Papers
- Back
Dual Cross-Attention Learning for Fine-Grained Visual Categorization and Object Re-Identification-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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?-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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-
[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