction With Attention-Guided Graph Convolution}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {1664-1674} }
Regional Semantic Contrast and Aggregation for Weakly Supervised Semantic Segmentation: Tianfei Zhou,

Meijie Zhang,

Fang Zhao,

Jianwu Li; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhou_2022_CVPR, author = {Zhou, Tianfei and Zhang, Meijie and Zhao, Fang and Li, Jianwu}, title = {Regional Semantic Contrast and Aggregation for Weakly Supervised Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {4299-4309} }
Class Re-Activation Maps for Weakly-Supervised Semantic Segmentation: Zhaozheng Chen,

Tan Wang,

Xiongwei Wu,

Xian-Sheng Hua,

Hanwang Zhang,

Qianru Sun; [pdf] [arXiv]
[bibtex]
@InProceedings{Chen_2022_CVPR, author = {Chen, Zhaozheng and Wang, Tan and Wu, Xiongwei and Hua, Xian-Sheng and Zhang, Hanwang and Sun, Qianru}, title = {Class Re-Activation Maps for Weakly-Supervised Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {969-978} }
TransWeather: Transformer-Based Restoration of Images Degraded by Adverse Weather Conditions: Jeya Maria Jose Valanarasu,

Rajeev Yasarla,

Vishal M. Patel; [pdf] [arXiv]
[bibtex]
@InProceedings{Valanarasu_2022_CVPR, author = {Valanarasu, Jeya Maria Jose and Yasarla, Rajeev and Patel, Vishal M.}, title = {TransWeather: Transformer-Based Restoration of Images Degraded by Adverse Weather Conditions}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {2353-2363} }
P3Depth: Monocular Depth Estimation With a Piecewise Planarity Prior: Vaishakh Patil,

Christos Sakaridis,

Alexander Liniger,

Luc Van Gool; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Patil_2022_CVPR, author = {Patil, Vaishakh and Sakaridis, Christos and Liniger, Alexander and Van Gool, Luc}, title = {P3Depth: Monocular Depth Estimation With a Piecewise Planarity Prior}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {1610-1621} }
MLP-3D: A MLP-Like 3D Architecture With Grouped Time Mixing: Zhaofan Qiu,

Ting Yao,

Chong-Wah Ngo,

Tao Mei; [pdf]
[bibtex]
@InProceedings{Qiu_2022_CVPR, author = {Qiu, Zhaofan and Yao, Ting and Ngo, Chong-Wah and Mei, Tao}, title = {MLP-3D: A MLP-Like 3D Architecture With Grouped Time Mixing}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {3062-3072} }
BANMo: Building Animatable 3D Neural Models From Many Casual Videos: Gengshan Yang,

Minh Vo,

Natalia Neverova,

Deva Ramanan,

Andrea Vedaldi,

Hanbyul Joo; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yang_2022_CVPR, author = {Yang, Gengshan and Vo, Minh and Neverova, Natalia and Ramanan, Deva and Vedaldi, Andrea and Joo, Hanbyul}, title = {BANMo: Building Animatable 3D Neural Models From Many Casual Videos}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {2863-2873} }
Language As Queries for Referring Video Object Segmentation: Jiannan Wu,

Yi Jiang,

Peize Sun,

Zehuan Yuan,

Ping Luo; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wu_2022_CVPR, author = {Wu, Jiannan and Jiang, Yi and Sun, Peize and Yuan, Zehuan and Luo, Ping}, title = {Language As Queries for Referring Video Object Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {4974-4984} }
Investigating the Impact of Multi-LiDAR Placement on Object Detection for Autonomous Driving: Hanjiang Hu,

Zuxin Liu,

Sharad Chitlangia,

Akhil Agnihotri,

Ding Zhao; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Hu_2022_CVPR, author = {Hu, Hanjiang and Liu, Zuxin and Chitlangia, Sharad and Agnihotri, Akhil and Zhao, Ding}, title = {Investigating the Impact of Multi-LiDAR Placement on Object Detection for Autonomous Driving}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {2550-2559} }
MViTv2: Improved Multiscale Vision Transformers for Classification and Detection: Yanghao Li,

Chao-Yuan Wu,

Haoqi Fan,

Karttikeya Mangalam,

Bo Xiong,

Jitendra Malik,

Christoph Feichtenhofer; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Li_2022_CVPR, author = {Li, Yanghao and Wu, Chao-Yuan and Fan, Haoqi and Mangalam, Karttikeya and Xiong, Bo and Malik, Jitendra and Feichtenhofer, Christoph}, title = {MViTv2: Improved Multiscale Vision Transformers for Classification and Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {4804-4814} }
Self-Supervised Arbitrary-Scale Point Clouds Upsampling via Implicit Neural Representation: Wenbo Zhao,

Xianming Liu,

Zhiwei Zhong,

Junjun Jiang,

Wei Gao,

Ge Li,

Xiangyang Ji; [pdf] [arXiv]
[bibtex]
@InProceedings{Zhao_2022_CVPR, author = {Zhao, Wenbo and Liu, Xianming and Zhong, Zhiwei and Jiang, Junjun and Gao, Wei and Li, Ge and Ji, Xiangyang}, title = {Self-Supervised Arbitrary-Scale Point Clouds Upsampling via Implicit Neural Representation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {1999-2007} }
AIM: An Auto-Augmenter for Images and Meshes: Vinit Veerendraveer Singh,

Chandra Kambhamettu; [pdf]
[bibtex]
@InProceedings{Singh_2022_CVPR, author = {Singh, Vinit Veerendraveer and Kambhamettu, Chandra}, title = {AIM: An Auto-Augmenter for Images and Meshes}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {722-731} }
VISOLO: Grid-Based Space-Time Aggregation for Efficient Online Video Instance Segmentation: Su Ho Han,

Sukjun Hwang,

Seoung Wug Oh,

Yeonchool Park,

Hyunwoo Kim,

Min-Jung Kim,

Seon Joo Kim; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Han_2022_CVPR, author = {Han, Su Ho and Hwang, Sukjun and Oh, Seoung Wug and Park, Yeonchool and Kim, Hyunwoo and Kim, Min-Jung and Kim, Seon Joo}, title = {VISOLO: Grid-Based Space-Time Aggregation for Efficient Online Video Instance Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {2896-2905} }
Incremental Learning in Semantic Segmentation From Image Labels: Fabio Cermelli,

Dario Fontanel,

Antonio Tavera,

Marco Ciccone,

Barbara Caputo; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Cermelli_2022_CVPR, author = {Cermelli, Fabio and Fontanel, Dario and Tavera, Antonio and Ciccone, Marco and Caputo, Barbara}, title = {Incremental Learning in Semantic Segmentation From Image Labels}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {4371-4381} }
Playable Environments: Video Manipulation in Space and Time: Willi Menapace,

Stéphane Lathuilière,

Aliaksandr Siarohin,

Christian Theobalt,

Sergey Tulyakov,

Vladislav Golyanik,

Elisa Ricci; [pdf] [supp]
[bibtex]
@InProceedings{Menapace_2022_CVPR, author = {Menapace, Willi and Lathuili\`ere, St\'ephane and Siarohin, Aliaksandr and Theobalt, Christian and Tulyakov, Sergey and Golyanik, Vladislav and Ricci, Elisa}, title = {Playable Environments: Video Manipulation in Space and Time}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {3584-3593} }
CO-SNE: Dimensionality Reduction and Visualization for Hyperbolic Data: Yunhui Guo,

Haoran Guo,

Stella X. Yu; [pdf] [supp]
[bibtex]
@InProceedings{Guo_2022_CVPR, author = {Guo, Yunhui and Guo, Haoran and Yu, Stella X.}, title = {CO-SNE: Dimensionality Reduction and Visualization for Hyperbolic Data}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {21-30} }
Revisiting Skeleton-Based Action Recognition: Haodong Duan,

Yue Zhao,

Kai Chen,

Dahua Lin,

Bo Dai; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Duan_2022_CVPR, author = {Duan, Haodong and Zhao, Yue and Chen, Kai and Lin, Dahua and Dai, Bo}, title = {Revisiting Skeleton-Based Action Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {2969-2978} }
LOLNerf: Learn From One Look: Daniel Rebain,

Mark Matthews,

Kwang Moo Yi,

Dmitry Lagun,

Andrea Tagliasacchi; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Rebain_2022_CVPR, author = {Rebain, Daniel and Matthews, Mark and Yi, Kwang Moo and Lagun, Dmitry and Tagliasacchi, Andrea}, title = {LOLNerf: Learn From One Look}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {1558-1567} }
Geometry-Aware Guided Loss for Deep Crack Recognition: Zhuangzhuang Chen,

Jin Zhang,

Zhuonan Lai,

Jie Chen,

Zun Liu,

Jianqiang Li; [pdf]
[bibtex]
@InProceedings{Chen_2022_CVPR, author = {Chen, Zhuangzhuang and Zhang, Jin and Lai, Zhuonan and Chen, Jie and Liu, Zun and Li, Jianqiang}, title = {Geometry-Aware Guided Loss for Deep Crack Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {4703-4712} }
Maintaining Reasoning Consistency in Compositional Visual Question Answering: Chenchen Jing,

Yunde Jia,

Yuwei Wu,

Xinyu Liu,

Qi Wu; [pdf] [supp]
[bibtex]
@InProceedings{Jing_2022_CVPR, author = {Jing, Chenchen and Jia, Yunde and Wu, Yuwei and Liu, Xinyu and Wu, Qi}, title = {Maintaining Reasoning Consistency in Compositional Visual Question Answering}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {5099-5108} }
Structure-Aware Motion Transfer With Deformable Anchor Model: Jiale Tao,

Biao Wang,

Borun Xu,

Tiezheng Ge,

Yuning Jiang,

Wen Li,

Lixin Duan; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Tao_2022_CVPR, author = {Tao, Jiale and Wang, Biao and Xu, Borun and Ge, Tiezheng and Jiang, Yuning and Li, Wen and Duan, Lixin}, title = {Structure-Aware Motion Transfer With Deformable Anchor Model}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {3637-3646} }
Pix2NeRF: Unsupervised Conditional p-GAN for Single Image to Neural Radiance Fields Translation: Shengqu Cai,

Anton Obukhov,

Dengxin Dai,

Luc Van Gool; [pdf] [supp]
[bibtex]
@InProceedings{Cai_2022_CVPR, author = {Cai, Shengqu and Obukhov, Anton and Dai, Dengxin and Van Gool, Luc}, title = {Pix2NeRF: Unsupervised Conditional p-GAN for Single Image to Neural Radiance Fields Translation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {3981-3990} }
Rethinking Image Cropping: Exploring Diverse Compositions From Global Views: Gengyun Jia,

Huaibo Huang,

Chaoyou Fu,

Ran He; [pdf] [supp]
[bibtex]
@InProceedings{Jia_2022_CVPR, author = {Jia, Gengyun and Huang, Huaibo and Fu, Chaoyou and He, Ran}, title = {Rethinking Image Cropping: Exploring Diverse Compositions From Global Views}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {2446-2455} }
Threshold Matters in WSSS: Manipulating the Activation for the Robust and Accurate Segmentation Model Against Thresholds: Minhyun Lee,

Dongseob Kim,

Hyunjung Shim; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Lee_2022_CVPR, author = {Lee, Minhyun and Kim, Dongseob and Shim, Hyunjung}, title = {Threshold Matters in WSSS: Manipulating the Activation for the Robust and Accurate Segmentation Model Against Thresholds}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {4330-4339} }
Data-Free Network Compression via Parametric Non-Uniform Mixed Precision Quantization: Vladimir Chikin,

Mikhail Antiukh; [pdf] [supp]
[bibtex]
@InProceedings{Chikin_2022_CVPR, author = {Chikin, Vladimir and Antiukh, Mikhail}, title = {Data-Free Network Compression via Parametric Non-Uniform Mixed Precision Quantization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {450-459} }
ROCA: Robust CAD Model Retrieval and Alignment From a Single Image: Can Gümeli,

Angela Dai,

Matthias Nießner; [pdf] [supp]
[bibtex]
@InProceedings{Gumeli_2022_CVPR, author = {G\"umeli, Can and Dai, Angela and Nie{\ss}ner, Matthias}, title = {ROCA: Robust CAD Model Retrieval and Alignment From a Single Image}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {4022-4031} }
Wnet: Audio-Guided Video Object Segmentation via Wavelet-Based Cross-Modal Denoising Networks: Wenwen Pan,

Haonan Shi,

Zhou Zhao,

Jieming Zhu,

Xiuqiang He,

Zhigeng Pan,

Lianli Gao,

Jun Yu,

Fei Wu,

Qi Tian; [pdf] [supp]
[bibtex]
@InProceedings{Pan_2022_CVPR, author = {Pan, Wenwen and Shi, Haonan and Zhao, Zhou and Zhu, Jieming and He, Xiuqiang and Pan, Zhigeng and Gao, Lianli and Yu, Jun and Wu, Fei and Tian, Qi}, title = {Wnet: Audio-Guided Video Object Segmentation via Wavelet-Based Cross-Modal Denoising Networks}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {1320-1331} }
PubTables-1M: Towards Comprehensive Table Extraction From Unstructured Documents: Brandon Smock,

Rohith Pesala,

Robin Abraham; [pdf]
[bibtex]
@InProceedings{Smock_2022_CVPR, author = {Smock, Brandon and Pesala, Rohith and Abraham, Robin}, title = {PubTables-1M: Towards Comprehensive Table Extraction From Unstructured Documents}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {4634-4642} }
Meta-Attention for ViT-Backed Continual Learning: Mengqi Xue,

Haofei Zhang,

Jie Song,

Mingli Song; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Xue_2022_CVPR, author = {Xue, Mengqi and Zhang, Haofei and Song, Jie and Song, Mingli}, title = {Meta-Attention for ViT-Backed Continual Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {150-159} }
Photorealistic Monocular 3D Reconstruction of Humans Wearing Clothing: Thiemo Alldieck,

Mihai Zanfir,

Cristian Sminchisescu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Alldieck_2022_CVPR, author = {Alldieck, Thiemo and Zanfir, Mihai and Sminchisescu, Cristian}, title = {Photorealistic Monocular 3D Reconstruction of Humans Wearing Clothing}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {1506-1515} }
Generalizing Interactive Backpropagating Refinement for Dense Prediction Networks: Fanqing Lin,

Brian Price,

Tony Martinez; [pdf] [supp]
[bibtex]
@InProceedings{Lin_2022_CVPR, author = {Lin, Fanqing and Price, Brian and Martinez, Tony}, title = {Generalizing Interactive Backpropagating Refinement for Dense Prediction Networks}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {773-782} }
Look Outside the Room: Synthesizing a Consistent Long-Term 3D Scene Video From a Single Image: Xuanchi Ren,

Xiaolong Wang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ren_2022_CVPR, author = {Ren, Xuanchi and Wang, Xiaolong}, title = {Look Outside the Room: Synthesizing a Consistent Long-Term 3D Scene Video From a Single Image}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {3563-3573} }
Full-Range Virtual Try-On With Recurrent Tri-Level Transform: Han Yang,

Xinrui Yu,

Ziwei Liu; [pdf] [supp]
[bibtex]
@InProceedings{Yang_2022_CVPR, author = {Yang, Han and Yu, Xinrui and Liu, Ziwei}, title = {Full-Range Virtual Try-On With Recurrent Tri-Level Transform}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {3460-3469} }
Multiview Transformers for Video Recognition: Shen Yan,

Xuehan Xiong,

Anurag Arnab,

Zhichao Lu,

Mi Zhang,

Chen Sun,

Cordelia Schmid; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yan_2022_CVPR, author = {Yan, Shen and Xiong, Xuehan and Arnab, Anurag and Lu, Zhichao and Zhang, Mi and Sun, Chen and Schmid, Cordelia}, title = {Multiview Transformers for Video Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {3333-3343} }
Learning Structured Gaussians To Approximate Deep Ensembles: Ivor J. A. Simpson,

Sara Vicente,

Neill D. F. Campbell; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Simpson_2022_CVPR, author = {Simpson, Ivor J. A. and Vicente, Sara and Campbell, Neill D. F.}, title = {Learning Structured Gaussians To Approximate Deep Ensembles}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {366-374} }
Total Variation Optimization Layers for Computer Vision: Raymond A. Yeh,

Yuan-Ting Hu,

Zhongzheng Ren,

Alexander G. Schwing; [pdf] [arXiv]
[bibtex]
@InProceedings{Yeh_2022_CVPR, author = {Yeh, Raymond A. and Hu, Yuan-Ting and Ren, Zhongzheng and Schwing, Alexander G.}, title = {Total Variation Optimization Layers for Computer Vision}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {711-721} }
Defensive Patches for Robust Recognition in the Physical World: Jiakai Wang,

Zixin Yin,

Pengfei Hu,

Aishan Liu,

Renshuai Tao,

Haotong Qin,

Xianglong Liu,

Dacheng Tao; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2022_CVPR, author = {Wang, Jiakai and Yin, Zixin and Hu, Pengfei and Liu, Aishan and Tao, Renshuai and Qin, Haotong and Liu, Xianglong and Tao, Dacheng}, title = {Defensive Patches for Robust Recognition in the Physical World}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {2456-2465} }
Sequential Voting With Relational Box Fields for Active Object Detection: Qichen Fu,

Xingyu Liu,

Kris Kitani; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Fu_2022_CVPR, author = {Fu, Qichen and Liu, Xingyu and Kitani, Kris}, title = {Sequential Voting With Relational Box Fields for Active Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {2374-2383} }
Learning Transferable Human-Object Interaction Detector With Natural Language Supervision: Suchen Wang,

Yueqi Duan,

Henghui Ding,

Yap-Peng Tan,

Kim-Hui Yap,

Junsong Yuan; [pdf]
[bibtex]
@InProceedings{Wang_2022_CVPR, author = {Wang, Suchen and Duan, Yueqi and Ding, Henghui and Tan, Yap-Peng and Yap, Kim-Hui and Yuan, Junsong}, title = {Learning Transferable Human-Object Interaction Detector With Natural Language Supervision}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {939-948} }
Fourier Document Restoration for Robust Document Dewarping and Recognition: Chuhui Xue,

Zichen Tian,

Fangneng Zhan,

Shijian Lu,

Song Bai; [pdf] [arXiv]
[bibtex]
@InProceedings{Xue_2022_CVPR, author = {Xue, Chuhui and Tian, Zichen and Zhan, Fangneng and Lu, Shijian and Bai, Song}, title = {Fourier Document Restoration for Robust Document Dewarping and Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {4573-4582} }
Consistency Learning via Decoding Path Augmentation for Transformers in Human Object Interaction Detection: Jihwan Park,

SeungJun Lee,

Hwan Heo,

Hyeong Kyu Choi,

Hyunwoo J. Kim; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Park_2022_CVPR, author = {Park, Jihwan and Lee, SeungJun and Heo, Hwan and Choi, Hyeong Kyu and Kim, Hyunwoo J.}, title = {Consistency Learning via Decoding Path Augmentation for Transformers in Human Object Interaction Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {1019-1028} }
Learning With Neighbor Consistency for Noisy Labels: Ahmet Iscen,

Jack Valmadre,

Anurag Arnab,

Cordelia Schmid; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Iscen_2022_CVPR, author = {Iscen, Ahmet and Valmadre, Jack and Arnab, Anurag and Schmid, Cordelia}, title = {Learning With Neighbor Consistency for Noisy Labels}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {4672-4681} }
Depth Estimation by Combining Binocular Stereo and Monocular Structured-Light: Yuhua Xu,

Xiaoli Yang,

Yushan Yu,

Wei Jia,

Zhaobi Chu,

Yulan Guo; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Xu_2022_CVPR, author = {Xu, Yuhua and Yang, Xiaoli and Yu, Yushan and Jia, Wei and Chu, Zhaobi and Guo, Yulan}, title = {Depth Estimation by Combining Binocular Stereo and Monocular Structured-Light}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {1746-1755} }
Object-Region Video Transformers: Roei Herzig,

Elad Ben-Avraham,

Karttikeya Mangalam,

Amir Bar,

Gal Chechik,

Anna Rohrbach,

Trevor Darrell,

Amir Globerson; [pdf] [supp]
[bibtex]
@InProceedings{Herzig_2022_CVPR, author = {Herzig, Roei and Ben-Avraham, Elad and Mangalam, Karttikeya and Bar, Amir and Chechik, Gal and Rohrbach, Anna and Darrell, Trevor and Globerson, Amir}, title = {Object-Region Video Transformers}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {3148-3159} }
AME: Attention and Memory Enhancement in Hyper-Parameter Optimization: Nuo Xu,

Jianlong Chang,

Xing Nie,

Chunlei Huo,

Shiming Xiang,

Chunhong Pan; [pdf] [supp]
[bibtex]
@InProceedings{Xu_2022_CVPR, author = {Xu, Nuo and Chang, Jianlong and Nie, Xing and Huo, Chunlei and Xiang, Shiming and Pan, Chunhong}, title = {AME: Attention and Memory Enhancement in Hyper-Parameter Optimization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {480-489} }
RepMLPNet: Hierarchical Vision MLP With Re-Parameterized Locality: Xiaohan Ding,

Honghao Chen,

Xiangyu Zhang,

Jungong Han,

Guiguang Ding; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ding_2022_CVPR, author = {Ding, Xiaohan and Chen, Honghao and Zhang, Xiangyu and Han, Jungong and Ding, Guiguang}, title = {RepMLPNet: Hierarchical Vision MLP With Re-Parameterized Locality}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {578-587} }
DR.VIC: Decomposition and Reasoning for Video Individual Counting: Tao Han,

Lei Bai,

Junyu Gao,

Qi Wang,

Wanli Ouyang; [pdf] [supp]
[bibtex]
@InProceedings{Han_2022_CVPR, author = {Han, Tao and Bai, Lei and Gao, Junyu and Wang, Qi and Ouyang, Wanli}, title = {DR.VIC: Decomposition and Reasoning for Video Individual Counting}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {3083-3092} }
Revisiting Document Image Dewarping by Grid Regularization: Xiangwei Jiang,

Rujiao Long,

Nan Xue,

Zhibo Yang,

Cong Yao,

Gui-Song Xia; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Jiang_2022_CVPR, author = {Jiang, Xiangwei and Long, Rujiao and Xue, Nan and Yang, Zhibo and Yao, Cong and Xia, Gui-Song}, title = {Revisiting Document Image Dewarping by Grid Regularization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {4543-4552} }
CMT-DeepLab: Clustering Mask Transformers for Panoptic Segmentation: Qihang Yu,

Huiyu Wang,

Dahun Kim,

Siyuan Qiao,

Maxwell Collins,

Yukun Zhu,

Hartwig Adam,

Alan Yuille,

Liang-Chieh Chen; [pdf] [supp]
[bibtex]
@InProceedings{Yu_2022_CVPR, author = {Yu, Qihang and Wang, Huiyu and Kim, Dahun and Qiao, Siyuan and Collins, Maxwell and Zhu, Yukun and Adam, Hartwig and Yuille, Alan and Chen, Liang-Chieh}, title = {CMT-DeepLab: Clustering Mask Transformers for Panoptic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {2560-2570} }
Novel Class Discovery in Semantic Segmentation: Yuyang Zhao,

Zhun Zhong,

Nicu Sebe,

Gim Hee Lee; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhao_2022_CVPR, author = {Zhao, Yuyang and Zhong, Zhun and Sebe, Nicu and Lee, Gim Hee}, title = {Novel Class Discovery in Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {4340-4349} }
GCFSR: A Generative and Controllable Face Super Resolution Method Without Facial and GAN Priors: Jingwen He,

Wu Shi,

Kai Chen,

Lean Fu,

Chao Dong; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{He_2022_CVPR, author = {He, Jingwen and Shi, Wu and Chen, Kai and Fu, Lean and Dong, Chao}, title = {GCFSR: A Generative and Controllable Face Super Resolution Method Without Facial and GAN Priors}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {1889-1898} }
Using 3D Topological Connectivity for Ghost Particle Reduction in Flow Reconstruction: Christina Tsalicoglou,

Thomas Rösgen; [pdf] [supp]
[bibtex]
@InProceedings{Tsalicoglou_2022_CVPR, author = {Tsalicoglou, Christina and R\"osgen, Thomas}, title = {Using 3D Topological Connectivity for Ghost Particle Reduction in Flow Reconstruction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {1839-1847} }
On the Integration of Self-Attention and Convolution: Xuran Pan,

Chunjiang Ge,

Rui Lu,

Shiji Song,

Guanfu Chen,

Zeyi Huang,

Gao Huang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Pan_2022_CVPR, author = {Pan, Xuran and Ge, Chunjiang and Lu, Rui and Song, Shiji and Chen, Guanfu and Huang, Zeyi and Huang, Gao}, title = {On the Integration of Self-Attention and Convolution}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {815-825} }
Consistency Driven Sequential Transformers Attention Model for Partially Observable Scenes: Samrudhdhi B. Rangrej,

Chetan L. Srinidhi,

James J. Clark; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Rangrej_2022_CVPR, author = {Rangrej, Samrudhdhi B. and Srinidhi, Chetan L. and Clark, James J.}, title = {Consistency Driven Sequential Transformers Attention Model for Partially Observable Scenes}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {2518-2527} }
DiffusionCLIP: Text-Guided Diffusion Models for Robust Image Manipulation: Gwanghyun Kim,

Taesung Kwon,

Jong Chul Ye; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kim_2022_CVPR, author = {Kim, Gwanghyun and Kwon, Taesung and Ye, Jong Chul}, title = {DiffusionCLIP: Text-Guided Diffusion Models for Robust Image Manipulation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {2426-2435} }
GlideNet: Global, Local and Intrinsic Based Dense Embedding NETwork for Multi-Category Attributes Prediction: Kareem Metwaly,

Aerin Kim,

Elliot Branson,

Vishal Monga; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Metwaly_2022_CVPR, author = {Metwaly, Kareem and Kim, Aerin and Branson, Elliot and Monga, Vishal}, title = {GlideNet: Global, Local and Intrinsic Based Dense Embedding NETwork for Multi-Category Attributes Prediction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {4835-4846} }
Towards Better Plasticity-Stability Trade-Off in Incremental Learning: A Simple Linear Connector: Guoliang Lin,

Hanlu Chu,

Hanjiang Lai; [pdf] [arXiv]
[bibtex]
@InProceedings{Lin_2022_CVPR, author = {Lin, Guoliang and Chu, Hanlu and Lai, Hanjiang}, title = {Towards Better Plasticity-Stability Trade-Off in Incremental Learning: A Simple Linear Connector}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {89-98} }
Delving Into the Estimation Shift of Batch Normalization in a Network: Lei Huang,

Yi Zhou,

Tian Wang,

Jie Luo,

Xianglong Liu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Huang_2022_CVPR, author = {Huang, Lei and Zhou, Yi and Wang, Tian and Luo, Jie and Liu, Xianglong}, title = {Delving Into the Estimation Shift of Batch Normalization in a Network}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {763-772} }
Joint Forecasting of Panoptic Segmentations With Difference Attention: Colin Graber,

Cyril Jazra,

Wenjie Luo,

Liangyan Gui,

Alexander G. Schwing; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Graber_2022_CVPR, author = {Graber, Colin and Jazra, Cyril and Luo, Wenjie and Gui, Liangyan and Schwing, Alexander G.}, title = {Joint Forecasting of Panoptic Segmentations With Difference Attention}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {2627-2636} }
Imposing Consistency for Optical Flow Estimation: Jisoo Jeong,

Jamie Menjay Lin,

Fatih Porikli,

Nojun Kwak; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Jeong_2022_CVPR, author = {Jeong, Jisoo and Lin, Jamie Menjay and Porikli, Fatih and Kwak, Nojun}, title = {Imposing Consistency for Optical Flow Estimation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {3181-3191} }
Towards Robust and Reproducible Active Learning Using Neural Networks: Prateek Munjal,

Nasir Hayat,

Munawar Hayat,

Jamshid Sourati,

Shadab Khan; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Munjal_2022_CVPR, author = {Munjal, Prateek and Hayat, Nasir and Hayat, Munawar and Sourati, Jamshid and Khan, Shadab}, title = {Towards Robust and Reproducible Active Learning Using Neural Networks}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {223-232} }
Temporally Efficient Vision Transformer for Video Instance Segmentation: Shusheng Yang,

Xinggang Wang,

Yu Li,

Yuxin Fang,

Jiemin Fang,

Wenyu Liu,

Xun Zhao,

Ying Shan; [pdf] [arXiv]
[bibtex]
@InProceedings{Yang_2022_CVPR, author = {Yang, Shusheng and Wang, Xinggang and Li, Yu and Fang, Yuxin and Fang, Jiemin and Liu, Wenyu and Zhao, Xun and Shan, Ying}, title = {Temporally Efficient Vision Transformer for Video Instance Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {2885-2895} }
The Devil Is in the Margin: Margin-Based Label Smoothing for Network Calibration: Bingyuan Liu,

Ismail Ben Ayed,

Adrian Galdran,

Jose Dolz; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Liu_2022_CVPR, author = {Liu, Bingyuan and Ben Ayed, Ismail and Galdran, Adrian and Dolz, Jose}, title = {The Devil Is in the Margin: Margin-Based Label Smoothing for Network Calibration}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {80-88} }
Revealing Occlusions With 4D Neural Fields: Basile Van Hoorick,

Purva Tendulkar,

Dídac Surís,

Dennis Park,

Simon Stent,

Carl Vondrick; [pdf] [supp]
[bibtex]
@InProceedings{Van_Hoorick_2022_CVPR, author = {Van Hoorick, Basile and Tendulkar, Purva and Sur{\'\i}s, D{\'\i}dac and Park, Dennis and Stent, Simon and Vondrick, Carl}, title = {Revealing Occlusions With 4D Neural Fields}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {3011-3021} }
Self-Supervised Deep Image Restoration via Adaptive Stochastic Gradient Langevin Dynamics: Weixi Wang,

Ji Li,

Hui Ji; [pdf] [supp]
[bibtex]
@InProceedings{Wang_2022_CVPR, author = {Wang, Weixi and Li, Ji and Ji, Hui}, title = {Self-Supervised Deep Image Restoration via Adaptive Stochastic Gradient Langevin Dynamics}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {1989-1998} }
AutoLoss-Zero: Searching Loss Functions From Scratch for Generic Tasks: Hao Li,

Tianwen Fu,

Jifeng Dai,

Hongsheng Li,

Gao Huang,

Xizhou Zhu; [pdf] [supp]
[bibtex]
@InProceedings{Li_2022_CVPR, author = {Li, Hao and Fu, Tianwen and Dai, Jifeng and Li, Hongsheng and Huang, Gao and Zhu, Xizhou}, title = {AutoLoss-Zero: Searching Loss Functions From Scratch for Generic Tasks}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {1009-1018} }
Scalable Penalized Regression for Noise Detection in Learning With Noisy Labels: Yikai Wang,

Xinwei Sun,

Yanwei Fu; [pdf] [arXiv]
[bibtex]
@InProceedings{Wang_2022_CVPR, author = {Wang, Yikai and Sun, Xinwei and Fu, Yanwei}, title = {Scalable Penalized Regression for Noise Detection in Learning With Noisy Labels}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {346-355} }
Registering Explicit to Implicit: Towards High-Fidelity Garment Mesh Reconstruction From Single Images: Heming Zhu,

Lingteng Qiu,

Yuda Qiu,

Xiaoguang Han; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhu_2022_CVPR, author = {Zhu, Heming and Qiu, Lingteng and Qiu, Yuda and Han, Xiaoguang}, title = {Registering Explicit to Implicit: Towards High-Fidelity Garment Mesh Reconstruction From Single Images}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {3845-3854} }
Layered Depth Refinement With Mask Guidance: Soo Ye Kim,

Jianming Zhang,

Simon Niklaus,

Yifei Fan,

Simon Chen,

Zhe Lin,

Munchurl Kim; [pdf] [supp]
[bibtex]
@InProceedings{Kim_2022_CVPR, author = {Kim, Soo Ye and Zhang, Jianming and Niklaus, Simon and Fan, Yifei and Chen, Simon and Lin, Zhe and Kim, Munchurl}, title = {Layered Depth Refinement With Mask Guidance}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {3855-3865} }
LAKe-Net: Topology-Aware Point Cloud Completion by Localizing Aligned Keypoints: Junshu Tang,

Zhijun Gong,

Ran Yi,

Yuan Xie,

Lizhuang Ma; [pdf] [supp]
[bibtex]
@InProceedings{Tang_2022_CVPR, author = {Tang, Junshu and Gong, Zhijun and Yi, Ran and Xie, Yuan and Ma, Lizhuang}, title = {LAKe-Net: Topology-Aware Point Cloud Completion by Localizing Aligned Keypoints}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {1726-1735} }
Scribble-Supervised LiDAR Semantic Segmentation: Ozan Unal,

Dengxin Dai,

Luc Van Gool; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Unal_2022_CVPR, author = {Unal, Ozan and Dai, Dengxin and Van Gool, Luc}, title = {Scribble-Supervised LiDAR Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {2697-2707} }
Vision Transformer Slimming: Multi-Dimension Searching in Continuous Optimization Space: Arnav Chavan,

Zhiqiang Shen,

Zhuang Liu,

Zechun Liu,

Kwang-Ting Cheng,

Eric P. Xing; [pdf] [arXiv]
[bibtex]
@InProceedings{Chavan_2022_CVPR, author = {Chavan, Arnav and Shen, Zhiqiang and Liu, Zhuang and Liu, Zechun and Cheng, Kwang-Ting and Xing, Eric P.}, title = {Vision Transformer Slimming: Multi-Dimension Searching in Continuous Optimization Space}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {4931-4941} }
Brain-Inspired Multilayer Perceptron With Spiking Neurons: Wenshuo Li,

Hanting Chen,

Jianyuan Guo,

Ziyang Zhang,

Yunhe Wang; [pdf] [arXiv]
[bibtex]
@InProceedings{Li_2022_CVPR, author = {Li, Wenshuo and Chen, Hanting and Guo, Jianyuan and Zhang, Ziyang and Wang, Yunhe}, title = {Brain-Inspired Multilayer Perceptron With Spiking Neurons}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {783-793} }
Learning To Estimate Robust 3D Human Mesh From In-the-Wild Crowded Scenes: Hongsuk Choi,

Gyeongsik Moon,

JoonKyu Park,

Kyoung Mu Lee; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Choi_2022_CVPR, author = {Choi, Hongsuk and Moon, Gyeongsik and Park, JoonKyu and Lee, Kyoung Mu}, title = {Learning To Estimate Robust 3D Human Mesh From In-the-Wild Crowded Scenes}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {1475-1484} }
ObjectFormer for Image Manipulation Detection and Localization: Junke Wang,

Zuxuan Wu,

Jingjing Chen,

Xintong Han,

Abhinav Shrivastava,

Ser-Nam Lim,

Yu-Gang Jiang; [pdf] [arXiv]
[bibtex]
@InProceedings{Wang_2022_CVPR, author = {Wang, Junke and Wu, Zuxuan and Chen, Jingjing and Han, Xintong and Shrivastava, Abhinav and Lim, Ser-Nam and Jiang, Yu-Gang}, title = {ObjectFormer for Image Manipulation Detection and Localization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {2364-2373} }
Towards Semi-Supervised Deep Facial Expression Recognition With an Adaptive Confidence Margin: Hangyu Li,

Nannan Wang,

Xi Yang,

Xiaoyu Wang,

Xinbo Gao; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Li_2022_CVPR, author = {Li, Hangyu and Wang, Nannan and Yang, Xi and Wang, Xiaoyu and Gao, Xinbo}, title = {Towards Semi-Supervised Deep Facial Expression Recognition With an Adaptive Confidence Margin}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {4166-4175} }
Masked-Attention Mask Transformer for Universal Image Segmentation: Bowen Cheng,

Ishan Misra,

Alexander G. Schwing,

Alexander Kirillov,

Rohit Girdhar; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Cheng_2022_CVPR, author = {Cheng, Bowen and Misra, Ishan and Schwing, Alexander G. and Kirillov, Alexander and Girdhar, Rohit}, title = {Masked-Attention Mask Transformer for Universal Image Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {1290-1299} }
Language-Bridged Spatial-Temporal Interaction for Referring Video Object Segmentation: Zihan Ding,

Tianrui Hui,

Junshi Huang,

Xiaoming Wei,

Jizhong Han,

Si Liu; [pdf]
[bibtex]
@InProceedings{Ding_2022_CVPR, author = {Ding, Zihan and Hui, Tianrui and Huang, Junshi and Wei, Xiaoming and Han, Jizhong and Liu, Si}, title = {Language-Bridged Spatial-Temporal Interaction for Referring Video Object Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {4964-4973} }
Adaptive Hierarchical Representation Learning for Long-Tailed Object Detection: Banghuai Li; [pdf] [supp]
[bibtex]
@InProceedings{Li_2022_CVPR, author = {Li, Banghuai}, title = {Adaptive Hierarchical Representation Learning for Long-Tailed Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {2313-2322} }
Whose Hands Are These? Hand Detection and Hand-Body Association in the Wild: Supreeth Narasimhaswamy,

Thanh Nguyen,

Mingzhen Huang,

Minh Hoai; [pdf] [supp]
[bibtex]
@InProceedings{Narasimhaswamy_2022_CVPR, author = {Narasimhaswamy, Supreeth and Nguyen, Thanh and Huang, Mingzhen and Hoai, Minh}, title = {Whose Hands Are These? Hand Detection and Hand-Body Association in the Wild}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {4889-4899} }
Training Quantised Neural Networks With STE Variants: The Additive Noise Annealing Algorithm: Matteo Spallanzani,

Gian Paolo Leonardi,

Luca Benini; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Spallanzani_2022_CVPR, author = {Spallanzani, Matteo and Leonardi, Gian Paolo and Benini, Luca}, title = {Training Quantised Neural Networks With STE Variants: The Additive Noise Annealing Algorithm}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {470-479} }
Split Hierarchical Variational Compression: Tom Ryder,

Chen Zhang,

Ning Kang,

Shifeng Zhang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ryder_2022_CVPR, author = {Ryder, Tom and Zhang, Chen and Kang, Ning and Zhang, Shifeng}, title = {Split Hierarchical Variational Compression}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {386-395} }
Video Swin Transformer: Ze Liu,

Jia Ning,

Yue Cao,

Yixuan Wei,

Zheng Zhang,

Stephen Lin,

Han Hu; [pdf] [arXiv]
[bibtex]
@InProceedings{Liu_2022_CVPR, author = {Liu, Ze and Ning, Jia and Cao, Yue and Wei, Yixuan and Zhang, Zheng and Lin, Stephen and Hu, Han}, title = {Video Swin Transformer}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {3202-3211} }
BoxeR: Box-Attention for 2D and 3D Transformers: Duy-Kien Nguyen,

Jihong Ju,

Olaf Booij,

Martin R. Oswald,

Cees G. M. Snoek; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Nguyen_2022_CVPR, author = {Nguyen, Duy-Kien and Ju, Jihong and Booij, Olaf and Oswald, Martin R. and Snoek, Cees G. M.}, title = {BoxeR: Box-Attention for 2D and 3D Transformers}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {4773-4782} }
A Proposal-Based Paradigm for Self-Supervised Sound Source Localization in Videos: Hanyu Xuan,

Zhiliang Wu,

Jian Yang,

Yan Yan,

Xavier Alameda-Pineda; [pdf]
[bibtex]
@InProceedings{Xuan_2022_CVPR, author = {Xuan, Hanyu and Wu, Zhiliang and Yang, Jian and Yan, Yan and Alameda-Pineda, Xavier}, title = {A Proposal-Based Paradigm for Self-Supervised Sound Source Localization in Videos}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {1029-1038} }
P3IV: Probabilistic Procedure Planning From Instructional Videos With Weak Supervision: He Zhao,

Isma Hadji,

Nikita Dvornik,

Konstantinos G. Derpanis,

Richard P. Wildes,

Allan D. Jepson; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhao_2022_CVPR, author = {Zhao, He and Hadji, Isma and Dvornik, Nikita and Derpanis, Konstantinos G. and Wildes, Richard P. and Jepson, Allan D.}, title = {P3IV: Probabilistic Procedure Planning From Instructional Videos With Weak Supervision}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {2938-2948} }
Hierarchical Nearest Neighbor Graph Embedding for Efficient Dimensionality Reduction: Saquib Sarfraz,

Marios Koulakis,

Constantin Seibold,

Rainer Stiefelhagen; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Sarfraz_2022_CVPR, author = {Sarfraz, Saquib and Koulakis, Marios and Seibold, Constantin and Stiefelhagen, Rainer}, title = {Hierarchical Nearest Neighbor Graph Embedding for Efficient Dimensionality Reduction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {336-345} }
Semi-Supervised Video Paragraph Grounding With Contrastive Encoder: Xun Jiang,

Xing Xu,

Jingran Zhang,

Fumin Shen,

Zuo Cao,

Heng Tao Shen; [pdf]
[bibtex]
@InProceedings{Jiang_2022_CVPR, author = {Jiang, Xun and Xu, Xing and Zhang, Jingran and Shen, Fumin and Cao, Zuo and Shen, Heng Tao}, title = {Semi-Supervised Video Paragraph Grounding With Contrastive Encoder}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {2466-2475} }
BARC: Learning To Regress 3D Dog Shape From Images by Exploiting Breed Information: Nadine Rüegg,

Silvia Zuffi,

Konrad Schindler,

Michael J. Black; [pdf] [supp]
[bibtex]
@InProceedings{Ruegg_2022_CVPR, author = {R\"uegg, Nadine and Zuffi, Silvia and Schindler, Konrad and Black, Michael J.}, title = {BARC: Learning To Regress 3D Dog Shape From Images by Exploiting Breed Information}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {3876-3884} }
Frame Averaging for Equivariant Shape Space Learning: Matan Atzmon,

Koki Nagano,

Sanja Fidler,

Sameh Khamis,

Yaron Lipman; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Atzmon_2022_CVPR, author = {Atzmon, Matan and Nagano, Koki and Fidler, Sanja and Khamis, Sameh and Lipman, Yaron}, title = {Frame Averaging for Equivariant Shape Space Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {631-641} }
Panoptic SegFormer: Delving Deeper Into Panoptic Segmentation With Transformers: Zhiqi Li,

Wenhai Wang,

Enze Xie,

Zhiding Yu,

Anima Anandkumar,

Jose M. Alvarez,

Ping Luo,

Tong Lu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Li_2022_CVPR, author = {Li, Zhiqi and Wang, Wenhai and Xie, Enze and Yu, Zhiding and Anandkumar, Anima and Alvarez, Jose M. and Luo, Ping and Lu, Tong}, title = {Panoptic SegFormer: Delving Deeper Into Panoptic Segmentation With Transformers}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {1280-1289} }
Hypergraph-Induced Semantic Tuplet Loss for Deep Metric Learning: Jongin Lim,

Sangdoo Yun,

Seulki Park,

Jin Young Choi; [pdf] [supp]
[bibtex]
@InProceedings{Lim_2022_CVPR, author = {Lim, Jongin and Yun, Sangdoo and Park, Seulki and Choi, Jin Young}, title = {Hypergraph-Induced Semantic Tuplet Loss for Deep Metric Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {212-222} }
Computing Wasserstein-p Distance Between Images With Linear Cost: Yidong Chen,

Chen Li,

Zhonghua Lu; [pdf] [supp]
[bibtex]
@InProceedings{Chen_2022_CVPR, author = {Chen, Yidong and Li, Chen and Lu, Zhonghua}, title = {Computing Wasserstein-p Distance Between Images With Linear Cost}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {519-528} }
DLFormer: Discrete Latent Transformer for Video Inpainting: Jingjing Ren,

Qingqing Zheng,

Yuanyuan Zhao,

Xuemiao Xu,

Chen Li; [pdf]
[bibtex]
@InProceedings{Ren_2022_CVPR, author = {Ren, Jingjing and Zheng, Qingqing and Zhao, Yuanyuan and Xu, Xuemiao and Li, Chen}, title = {DLFormer: Discrete Latent Transformer for Video Inpainting}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {3511-3520} }
High Quality Segmentation for Ultra High-Resolution Images: Tiancheng Shen,

Yuechen Zhang,

Lu Qi,

Jason Kuen,

Xingyu Xie,

Jianlong Wu,

Zhe Lin,

Jiaya Jia; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Shen_2022_CVPR, author = {Shen, Tiancheng and Zhang, Yuechen and Qi, Lu and Kuen, Jason and Xie, Xingyu and Wu, Jianlong and Lin, Zhe and Jia, Jiaya}, title = {High Quality Segmentation for Ultra High-Resolution Images}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {1310-1319} }
Aesthetic Text Logo Synthesis via Content-Aware Layout Inferring: Yizhi Wang,

Guo Pu,

Wenhan Luo,

Yexin Wang,

Pengfei Xiong,

Hongwen Kang,

Zhouhui Lian; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2022_CVPR, author = {Wang, Yizhi and Pu, Guo and Luo, Wenhan and Wang, Yexin and Xiong, Pengfei and Kang, Hongwen and Lian, Zhouhui}, title = {Aesthetic Text Logo Synthesis via Content-Aware Layout Inferring}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {2436-2445} }
Oriented RepPoints for Aerial Object Detection: Wentong Li,

Yijie Chen,

Kaixuan Hu,

Jianke Zhu; [pdf] [arXiv]
[bibtex]
@InProceedings{Li_2022_CVPR, author = {Li, Wentong and Chen, Yijie and Hu, Kaixuan and Zhu, Jianke}, title = {Oriented RepPoints for Aerial Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {1829-1838} }
OccAM's Laser: Occlusion-Based Attribution Maps for 3D Object Detectors on LiDAR Data: David Schinagl,

Georg Krispel,

Horst Possegger,

Peter M. Roth,

Horst Bischof; [pdf] [supp]
[bibtex]
@InProceedings{Schinagl_2022_CVPR, author = {Schinagl, David and Krispel, Georg and Possegger, Horst and Roth, Peter M. and Bischof, Horst}, title = {OccAM's Laser: Occlusion-Based Attribution Maps for 3D Object Detectors on LiDAR Data}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {1141-1150} }
Pre-Train, Self-Train, Distill: A Simple Recipe for Supersizing 3D Reconstruction: Kalyan Vasudev Alwala,

Abhinav Gupta,

Shubham Tulsiani; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Alwala_2022_CVPR, author = {Alwala, Kalyan Vasudev and Gupta, Abhinav and Tulsiani, Shubham}, title = {Pre-Train, Self-Train, Distill: A Simple Recipe for Supersizing 3D Reconstruction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {3773-3782} }
Meta Distribution Alignment for Generalizable Person Re-Identification: Hao Ni,

Jingkuan Song,

Xiaopeng Luo,

Feng Zheng,

Wen Li,

Heng Tao Shen; [pdf]
[bibtex]
@InProceedings{Ni_2022_CVPR, author = {Ni, Hao and Song, Jingkuan and Luo, Xiaopeng and Zheng, Feng and Li, Wen and Shen, Heng Tao}, title = {Meta Distribution Alignment for Generalizable Person Re-Identification}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {2487-2496} }
BoosterNet: Improving Domain Generalization of Deep Neural Nets Using Culpability-Ranked Features: Nourhan Bayasi,

Ghassan Hamarneh,

Rafeef Garbi; [pdf]
[bibtex]
@InProceedings{Bayasi_2022_CVPR, author = {Bayasi, Nourhan and Hamarneh, Ghassan and Garbi, Rafeef}, title = {BoosterNet: Improving Domain Generalization of Deep Neural Nets Using Culpability-Ranked Features}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {538-548} }
Selective-Supervised Contrastive Learning With Noisy Labels: Shikun Li,

Xiaobo Xia,

Shiming Ge,

Tongliang Liu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Li_2022_CVPR, author = {Li, Shikun and Xia, Xiaobo and Ge, Shiming and Liu, Tongliang}, title = {Selective-Supervised Contrastive Learning With Noisy Labels}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {316-325} }
Co-Domain Symmetry for Complex-Valued Deep Learning: Utkarsh Singhal,

Yifei Xing,

Stella X. Yu; [pdf] [arXiv]
[bibtex]
@InProceedings{Singhal_2022_CVPR, author = {Singhal, Utkarsh and Xing, Yifei and Yu, Stella X.}, title = {Co-Domain Symmetry for Complex-Valued Deep Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {681-690} }
Neural Collaborative Graph Machines for Table Structure Recognition: Hao Liu,

Xin Li,

Bing Liu,

Deqiang Jiang,

Yinsong Liu,

Bo Ren; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Liu_2022_CVPR, author = {Liu, Hao and Li, Xin and Liu, Bing and Jiang, Deqiang and Liu, Yinsong and Ren, Bo}, title = {Neural Collaborative Graph Machines for Table Structure Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {4533-4542} }
Learning Affordance Grounding From Exocentric Images: Hongchen Luo,

Wei Zhai,

Jing Zhang,

Yang Cao,

Dacheng Tao; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Luo_2022_CVPR, author = {Luo, Hongchen and Zhai, Wei and Zhang, Jing and Cao, Yang and Tao, Dacheng}, title = {Learning Affordance Grounding From Exocentric Images}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {2252-2261} }
C2AM: Contrastive Learning of Class-Agnostic Activation Map for Weakly Supervised Object Localization and Semantic Segmentation: Jinheng Xie,

Jianfeng Xiang,

Junliang Chen,

Xianxu Hou,

Xiaodong Zhao,

Linlin Shen; [pdf] [supp]
[bibtex]
@InProceedings{Xie_2022_CVPR, author = {Xie, Jinheng and Xiang, Jianfeng and Chen, Junliang and Hou, Xianxu and Zhao, Xiaodong and Shen, Linlin}, title = {C2AM: Contrastive Learning of Class-Agnostic Activation Map for Weakly Supervised Object Localization and Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {989-998} }
Understanding 3D Object Articulation in Internet Videos: Shengyi Qian,

Linyi Jin,

Chris Rockwell,

Siyi Chen,

David F. Fouhey; [pdf] [arXiv]
[bibtex]
@InProceedings{Qian_2022_CVPR, author = {Qian, Shengyi and Jin, Linyi and Rockwell, Chris and Chen, Siyi and Fouhey, David F.}, title = {Understanding 3D Object Articulation in Internet Videos}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {1599-1609} }
Multi-Level Representation Learning With Semantic Alignment for Referring Video Object Segmentation: Dongming Wu,

Xingping Dong,

Ling Shao,

Jianbing Shen; [pdf]
[bibtex]
@InProceedings{Wu_2022_CVPR, author = {Wu, Dongming and Dong, Xingping and Shao, Ling and Shen, Jianbing}, title = {Multi-Level Representation Learning With Semantic Alignment for Referring Video Object Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {4996-5005} }
Paramixer: Parameterizing Mixing Links in Sparse Factors Works Better Than Dot-Product Self-Attention: Tong Yu,

Ruslan Khalitov,

Lei Cheng,

Zhirong Yang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yu_2022_CVPR, author = {Yu, Tong and Khalitov, Ruslan and Cheng, Lei and Yang, Zhirong}, title = {Paramixer: Parameterizing Mixing Links in Sparse Factors Works Better Than Dot-Product Self-Attention}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {691-700} }
Pseudo-Stereo for Monocular 3D Object Detection in Autonomous Driving: Yi-Nan Chen,

Hang Dai,

Yong Ding; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chen_2022_CVPR, author = {Chen, Yi-Nan and Dai, Hang and Ding, Yong}, title = {Pseudo-Stereo for Monocular 3D Object Detection in Autonomous Driving}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {887-897} }
Syntax-Aware Network for Handwritten Mathematical Expression Recognition: Ye Yuan,

Xiao Liu,

Wondimu Dikubab,

Hui Liu,

Zhilong Ji,

Zhongqin Wu,

Xiang Bai; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yuan_2022_CVPR, author = {Yuan, Ye and Liu, Xiao and Dikubab, Wondimu and Liu, Hui and Ji, Zhilong and Wu, Zhongqin and Bai, Xiang}, title = {Syntax-Aware Network for Handwritten Mathematical Expression Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {4553-4562} }
Sketching Without Worrying: Noise-Tolerant Sketch-Based Image Retrieval: Ayan Kumar Bhunia,

Subhadeep Koley,

Abdullah Faiz Ur Rahman Khilji,

Aneeshan Sain,

Pinaki Nath Chowdhury,

Tao Xiang,

Yi-Zhe Song; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Bhunia_2022_CVPR, author = {Bhunia, Ayan Kumar and Koley, Subhadeep and Khilji, Abdullah Faiz Ur Rahman and Sain, Aneeshan and Chowdhury, Pinaki Nath and Xiang, Tao and Song, Yi-Zhe}, title = {Sketching Without Worrying: Noise-Tolerant Sketch-Based Image Retrieval}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {999-1008} }
PUMP: Pyramidal and Uniqueness Matching Priors for Unsupervised Learning of Local Descriptors: Jérome Revaud,

Vincent Leroy,

Philippe Weinzaepfel,

Boris Chidlovskii; [pdf] [supp]
[bibtex]
@InProceedings{Revaud_2022_CVPR, author = {Revaud, J\'erome and Leroy, Vincent and Weinzaepfel, Philippe and Chidlovskii, Boris}, title = {PUMP: Pyramidal and Uniqueness Matching Priors for Unsupervised Learning of Local Descriptors}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {3926-3936} }
Deep Equilibrium Optical Flow Estimation: Shaojie Bai,

Zhengyang Geng,

Yash Savani,

J. Zico Kolter; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Bai_2022_CVPR, author = {Bai, Shaojie and Geng, Zhengyang and Savani, Yash and Kolter, J. Zico}, title = {Deep Equilibrium Optical Flow Estimation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {620-630} }
Joint Hand Motion and Interaction Hotspots Prediction From Egocentric Videos: Shaowei Liu,

Subarna Tripathi,

Somdeb Majumdar,

Xiaolong Wang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Liu_2022_CVPR, author = {Liu, Shaowei and Tripathi, Subarna and Majumdar, Somdeb and Wang, Xiaolong}, title = {Joint Hand Motion and Interaction Hotspots Prediction From Egocentric Videos}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {3282-3292} }
Revisiting the "Video" in Video-Language Understanding: Shyamal Buch,

Cristóbal Eyzaguirre,

Adrien Gaidon,

Jiajun Wu,

Li Fei-Fei,

Juan Carlos Niebles; [pdf]
[bibtex]
@InProceedings{Buch_2022_CVPR, author = {Buch, Shyamal and Eyzaguirre, Crist\'obal and Gaidon, Adrien and Wu, Jiajun and Fei-Fei, Li and Niebles, Juan Carlos}, title = {Revisiting the ''Video'' in Video-Language Understanding}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {2917-2927} }
Local Texture Estimator for Implicit Representation Function: Jaewon Lee,

Kyong Hwan Jin; [pdf] [arXiv]
[bibtex]
@InProceedings{Lee_2022_CVPR, author = {Lee, Jaewon and Jin, Kyong Hwan}, title = {Local Texture Estimator for Implicit Representation Function}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {1929-1938} }
A Voxel Graph CNN for Object Classification With Event Cameras: Yongjian Deng,

Hao Chen,

Hai Liu,

Youfu Li; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Deng_2022_CVPR, author = {Deng, Yongjian and Chen, Hao and Liu, Hai and Li, Youfu}, title = {A Voxel Graph CNN for Object Classification With Event Cameras}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {1172-1181} }
ViSTA: Vision and Scene Text Aggregation for Cross-Modal Retrieval: Mengjun Cheng,

Yipeng Sun,

Longchao Wang,

Xiongwei Zhu,

Kun Yao,

Jie Chen,

Guoli Song,

Junyu Han,

Jingtuo Liu,

Errui Ding,

Jingdong Wang; [pdf] [arXiv]
[bibtex]
@InProceedings{Cheng_2022_CVPR, author = {Cheng, Mengjun and Sun, Yipeng and Wang, Longchao and Zhu, Xiongwei and Yao, Kun and Chen, Jie and Song, Guoli and Han, Junyu and Liu, Jingtuo and Ding, Errui and Wang, Jingdong}, title = {ViSTA: Vision and Scene Text Aggregation for Cross-Modal Retrieval}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {5184-5193} }
Likert Scoring With Grade Decoupling for Long-Term Action Assessment: Angchi Xu,

Ling-An Zeng,

Wei-Shi Zheng; [pdf] [supp]
[bibtex]
@InProceedings{Xu_2022_CVPR, author = {Xu, Angchi and Zeng, Ling-An and Zheng, Wei-Shi}, title = {Likert Scoring With Grade Decoupling for Long-Term Action Assessment}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {3232-3241} }
Many-to-Many Splatting for Efficient Video Frame Interpolation: Ping Hu,

Simon Niklaus,

Stan Sclaroff,

Kate Saenko; [pdf] [arXiv]
[bibtex]
@InProceedings{Hu_2022_CVPR, author = {Hu, Ping and Niklaus, Simon and Sclaroff, Stan and Saenko, Kate}, title = {Many-to-Many Splatting for Efficient Video Frame Interpolation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {3553-3562} }
Learning To Learn by Jointly Optimizing Neural Architecture and Weights: Yadong Ding,

Yu Wu,

Chengyue Huang,

Siliang Tang,

Yi Yang,

Longhui Wei,

Yueting Zhuang,

Qi Tian; [pdf] [supp]
[bibtex]
@InProceedings{Ding_2022_CVPR, author = {Ding, Yadong and Wu, Yu and Huang, Chengyue and Tang, Siliang and Yang, Yi and Wei, Longhui and Zhuang, Yueting and Tian, Qi}, title = {Learning To Learn by Jointly Optimizing Neural Architecture and Weights}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {129-138} }
A Keypoint-Based Global Association Network for Lane Detection: Jinsheng Wang,

Yinchao Ma,

Shaofei Huang,

Tianrui Hui,

Fei Wang,

Chen Qian,

Tianzhu Zhang; [pdf] [arXiv]
[bibtex]
@InProceedings{Wang_2022_CVPR, author = {Wang, Jinsheng and Ma, Yinchao and Huang, Shaofei and Hui, Tianrui and Wang, Fei and Qian, Chen and Zhang, Tianzhu}, title = {A Keypoint-Based Global Association Network for Lane Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {1392-1401} }
Few-Shot Incremental Learning for Label-to-Image Translation: Pei Chen,

Yangkang Zhang,

Zejian Li,

Lingyun Sun; [pdf] [supp]
[bibtex]
@InProceedings{Chen_2022_CVPR, author = {Chen, Pei and Zhang, Yangkang and Li, Zejian and Sun, Lingyun}, title = {Few-Shot Incremental Learning for Label-to-Image Translation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {3697-3707} }
Recurrent Variational Network: A Deep Learning Inverse Problem Solver Applied to the Task of Accelerated MRI Reconstruction: George Yiasemis,

Jan-Jakob Sonke,

Clarisa Sánchez,

Jonas Teuwen; [pdf] [supp]
[bibtex]
@InProceedings{Yiasemis_2022_CVPR, author = {Yiasemis, George and Sonke, Jan-Jakob and S\'anchez, Clarisa and Teuwen, Jonas}, title = {Recurrent Variational Network: A Deep Learning Inverse Problem Solver Applied to the Task of Accelerated MRI Reconstruction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {732-741} }
CroMo: Cross-Modal Learning for Monocular Depth Estimation: Yannick Verdié,

Jifei Song,

Barnabé Mas,

Benjamin Busam,

Ales̆ Leonardis,

Steven McDonagh; [pdf] [supp]
[bibtex]
@InProceedings{Verdie_2022_CVPR, author = {Verdi\'e, Yannick and Song, Jifei and Mas, Barnab\'e and Busam, Benjamin and Leonardis, Ales̆ and McDonagh, Steven}, title = {CroMo: Cross-Modal Learning for Monocular Depth Estimation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {3937-3947} }
PanopticDepth: A Unified Framework for Depth-Aware Panoptic Segmentation: Naiyu Gao,

Fei He,

Jian Jia,

Yanhu Shan,

Haoyang Zhang,

Xin Zhao,

Kaiqi Huang; [pdf] [arXiv]
[bibtex]
@InProceedings{Gao_2022_CVPR, author = {Gao, Naiyu and He, Fei and Jia, Jian and Shan, Yanhu and Zhang, Haoyang and Zhao, Xin and Huang, Kaiqi}, title = {PanopticDepth: A Unified Framework for Depth-Aware Panoptic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {1632-1642} }
3D Shape Reconstruction From 2D Images With Disentangled Attribute Flow: Xin Wen,

Junsheng Zhou,

Yu-Shen Liu,

Hua Su,

Zhen Dong,

Zhizhong Han; [pdf] [arXiv]
[bibtex]
@InProceedings{Wen_2022_CVPR, author = {Wen, Xin and Zhou, Junsheng and Liu, Yu-Shen and Su, Hua and Dong, Zhen and Han, Zhizhong}, title = {3D Shape Reconstruction From 2D Images With Disentangled Attribute Flow}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {3803-3813} }
OpenTAL: Towards Open Set Temporal Action Localization: Wentao Bao,

Qi Yu,

Yu Kong; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Bao_2022_CVPR, author = {Bao, Wentao and Yu, Qi and Kong, Yu}, title = {OpenTAL: Towards Open Set Temporal Action Localization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {2979-2989} }
Sparse and Complete Latent Organization for Geospatial Semantic Segmentation: Fengyu Yang,

Chenyang Ma; [pdf]
[bibtex]
@InProceedings{Yang_2022_CVPR, author = {Yang, Fengyu and Ma, Chenyang}, title = {Sparse and Complete Latent Organization for Geospatial Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {1809-1818} }
ST++: Make Self-Training Work Better for Semi-Supervised Semantic Segmentation: Lihe Yang,

Wei Zhuo,

Lei Qi,

Yinghuan Shi,

Yang Gao; [pdf] [supp]
[bibtex]
@InProceedings{Yang_2022_CVPR, author = {Yang, Lihe and Zhuo, Wei and Qi, Lei and Shi, Yinghuan and Gao, Yang}, title = {ST++: Make Self-Training Work Better for Semi-Supervised Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {4268-4277} }
Interacting Attention Graph for Single Image Two-Hand Reconstruction: Mengcheng Li,

Liang An,

Hongwen Zhang,

Lianpeng Wu,

Feng Chen,

Tao Yu,

Yebin Liu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Li_2022_CVPR, author = {Li, Mengcheng and An, Liang and Zhang, Hongwen and Wu, Lianpeng and Chen, Feng and Yu, Tao and Liu, Yebin}, title = {Interacting Attention Graph for Single Image Two-Hand Reconstruction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {2761-2770} }
Exploring and Evaluating Image Restoration Potential in Dynamic Scenes: Cheng Zhang,

Shaolin Su,

Yu Zhu,

Qingsen Yan,

Jinqiu Sun,

Yanning Zhang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhang_2022_CVPR, author = {Zhang, Cheng and Su, Shaolin and Zhu, Yu and Yan, Qingsen and Sun, Jinqiu and Zhang, Yanning}, title = {Exploring and Evaluating Image Restoration Potential in Dynamic Scenes}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {2067-2076} }
Simulated Adversarial Testing of Face Recognition Models: Nataniel Ruiz,

Adam Kortylewski,

Weichao Qiu,

Cihang Xie,

Sarah Adel Bargal,

Alan Yuille,

Stan Sclaroff; [pdf] [supp] [arXiv ]
[bibtex]
@InProceedings{Ruiz_2022_CVPR, author = {Ruiz, Nataniel and Kortylewski, Adam and Qiu, Weichao and Xie, Cihang and Bargal, Sarah Adel and Yuille, Alan and Sclaroff, Stan}, title = {Simulated Adversarial Testing of Face Recognition Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {4145-4155} }
CAT-Det: Contrastively Augmented Transformer for Multi-Modal 3D Object Detection: Yanan Zhang,

Jiaxin Chen,

Di Huang; [pdf] [supp]
[bibtex]
@InProceedings{Zhang_2022_CVPR, author = {Zhang, Yanan and Chen, Jiaxin and Huang, Di}, title = {CAT-Det: Contrastively Augmented Transformer for Multi-Modal 3D Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {908-917} }
Diversity Matters: Fully Exploiting Depth Clues for Reliable Monocular 3D Object Detection: Zhuoling Li,

Zhan Qu,

Yang Zhou,

Jianzhuang Liu,

Haoqian Wang,

Lihui Jiang; [pdf] [arXiv]
[bibtex]
@InProceedings{Li_2022_CVPR, author = {Li, Zhuoling and Qu, Zhan and Zhou, Yang and Liu, Jianzhuang and Wang, Haoqian and Jiang, Lihui}, title = {Diversity Matters: Fully Exploiting Depth Clues for Reliable Monocular 3D Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {2791-2800} }
ST-MFNet: A Spatio-Temporal Multi-Flow Network for Frame Interpolation: Duolikun Danier,

Fan Zhang,

David Bull; [pdf] [supp]
[bibtex]
@InProceedings{Danier_2022_CVPR, author = {Danier, Duolikun and Zhang, Fan and Bull, David}, title = {ST-MFNet: A Spatio-Temporal Multi-Flow Network for Frame Interpolation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {3521-3531} }
Self-Supervised Super-Resolution for Multi-Exposure Push-Frame Satellites: Ngoc Long Nguyen,

Jérémy Anger,

Axel Davy,

Pablo Arias,

Gabriele Facciolo; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Nguyen_2022_CVPR, author = {Nguyen, Ngoc Long and Anger, J\'er\'emy and Davy, Axel and Arias, Pablo and Facciolo, Gabriele}, title = {Self-Supervised Super-Resolution for Multi-Exposure Push-Frame Satellites}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {1858-1868} }
Stability-Driven Contact Reconstruction From Monocular Color Images: Zimeng Zhao,

Binghui Zuo,

Wei Xie,

Yangang Wang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhao_2022_CVPR, author = {Zhao, Zimeng and Zuo, Binghui and Xie, Wei and Wang, Yangang}, title = {Stability-Driven Contact Reconstruction From Monocular Color Images}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {1643-1653} }
Texture-Based Error Analysis for Image Super-Resolution: Salma Abdel Magid,

Zudi Lin,

Donglai Wei,

Yulun Zhang,

Jinjin Gu,

Hanspeter Pfister; [pdf]
[bibtex]
@InProceedings{Magid_2022_CVPR, author = {Magid, Salma Abdel and Lin, Zudi and Wei, Donglai and Zhang, Yulun and Gu, Jinjin and Pfister, Hanspeter}, title = {Texture-Based Error Analysis for Image Super-Resolution}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {2118-2127} }
PILC: Practical Image Lossless Compression With an End-to-End GPU Oriented Neural Framework: Ning Kang,

Shanzhao Qiu,

Shifeng Zhang,

Zhenguo Li,

Shu-Tao Xia; [pdf] [supp]
[bibtex]
@InProceedings{Kang_2022_CVPR, author = {Kang, Ning and Qiu, Shanzhao and Zhang, Shifeng and Li, Zhenguo and Xia, Shu-Tao}, title = {PILC: Practical Image Lossless Compression With an End-to-End GPU Oriented Neural Framework}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {3739-3748} }
Learning To Align Sequential Actions in the Wild: Weizhe Liu,

Bugra Tekin,

Huseyin Coskun,

Vibhav Vineet,

Pascal Fua,

Marc Pollefeys; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Liu_2022_CVPR, author = {Liu, Weizhe and Tekin, Bugra and Coskun, Huseyin and Vineet, Vibhav and Fua, Pascal and Pollefeys, Marc}, title = {Learning To Align Sequential Actions in the Wild}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {2181-2191} }
GCR: Gradient Coreset Based Replay Buffer Selection for Continual Learning: Rishabh Tiwari,

Krishnateja Killamsetty,

Rishabh Iyer,

Pradeep Shenoy; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Tiwari_2022_CVPR, author = {Tiwari, Rishabh and Killamsetty, Krishnateja and Iyer, Rishabh and Shenoy, Pradeep}, title = {GCR: Gradient Coreset Based Replay Buffer Selection for Continual Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {99-108} }
Deep Color Consistent Network for Low-Light Image Enhancement: Zhao Zhang,

Huan Zheng,

Richang Hong,

Mingliang Xu,

Shuicheng Yan,

Meng Wang; [pdf]
[bibtex]
@InProceedings{Zhang_2022_CVPR, author = {Zhang, Zhao and Zheng, Huan and Hong, Richang and Xu, Mingliang and Yan, Shuicheng and Wang, Meng}, title = {Deep Color Consistent Network for Low-Light Image Enhancement}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {1899-1908} }
AdaSTE: An Adaptive Straight-Through Estimator To Train Binary Neural Networks: Huu Le,

Rasmus Kjær Høier,

Che-Tsung Lin,

Christopher Zach; [pdf] [supp]
[bibtex]
@InProceedings{Le_2022_CVPR, author = {Le, Huu and H{\o}ier, Rasmus Kj{\ae}r and Lin, Che-Tsung and Zach, Christopher}, title = {AdaSTE: An Adaptive Straight-Through Estimator To Train Binary Neural Networks}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {460-469} }
Pooling Revisited: Your Receptive Field Is Suboptimal: Dong-Hwan Jang,

Sanghyeok Chu,

Joonhyuk Kim,

Bohyung Han; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Jang_2022_CVPR, author = {Jang, Dong-Hwan and Chu, Sanghyeok and Kim, Joonhyuk and Han, Bohyung}, title = {Pooling Revisited: Your Receptive Field Is Suboptimal}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {549-558} }
Show Me What and Tell Me How: Video Synthesis via Multimodal Conditioning: Ligong Han,

Jian Ren,

Hsin-Ying Lee,

Francesco Barbieri,

Kyle Olszewski,

Shervin Minaee,

Dimitris Metaxas,

Sergey Tulyakov; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Han_2022_CVPR, author = {Han, Ligong and Ren, Jian and Lee, Hsin-Ying and Barbieri, Francesco and Olszewski, Kyle and Minaee, Shervin and Metaxas, Dimitris and Tulyakov, Sergey}, title = {Show Me What and Tell Me How: Video Synthesis via Multimodal Conditioning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {3615-3625} }
Confidence Propagation Cluster: Unleash Full Potential of Object Detectors: Yichun Shen,

Wanli Jiang,

Zhen Xu,

Rundong Li,

Junghyun Kwon,

Siyi Li; [pdf] [arXiv]
[bibtex]
@InProceedings{Shen_2022_CVPR, author = {Shen, Yichun and Jiang, Wanli and Xu, Zhen and Li, Rundong and Kwon, Junghyun and Li, Siyi}, title = {Confidence Propagation Cluster: Unleash Full Potential of Object Detectors}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {1151-1161} }
ISNet: Shape Matters for Infrared Small Target Detection: Mingjin Zhang,

Rui Zhang,

Yuxiang Yang,

Haichen Bai,

Jing Zhang,

Jie Guo; [pdf]
[bibtex]
@InProceedings{Zhang_2022_CVPR, author = {Zhang, Mingjin and Zhang, Rui and Yang, Yuxiang and Bai, Haichen and Zhang, Jing and Guo, Jie}, title = {ISNet: Shape Matters for Infrared Small Target Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {877-886} }
Segment, Magnify and Reiterate: Detecting Camouflaged Objects the Hard Way: Qi Jia,

Shuilian Yao,

Yu Liu,

Xin Fan,

Risheng Liu,

Zhongxuan Luo; [pdf]
[bibtex]
@InProceedings{Jia_2022_CVPR, author = {Jia, Qi and Yao, Shuilian and Liu, Yu and Fan, Xin and Liu, Risheng and Luo, Zhongxuan}, title = {Segment, Magnify and Reiterate: Detecting Camouflaged Objects the Hard Way}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {4713-4722} }
SIMBAR: Single Image-Based Scene Relighting for Effective Data Augmentation for Automated Driving Vision Tasks: Xianling Zhang,

Nathan Tseng,

Ameerah Syed,

Rohan Bhasin,

Nikita Jaipuria; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhang_2022_CVPR, author = {Zhang, Xianling and Tseng, Nathan and Syed, Ameerah and Bhasin, Rohan and Jaipuria, Nikita}, title = {SIMBAR: Single Image-Based Scene Relighting for Effective Data Augmentation for Automated Driving Vision Tasks}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {3718-3728} }
Multi-Label Classification With Partial Annotations Using Class-Aware Selective Loss: Emanuel Ben-Baruch,

Tal Ridnik,

Itamar Friedman,

Avi Ben-Cohen,

Nadav Zamir,

Asaf Noy,

Lihi Zelnik-Manor; [pdf] [supp]
[bibtex]
@InProceedings{Ben-Baruch_2022_CVPR, author = {Ben-Baruch, Emanuel and Ridnik, Tal and Friedman, Itamar and Ben-Cohen, Avi and Zamir, Nadav and Noy, Asaf and Zelnik-Manor, Lihi}, title = {Multi-Label Classification With Partial Annotations Using Class-Aware Selective Loss}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {4764-4772} }
Weakly-Supervised Metric Learning With Cross-Module Communications for the Classification of Anterior Chamber Angle Images: Jingqi Huang,

Yue Ning,

Dong Nie,

Linan Guan,

Xiping Jia; [pdf] [supp]
[bibtex]
@InProceedings{Huang_2022_CVPR, author = {Huang, Jingqi and Ning, Yue and Nie, Dong and Guan, Linan and Jia, Xiping}, title = {Weakly-Supervised Metric Learning With Cross-Module Communications for the Classification of Anterior Chamber Angle Images}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {752-762} }
Rethinking Semantic Segmentation: A Prototype View: Tianfei Zhou,

Wenguan Wang,

Ender Konukoglu,

Luc Van Gool; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhou_2022_CVPR, author = {Zhou, Tianfei and Wang, Wenguan and Konukoglu, Ender and Van Gool, Luc}, title = {Rethinking Semantic Segmentation: A Prototype View}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {2582-2593} }
Cross-Model Pseudo-Labeling for Semi-Supervised Action Recognition: Yinghao Xu,

Fangyun Wei,

Xiao Sun,

Ceyuan Yang,

Yujun Shen,

Bo Dai,

Bolei Zhou,

Stephen Lin; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Xu_2022_CVPR, author = {Xu, Yinghao and Wei, Fangyun and Sun, Xiao and Yang, Ceyuan and Shen, Yujun and Dai, Bo and Zhou, Bolei and Lin, Stephen}, title = {Cross-Model Pseudo-Labeling for Semi-Supervised Action Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {2959-2968} }
UMT: Unified Multi-Modal Transformers for Joint Video Moment Retrieval and Highlight Detection: Ye Liu,

Siyuan Li,

Yang Wu,

Chang-Wen Chen,

Ying Shan,

Xiaohu Qie; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Liu_2022_CVPR, author = {Liu, Ye and Li, Siyuan and Wu, Yang and Chen, Chang-Wen and Shan, Ying and Qie, Xiaohu}, title = {UMT: Unified Multi-Modal Transformers for Joint Video Moment Retrieval and Highlight Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {3042-3051} }
Image Disentanglement Autoencoder for Steganography Without Embedding: Xiyao Liu,

Ziping Ma,

Junxing Ma,

Jian Zhang,

Gerald Schaefer,

Hui Fang; [pdf]
[bibtex]
@InProceedings{Liu_2022_CVPR, author = {Liu, Xiyao and Ma, Ziping and Ma, Junxing and Zhang, Jian and Schaefer, Gerald and Fang, Hui}, title = {Image Disentanglement Autoencoder for Steganography Without Embedding}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {2303-2312} }
PolyWorld: Polygonal Building Extraction With Graph Neural Networks in Satellite Images: Stefano Zorzi,

Shabab Bazrafkan,

Stefan Habenschuss,

Friedrich Fraundorfer; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zorzi_2022_CVPR, author = {Zorzi, Stefano and Bazrafkan, Shabab and Habenschuss, Stefan and Fraundorfer, Friedrich}, title = {PolyWorld: Polygonal Building Extraction With Graph Neural Networks in Satellite Images}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {1848-1857} }
Learning Pixel-Level Distinctions for Video Highlight Detection: Fanyue Wei,

Biao Wang,

Tiezheng Ge,

Yuning Jiang,

Wen Li,

Lixin Duan; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wei_2022_CVPR, author = {Wei, Fanyue and Wang, Biao and Ge, Tiezheng and Jiang, Yuning and Li, Wen and Duan, Lixin}, title = {Learning Pixel-Level Distinctions for Video Highlight Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {3073-3082} }
Noise Distribution Adaptive Self-Supervised Image Denoising Using Tweedie Distribution and Score Matching: Kwanyoung Kim,

Taesung Kwon,

Jong Chul Ye; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kim_2022_CVPR, author = {Kim, Kwanyoung and Kwon, Taesung and Ye, Jong Chul}, title = {Noise Distribution Adaptive Self-Supervised Image Denoising Using Tweedie Distribution and Score Matching}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {2008-2016} }
KNN Local Attention for Image Restoration: Hunsang Lee,

Hyesong Choi,

Kwanghoon Sohn,

Dongbo Min; [pdf] [supp]
[bibtex]
@InProceedings{Lee_2022_CVPR, author = {Lee, Hunsang and Choi, Hyesong and Sohn, Kwanghoon and Min, Dongbo}, title = {KNN Local Attention for Image Restoration}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {2139-2149} }
Face Relighting With Geometrically Consistent Shadows: Andrew Hou,

Michel Sarkis,

Ning Bi,

Yiying Tong,

Xiaoming Liu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Hou_2022_CVPR, author = {Hou, Andrew and Sarkis, Michel and Bi, Ning and Tong, Yiying and Liu, Xiaoming}, title = {Face Relighting With Geometrically Consistent Shadows}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {4217-4226} }
Open-Set Text Recognition via Character-Context Decoupling: Chang Liu,

Chun Yang,

Xu-Cheng Yin; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Liu_2022_CVPR, author = {Liu, Chang and Yang, Chun and Yin, Xu-Cheng}, title = {Open-Set Text Recognition via Character-Context Decoupling}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {4523-4532} }
Image Animation With Perturbed Masks: Yoav Shalev,

Lior Wolf; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Shalev_2022_CVPR, author = {Shalev, Yoav and Wolf, Lior}, title = {Image Animation With Perturbed Masks}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {3647-3656} }
Domain Generalization via Shuffled Style Assembly for Face Anti-Spoofing: Zhuo Wang,

Zezheng Wang,

Zitong Yu,

Weihong Deng,

Jiahong Li,

Tingting Gao,

Zhongyuan Wang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2022_CVPR, author = {Wang, Zhuo and Wang, Zezheng and Yu, Zitong and Deng, Weihong and Li, Jiahong and Gao, Tingting and Wang, Zhongyuan}, title = {Domain Generalization via Shuffled Style Assembly for Face Anti-Spoofing}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {4123-4133} }
OcclusionFusion: Occlusion-Aware Motion Estimation for Real-Time Dynamic 3D Reconstruction: Wenbin Lin,

Chengwei Zheng,

Jun-Hai Yong,

Feng Xu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Lin_2022_CVPR, author = {Lin, Wenbin and Zheng, Chengwei and Yong, Jun-Hai and Xu, Feng}, title = {OcclusionFusion: Occlusion-Aware Motion Estimation for Real-Time Dynamic 3D Reconstruction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {1736-1745} }
MonoScene: Monocular 3D Semantic Scene Completion: Anh-Quan Cao,

Raoul de Charette; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Cao_2022_CVPR, author = {Cao, Anh-Quan and de Charette, Raoul}, title = {MonoScene: Monocular 3D Semantic Scene Completion}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {3991-4001} }
What's in Your Hands? 3D Reconstruction of Generic Objects in Hands: Yufei Ye,

Abhinav Gupta,

Shubham Tulsiani; [pdf] [supp]
[bibtex]
@InProceedings{Ye_2022_CVPR, author = {Ye, Yufei and Gupta, Abhinav and Tulsiani, Shubham}, title = {What's in Your Hands? 3D Reconstruction of Generic Objects in Hands}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {3895-3905} }
RecDis-SNN: Rectifying Membrane Potential Distribution for Directly Training Spiking Neural Networks: Yufei Guo,

Xinyi Tong,

Yuanpei Chen,

Liwen Zhang,

Xiaode Liu,

Zhe Ma,

Xuhui Huang; [pdf]
[bibtex]
@InProceedings{Guo_2022_CVPR, author = {Guo, Yufei and Tong, Xinyi and Chen, Yuanpei and Zhang, Liwen and Liu, Xiaode and Ma, Zhe and Huang, Xuhui}, title = {RecDis-SNN: Rectifying Membrane Potential Distribution for Directly Training Spiking Neural Networks}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {326-335} }
Human-Aware Object Placement for Visual Environment Reconstruction: Hongwei Yi,

Chun-Hao P. Huang,

Dimitrios Tzionas,

Muhammed Kocabas,

Mohamed Hassan,

Siyu Tang,

Justus Thies,

Michael J. Black; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yi_2022_CVPR, author = {Yi, Hongwei and Huang, Chun-Hao P. and Tzionas, Dimitrios and Kocabas, Muhammed and Hassan, Mohamed and Tang, Siyu and Thies, Justus and Black, Michael J.}, title = {Human-Aware Object Placement for Visual Environment Reconstruction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {3959-3970} }
X-Pool: Cross-Modal Language-Video Attention for Text-Video Retrieval: Satya Krishna Gorti,

Noël Vouitsis,

Junwei Ma,

Keyvan Golestan,

Maksims Volkovs,

Animesh Garg,

Guangwei Yu; [pdf] [supp]
[bibtex]
@InProceedings{Gorti_2022_CVPR, author = {Gorti, Satya Krishna and Vouitsis, No\"el and Ma, Junwei and Golestan, Keyvan and Volkovs, Maksims and Garg, Animesh and Yu, Guangwei}, title = {X-Pool: Cross-Modal Language-Video Attention for Text-Video Retrieval}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {5006-5015} }
Towards Weakly-Supervised Text Spotting Using a Multi-Task Transformer: Yair Kittenplon,

Inbal Lavi,

Sharon Fogel,

Yarin Bar,

R. Manmatha,

Pietro Perona; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kittenplon_2022_CVPR, author = {Kittenplon, Yair and Lavi, Inbal and Fogel, Sharon and Bar, Yarin and Manmatha, R. and Perona, Pietro}, title = {Towards Weakly-Supervised Text Spotting Using a Multi-Task Transformer}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {4604-4613} }
Gated2Gated: Self-Supervised Depth Estimation From Gated Images: Amanpreet Walia,

Stefanie Walz,

Mario Bijelic,

Fahim Mannan,

Frank Julca-Aguilar,

Michael Langer,

Werner Ritter,

Felix Heide; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Walia_2022_CVPR, author = {Walia, Amanpreet and Walz, Stefanie and Bijelic, Mario and Mannan, Fahim and Julca-Aguilar, Frank and Langer, Michael and Ritter, Werner and Heide, Felix}, title = {Gated2Gated: Self-Supervised Depth Estimation From Gated Images}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {2811-2821} }
Mask Transfiner for High-Quality Instance Segmentation: Lei Ke,

Martin Danelljan,

Xia Li,

Yu-Wing Tai,

Chi-Keung Tang,

Fisher Yu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ke_2022_CVPR, author = {Ke, Lei and Danelljan, Martin and Li, Xia and Tai, Yu-Wing and Tang, Chi-Keung and Yu, Fisher}, title = {Mask Transfiner for High-Quality Instance Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {4412-4421} }
End-to-End Reconstruction-Classification Learning for Face Forgery Detection: Junyi Cao,

Chao Ma,

Taiping Yao,

Shen Chen,

Shouhong Ding,

Xiaokang Yang; [pdf] [supp]
[bibtex]
@InProceedings{Cao_2022_CVPR, author = {Cao, Junyi and Ma, Chao and Yao, Taiping and Chen, Shen and Ding, Shouhong and Yang, Xiaokang}, title = {End-to-End Reconstruction-Classification Learning for Face Forgery Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {4113-4122} }
Watch It Move: Unsupervised Discovery of 3D Joints for Re-Posing of Articulated Objects: Atsuhiro Noguchi,

Umar Iqbal,

Jonathan Tremblay,

Tatsuya Harada,

Orazio Gallo; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Noguchi_2022_CVPR, author = {Noguchi, Atsuhiro and Iqbal, Umar and Tremblay, Jonathan and Harada, Tatsuya and Gallo, Orazio}, title = {Watch It Move: Unsupervised Discovery of 3D Joints for Re-Posing of Articulated Objects}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {3677-3687} }
Event-Based Video Reconstruction via Potential-Assisted Spiking Neural Network: Lin Zhu,

Xiao Wang,

Yi Chang,

Jianing Li,

Tiejun Huang,

Yonghong Tian; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhu_2022_CVPR, author = {Zhu, Lin and Wang, Xiao and Chang, Yi and Li, Jianing and Huang, Tiejun and Tian, Yonghong}, title = {Event-Based Video Reconstruction via Potential-Assisted Spiking Neural Network}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {3594-3604} }
Efficient Maximal Coding Rate Reduction by Variational Forms: Christina Baek,

Ziyang Wu,

Kwan Ho Ryan Chan,

Tianjiao Ding,

Yi Ma,

Benjamin D. Haeffele; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Baek_2022_CVPR, author = {Baek, Christina and Wu, Ziyang and Chan, Kwan Ho Ryan and Ding, Tianjiao and Ma, Yi and Haeffele, Benjamin D.}, title = {Efficient Maximal Coding Rate Reduction by Variational Forms}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {500-508} }
AutoLoss-GMS: Searching Generalized Margin-Based Softmax Loss Function for Person Re-Identification: Hongyang Gu,

Jianmin Li,

Guangyuan Fu,

Chifong Wong,

Xinghao Chen,

Jun Zhu; [pdf] [supp]
[bibtex]
@InProceedings{Gu_2022_CVPR, author = {Gu, Hongyang and Li, Jianmin and Fu, Guangyuan and Wong, Chifong and Chen, Xinghao and Zhu, Jun}, title = {AutoLoss-GMS: Searching Generalized Margin-Based Softmax Loss Function for Person Re-Identification}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {4744-4753} }
Sound-Guided Semantic Image Manipulation: Seung Hyun Lee,

Wonseok Roh,

Wonmin Byeon,

Sang Ho Yoon,

Chanyoung Kim,

Jinkyu Kim,

Sangpil Kim; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Lee_2022_CVPR, author = {Lee, Seung Hyun and Roh, Wonseok and Byeon, Wonmin and Yoon, Sang Ho and Kim, Chanyoung and Kim, Jinkyu and Kim, Sangpil}, title = {Sound-Guided Semantic Image Manipulation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {3377-3386} }
End-to-End Human-Gaze-Target Detection With Transformers: Danyang Tu,

Xiongkuo Min,

Huiyu Duan,

Guodong Guo,

Guangtao Zhai,

Wei Shen; [pdf] [arXiv]
[bibtex]
@InProceedings{Tu_2022_CVPR, author = {Tu, Danyang and Min, Xiongkuo and Duan, Huiyu and Guo, Guodong and Zhai, Guangtao and Shen, Wei}, title = {End-to-End Human-Gaze-Target Detection With Transformers}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {2202-2210} }
Compositional Temporal Grounding With Structured Variational Cross-Graph Correspondence Learning: Juncheng Li,

Junlin Xie,

Long Qian,

Linchao Zhu,

Siliang Tang,

Fei Wu,

Yi Yang,

Yueting Zhuang,

Xin Eric Wang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Li_2022_CVPR, author = {Li, Juncheng and Xie, Junlin and Qian, Long and Zhu, Linchao and Tang, Siliang and Wu, Fei and Yang, Yi and Zhuang, Yueting and Wang, Xin Eric}, title = {Compositional Temporal Grounding With Structured Variational Cross-Graph Correspondence Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {3032-3041} }
Future Transformer for Long-Term Action Anticipation: Dayoung Gong,

Joonseok Lee,

Manjin Kim,

Seong Jong Ha,

Minsu Cho; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Gong_2022_CVPR, author = {Gong, Dayoung and Lee, Joonseok and Kim, Manjin and Ha, Seong Jong and Cho, Minsu}, title = {Future Transformer for Long-Term Action Anticipation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {3052-3061} }
Self-Supervised Video Transformer: Kanchana Ranasinghe,

Muzammal Naseer,

Salman Khan,

Fahad Shahbaz Khan,

Michael S. Ryoo; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ranasinghe_2022_CVPR, author = {Ranasinghe, Kanchana and Naseer, Muzammal and Khan, Salman and Khan, Fahad Shahbaz and Ryoo, Michael S.}, title = {Self-Supervised Video Transformer}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {2874-2884} }
AutoRF: Learning 3D Object Radiance Fields From Single View Observations: Norman Müller,

Andrea Simonelli,

Lorenzo Porzi,

Samuel Rota Bulò,

Matthias Nießner,

Peter Kontschieder; [pdf] [supp]
[bibtex]
@InProceedings{Muller_2022_CVPR, author = {M\"uller, Norman and Simonelli, Andrea and Porzi, Lorenzo and Bul\`o, Samuel Rota and Nie{\ss}ner, Matthias and Kontschieder, Peter}, title = {AutoRF: Learning 3D Object Radiance Fields From Single View Observations}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {3971-3980} }
Condensing CNNs With Partial Differential Equations: Anil Kag,

Venkatesh Saligrama; [pdf] [supp]
[bibtex]
@InProceedings{Kag_2022_CVPR, author = {Kag, Anil and Saligrama, Venkatesh}, title = {Condensing CNNs With Partial Differential Equations}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {610-619} }
Unsupervised Hierarchical Semantic Segmentation With Multiview Cosegmentation and Clustering Transformers: Tsung-Wei Ke,

Jyh-Jing Hwang,

Yunhui Guo,

Xudong Wang,

Stella X. Yu; [pdf] [arXiv]
[bibtex]
@InProceedings{Ke_2022_CVPR, author = {Ke, Tsung-Wei and Hwang, Jyh-Jing and Guo, Yunhui and Wang, Xudong and Yu, Stella X.}, title = {Unsupervised Hierarchical Semantic Segmentation With Multiview Cosegmentation and Clustering Transformers}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {2571-2581} }
Kubric: A Scalable Dataset Generator: Klaus Greff,

Francois Belletti,

Lucas Beyer,

Carl Doersch,

Yilun Du,

Daniel Duckworth,

David J. Fleet,

Dan Gnanapragasam,

Florian Golemo,

Charles Herrmann,

Thomas Kipf,

Abhijit Kundu,

Dmitry Lagun,

Issam Laradji,

Hsueh-Ti (Derek) Liu,

Henning Meyer,

Yishu Miao,

Derek Nowrouzezahrai,

Cengiz Oztireli,

Etienne Pot,

Noha Radwan,

Daniel Rebain,

Sara Sabour,

Mehdi S. M. Sajjadi,

Matan Sela,

Vincent Sitzmann,

Austin Stone,

Deqing Sun,

Suhani Vora,

Ziyu Wang,

Tianhao Wu,

Kwang Moo Yi,

Fangcheng Zhong,

Andrea Tagliasacchi; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Greff_2022_CVPR, author = {Greff, Klaus and Belletti, Francois and Beyer, Lucas and Doersch, Carl and Du, Yilun and Duckworth, Daniel and Fleet, David J. and Gnanapragasam, Dan and Golemo, Florian and Herrmann, Charles and Kipf, Thomas and Kundu, Abhijit and Lagun, Dmitry and Laradji, Issam and Liu, Hsueh-Ti (Derek) and Meyer, Henning and Miao, Yishu and Nowrouzezahrai, Derek and Oztireli, Cengiz and Pot, Etienne and Radwan, Noha and Rebain, Daniel and Sabour, Sara and Sajjadi, Mehdi S. M. and Sela, Matan and Sitzmann, Vincent and Stone, Austin and Sun, Deqing and Vora, Suhani and Wang, Ziyu and Wu, Tianhao and Yi, Kwang Moo and Zhong, Fangcheng and Tagliasacchi, Andrea}, title = {Kubric: A Scalable Dataset Generator}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {3749-3761} }
Unpaired Deep Image Deraining Using Dual Contrastive Learning: Xiang Chen,

Jinshan Pan,

Kui Jiang,

Yufeng Li,

Yufeng Huang,

Caihua Kong,

Longgang Dai,

Zhentao Fan; [pdf] [arXiv]
[bibtex]
@InProceedings{Chen_2022_CVPR, author = {Chen, Xiang and Pan, Jinshan and Jiang, Kui and Li, Yufeng and Huang, Yufeng and Kong, Caihua and Dai, Longgang and Fan, Zhentao}, title = {Unpaired Deep Image Deraining Using Dual Contrastive Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {2017-2026} }
TransFusion: Robust LiDAR-Camera Fusion for 3D Object Detection With Transformers: Xuyang Bai,

Zeyu Hu,

Xinge Zhu,

Qingqiu Huang,

Yilun Chen,

Hongbo Fu,

Chiew-Lan Tai; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Bai_2022_CVPR, author = {Bai, Xuyang and Hu, Zeyu and Zhu, Xinge and Huang, Qingqiu and Chen, Yilun and Fu, Hongbo and Tai, Chiew-Lan}, title = {TransFusion: Robust LiDAR-Camera Fusion for 3D Object Detection With Transformers}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {1090-1099} }
Complex Video Action Reasoning via Learnable Markov Logic Network: Yang Jin,

Linchao Zhu,

Yadong Mu; [pdf] [supp]
[bibtex]
@InProceedings{Jin_2022_CVPR, author = {Jin, Yang and Zhu, Linchao and Mu, Yadong}, title = {Complex Video Action Reasoning via Learnable Markov Logic Network}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {3242-3251} }
Per-Clip Video Object Segmentation: Kwanyong Park,

Sanghyun Woo,

Seoung Wug Oh,

In So Kweon,

Joon-Young Lee; [pdf] [supp]
[bibtex]
@InProceedings{Park_2022_CVPR, author = {Park, Kwanyong and Woo, Sanghyun and Oh, Seoung Wug and Kweon, In So and Lee, Joon-Young}, title = {Per-Clip Video Object Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {1352-1361} }
Coarse-To-Fine Feature Mining for Video Semantic Segmentation: Guolei Sun,

Yun Liu,

Henghui Ding,

Thomas Probst,

Luc Van Gool; [pdf] [arXiv]
[bibtex]
@InProceedings{Sun_2022_CVPR, author = {Sun, Guolei and Liu, Yun and Ding, Henghui and Probst, Thomas and Van Gool, Luc}, title = {Coarse-To-Fine Feature Mining for Video Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {3126-3137} }
Compressing Models With Few Samples: Mimicking Then Replacing: Huanyu Wang,

Junjie Liu,

Xin Ma,

Yang Yong,

Zhenhua Chai,

Jianxin Wu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2022_CVPR, author = {Wang, Huanyu and Liu, Junjie and Ma, Xin and Yong, Yang and Chai, Zhenhua and Wu, Jianxin}, title = {Compressing Models With Few Samples: Mimicking Then Replacing}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {701-710} }
Zoom in and Out: A Mixed-Scale Triplet Network for Camouflaged Object Detection: Youwei Pang,

Xiaoqi Zhao,

Tian-Zhu Xiang,

Lihe Zhang,

Huchuan Lu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Pang_2022_CVPR, author = {Pang, Youwei and Zhao, Xiaoqi and Xiang, Tian-Zhu and Zhang, Lihe and Lu, Huchuan}, title = {Zoom in and Out: A Mixed-Scale Triplet Network for Camouflaged Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {2160-2170} }
MISF: Multi-Level Interactive Siamese Filtering for High-Fidelity Image Inpainting: Xiaoguang Li,

Qing Guo,

Di Lin,

Ping Li,

Wei Feng,

Song Wang; [pdf] [arXiv]
[bibtex]
@InProceedings{Li_2022_CVPR, author = {Li, Xiaoguang and Guo, Qing and Lin, Di and Li, Ping and Feng, Wei and Wang, Song}, title = {MISF: Multi-Level Interactive Siamese Filtering for High-Fidelity Image Inpainting}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {1869-1878} }
An Efficient Training Approach for Very Large Scale Face Recognition: Kai Wang,

Shuo Wang,

Panpan Zhang,

Zhipeng Zhou,

Zheng Zhu,

Xiaobo Wang,

Xiaojiang Peng,

Baigui Sun,

Hao Li,

Yang You; [pdf] [arXiv]
[bibtex]
@InProceedings{Wang_2022_CVPR, author = {Wang, Kai and Wang, Shuo and Zhang, Panpan and Zhou, Zhipeng and Zhu, Zheng and Wang, Xiaobo and Peng, Xiaojiang and Sun, Baigui and Li, Hao and You, Yang}, title = {An Efficient Training Approach for Very Large Scale Face Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {4083-4092} }
Long-Term Video Frame Interpolation via Feature Propagation: Dawit Mureja Argaw,

In So Kweon; [pdf] [arXiv]
[bibtex]
@InProceedings{Argaw_2022_CVPR, author = {Argaw, Dawit Mureja and Kweon, In So}, title = {Long-Term Video Frame Interpolation via Feature Propagation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {3543-3552} }
Group Contextualization for Video Recognition: Yanbin Hao,

Hao Zhang,

Chong-Wah Ngo,

Xiangnan He; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Hao_2022_CVPR, author = {Hao, Yanbin and Zhang, Hao and Ngo, Chong-Wah and He, Xiangnan}, title = {Group Contextualization for Video Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {928-938} }
Single-Domain Generalized Object Detection in Urban Scene via Cyclic-Disentangled Self-Distillation: Aming Wu,

Cheng Deng; [pdf] [supp]
[bibtex]
@InProceedings{Wu_2022_CVPR, author = {Wu, Aming and Deng, Cheng}, title = {Single-Domain Generalized Object Detection in Urban Scene via Cyclic-Disentangled Self-Distillation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {847-856} }
Rethinking Bayesian Deep Learning Methods for Semi-Supervised Volumetric Medical Image Segmentation: Jianfeng Wang,

Thomas Lukasiewicz; [pdf] [supp]
[bibtex]
@InProceedings{Wang_2022_CVPR, author = {Wang, Jianfeng and Lukasiewicz, Thomas}, title = {Rethinking Bayesian Deep Learning Methods for Semi-Supervised Volumetric Medical Image Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {182-190} }
Continual Learning With Lifelong Vision Transformer: Zhen Wang,

Liu Liu,

Yiqun Duan,

Yajing Kong,

Dacheng Tao; [pdf] [supp]
[bibtex]
@InProceedings{Wang_2022_CVPR, author = {Wang, Zhen and Liu, Liu and Duan, Yiqun and Kong, Yajing and Tao, Dacheng}, title = {Continual Learning With Lifelong Vision Transformer}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {171-181} }
Accurate 3D Body Shape Regression Using Metric and Semantic Attributes: Vasileios Choutas,

Lea Müller,

Chun-Hao P. Huang,

Siyu Tang,

Dimitrios Tzionas,

Michael J. Black; [pdf] [supp]
[bibtex]
@InProceedings{Choutas_2022_CVPR, author = {Choutas, Vasileios and M\"uller, Lea and Huang, Chun-Hao P. and Tang, Siyu and Tzionas, Dimitrios and Black, Michael J.}, title = {Accurate 3D Body Shape Regression Using Metric and Semantic Attributes}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {2718-2728} }
Privacy-Preserving Online AutoML for Domain-Specific Face Detection: Chenqian Yan,

Yuge Zhang,

Quanlu Zhang,

Yaming Yang,

Xinyang Jiang,

Yuqing Yang,

Baoyuan Wang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yan_2022_CVPR, author = {Yan, Chenqian and Zhang, Yuge and Zhang, Quanlu and Yang, Yaming and Jiang, Xinyang and Yang, Yuqing and Wang, Baoyuan}, title = {Privacy-Preserving Online AutoML for Domain-Specific Face Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {4134-4144} }
Self-Augmented Unpaired Image Dehazing via Density and Depth Decomposition: Yang Yang,

Chaoyue Wang,

Risheng Liu,

Lin Zhang,

Xiaojie Guo,

Dacheng Tao; [pdf]
[bibtex]
@InProceedings{Yang_2022_CVPR, author = {Yang, Yang and Wang, Chaoyue and Liu, Risheng and Zhang, Lin and Guo, Xiaojie and Tao, Dacheng}, title = {Self-Augmented Unpaired Image Dehazing via Density and Depth Decomposition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {2037-2046} }
Sparse Object-Level Supervision for Instance Segmentation With Pixel Embeddings: Adrian Wolny,

Qin Yu,

Constantin Pape,

Anna Kreshuk; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wolny_2022_CVPR, author = {Wolny, Adrian and Yu, Qin and Pape, Constantin and Kreshuk, Anna}, title = {Sparse Object-Level Supervision for Instance Segmentation With Pixel Embeddings}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {4402-4411} }
How Much More Data Do I Need? Estimating Requirements for Downstream Tasks: Rafid Mahmood,

James Lucas,

David Acuna,

Daiqing Li,

Jonah Philion,

Jose M. Alvarez,

Zhiding Yu,

Sanja Fidler,

Marc T. Law; [pdf] [supp]
[bibtex]
@InProceedings{Mahmood_2022_CVPR, author = {Mahmood, Rafid and Lucas, James and Acuna, David and Li, Daiqing and Philion, Jonah and Alvarez, Jose M. and Yu, Zhiding and Fidler, Sanja and Law, Marc T.}, title = {How Much More Data Do I Need? Estimating Requirements for Downstream Tasks}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {275-284} }
The Implicit Values of a Good Hand Shake: Handheld Multi-Frame Neural Depth Refinement: Ilya Chugunov,

Yuxuan Zhang,

Zhihao Xia,

Xuaner Zhang,

Jiawen Chen,

Felix Heide; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chugunov_2022_CVPR, author = {Chugunov, Ilya and Zhang, Yuxuan and Xia, Zhihao and Zhang, Xuaner and Chen, Jiawen and Heide, Felix}, title = {The Implicit Values of a Good Hand Shake: Handheld Multi-Frame Neural Depth Refinement}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {2852-2862} }
Towards Unsupervised Domain Generalization: Xingxuan Zhang,

Linjun Zhou,

Renzhe Xu,

Peng Cui,

Zheyan Shen,

Haoxin Liu; [pdf] [arXiv]
[bibtex]
@InProceedings{Zhang_2022_CVPR, author = {Zhang, Xingxuan and Zhou, Linjun and Xu, Renzhe and Cui, Peng and Shen, Zheyan and Liu, Haoxin}, title = {Towards Unsupervised Domain Generalization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {4910-4920} }
HyperTransformer: A Textural and Spectral Feature Fusion Transformer for Pansharpening: Wele Gedara Chaminda Bandara,

Vishal M. Patel; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Bandara_2022_CVPR, author = {Bandara, Wele Gedara Chaminda and Patel, Vishal M.}, title = {HyperTransformer: A Textural and Spectral Feature Fusion Transformer for Pansharpening}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {1767-1777} }
Segment-Fusion: Hierarchical Context Fusion for Robust 3D Semantic Segmentation: Anirud Thyagharajan,

Benjamin Ummenhofer,

Prashant Laddha,

Om Ji Omer,

Sreenivas Subramoney; [pdf] [supp]
[bibtex]
@InProceedings{Thyagharajan_2022_CVPR, author = {Thyagharajan, Anirud and Ummenhofer, Benjamin and Laddha, Prashant and Omer, Om Ji and Subramoney, Sreenivas}, title = {Segment-Fusion: Hierarchical Context Fusion for Robust 3D Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {1236-1245} }
MonoGround: Detecting Monocular 3D Objects From the Ground: Zequn Qin,

Xi Li; [pdf]
[bibtex]
@InProceedings{Qin_2022_CVPR, author = {Qin, Zequn and Li, Xi}, title = {MonoGround: Detecting Monocular 3D Objects From the Ground}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {3793-3802} }
Semiconductor Defect Detection by Hybrid Classical-Quantum Deep Learning: Yuan-Fu Yang,

Min Sun; [pdf] [supp]
[bibtex]
@InProceedings{Yang_2022_CVPR, author = {Yang, Yuan-Fu and Sun, Min}, title = {Semiconductor Defect Detection by Hybrid Classical-Quantum Deep Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {2323-2332} }
StyleGAN-V: A Continuous Video Generator With the Price, Image Quality and Perks of StyleGAN2: Ivan Skorokhodov,

Sergey Tulyakov,

Mohamed Elhoseiny; [pdf] [supp]
[bibtex]
@InProceedings{Skorokhodov_2022_CVPR, author = {Skorokhodov, Ivan and Tulyakov, Sergey and Elhoseiny, Mohamed}, title = {StyleGAN-V: A Continuous Video Generator With the Price, Image Quality and Perks of StyleGAN2}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {3626-3636} }
Pin the Memory: Learning To Generalize Semantic Segmentation: Jin Kim,

Jiyoung Lee,

Jungin Park,

Dongbo Min,

Kwanghoon Sohn; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kim_2022_CVPR, author = {Kim, Jin and Lee, Jiyoung and Park, Jungin and Min, Dongbo and Sohn, Kwanghoon}, title = {Pin the Memory: Learning To Generalize Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {4350-4360} }
Iterative Deep Homography Estimation: Si-Yuan Cao,

Jianxin Hu,

Zehua Sheng,

Hui-Liang Shen; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Cao_2022_CVPR, author = {Cao, Si-Yuan and Hu, Jianxin and Sheng, Zehua and Shen, Hui-Liang}, title = {Iterative Deep Homography Estimation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {1879-1888} }
Colar: Effective and Efficient Online Action Detection by Consulting Exemplars: Le Yang,

Junwei Han,

Dingwen Zhang; [pdf] [arXiv]
[bibtex]
@InProceedings{Yang_2022_CVPR, author = {Yang, Le and Han, Junwei and Zhang, Dingwen}, title = {Colar: Effective and Efficient Online Action Detection by Consulting Exemplars}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {3160-3169} }
Gaussian Process Modeling of Approximate Inference Errors for Variational Autoencoders: Minyoung Kim; [pdf] [supp]
[bibtex]
@InProceedings{Kim_2022_CVPR, author = {Kim, Minyoung}, title = {Gaussian Process Modeling of Approximate Inference Errors for Variational Autoencoders}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {244-253} }
SoftGroup for 3D Instance Segmentation on Point Clouds: Thang Vu,

Kookhoi Kim,

Tung M. Luu,

Thanh Nguyen,

Chang D. Yoo; [pdf] [arXiv]
[bibtex]
@InProceedings{Vu_2022_CVPR, author = {Vu, Thang and Kim, Kookhoi and Luu, Tung M. and Nguyen, Thanh and Yoo, Chang D.}, title = {SoftGroup for 3D Instance Segmentation on Point Clouds}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {2708-2717} }
SharpContour: A Contour-Based Boundary Refinement Approach for Efficient and Accurate Instance Segmentation: Chenming Zhu,

Xuanye Zhang,

Yanran Li,

Liangdong Qiu,

Kai Han,

Xiaoguang Han; [pdf] [arXiv]
[bibtex]
@InProceedings{Zhu_2022_CVPR, author = {Zhu, Chenming and Zhang, Xuanye and Li, Yanran and Qiu, Liangdong and Han, Kai and Han, Xiaoguang}, title = {SharpContour: A Contour-Based Boundary Refinement Approach for Efficient and Accurate Instance Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {4392-4401} }
Beyond Semantic to Instance Segmentation: Weakly-Supervised Instance Segmentation via Semantic Knowledge Transfer and Self-Refinement: Beomyoung Kim,

YoungJoon Yoo,

Chae Eun Rhee,

Junmo Kim; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kim_2022_CVPR, author = {Kim, Beomyoung and Yoo, YoungJoon and Rhee, Chae Eun and Kim, Junmo}, title = {Beyond Semantic to Instance Segmentation: Weakly-Supervised Instance Segmentation via Semantic Knowledge Transfer and Self-Refinement}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {4278-4287} }
EDTER: Edge Detection With Transformer: Mengyang Pu,

Yaping Huang,

Yuming Liu,

Qingji Guan,

Haibin Ling; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Pu_2022_CVPR, author = {Pu, Mengyang and Huang, Yaping and Liu, Yuming and Guan, Qingji and Ling, Haibin}, title = {EDTER: Edge Detection With Transformer}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {1402-1412} }
JIFF: Jointly-Aligned Implicit Face Function for High Quality Single View Clothed Human Reconstruction: Yukang Cao,

Guanying Chen,

Kai Han,

Wenqi Yang,

Kwan-Yee K. Wong; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Cao_2022_CVPR, author = {Cao, Yukang and Chen, Guanying and Han, Kai and Yang, Wenqi and Wong, Kwan-Yee K.}, title = {JIFF: Jointly-Aligned Implicit Face Function for High Quality Single View Clothed Human Reconstruction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {2729-2739} }
Semantic-Aware Domain Generalized Segmentation: Duo Peng,

Yinjie Lei,

Munawar Hayat,

Yulan Guo,

Wen Li; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Peng_2022_CVPR, author = {Peng, Duo and Lei, Yinjie and Hayat, Munawar and Guo, Yulan and Li, Wen}, title = {Semantic-Aware Domain Generalized Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {2594-2605} }
Egocentric Scene Understanding via Multimodal Spatial Rectifier: Tien Do,

Khiem Vuong,

Hyun Soo Park; [pdf] [supp]
[bibtex]
@InProceedings{Do_2022_CVPR, author = {Do, Tien and Vuong, Khiem and Park, Hyun Soo}, title = {Egocentric Scene Understanding via Multimodal Spatial Rectifier}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {2832-2841} }
Semi-Supervised Semantic Segmentation Using Unreliable Pseudo-Labels: Yuchao Wang,

Haochen Wang,

Yujun Shen,

Jingjing Fei,

Wei Li,

Guoqiang Jin,

Liwei Wu,

Rui Zhao,

Xinyi Le; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2022_CVPR, author = {Wang, Yuchao and Wang, Haochen and Shen, Yujun and Fei, Jingjing and Li, Wei and Jin, Guoqiang and Wu, Liwei and Zhao, Rui and Le, Xinyi}, title = {Semi-Supervised Semantic Segmentation Using Unreliable Pseudo-Labels}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {4248-4257} }; Back