CVPR 2023 Open Access Repository

Papers

Back
Revisiting Self-Similarity: Structural Embedding for Image Retrieval: Seongwon Lee,

Suhyeon Lee,

Hongje Seong,

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

Long Peng,

Liang Li,

Yang Cao,

Zheng-Jun Zha; [pdf]
[bibtex]
@InProceedings{Wang_2023_CVPR, author = {Wang, Yang and Peng, Long and Li, Liang and Cao, Yang and Zha, Zheng-Jun}, title = {Decoupling-and-Aggregating for Image Exposure Correction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {18115-18124} }
MSeg3D: Multi-Modal 3D Semantic Segmentation for Autonomous Driving: Jiale Li,

Hang Dai,

Hao Han,

Yong Ding; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Li_2023_CVPR, author = {Li, Jiale and Dai, Hang and Han, Hao and Ding, Yong}, title = {MSeg3D: Multi-Modal 3D Semantic Segmentation for Autonomous Driving}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {21694-21704} }
Dynamically Instance-Guided Adaptation: A Backward-Free Approach for Test-Time Domain Adaptive Semantic Segmentation: Wei Wang,

Zhun Zhong,

Weijie Wang,

Xi Chen,

Charles Ling,

Boyu Wang,

Nicu Sebe; [pdf] [supp]
[bibtex]
@InProceedings{Wang_2023_CVPR, author = {Wang, Wei and Zhong, Zhun and Wang, Weijie and Chen, Xi and Ling, Charles and Wang, Boyu and Sebe, Nicu}, title = {Dynamically Instance-Guided Adaptation: A Backward-Free Approach for Test-Time Domain Adaptive Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {24090-24099} }
LANIT: Language-Driven Image-to-Image Translation for Unlabeled Data: Jihye Park,

Sunwoo Kim,

Soohyun Kim,

Seokju Cho,

Jaejun Yoo,

Youngjung Uh,

Seungryong Kim; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Park_2023_CVPR, author = {Park, Jihye and Kim, Sunwoo and Kim, Soohyun and Cho, Seokju and Yoo, Jaejun and Uh, Youngjung and Kim, Seungryong}, title = {LANIT: Language-Driven Image-to-Image Translation for Unlabeled Data}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {23401-23411} }
MoLo: Motion-Augmented Long-Short Contrastive Learning for Few-Shot Action Recognition: Xiang Wang,

Shiwei Zhang,

Zhiwu Qing,

Changxin Gao,

Yingya Zhang,

Deli Zhao,

Nong Sang; [pdf] [arXiv]
[bibtex]
@InProceedings{Wang_2023_CVPR, author = {Wang, Xiang and Zhang, Shiwei and Qing, Zhiwu and Gao, Changxin and Zhang, Yingya and Zhao, Deli and Sang, Nong}, title = {MoLo: Motion-Augmented Long-Short Contrastive Learning for Few-Shot Action Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {18011-18021} }
Text-Guided Unsupervised Latent Transformation for Multi-Attribute Image Manipulation: Xiwen Wei,

Zhen Xu,

Cheng Liu,

Si Wu,

Zhiwen Yu,

Hau San Wong; [pdf]
[bibtex]
@InProceedings{Wei_2023_CVPR, author = {Wei, Xiwen and Xu, Zhen and Liu, Cheng and Wu, Si and Yu, Zhiwen and Wong, Hau San}, title = {Text-Guided Unsupervised Latent Transformation for Multi-Attribute Image Manipulation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {19285-19294} }
Contrastive Semi-Supervised Learning for Underwater Image Restoration via Reliable Bank: Shirui Huang,

Keyan Wang,

Huan Liu,

Jun Chen,

Yunsong Li; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Huang_2023_CVPR, author = {Huang, Shirui and Wang, Keyan and Liu, Huan and Chen, Jun and Li, Yunsong}, title = {Contrastive Semi-Supervised Learning for Underwater Image Restoration via Reliable Bank}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {18145-18155} }
Multiclass Confidence and Localization Calibration for Object Detection: Bimsara Pathiraja,

Malitha Gunawardhana,

Muhammad Haris Khan; [pdf] [supp]
[bibtex]
@InProceedings{Pathiraja_2023_CVPR, author = {Pathiraja, Bimsara and Gunawardhana, Malitha and Khan, Muhammad Haris}, title = {Multiclass Confidence and Localization Calibration for Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {19734-19743} }
Query-Dependent Video Representation for Moment Retrieval and Highlight Detection: WonJun Moon,

Sangeek Hyun,

SangUk Park,

Dongchan Park,

Jae-Pil Heo; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Moon_2023_CVPR, author = {Moon, WonJun and Hyun, Sangeek and Park, SangUk and Park, Dongchan and Heo, Jae-Pil}, title = {Query-Dependent Video Representation for Moment Retrieval and Highlight Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {23023-23033} }
Instance-Specific and Model-Adaptive Supervision for Semi-Supervised Semantic Segmentation: Zhen Zhao,

Sifan Long,

Jimin Pi,

Jingdong Wang,

Luping Zhou; [pdf] [arXiv]
[bibtex]
@InProceedings{Zhao_2023_CVPR, author = {Zhao, Zhen and Long, Sifan and Pi, Jimin and Wang, Jingdong and Zhou, Luping}, title = {Instance-Specific and Model-Adaptive Supervision for Semi-Supervised Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {23705-23714} }
X-Pruner: eXplainable Pruning for Vision Transformers: Lu Yu,

Wei Xiang; [pdf]
[bibtex]
@InProceedings{Yu_2023_CVPR, author = {Yu, Lu and Xiang, Wei}, title = {X-Pruner: eXplainable Pruning for Vision Transformers}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {24355-24363} }
Hard Sample Matters a Lot in Zero-Shot Quantization: Huantong Li,

Xiangmiao Wu,

Fanbing Lv,

Daihai Liao,

Thomas H. Li,

Yonggang Zhang,

Bo Han,

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

Mark He Huang,

Xindi Shang,

Zehuan Yuan,

Ying Sun,

Jun Liu; [pdf] [arXiv]
[bibtex]
@InProceedings{Xu_2023_CVPR, author = {Xu, Li and Huang, Mark He and Shang, Xindi and Yuan, Zehuan and Sun, Ying and Liu, Jun}, title = {Meta Compositional Referring Expression Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {19478-19487} }
A Light Weight Model for Active Speaker Detection: Junhua Liao,

Haihan Duan,

Kanghui Feng,

Wanbing Zhao,

Yanbing Yang,

Liangyin Chen; [pdf] [arXiv]
[bibtex]
@InProceedings{Liao_2023_CVPR, author = {Liao, Junhua and Duan, Haihan and Feng, Kanghui and Zhao, Wanbing and Yang, Yanbing and Chen, Liangyin}, title = {A Light Weight Model for Active Speaker Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {22932-22941} }
GCFAgg: Global and Cross-View Feature Aggregation for Multi-View Clustering: Weiqing Yan,

Yuanyang Zhang,

Chenlei Lv,

Chang Tang,

Guanghui Yue,

Liang Liao,

Weisi Lin; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yan_2023_CVPR, author = {Yan, Weiqing and Zhang, Yuanyang and Lv, Chenlei and Tang, Chang and Yue, Guanghui and Liao, Liang and Lin, Weisi}, title = {GCFAgg: Global and Cross-View Feature Aggregation for Multi-View Clustering}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {19863-19872} }
DeGPR: Deep Guided Posterior Regularization for Multi-Class Cell Detection and Counting: Aayush Kumar Tyagi,

Chirag Mohapatra,

Prasenjit Das,

Govind Makharia,

Lalita Mehra,

Prathosh AP,

Mausam; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Tyagi_2023_CVPR, author = {Tyagi, Aayush Kumar and Mohapatra, Chirag and Das, Prasenjit and Makharia, Govind and Mehra, Lalita and AP, Prathosh and Mausam}, title = {DeGPR: Deep Guided Posterior Regularization for Multi-Class Cell Detection and Counting}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {23913-23923} }
SliceMatch: Geometry-Guided Aggregation for Cross-View Pose Estimation: Ted Lentsch,

Zimin Xia,

Holger Caesar,

Julian F. P. Kooij; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Lentsch_2023_CVPR, author = {Lentsch, Ted and Xia, Zimin and Caesar, Holger and Kooij, Julian F. P.}, title = {SliceMatch: Geometry-Guided Aggregation for Cross-View Pose Estimation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {17225-17234} }
Single View Scene Scale Estimation Using Scale Field: Byeong-Uk Lee,

Jianming Zhang,

Yannick Hold-Geoffroy,

In So Kweon; [pdf] [supp]
[bibtex]
@InProceedings{Lee_2023_CVPR, author = {Lee, Byeong-Uk and Zhang, Jianming and Hold-Geoffroy, Yannick and Kweon, In So}, title = {Single View Scene Scale Estimation Using Scale Field}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {21435-21444} }
Learning Semantic-Aware Disentangled Representation for Flexible 3D Human Body Editing: Xiaokun Sun,

Qiao Feng,

Xiongzheng Li,

Jinsong Zhang,

Yu-Kun Lai,

Jingyu Yang,

Kun Li; [pdf] [supp]
[bibtex]
@InProceedings{Sun_2023_CVPR, author = {Sun, Xiaokun and Feng, Qiao and Li, Xiongzheng and Zhang, Jinsong and Lai, Yu-Kun and Yang, Jingyu and Li, Kun}, title = {Learning Semantic-Aware Disentangled Representation for Flexible 3D Human Body Editing}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16985-16994} }
Generating Features With Increased Crop-Related Diversity for Few-Shot Object Detection: Jingyi Xu,

Hieu Le,

Dimitris Samaras; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Xu_2023_CVPR, author = {Xu, Jingyi and Le, Hieu and Samaras, Dimitris}, title = {Generating Features With Increased Crop-Related Diversity for Few-Shot Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {19713-19722} }
Towards Compositional Adversarial Robustness: Generalizing Adversarial Training to Composite Semantic Perturbations: Lei Hsiung,

Yun-Yun Tsai,

Pin-Yu Chen,

Tsung-Yi Ho; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Hsiung_2023_CVPR, author = {Hsiung, Lei and Tsai, Yun-Yun and Chen, Pin-Yu and Ho, Tsung-Yi}, title = {Towards Compositional Adversarial Robustness: Generalizing Adversarial Training to Composite Semantic Perturbations}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {24658-24667} }
CVT-SLR: Contrastive Visual-Textual Transformation for Sign Language Recognition With Variational Alignment: Jiangbin Zheng,

Yile Wang,

Cheng Tan,

Siyuan Li,

Ge Wang,

Jun Xia,

Yidong Chen,

Stan Z. Li; [pdf]
[bibtex]
@InProceedings{Zheng_2023_CVPR, author = {Zheng, Jiangbin and Wang, Yile and Tan, Cheng and Li, Siyuan and Wang, Ge and Xia, Jun and Chen, Yidong and Li, Stan Z.}, title = {CVT-SLR: Contrastive Visual-Textual Transformation for Sign Language Recognition With Variational Alignment}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {23141-23150} }
Paint by Example: Exemplar-Based Image Editing With Diffusion Models: Binxin Yang,

Shuyang Gu,

Bo Zhang,

Ting Zhang,

Xuejin Chen,

Xiaoyan Sun,

Dong Chen,

Fang Wen; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yang_2023_CVPR, author = {Yang, Binxin and Gu, Shuyang and Zhang, Bo and Zhang, Ting and Chen, Xuejin and Sun, Xiaoyan and Chen, Dong and Wen, Fang}, title = {Paint by Example: Exemplar-Based Image Editing With Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {18381-18391} }
Ego-Body Pose Estimation via Ego-Head Pose Estimation: Jiaman Li,

Karen Liu,

Jiajun Wu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Li_2023_CVPR, author = {Li, Jiaman and Liu, Karen and Wu, Jiajun}, title = {Ego-Body Pose Estimation via Ego-Head Pose Estimation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {17142-17151} }
Learning Rotation-Equivariant Features for Visual Correspondence: Jongmin Lee,

Byungjin Kim,

Seungwook Kim,

Minsu Cho; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Lee_2023_CVPR, author = {Lee, Jongmin and Kim, Byungjin and Kim, Seungwook and Cho, Minsu}, title = {Learning Rotation-Equivariant Features for Visual Correspondence}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {21887-21897} }
DexArt: Benchmarking Generalizable Dexterous Manipulation With Articulated Objects: Chen Bao,

Helin Xu,

Yuzhe Qin,

Xiaolong Wang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Bao_2023_CVPR, author = {Bao, Chen and Xu, Helin and Qin, Yuzhe and Wang, Xiaolong}, title = {DexArt: Benchmarking Generalizable Dexterous Manipulation With Articulated Objects}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {21190-21200} }
You Do Not Need Additional Priors or Regularizers in Retinex-Based Low-Light Image Enhancement: Huiyuan Fu,

Wenkai Zheng,

Xiangyu Meng,

Xin Wang,

Chuanming Wang,

Huadong Ma; [pdf]
[bibtex]
@InProceedings{Fu_2023_CVPR, author = {Fu, Huiyuan and Zheng, Wenkai and Meng, Xiangyu and Wang, Xin and Wang, Chuanming and Ma, Huadong}, title = {You Do Not Need Additional Priors or Regularizers in Retinex-Based Low-Light Image Enhancement}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {18125-18134} }
SCADE: NeRFs from Space Carving With Ambiguity-Aware Depth Estimates: Mikaela Angelina Uy,

Ricardo Martin-Brualla,

Leonidas Guibas,

Ke Li; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Uy_2023_CVPR, author = {Uy, Mikaela Angelina and Martin-Brualla, Ricardo and Guibas, Leonidas and Li, Ke}, title = {SCADE: NeRFs from Space Carving With Ambiguity-Aware Depth Estimates}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16518-16527} }
1% VS 100%: Parameter-Efficient Low Rank Adapter for Dense Predictions: Dongshuo Yin,

Yiran Yang,

Zhechao Wang,

Hongfeng Yu,

Kaiwen Wei,

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

Zuxuan Wu,

Qi Dai,

Han Hu,

Yu Qiao,

Yu-Gang Jiang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Tian_2023_CVPR, author = {Tian, Rui and Wu, Zuxuan and Dai, Qi and Hu, Han and Qiao, Yu and Jiang, Yu-Gang}, title = {ResFormer: Scaling ViTs With Multi-Resolution Training}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {22721-22731} }
Hierarchical Video-Moment Retrieval and Step-Captioning: Abhay Zala,

Jaemin Cho,

Satwik Kottur,

Xilun Chen,

Barlas Oguz,

Yashar Mehdad,

Mohit Bansal; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zala_2023_CVPR, author = {Zala, Abhay and Cho, Jaemin and Kottur, Satwik and Chen, Xilun and Oguz, Barlas and Mehdad, Yashar and Bansal, Mohit}, title = {Hierarchical Video-Moment Retrieval and Step-Captioning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {23056-23065} }
PD-Quant: Post-Training Quantization Based on Prediction Difference Metric: Jiawei Liu,

Lin Niu,

Zhihang Yuan,

Dawei Yang,

Xinggang Wang,

Wenyu Liu; [pdf] [supp]
[bibtex]
@InProceedings{Liu_2023_CVPR, author = {Liu, Jiawei and Niu, Lin and Yuan, Zhihang and Yang, Dawei and Wang, Xinggang and Liu, Wenyu}, title = {PD-Quant: Post-Training Quantization Based on Prediction Difference Metric}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {24427-24437} }
AUNet: Learning Relations Between Action Units for Face Forgery Detection: Weiming Bai,

Yufan Liu,

Zhipeng Zhang,

Bing Li,

Weiming Hu; [pdf] [supp]
[bibtex]
@InProceedings{Bai_2023_CVPR, author = {Bai, Weiming and Liu, Yufan and Zhang, Zhipeng and Li, Bing and Hu, Weiming}, title = {AUNet: Learning Relations Between Action Units for Face Forgery Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {24709-24719} }
PolyFormer: Referring Image Segmentation As Sequential Polygon Generation: Jiang Liu,

Hui Ding,

Zhaowei Cai,

Yuting Zhang,

Ravi Kumar Satzoda,

Vijay Mahadevan,

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

Hong Wang,

Qian Zhao,

Yuexiang Li,

Yawen Huang,

Deyu Meng,

Yefeng Zheng; [pdf] [supp]
[bibtex]
@InProceedings{Zhou_2023_CVPR, author = {Zhou, Minghao and Wang, Hong and Zhao, Qian and Li, Yuexiang and Huang, Yawen and Meng, Deyu and Zheng, Yefeng}, title = {Interactive Segmentation As Gaussion Process Classification}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {19488-19497} }
A Practical Stereo Depth System for Smart Glasses: Jialiang Wang,

Daniel Scharstein,

Akash Bapat,

Kevin Blackburn-Matzen,

Matthew Yu,

Jonathan Lehman,

Suhib Alsisan,

Yanghan Wang,

Sam Tsai,

Jan-Michael Frahm,

Zijian He,

Peter Vajda,

Michael F. Cohen,

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

Li Fuxin,

Qi Shan; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wu_2023_CVPR, author = {Wu, Wenxuan and Fuxin, Li and Shan, Qi}, title = {PointConvFormer: Revenge of the Point-Based Convolution}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {21802-21813} }
Variational Distribution Learning for Unsupervised Text-to-Image Generation: Minsoo Kang,

Doyup Lee,

Jiseob Kim,

Saehoon Kim,

Bohyung Han; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kang_2023_CVPR, author = {Kang, Minsoo and Lee, Doyup and Kim, Jiseob and Kim, Saehoon and Han, Bohyung}, title = {Variational Distribution Learning for Unsupervised Text-to-Image Generation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {23380-23389} }
MetaMix: Towards Corruption-Robust Continual Learning With Temporally Self-Adaptive Data Transformation: Zhenyi Wang,

Li Shen,

Donglin Zhan,

Qiuling Suo,

Yanjun Zhu,

Tiehang Duan,

Mingchen Gao; [pdf] [supp]
[bibtex]
@InProceedings{Wang_2023_CVPR, author = {Wang, Zhenyi and Shen, Li and Zhan, Donglin and Suo, Qiuling and Zhu, Yanjun and Duan, Tiehang and Gao, Mingchen}, title = {MetaMix: Towards Corruption-Robust Continual Learning With Temporally Self-Adaptive Data Transformation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {24521-24531} }
Ultra-High Resolution Segmentation With Ultra-Rich Context: A Novel Benchmark: Deyi Ji,

Feng Zhao,

Hongtao Lu,

Mingyuan Tao,

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

Yixiao Ge,

Feng Zheng,

Ran Cheng,

Ying Shan,

Xiaohu Qie,

Ping Luo; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2023_CVPR, author = {Wang, Teng and Ge, Yixiao and Zheng, Feng and Cheng, Ran and Shan, Ying and Qie, Xiaohu and Luo, Ping}, title = {Accelerating Vision-Language Pretraining With Free Language Modeling}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {23161-23170} }
Efficient Mask Correction for Click-Based Interactive Image Segmentation: Fei Du,

Jianlong Yuan,

Zhibin Wang,

Fan Wang; [pdf] [supp]
[bibtex]
@InProceedings{Du_2023_CVPR, author = {Du, Fei and Yuan, Jianlong and Wang, Zhibin and Wang, Fan}, title = {Efficient Mask Correction for Click-Based Interactive Image Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {22773-22782} }
Graphics Capsule: Learning Hierarchical 3D Face Representations From 2D Images: Chang Yu,

Xiangyu Zhu,

Xiaomei Zhang,

Zhaoxiang Zhang,

Zhen Lei; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yu_2023_CVPR, author = {Yu, Chang and Zhu, Xiangyu and Zhang, Xiaomei and Zhang, Zhaoxiang and Lei, Zhen}, title = {Graphics Capsule: Learning Hierarchical 3D Face Representations From 2D Images}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {20981-20990} }
Masked Autoencoders Enable Efficient Knowledge Distillers: Yutong Bai,

Zeyu Wang,

Junfei Xiao,

Chen Wei,

Huiyu Wang,

Alan L. Yuille,

Yuyin Zhou,

Cihang Xie; [pdf] [arXiv]
[bibtex]
@InProceedings{Bai_2023_CVPR, author = {Bai, Yutong and Wang, Zeyu and Xiao, Junfei and Wei, Chen and Wang, Huiyu and Yuille, Alan L. and Zhou, Yuyin and Xie, Cihang}, title = {Masked Autoencoders Enable Efficient Knowledge Distillers}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {24256-24265} }
Persistent Nature: A Generative Model of Unbounded 3D Worlds: Lucy Chai,

Richard Tucker,

Zhengqi Li,

Phillip Isola,

Noah Snavely; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chai_2023_CVPR, author = {Chai, Lucy and Tucker, Richard and Li, Zhengqi and Isola, Phillip and Snavely, Noah}, title = {Persistent Nature: A Generative Model of Unbounded 3D Worlds}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {20863-20874} }
Hierarchical Neural Memory Network for Low Latency Event Processing: Ryuhei Hamaguchi,

Yasutaka Furukawa,

Masaki Onishi,

Ken Sakurada; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Hamaguchi_2023_CVPR, author = {Hamaguchi, Ryuhei and Furukawa, Yasutaka and Onishi, Masaki and Sakurada, Ken}, title = {Hierarchical Neural Memory Network for Low Latency Event Processing}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {22867-22876} }
DaFKD: Domain-Aware Federated Knowledge Distillation: Haozhao Wang,

Yichen Li,

Wenchao Xu,

Ruixuan Li,

Yufeng Zhan,

Zhigang Zeng; [pdf] [supp]
[bibtex]
@InProceedings{Wang_2023_CVPR, author = {Wang, Haozhao and Li, Yichen and Xu, Wenchao and Li, Ruixuan and Zhan, Yufeng and Zeng, Zhigang}, title = {DaFKD: Domain-Aware Federated Knowledge Distillation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {20412-20421} }
Boost Vision Transformer With GPU-Friendly Sparsity and Quantization: Chong Yu,

Tao Chen,

Zhongxue Gan,

Jiayuan Fan; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yu_2023_CVPR, author = {Yu, Chong and Chen, Tao and Gan, Zhongxue and Fan, Jiayuan}, title = {Boost Vision Transformer With GPU-Friendly Sparsity and Quantization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {22658-22668} }
Spectral Bayesian Uncertainty for Image Super-Resolution: Tao Liu,

Jun Cheng,

Shan Tan; [pdf] [supp]
[bibtex]
@InProceedings{Liu_2023_CVPR, author = {Liu, Tao and Cheng, Jun and Tan, Shan}, title = {Spectral Bayesian Uncertainty for Image Super-Resolution}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {18166-18175} }
Mutual Information-Based Temporal Difference Learning for Human Pose Estimation in Video: Runyang Feng,

Yixing Gao,

Xueqing Ma,

Tze Ho Elden Tse,

Hyung Jin Chang; [pdf] [arXiv]
[bibtex]
@InProceedings{Feng_2023_CVPR, author = {Feng, Runyang and Gao, Yixing and Ma, Xueqing and Tse, Tze Ho Elden and Chang, Hyung Jin}, title = {Mutual Information-Based Temporal Difference Learning for Human Pose Estimation in Video}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {17131-17141} }
SynthVSR: Scaling Up Visual Speech Recognition With Synthetic Supervision: Xubo Liu,

Egor Lakomkin,

Konstantinos Vougioukas,

Pingchuan Ma,

Honglie Chen,

Ruiming Xie,

Morrie Doulaty,

Niko Moritz,

Jachym Kolar,

Stavros Petridis,

Maja Pantic,

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

Rodrigo Caye Daudt,

Torben Peters,

Reinhard Furrer,

Jan D. Wegner,

Konrad Schindler; [pdf] [supp]
[bibtex]
@InProceedings{Kalischek_2023_CVPR, author = {Kalischek, Nikolai and Daudt, Rodrigo Caye and Peters, Torben and Furrer, Reinhard and Wegner, Jan D. and Schindler, Konrad}, title = {BiasBed - Rigorous Texture Bias Evaluation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {22221-22230} }
Open-Category Human-Object Interaction Pre-Training via Language Modeling Framework: Sipeng Zheng,

Boshen Xu,

Qin Jin; [pdf] [supp]
[bibtex]
@InProceedings{Zheng_2023_CVPR, author = {Zheng, Sipeng and Xu, Boshen and Jin, Qin}, title = {Open-Category Human-Object Interaction Pre-Training via Language Modeling Framework}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {19392-19402} }
Explicit Boundary Guided Semi-Push-Pull Contrastive Learning for Supervised Anomaly Detection: Xincheng Yao,

Ruoqi Li,

Jing Zhang,

Jun Sun,

Chongyang Zhang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yao_2023_CVPR, author = {Yao, Xincheng and Li, Ruoqi and Zhang, Jing and Sun, Jun and Zhang, Chongyang}, title = {Explicit Boundary Guided Semi-Push-Pull Contrastive Learning for Supervised Anomaly Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {24490-24499} }
DeCo: Decomposition and Reconstruction for Compositional Temporal Grounding via Coarse-To-Fine Contrastive Ranking: Lijin Yang,

Quan Kong,

Hsuan-Kung Yang,

Wadim Kehl,

Yoichi Sato,

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

Ying Fu,

Dezhi Zheng,

Chunshui Cao,

Xuecai Hu,

Yongzhen Huang; [pdf]
[bibtex]
@InProceedings{Ma_2023_CVPR, author = {Ma, Kang and Fu, Ying and Zheng, Dezhi and Cao, Chunshui and Hu, Xuecai and Huang, Yongzhen}, title = {Dynamic Aggregated Network for Gait Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {22076-22085} }
Sphere-Guided Training of Neural Implicit Surfaces: Andreea Dogaru,

Andrei-Timotei Ardelean,

Savva Ignatyev,

Egor Zakharov,

Evgeny Burnaev; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Dogaru_2023_CVPR, author = {Dogaru, Andreea and Ardelean, Andrei-Timotei and Ignatyev, Savva and Zakharov, Egor and Burnaev, Evgeny}, title = {Sphere-Guided Training of Neural Implicit Surfaces}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {20844-20853} }
Bias Mimicking: A Simple Sampling Approach for Bias Mitigation: Maan Qraitem,

Kate Saenko,

Bryan A. Plummer; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Qraitem_2023_CVPR, author = {Qraitem, Maan and Saenko, Kate and Plummer, Bryan A.}, title = {Bias Mimicking: A Simple Sampling Approach for Bias Mitigation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {20311-20320} }
NoisyQuant: Noisy Bias-Enhanced Post-Training Activation Quantization for Vision Transformers: Yijiang Liu,

Huanrui Yang,

Zhen Dong,

Kurt Keutzer,

Li Du,

Shanghang Zhang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Liu_2023_CVPR, author = {Liu, Yijiang and Yang, Huanrui and Dong, Zhen and Keutzer, Kurt and Du, Li and Zhang, Shanghang}, title = {NoisyQuant: Noisy Bias-Enhanced Post-Training Activation Quantization for Vision Transformers}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {20321-20330} }
Semi-Supervised Stereo-Based 3D Object Detection via Cross-View Consensus: Wenhao Wu,

Hau San Wong,

Si Wu; [pdf] [supp]
[bibtex]
@InProceedings{Wu_2023_CVPR, author = {Wu, Wenhao and Wong, Hau San and Wu, Si}, title = {Semi-Supervised Stereo-Based 3D Object Detection via Cross-View Consensus}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {17471-17481} }
Video Compression With Entropy-Constrained Neural Representations: Carlos Gomes,

Roberto Azevedo,

Christopher Schroers; [pdf] [supp]
[bibtex]
@InProceedings{Gomes_2023_CVPR, author = {Gomes, Carlos and Azevedo, Roberto and Schroers, Christopher}, title = {Video Compression With Entropy-Constrained Neural Representations}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {18497-18506} }
Deep Random Projector: Accelerated Deep Image Prior: Taihui Li,

Hengkang Wang,

Zhong Zhuang,

Ju Sun; [pdf] [supp]
[bibtex]
@InProceedings{Li_2023_CVPR, author = {Li, Taihui and Wang, Hengkang and Zhuang, Zhong and Sun, Ju}, title = {Deep Random Projector: Accelerated Deep Image Prior}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {18176-18185} }
SCPNet: Semantic Scene Completion on Point Cloud: Zhaoyang Xia,

Youquan Liu,

Xin Li,

Xinge Zhu,

Yuexin Ma,

Yikang Li,

Yuenan Hou,

Yu Qiao; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Xia_2023_CVPR, author = {Xia, Zhaoyang and Liu, Youquan and Li, Xin and Zhu, Xinge and Ma, Yuexin and Li, Yikang and Hou, Yuenan and Qiao, Yu}, title = {SCPNet: Semantic Scene Completion on Point Cloud}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {17642-17651} }
Revisiting Prototypical Network for Cross Domain Few-Shot Learning: Fei Zhou,

Peng Wang,

Lei Zhang,

Wei Wei,

Yanning Zhang; [pdf] [supp]
[bibtex]
@InProceedings{Zhou_2023_CVPR, author = {Zhou, Fei and Wang, Peng and Zhang, Lei and Wei, Wei and Zhang, Yanning}, title = {Revisiting Prototypical Network for Cross Domain Few-Shot Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {20061-20070} }
Learning Accurate 3D Shape Based on Stereo Polarimetric Imaging: Tianyu Huang,

Haoang Li,

Kejing He,

Congying Sui,

Bin Li,

Yun-Hui Liu; [pdf] [supp]
[bibtex]
@InProceedings{Huang_2023_CVPR, author = {Huang, Tianyu and Li, Haoang and He, Kejing and Sui, Congying and Li, Bin and Liu, Yun-Hui}, title = {Learning Accurate 3D Shape Based on Stereo Polarimetric Imaging}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {17287-17296} }
RA-CLIP: Retrieval Augmented Contrastive Language-Image Pre-Training: Chen-Wei Xie,

Siyang Sun,

Xiong Xiong,

Yun Zheng,

Deli Zhao,

Jingren Zhou; [pdf] [supp]
[bibtex]
@InProceedings{Xie_2023_CVPR, author = {Xie, Chen-Wei and Sun, Siyang and Xiong, Xiong and Zheng, Yun and Zhao, Deli and Zhou, Jingren}, title = {RA-CLIP: Retrieval Augmented Contrastive Language-Image Pre-Training}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {19265-19274} }
A Practical Upper Bound for the Worst-Case Attribution Deviations: Fan Wang,

Adams Wai-Kin Kong; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2023_CVPR, author = {Wang, Fan and Kong, Adams Wai-Kin}, title = {A Practical Upper Bound for the Worst-Case Attribution Deviations}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {24616-24625} }
Teacher-Generated Spatial-Attention Labels Boost Robustness and Accuracy of Contrastive Models: Yushi Yao,

Chang Ye,

Junfeng He,

Gamaleldin F. Elsayed; [pdf] [supp]
[bibtex]
@InProceedings{Yao_2023_CVPR, author = {Yao, Yushi and Ye, Chang and He, Junfeng and Elsayed, Gamaleldin F.}, title = {Teacher-Generated Spatial-Attention Labels Boost Robustness and Accuracy of Contrastive Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {23282-23291} }
Exploring and Exploiting Uncertainty for Incomplete Multi-View Classification: Mengyao Xie,

Zongbo Han,

Changqing Zhang,

Yichen Bai,

Qinghua Hu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Xie_2023_CVPR, author = {Xie, Mengyao and Han, Zongbo and Zhang, Changqing and Bai, Yichen and Hu, Qinghua}, title = {Exploring and Exploiting Uncertainty for Incomplete Multi-View Classification}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {19873-19882} }
Discovering the Real Association: Multimodal Causal Reasoning in Video Question Answering: Chuanqi Zang,

Hanqing Wang,

Mingtao Pei,

Wei Liang; [pdf] [supp]
[bibtex]
@InProceedings{Zang_2023_CVPR, author = {Zang, Chuanqi and Wang, Hanqing and Pei, Mingtao and Liang, Wei}, title = {Discovering the Real Association: Multimodal Causal Reasoning in Video Question Answering}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {19027-19036} }
Learning Transformations To Reduce the Geometric Shift in Object Detection: Vidit Vidit,

Martin Engilberge,

Mathieu Salzmann; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Vidit_2023_CVPR, author = {Vidit, Vidit and Engilberge, Martin and Salzmann, Mathieu}, title = {Learning Transformations To Reduce the Geometric Shift in Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {17441-17450} }
OReX: Object Reconstruction From Planar Cross-Sections Using Neural Fields: Haim Sawdayee,

Amir Vaxman,

Amit H. Bermano; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Sawdayee_2023_CVPR, author = {Sawdayee, Haim and Vaxman, Amir and Bermano, Amit H.}, title = {OReX: Object Reconstruction From Planar Cross-Sections Using Neural Fields}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {20854-20862} }
SPIn-NeRF: Multiview Segmentation and Perceptual Inpainting With Neural Radiance Fields: Ashkan Mirzaei,

Tristan Aumentado-Armstrong,

Konstantinos G. Derpanis,

Jonathan Kelly,

Marcus A. Brubaker,

Igor Gilitschenski,

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

Viktor Larsson,

Daniel Barath; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhang_2023_CVPR, author = {Zhang, Ganlin and Larsson, Viktor and Barath, Daniel}, title = {Revisiting Rotation Averaging: Uncertainties and Robust Losses}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {17215-17224} }
Patch-Based 3D Natural Scene Generation From a Single Example: Weiyu Li,

Xuelin Chen,

Jue Wang,

Baoquan Chen; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Li_2023_CVPR, author = {Li, Weiyu and Chen, Xuelin and Wang, Jue and Chen, Baoquan}, title = {Patch-Based 3D Natural Scene Generation From a Single Example}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16762-16772} }
Leveraging Hidden Positives for Unsupervised Semantic Segmentation: Hyun Seok Seong,

WonJun Moon,

SuBeen Lee,

Jae-Pil Heo; [pdf] [arXiv]
[bibtex]
@InProceedings{Seong_2023_CVPR, author = {Seong, Hyun Seok and Moon, WonJun and Lee, SuBeen and Heo, Jae-Pil}, title = {Leveraging Hidden Positives for Unsupervised Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {19540-19549} }
LG-BPN: Local and Global Blind-Patch Network for Self-Supervised Real-World Denoising: Zichun Wang,

Ying Fu,

Ji Liu,

Yulun Zhang; [pdf]
[bibtex]
@InProceedings{Wang_2023_CVPR, author = {Wang, Zichun and Fu, Ying and Liu, Ji and Zhang, Yulun}, title = {LG-BPN: Local and Global Blind-Patch Network for Self-Supervised Real-World Denoising}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {18156-18165} }
Efficient View Synthesis and 3D-Based Multi-Frame Denoising With Multiplane Feature Representations: Thomas Tanay,

Aleš Leonardis,

Matteo Maggioni; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Tanay_2023_CVPR, author = {Tanay, Thomas and Leonardis, Ale\v{s} and Maggioni, Matteo}, title = {Efficient View Synthesis and 3D-Based Multi-Frame Denoising With Multiplane Feature Representations}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {20898-20907} }
Model Barrier: A Compact Un-Transferable Isolation Domain for Model Intellectual Property Protection: Lianyu Wang,

Meng Wang,

Daoqiang Zhang,

Huazhu Fu; [pdf] [arXiv]
[bibtex]
@InProceedings{Wang_2023_CVPR, author = {Wang, Lianyu and Wang, Meng and Zhang, Daoqiang and Fu, Huazhu}, title = {Model Barrier: A Compact Un-Transferable Isolation Domain for Model Intellectual Property Protection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {20475-20484} }
Object Detection With Self-Supervised Scene Adaptation: Zekun Zhang,

Minh Hoai; [pdf] [supp]
[bibtex]
@InProceedings{Zhang_2023_CVPR, author = {Zhang, Zekun and Hoai, Minh}, title = {Object Detection With Self-Supervised Scene Adaptation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {21589-21599} }
Self-Positioning Point-Based Transformer for Point Cloud Understanding: Jinyoung Park,

Sanghyeok Lee,

Sihyeon Kim,

Yunyang Xiong,

Hyunwoo J. Kim; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Park_2023_CVPR, author = {Park, Jinyoung and Lee, Sanghyeok and Kim, Sihyeon and Xiong, Yunyang and Kim, Hyunwoo J.}, title = {Self-Positioning Point-Based Transformer for Point Cloud Understanding}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {21814-21823} }
DeepLSD: Line Segment Detection and Refinement With Deep Image Gradients: Rémi Pautrat,

Daniel Barath,

Viktor Larsson,

Martin R. Oswald,

Marc Pollefeys; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Pautrat_2023_CVPR, author = {Pautrat, R\'emi and Barath, Daniel and Larsson, Viktor and Oswald, Martin R. and Pollefeys, Marc}, title = {DeepLSD: Line Segment Detection and Refinement With Deep Image Gradients}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {17327-17336} }
Executing Your Commands via Motion Diffusion in Latent Space: Xin Chen,

Biao Jiang,

Wen Liu,

Zilong Huang,

Bin Fu,

Tao Chen,

Gang Yu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chen_2023_CVPR, author = {Chen, Xin and Jiang, Biao and Liu, Wen and Huang, Zilong and Fu, Bin and Chen, Tao and Yu, Gang}, title = {Executing Your Commands via Motion Diffusion in Latent Space}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {18000-18010} }
Reconstructing Animatable Categories From Videos: Gengshan Yang,

Chaoyang Wang,

N. Dinesh Reddy,

Deva Ramanan; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yang_2023_CVPR, author = {Yang, Gengshan and Wang, Chaoyang and Reddy, N. Dinesh and Ramanan, Deva}, title = {Reconstructing Animatable Categories From Videos}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16995-17005} }
Co-Salient Object Detection With Uncertainty-Aware Group Exchange-Masking: Yang Wu,

Huihui Song,

Bo Liu,

Kaihua Zhang,

Dong Liu; [pdf] [supp]
[bibtex]
@InProceedings{Wu_2023_CVPR, author = {Wu, Yang and Song, Huihui and Liu, Bo and Zhang, Kaihua and Liu, Dong}, title = {Co-Salient Object Detection With Uncertainty-Aware Group Exchange-Masking}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {19639-19648} }
Tangentially Elongated Gaussian Belief Propagation for Event-Based Incremental Optical Flow Estimation: Jun Nagata,

Yusuke Sekikawa; [pdf] [supp]
[bibtex]
@InProceedings{Nagata_2023_CVPR, author = {Nagata, Jun and Sekikawa, Yusuke}, title = {Tangentially Elongated Gaussian Belief Propagation for Event-Based Incremental Optical Flow Estimation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {21940-21949} }
Adaptive Sparse Pairwise Loss for Object Re-Identification: Xiao Zhou,

Yujie Zhong,

Zhen Cheng,

Fan Liang,

Lin Ma; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhou_2023_CVPR, author = {Zhou, Xiao and Zhong, Yujie and Cheng, Zhen and Liang, Fan and Ma, Lin}, title = {Adaptive Sparse Pairwise Loss for Object Re-Identification}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {19691-19701} }
Semi-Weakly Supervised Object Kinematic Motion Prediction: Gengxin Liu,

Qian Sun,

Haibin Huang,

Chongyang Ma,

Yulan Guo,

Li Yi,

Hui Huang,

Ruizhen Hu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Liu_2023_CVPR, author = {Liu, Gengxin and Sun, Qian and Huang, Haibin and Ma, Chongyang and Guo, Yulan and Yi, Li and Huang, Hui and Hu, Ruizhen}, title = {Semi-Weakly Supervised Object Kinematic Motion Prediction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {21726-21735} }
Learning a Simple Low-Light Image Enhancer From Paired Low-Light Instances: Zhenqi Fu,

Yan Yang,

Xiaotong Tu,

Yue Huang,

Xinghao Ding,

Kai-Kuang Ma; [pdf]
[bibtex]
@InProceedings{Fu_2023_CVPR, author = {Fu, Zhenqi and Yang, Yan and Tu, Xiaotong and Huang, Yue and Ding, Xinghao and Ma, Kai-Kuang}, title = {Learning a Simple Low-Light Image Enhancer From Paired Low-Light Instances}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {22252-22261} }
PivoTAL: Prior-Driven Supervision for Weakly-Supervised Temporal Action Localization: Mamshad Nayeem Rizve,

Gaurav Mittal,

Ye Yu,

Matthew Hall,

Sandra Sajeev,

Mubarak Shah,

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

Jian Liang,

Shuang Li,

Jinming Zhang,

Di Liu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Lv_2023_CVPR, author = {Lv, Fangrui and Liang, Jian and Li, Shuang and Zhang, Jinming and Liu, Di}, title = {Improving Generalization With Domain Convex Game}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {24315-24324} }
Fair Scratch Tickets: Finding Fair Sparse Networks Without Weight Training: Pengwei Tang,

Wei Yao,

Zhicong Li,

Yong Liu; [pdf] [supp]
[bibtex]
@InProceedings{Tang_2023_CVPR, author = {Tang, Pengwei and Yao, Wei and Li, Zhicong and Liu, Yong}, title = {Fair Scratch Tickets: Finding Fair Sparse Networks Without Weight Training}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {24406-24416} }
Intrinsic Physical Concepts Discovery With Object-Centric Predictive Models: Qu Tang,

Xiangyu Zhu,

Zhen Lei,

Zhaoxiang Zhang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Tang_2023_CVPR, author = {Tang, Qu and Zhu, Xiangyu and Lei, Zhen and Zhang, Zhaoxiang}, title = {Intrinsic Physical Concepts Discovery With Object-Centric Predictive Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {23252-23261} }
Towards Generalisable Video Moment Retrieval: Visual-Dynamic Injection to Image-Text Pre-Training: Dezhao Luo,

Jiabo Huang,

Shaogang Gong,

Hailin Jin,

Yang Liu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Luo_2023_CVPR, author = {Luo, Dezhao and Huang, Jiabo and Gong, Shaogang and Jin, Hailin and Liu, Yang}, title = {Towards Generalisable Video Moment Retrieval: Visual-Dynamic Injection to Image-Text Pre-Training}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {23045-23055} }
Learning Adaptive Dense Event Stereo From the Image Domain: Hoonhee Cho,

Jegyeong Cho,

Kuk-Jin Yoon; [pdf] [supp]
[bibtex]
@InProceedings{Cho_2023_CVPR, author = {Cho, Hoonhee and Cho, Jegyeong and Yoon, Kuk-Jin}, title = {Learning Adaptive Dense Event Stereo From the Image Domain}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {17797-17807} }
Foundation Model Drives Weakly Incremental Learning for Semantic Segmentation: Chaohui Yu,

Qiang Zhou,

Jingliang Li,

Jianlong Yuan,

Zhibin Wang,

Fan Wang; [pdf] [arXiv]
[bibtex]
@InProceedings{Yu_2023_CVPR, author = {Yu, Chaohui and Zhou, Qiang and Li, Jingliang and Yuan, Jianlong and Wang, Zhibin and Wang, Fan}, title = {Foundation Model Drives Weakly Incremental Learning for Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {23685-23694} }
NeRFVS: Neural Radiance Fields for Free View Synthesis via Geometry Scaffolds: Chen Yang,

Peihao Li,

Zanwei Zhou,

Shanxin Yuan,

Bingbing Liu,

Xiaokang Yang,

Weichao Qiu,

Wei Shen; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yang_2023_CVPR, author = {Yang, Chen and Li, Peihao and Zhou, Zanwei and Yuan, Shanxin and Liu, Bingbing and Yang, Xiaokang and Qiu, Weichao and Shen, Wei}, title = {NeRFVS: Neural Radiance Fields for Free View Synthesis via Geometry Scaffolds}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16549-16558} }
Auto-CARD: Efficient and Robust Codec Avatar Driving for Real-Time Mobile Telepresence: Yonggan Fu,

Yuecheng Li,

Chenghui Li,

Jason Saragih,

Peizhao Zhang,

Xiaoliang Dai,

Yingyan (Celine) Lin; [pdf] [supp]
[bibtex]
@InProceedings{Fu_2023_CVPR, author = {Fu, Yonggan and Li, Yuecheng and Li, Chenghui and Saragih, Jason and Zhang, Peizhao and Dai, Xiaoliang and Lin, Yingyan (Celine)}, title = {Auto-CARD: Efficient and Robust Codec Avatar Driving for Real-Time Mobile Telepresence}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {21036-21045} }
Conjugate Product Graphs for Globally Optimal 2D-3D Shape Matching: Paul Roetzer,

Zorah Lähner,

Florian Bernard; [pdf] [supp]
[bibtex]
@InProceedings{Roetzer_2023_CVPR, author = {Roetzer, Paul and L\"ahner, Zorah and Bernard, Florian}, title = {Conjugate Product Graphs for Globally Optimal 2D-3D Shape Matching}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {21866-21875} }
Multi-Realism Image Compression With a Conditional Generator: Eirikur Agustsson,

David Minnen,

George Toderici,

Fabian Mentzer; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Agustsson_2023_CVPR, author = {Agustsson, Eirikur and Minnen, David and Toderici, George and Mentzer, Fabian}, title = {Multi-Realism Image Compression With a Conditional Generator}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {22324-22333} }
Best of Both Worlds: Multimodal Contrastive Learning With Tabular and Imaging Data: Paul Hager,

Martin J. Menten,

Daniel Rueckert; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Hager_2023_CVPR, author = {Hager, Paul and Menten, Martin J. and Rueckert, Daniel}, title = {Best of Both Worlds: Multimodal Contrastive Learning With Tabular and Imaging Data}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {23924-23935} }
Masked Images Are Counterfactual Samples for Robust Fine-Tuning: Yao Xiao,

Ziyi Tang,

Pengxu Wei,

Cong Liu,

Liang Lin; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Xiao_2023_CVPR, author = {Xiao, Yao and Tang, Ziyi and Wei, Pengxu and Liu, Cong and Lin, Liang}, title = {Masked Images Are Counterfactual Samples for Robust Fine-Tuning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {20301-20310} }
StepFormer: Self-Supervised Step Discovery and Localization in Instructional Videos: Nikita Dvornik,

Isma Hadji,

Ran Zhang,

Konstantinos G. Derpanis,

Richard P. Wildes,

Allan D. Jepson; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Dvornik_2023_CVPR, author = {Dvornik, Nikita and Hadji, Isma and Zhang, Ran and Derpanis, Konstantinos G. and Wildes, Richard P. and Jepson, Allan D.}, title = {StepFormer: Self-Supervised Step Discovery and Localization in Instructional Videos}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {18952-18961} }
Open Vocabulary Semantic Segmentation With Patch Aligned Contrastive Learning: Jishnu Mukhoti,

Tsung-Yu Lin,

Omid Poursaeed,

Rui Wang,

Ashish Shah,

Philip H.S. Torr,

Ser-Nam Lim; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Mukhoti_2023_CVPR, author = {Mukhoti, Jishnu and Lin, Tsung-Yu and Poursaeed, Omid and Wang, Rui and Shah, Ashish and Torr, Philip H.S. and Lim, Ser-Nam}, title = {Open Vocabulary Semantic Segmentation With Patch Aligned Contrastive Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {19413-19423} }
Camouflaged Instance Segmentation via Explicit De-Camouflaging: Naisong Luo,

Yuwen Pan,

Rui Sun,

Tianzhu Zhang,

Zhiwei Xiong,

Feng Wu; [pdf] [supp]
[bibtex]
@InProceedings{Luo_2023_CVPR, author = {Luo, Naisong and Pan, Yuwen and Sun, Rui and Zhang, Tianzhu and Xiong, Zhiwei and Wu, Feng}, title = {Camouflaged Instance Segmentation via Explicit De-Camouflaging}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {17918-17927} }
Pic2Word: Mapping Pictures to Words for Zero-Shot Composed Image Retrieval: Kuniaki Saito,

Kihyuk Sohn,

Xiang Zhang,

Chun-Liang Li,

Chen-Yu Lee,

Kate Saenko,

Tomas Pfister; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Saito_2023_CVPR, author = {Saito, Kuniaki and Sohn, Kihyuk and Zhang, Xiang and Li, Chun-Liang and Lee, Chen-Yu and Saenko, Kate and Pfister, Tomas}, title = {Pic2Word: Mapping Pictures to Words for Zero-Shot Composed Image Retrieval}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {19305-19314} }
MMANet: Margin-Aware Distillation and Modality-Aware Regularization for Incomplete Multimodal Learning: Shicai Wei,

Chunbo Luo,

Yang Luo; [pdf] [arXiv]
[bibtex]
@InProceedings{Wei_2023_CVPR, author = {Wei, Shicai and Luo, Chunbo and Luo, Yang}, title = {MMANet: Margin-Aware Distillation and Modality-Aware Regularization for Incomplete Multimodal Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {20039-20049} }
Putting People in Their Place: Affordance-Aware Human Insertion Into Scenes: Sumith Kulal,

Tim Brooks,

Alex Aiken,

Jiajun Wu,

Jimei Yang,

Jingwan Lu,

Alexei A. Efros,

Krishna Kumar Singh; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kulal_2023_CVPR, author = {Kulal, Sumith and Brooks, Tim and Aiken, Alex and Wu, Jiajun and Yang, Jimei and Lu, Jingwan and Efros, Alexei A. and Singh, Krishna Kumar}, title = {Putting People in Their Place: Affordance-Aware Human Insertion Into Scenes}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {17089-17099} }
3D Neural Field Generation Using Triplane Diffusion: J. Ryan Shue,

Eric Ryan Chan,

Ryan Po,

Zachary Ankner,

Jiajun Wu,

Gordon Wetzstein; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Shue_2023_CVPR, author = {Shue, J. Ryan and Chan, Eric Ryan and Po, Ryan and Ankner, Zachary and Wu, Jiajun and Wetzstein, Gordon}, title = {3D Neural Field Generation Using Triplane Diffusion}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {20875-20886} }
Regularized Vector Quantization for Tokenized Image Synthesis: Jiahui Zhang,

Fangneng Zhan,

Christian Theobalt,

Shijian Lu; [pdf] [arXiv]
[bibtex]
@InProceedings{Zhang_2023_CVPR, author = {Zhang, Jiahui and Zhan, Fangneng and Theobalt, Christian and Lu, Shijian}, title = {Regularized Vector Quantization for Tokenized Image Synthesis}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {18467-18476} }
Improving Image Recognition by Retrieving From Web-Scale Image-Text Data: Ahmet Iscen,

Alireza Fathi,

Cordelia Schmid; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Iscen_2023_CVPR, author = {Iscen, Ahmet and Fathi, Alireza and Schmid, Cordelia}, title = {Improving Image Recognition by Retrieving From Web-Scale Image-Text Data}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {19295-19304} }
Multi-Level Logit Distillation: Ying Jin,

Jiaqi Wang,

Dahua Lin; [pdf] [supp]
[bibtex]
@InProceedings{Jin_2023_CVPR, author = {Jin, Ying and Wang, Jiaqi and Lin, Dahua}, title = {Multi-Level Logit Distillation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {24276-24285} }
DA Wand: Distortion-Aware Selection Using Neural Mesh Parameterization: Richard Liu,

Noam Aigerman,

Vladimir G. Kim,

Rana Hanocka; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Liu_2023_CVPR, author = {Liu, Richard and Aigerman, Noam and Kim, Vladimir G. and Hanocka, Rana}, title = {DA Wand: Distortion-Aware Selection Using Neural Mesh Parameterization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16739-16749} }
Hierarchical Semantic Correspondence Networks for Video Paragraph Grounding: Chaolei Tan,

Zihang Lin,

Jian-Fang Hu,

Wei-Shi Zheng,

Jianhuang Lai; [pdf] [supp]
[bibtex]
@InProceedings{Tan_2023_CVPR, author = {Tan, Chaolei and Lin, Zihang and Hu, Jian-Fang and Zheng, Wei-Shi and Lai, Jianhuang}, title = {Hierarchical Semantic Correspondence Networks for Video Paragraph Grounding}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {18973-18982} }
Temporal Attention Unit: Towards Efficient Spatiotemporal Predictive Learning: Cheng Tan,

Zhangyang Gao,

Lirong Wu,

Yongjie Xu,

Jun Xia,

Siyuan Li,

Stan Z. Li; [pdf] [arXiv]
[bibtex]
@InProceedings{Tan_2023_CVPR, author = {Tan, Cheng and Gao, Zhangyang and Wu, Lirong and Xu, Yongjie and Xia, Jun and Li, Siyuan and Li, Stan Z.}, title = {Temporal Attention Unit: Towards Efficient Spatiotemporal Predictive Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {18770-18782} }
BiCro: Noisy Correspondence Rectification for Multi-Modality Data via Bi-Directional Cross-Modal Similarity Consistency: Shuo Yang,

Zhaopan Xu,

Kai Wang,

Yang You,

Hongxun Yao,

Tongliang Liu,

Min Xu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yang_2023_CVPR, author = {Yang, Shuo and Xu, Zhaopan and Wang, Kai and You, Yang and Yao, Hongxun and Liu, Tongliang and Xu, Min}, title = {BiCro: Noisy Correspondence Rectification for Multi-Modality Data via Bi-Directional Cross-Modal Similarity Consistency}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {19883-19892} }
Transfer Knowledge From Head to Tail: Uncertainty Calibration Under Long-Tailed Distribution: Jiahao Chen,

Bing Su; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chen_2023_CVPR, author = {Chen, Jiahao and Su, Bing}, title = {Transfer Knowledge From Head to Tail: Uncertainty Calibration Under Long-Tailed Distribution}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {19978-19987} }
Global Vision Transformer Pruning With Hessian-Aware Saliency: Huanrui Yang,

Hongxu Yin,

Maying Shen,

Pavlo Molchanov,

Hai Li,

Jan Kautz; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yang_2023_CVPR, author = {Yang, Huanrui and Yin, Hongxu and Shen, Maying and Molchanov, Pavlo and Li, Hai and Kautz, Jan}, title = {Global Vision Transformer Pruning With Hessian-Aware Saliency}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {18547-18557} }
ScarceNet: Animal Pose Estimation With Scarce Annotations: Chen Li,

Gim Hee Lee; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Li_2023_CVPR, author = {Li, Chen and Lee, Gim Hee}, title = {ScarceNet: Animal Pose Estimation With Scarce Annotations}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {17174-17183} }
OmniCity: Omnipotent City Understanding With Multi-Level and Multi-View Images: Weijia Li,

Yawen Lai,

Linning Xu,

Yuanbo Xiangli,

Jinhua Yu,

Conghui He,

Gui-Song Xia,

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

Kyle Min,

Subarna Tripathi,

Nuno Vasconcelos; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Li_2023_CVPR, author = {Li, Yi and Min, Kyle and Tripathi, Subarna and Vasconcelos, Nuno}, title = {SViTT: Temporal Learning of Sparse Video-Text Transformers}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {18919-18929} }
Deep Fair Clustering via Maximizing and Minimizing Mutual Information: Theory, Algorithm and Metric: Pengxin Zeng,

Yunfan Li,

Peng Hu,

Dezhong Peng,

Jiancheng Lv,

Xi Peng; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zeng_2023_CVPR, author = {Zeng, Pengxin and Li, Yunfan and Hu, Peng and Peng, Dezhong and Lv, Jiancheng and Peng, Xi}, title = {Deep Fair Clustering via Maximizing and Minimizing Mutual Information: Theory, Algorithm and Metric}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {23986-23995} }
High Fidelity 3D Hand Shape Reconstruction via Scalable Graph Frequency Decomposition: Tianyu Luan,

Yuanhao Zhai,

Jingjing Meng,

Zhong Li,

Zhang Chen,

Yi Xu,

Junsong Yuan; [pdf] [supp]
[bibtex]
@InProceedings{Luan_2023_CVPR, author = {Luan, Tianyu and Zhai, Yuanhao and Meng, Jingjing and Li, Zhong and Chen, Zhang and Xu, Yi and Yuan, Junsong}, title = {High Fidelity 3D Hand Shape Reconstruction via Scalable Graph Frequency Decomposition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16795-16804} }
COT: Unsupervised Domain Adaptation With Clustering and Optimal Transport: Yang Liu,

Zhipeng Zhou,

Baigui Sun; [pdf]
[bibtex]
@InProceedings{Liu_2023_CVPR, author = {Liu, Yang and Zhou, Zhipeng and Sun, Baigui}, title = {COT: Unsupervised Domain Adaptation With Clustering and Optimal Transport}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {19998-20007} }
Learning To Exploit the Sequence-Specific Prior Knowledge for Image Processing Pipelines Optimization: Haina Qin,

Longfei Han,

Weihua Xiong,

Juan Wang,

Wentao Ma,

Bing Li,

Weiming Hu; [pdf] [supp]
[bibtex]
@InProceedings{Qin_2023_CVPR, author = {Qin, Haina and Han, Longfei and Xiong, Weihua and Wang, Juan and Ma, Wentao and Li, Bing and Hu, Weiming}, title = {Learning To Exploit the Sequence-Specific Prior Knowledge for Image Processing Pipelines Optimization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {22314-22323} }
Lite-Mono: A Lightweight CNN and Transformer Architecture for Self-Supervised Monocular Depth Estimation: Ning Zhang,

Francesco Nex,

George Vosselman,

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

Qianqian Wang,

Ruojin Cai,

Sida Peng,

Hadar Averbuch-Elor,

Xiaowei Zhou,

Noah Snavely; [pdf]
[bibtex]
@InProceedings{Lin_2023_CVPR, author = {Lin, Haotong and Wang, Qianqian and Cai, Ruojin and Peng, Sida and Averbuch-Elor, Hadar and Zhou, Xiaowei and Snavely, Noah}, title = {Neural Scene Chronology}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {20752-20761} }
TIPI: Test Time Adaptation With Transformation Invariance: A. Tuan Nguyen,

Thanh Nguyen-Tang,

Ser-Nam Lim,

Philip H.S. Torr; [pdf] [supp]
[bibtex]
@InProceedings{Nguyen_2023_CVPR, author = {Nguyen, A. Tuan and Nguyen-Tang, Thanh and Lim, Ser-Nam and Torr, Philip H.S.}, title = {TIPI: Test Time Adaptation With Transformation Invariance}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {24162-24171} }
OTAvatar: One-Shot Talking Face Avatar With Controllable Tri-Plane Rendering: Zhiyuan Ma,

Xiangyu Zhu,

Guo-Jun Qi,

Zhen Lei,

Lei Zhang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ma_2023_CVPR, author = {Ma, Zhiyuan and Zhu, Xiangyu and Qi, Guo-Jun and Lei, Zhen and Zhang, Lei}, title = {OTAvatar: One-Shot Talking Face Avatar With Controllable Tri-Plane Rendering}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16901-16910} }
Large-Capacity and Flexible Video Steganography via Invertible Neural Network: Chong Mou,

Youmin Xu,

Jiechong Song,

Chen Zhao,

Bernard Ghanem,

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

Michael J. Jones,

Erik G. Learned-Miller; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Singh_2023_CVPR, author = {Singh, Ashish and Jones, Michael J. and Learned-Miller, Erik G.}, title = {EVAL: Explainable Video Anomaly Localization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {18717-18726} }
Position-Guided Text Prompt for Vision-Language Pre-Training: Jinpeng Wang,

Pan Zhou,

Mike Zheng Shou,

Shuicheng Yan; [pdf] [arXiv]
[bibtex]
@InProceedings{Wang_2023_CVPR, author = {Wang, Jinpeng and Zhou, Pan and Shou, Mike Zheng and Yan, Shuicheng}, title = {Position-Guided Text Prompt for Vision-Language Pre-Training}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {23242-23251} }
HOLODIFFUSION: Training a 3D Diffusion Model Using 2D Images: Animesh Karnewar,

Andrea Vedaldi,

David Novotny,

Niloy J. Mitra; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Karnewar_2023_CVPR, author = {Karnewar, Animesh and Vedaldi, Andrea and Novotny, David and Mitra, Niloy J.}, title = {HOLODIFFUSION: Training a 3D Diffusion Model Using 2D Images}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {18423-18433} }
Stimulus Verification Is a Universal and Effective Sampler in Multi-Modal Human Trajectory Prediction: Jianhua Sun,

Yuxuan Li,

Liang Chai,

Cewu Lu; [pdf] [supp]
[bibtex]
@InProceedings{Sun_2023_CVPR, author = {Sun, Jianhua and Li, Yuxuan and Chai, Liang and Lu, Cewu}, title = {Stimulus Verification Is a Universal and Effective Sampler in Multi-Modal Human Trajectory Prediction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {22014-22023} }
LoGoNet: Towards Accurate 3D Object Detection With Local-to-Global Cross-Modal Fusion: Xin Li,

Tao Ma,

Yuenan Hou,

Botian Shi,

Yuchen Yang,

Youquan Liu,

Xingjiao Wu,

Qin Chen,

Yikang Li,

Yu Qiao,

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

Qiqi Zhou,

Ning Liu,

Zhiyuan Xu,

Zhicai Ou,

Xiaofeng Mou,

Jian Tang; [pdf]
[bibtex]
@InProceedings{Zhu_2023_CVPR, author = {Zhu, Yichen and Zhou, Qiqi and Liu, Ning and Xu, Zhiyuan and Ou, Zhicai and Mou, Xiaofeng and Tang, Jian}, title = {ScaleKD: Distilling Scale-Aware Knowledge in Small Object Detector}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {19723-19733} }
An Empirical Study of End-to-End Video-Language Transformers With Masked Visual Modeling: Tsu-Jui Fu,

Linjie Li,

Zhe Gan,

Kevin Lin,

William Yang Wang,

Lijuan Wang,

Zicheng Liu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Fu_2023_CVPR, author = {Fu, Tsu-Jui and Li, Linjie and Gan, Zhe and Lin, Kevin and Wang, William Yang and Wang, Lijuan and Liu, Zicheng}, title = {An Empirical Study of End-to-End Video-Language Transformers With Masked Visual Modeling}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {22898-22909} }
MethaneMapper: Spectral Absorption Aware Hyperspectral Transformer for Methane Detection: Satish Kumar,

Ivan Arevalo,

ASM Iftekhar,

B S Manjunath; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kumar_2023_CVPR, author = {Kumar, Satish and Arevalo, Ivan and Iftekhar, ASM and Manjunath, B S}, title = {MethaneMapper: Spectral Absorption Aware Hyperspectral Transformer for Methane Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {17609-17618} }
Autonomous Manipulation Learning for Similar Deformable Objects via Only One Demonstration: Yu Ren,

Ronghan Chen,

Yang Cong; [pdf]
[bibtex]
@InProceedings{Ren_2023_CVPR, author = {Ren, Yu and Chen, Ronghan and Cong, Yang}, title = {Autonomous Manipulation Learning for Similar Deformable Objects via Only One Demonstration}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {17069-17078} }
Representation Learning for Visual Object Tracking by Masked Appearance Transfer: Haojie Zhao,

Dong Wang,

Huchuan Lu; [pdf] [supp]
[bibtex]
@InProceedings{Zhao_2023_CVPR, author = {Zhao, Haojie and Wang, Dong and Lu, Huchuan}, title = {Representation Learning for Visual Object Tracking by Masked Appearance Transfer}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {18696-18705} }
Learning To Name Classes for Vision and Language Models: Sarah Parisot,

Yongxin Yang,

Steven McDonagh; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Parisot_2023_CVPR, author = {Parisot, Sarah and Yang, Yongxin and McDonagh, Steven}, title = {Learning To Name Classes for Vision and Language Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {23477-23486} }
Nighttime Smartphone Reflective Flare Removal Using Optical Center Symmetry Prior: Yuekun Dai,

Yihang Luo,

Shangchen Zhou,

Chongyi Li,

Chen Change Loy; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Dai_2023_CVPR, author = {Dai, Yuekun and Luo, Yihang and Zhou, Shangchen and Li, Chongyi and Loy, Chen Change}, title = {Nighttime Smartphone Reflective Flare Removal Using Optical Center Symmetry Prior}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {20783-20791} }
Balanced Spherical Grid for Egocentric View Synthesis: Changwoon Choi,

Sang Min Kim,

Young Min Kim; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Choi_2023_CVPR, author = {Choi, Changwoon and Kim, Sang Min and Kim, Young Min}, title = {Balanced Spherical Grid for Egocentric View Synthesis}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16590-16599} }
Box-Level Active Detection: Mengyao Lyu,

Jundong Zhou,

Hui Chen,

Yijie Huang,

Dongdong Yu,

Yaqian Li,

Yandong Guo,

Yuchen Guo,

Liuyu Xiang,

Guiguang Ding; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Lyu_2023_CVPR, author = {Lyu, Mengyao and Zhou, Jundong and Chen, Hui and Huang, Yijie and Yu, Dongdong and Li, Yaqian and Guo, Yandong and Guo, Yuchen and Xiang, Liuyu and Ding, Guiguang}, title = {Box-Level Active Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {23766-23775} }
Self-Supervised Non-Uniform Kernel Estimation With Flow-Based Motion Prior for Blind Image Deblurring: Zhenxuan Fang,

Fangfang Wu,

Weisheng Dong,

Xin Li,

Jinjian Wu,

Guangming Shi; [pdf] [supp]
[bibtex]
@InProceedings{Fang_2023_CVPR, author = {Fang, Zhenxuan and Wu, Fangfang and Dong, Weisheng and Li, Xin and Wu, Jinjian and Shi, Guangming}, title = {Self-Supervised Non-Uniform Kernel Estimation With Flow-Based Motion Prior for Blind Image Deblurring}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {18105-18114} }
Collecting Cross-Modal Presence-Absence Evidence for Weakly-Supervised Audio-Visual Event Perception: Junyu Gao,

Mengyuan Chen,

Changsheng Xu; [pdf]
[bibtex]
@InProceedings{Gao_2023_CVPR, author = {Gao, Junyu and Chen, Mengyuan and Xu, Changsheng}, title = {Collecting Cross-Modal Presence-Absence Evidence for Weakly-Supervised Audio-Visual Event Perception}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {18827-18836} }
AVFace: Towards Detailed Audio-Visual 4D Face Reconstruction: Aggelina Chatziagapi,

Dimitris Samaras; [pdf] [arXiv]
[bibtex]
@InProceedings{Chatziagapi_2023_CVPR, author = {Chatziagapi, Aggelina and Samaras, Dimitris}, title = {AVFace: Towards Detailed Audio-Visual 4D Face Reconstruction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16878-16889} }
ERM-KTP: Knowledge-Level Machine Unlearning via Knowledge Transfer: Shen Lin,

Xiaoyu Zhang,

Chenyang Chen,

Xiaofeng Chen,

Willy Susilo; [pdf]
[bibtex]
@InProceedings{Lin_2023_CVPR, author = {Lin, Shen and Zhang, Xiaoyu and Chen, Chenyang and Chen, Xiaofeng and Susilo, Willy}, title = {ERM-KTP: Knowledge-Level Machine Unlearning via Knowledge Transfer}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {20147-20155} }
DATE: Domain Adaptive Product Seeker for E-Commerce: Haoyuan Li,

Hao Jiang,

Tao Jin,

Mengyan Li,

Yan Chen,

Zhijie Lin,

Yang Zhao,

Zhou Zhao; [pdf]
[bibtex]
@InProceedings{Li_2023_CVPR, author = {Li, Haoyuan and Jiang, Hao and Jin, Tao and Li, Mengyan and Chen, Yan and Lin, Zhijie and Zhao, Yang and Zhao, Zhou}, title = {DATE: Domain Adaptive Product Seeker for E-Commerce}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {19315-19324} }
Self-Supervised Super-Plane for Neural 3D Reconstruction: Botao Ye,

Sifei Liu,

Xueting Li,

Ming-Hsuan Yang; [pdf] [supp]
[bibtex]
@InProceedings{Ye_2023_CVPR, author = {Ye, Botao and Liu, Sifei and Li, Xueting and Yang, Ming-Hsuan}, title = {Self-Supervised Super-Plane for Neural 3D Reconstruction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {21415-21424} }
DisCo-CLIP: A Distributed Contrastive Loss for Memory Efficient CLIP Training: Yihao Chen,

Xianbiao Qi,

Jianan Wang,

Lei Zhang; [pdf] [supp]
[bibtex]
@InProceedings{Chen_2023_CVPR, author = {Chen, Yihao and Qi, Xianbiao and Wang, Jianan and Zhang, Lei}, title = {DisCo-CLIP: A Distributed Contrastive Loss for Memory Efficient CLIP Training}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {22648-22657} }
GM-NeRF: Learning Generalizable Model-Based Neural Radiance Fields From Multi-View Images: Jianchuan Chen,

Wentao Yi,

Liqian Ma,

Xu Jia,

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

Jianming Zhang,

Yannick Hold-Geoffroy,

Oliver Wang,

Kevin Blackburn-Matzen,

Matthew Sticha,

David F. Fouhey; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Jin_2023_CVPR, author = {Jin, Linyi and Zhang, Jianming and Hold-Geoffroy, Yannick and Wang, Oliver and Blackburn-Matzen, Kevin and Sticha, Matthew and Fouhey, David F.}, title = {Perspective Fields for Single Image Camera Calibration}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {17307-17316} }
Towards Accurate Image Coding: Improved Autoregressive Image Generation With Dynamic Vector Quantization: Mengqi Huang,

Zhendong Mao,

Zhuowei Chen,

Yongdong Zhang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Huang_2023_CVPR, author = {Huang, Mengqi and Mao, Zhendong and Chen, Zhuowei and Zhang, Yongdong}, title = {Towards Accurate Image Coding: Improved Autoregressive Image Generation With Dynamic Vector Quantization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {22596-22605} }
WINNER: Weakly-Supervised hIerarchical decompositioN and aligNment for Spatio-tEmporal Video gRounding: Mengze Li,

Han Wang,

Wenqiao Zhang,

Jiaxu Miao,

Zhou Zhao,

Shengyu Zhang,

Wei Ji,

Fei Wu; [pdf]
[bibtex]
@InProceedings{Li_2023_CVPR, author = {Li, Mengze and Wang, Han and Zhang, Wenqiao and Miao, Jiaxu and Zhao, Zhou and Zhang, Shengyu and Ji, Wei and Wu, Fei}, title = {WINNER: Weakly-Supervised hIerarchical decompositioN and aligNment for Spatio-tEmporal Video gRounding}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {23090-23099} }
Preserving Linear Separability in Continual Learning by Backward Feature Projection: Qiao Gu,

Dongsub Shim,

Florian Shkurti; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Gu_2023_CVPR, author = {Gu, Qiao and Shim, Dongsub and Shkurti, Florian}, title = {Preserving Linear Separability in Continual Learning by Backward Feature Projection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {24286-24295} }
MHPL: Minimum Happy Points Learning for Active Source Free Domain Adaptation: Fan Wang,

Zhongyi Han,

Zhiyan Zhang,

Rundong He,

Yilong Yin; [pdf] [supp]
[bibtex]
@InProceedings{Wang_2023_CVPR, author = {Wang, Fan and Han, Zhongyi and Zhang, Zhiyan and He, Rundong and Yin, Yilong}, title = {MHPL: Minimum Happy Points Learning for Active Source Free Domain Adaptation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {20008-20018} }
Metadata-Based RAW Reconstruction via Implicit Neural Functions: Leyi Li,

Huijie Qiao,

Qi Ye,

Qinmin Yang; [pdf] [supp]
[bibtex]
@InProceedings{Li_2023_CVPR, author = {Li, Leyi and Qiao, Huijie and Ye, Qi and Yang, Qinmin}, title = {Metadata-Based RAW Reconstruction via Implicit Neural Functions}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {18196-18205} }
Multimodality Helps Unimodality: Cross-Modal Few-Shot Learning With Multimodal Models: Zhiqiu Lin,

Samuel Yu,

Zhiyi Kuang,

Deepak Pathak,

Deva Ramanan; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Lin_2023_CVPR, author = {Lin, Zhiqiu and Yu, Samuel and Kuang, Zhiyi and Pathak, Deepak and Ramanan, Deva}, title = {Multimodality Helps Unimodality: Cross-Modal Few-Shot Learning With Multimodal Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {19325-19337} }
3D Highlighter: Localizing Regions on 3D Shapes via Text Descriptions: Dale Decatur,

Itai Lang,

Rana Hanocka; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Decatur_2023_CVPR, author = {Decatur, Dale and Lang, Itai and Hanocka, Rana}, title = {3D Highlighter: Localizing Regions on 3D Shapes via Text Descriptions}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {20930-20939} }
Iterative Geometry Encoding Volume for Stereo Matching: Gangwei Xu,

Xianqi Wang,

Xiaohuan Ding,

Xin Yang; [pdf] [arXiv]
[bibtex]
@InProceedings{Xu_2023_CVPR, author = {Xu, Gangwei and Wang, Xianqi and Ding, Xiaohuan and Yang, Xin}, title = {Iterative Geometry Encoding Volume for Stereo Matching}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {21919-21928} }
GRES: Generalized Referring Expression Segmentation: Chang Liu,

Henghui Ding,

Xudong Jiang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Liu_2023_CVPR, author = {Liu, Chang and Ding, Henghui and Jiang, Xudong}, title = {GRES: Generalized Referring Expression Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {23592-23601} }
Open-Set Fine-Grained Retrieval via Prompting Vision-Language Evaluator: Shijie Wang,

Jianlong Chang,

Haojie Li,

Zhihui Wang,

Wanli Ouyang,

Qi Tian; [pdf]
[bibtex]
@InProceedings{Wang_2023_CVPR, author = {Wang, Shijie and Chang, Jianlong and Li, Haojie and Wang, Zhihui and Ouyang, Wanli and Tian, Qi}, title = {Open-Set Fine-Grained Retrieval via Prompting Vision-Language Evaluator}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {19381-19391} }
Sibling-Attack: Rethinking Transferable Adversarial Attacks Against Face Recognition: Zexin Li,

Bangjie Yin,

Taiping Yao,

Junfeng Guo,

Shouhong Ding,

Simin Chen,

Cong Liu; [pdf] [supp]
[bibtex]
@InProceedings{Li_2023_CVPR, author = {Li, Zexin and Yin, Bangjie and Yao, Taiping and Guo, Junfeng and Ding, Shouhong and Chen, Simin and Liu, Cong}, title = {Sibling-Attack: Rethinking Transferable Adversarial Attacks Against Face Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {24626-24637} }
PIRLNav: Pretraining With Imitation and RL Finetuning for ObjectNav: Ram Ramrakhya,

Dhruv Batra,

Erik Wijmans,

Abhishek Das; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ramrakhya_2023_CVPR, author = {Ramrakhya, Ram and Batra, Dhruv and Wijmans, Erik and Das, Abhishek}, title = {PIRLNav: Pretraining With Imitation and RL Finetuning for ObjectNav}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {17896-17906} }
StyleGene: Crossover and Mutation of Region-Level Facial Genes for Kinship Face Synthesis: Hao Li,

Xianxu Hou,

Zepeng Huang,

Linlin Shen; [pdf] [supp]
[bibtex]
@InProceedings{Li_2023_CVPR, author = {Li, Hao and Hou, Xianxu and Huang, Zepeng and Shen, Linlin}, title = {StyleGene: Crossover and Mutation of Region-Level Facial Genes for Kinship Face Synthesis}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {20960-20969} }
Clothed Human Performance Capture With a Double-Layer Neural Radiance Fields: Kangkan Wang,

Guofeng Zhang,

Suxu Cong,

Jian Yang; [pdf] [supp]
[bibtex]
@InProceedings{Wang_2023_CVPR, author = {Wang, Kangkan and Zhang, Guofeng and Cong, Suxu and Yang, Jian}, title = {Clothed Human Performance Capture With a Double-Layer Neural Radiance Fields}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {21098-21107} }
NeuFace: Realistic 3D Neural Face Rendering From Multi-View Images: Mingwu Zheng,

Haiyu Zhang,

Hongyu Yang,

Di Huang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zheng_2023_CVPR, author = {Zheng, Mingwu and Zhang, Haiyu and Yang, Hongyu and Huang, Di}, title = {NeuFace: Realistic 3D Neural Face Rendering From Multi-View Images}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16868-16877} }
Rethinking Domain Generalization for Face Anti-Spoofing: Separability and Alignment: Yiyou Sun,

Yaojie Liu,

Xiaoming Liu,

Yixuan Li,

Wen-Sheng Chu; [pdf] [supp]
[bibtex]
@InProceedings{Sun_2023_CVPR, author = {Sun, Yiyou and Liu, Yaojie and Liu, Xiaoming and Li, Yixuan and Chu, Wen-Sheng}, title = {Rethinking Domain Generalization for Face Anti-Spoofing: Separability and Alignment}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {24563-24574} }
SMOC-Net: Leveraging Camera Pose for Self-Supervised Monocular Object Pose Estimation: Tao Tan,

Qiulei Dong; [pdf]
[bibtex]
@InProceedings{Tan_2023_CVPR, author = {Tan, Tao and Dong, Qiulei}, title = {SMOC-Net: Leveraging Camera Pose for Self-Supervised Monocular Object Pose Estimation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {21307-21316} }
Learning Human Mesh Recovery in 3D Scenes: Zehong Shen,

Zhi Cen,

Sida Peng,

Qing Shuai,

Hujun Bao,

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

Lixin Xue,

Jie Song,

Otmar Hilliges; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ho_2023_CVPR, author = {Ho, Hsuan-I and Xue, Lixin and Song, Jie and Hilliges, Otmar}, title = {Learning Locally Editable Virtual Humans}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {21024-21035} }
PillarNeXt: Rethinking Network Designs for 3D Object Detection in LiDAR Point Clouds: Jinyu Li,

Chenxu Luo,

Xiaodong Yang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Li_2023_CVPR, author = {Li, Jinyu and Luo, Chenxu and Yang, Xiaodong}, title = {PillarNeXt: Rethinking Network Designs for 3D Object Detection in LiDAR Point Clouds}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {17567-17576} }
LINe: Out-of-Distribution Detection by Leveraging Important Neurons: Yong Hyun Ahn,

Gyeong-Moon Park,

Seong Tae Kim; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ahn_2023_CVPR, author = {Ahn, Yong Hyun and Park, Gyeong-Moon and Kim, Seong Tae}, title = {LINe: Out-of-Distribution Detection by Leveraging Important Neurons}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {19852-19862} }
Transforming Radiance Field With Lipschitz Network for Photorealistic 3D Scene Stylization: Zicheng Zhang,

Yinglu Liu,

Congying Han,

Yingwei Pan,

Tiande Guo,

Ting Yao; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhang_2023_CVPR, author = {Zhang, Zicheng and Liu, Yinglu and Han, Congying and Pan, Yingwei and Guo, Tiande and Yao, Ting}, title = {Transforming Radiance Field With Lipschitz Network for Photorealistic 3D Scene Stylization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {20712-20721} }
Guided Depth Super-Resolution by Deep Anisotropic Diffusion: Nando Metzger,

Rodrigo Caye Daudt,

Konrad Schindler; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Metzger_2023_CVPR, author = {Metzger, Nando and Daudt, Rodrigo Caye and Schindler, Konrad}, title = {Guided Depth Super-Resolution by Deep Anisotropic Diffusion}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {18237-18246} }
Fresnel Microfacet BRDF: Unification of Polari-Radiometric Surface-Body Reflection: Tomoki Ichikawa,

Yoshiki Fukao,

Shohei Nobuhara,

Ko Nishino; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ichikawa_2023_CVPR, author = {Ichikawa, Tomoki and Fukao, Yoshiki and Nobuhara, Shohei and Nishino, Ko}, title = {Fresnel Microfacet BRDF: Unification of Polari-Radiometric Surface-Body Reflection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16489-16497} }
Simulated Annealing in Early Layers Leads to Better Generalization: Amir M. Sarfi,

Zahra Karimpour,

Muawiz Chaudhary,

Nasir M. Khalid,

Mirco Ravanelli,

Sudhir Mudur,

Eugene Belilovsky; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Sarfi_2023_CVPR, author = {Sarfi, Amir M. and Karimpour, Zahra and Chaudhary, Muawiz and Khalid, Nasir M. and Ravanelli, Mirco and Mudur, Sudhir and Belilovsky, Eugene}, title = {Simulated Annealing in Early Layers Leads to Better Generalization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {20205-20214} }
Exploring Data Geometry for Continual Learning: Zhi Gao,

Chen Xu,

Feng Li,

Yunde Jia,

Mehrtash Harandi,

Yuwei Wu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Gao_2023_CVPR, author = {Gao, Zhi and Xu, Chen and Li, Feng and Jia, Yunde and Harandi, Mehrtash and Wu, Yuwei}, title = {Exploring Data Geometry for Continual Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {24325-24334} }
Learning Neural Parametric Head Models: Simon Giebenhain,

Tobias Kirschstein,

Markos Georgopoulos,

Martin Rünz,

Lourdes Agapito,

Matthias Nießner; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Giebenhain_2023_CVPR, author = {Giebenhain, Simon and Kirschstein, Tobias and Georgopoulos, Markos and R\"unz, Martin and Agapito, Lourdes and Nie{\ss}ner, Matthias}, title = {Learning Neural Parametric Head Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {21003-21012} }
Removing Objects From Neural Radiance Fields: Silvan Weder,

Guillermo Garcia-Hernando,

Áron Monszpart,

Marc Pollefeys,

Gabriel J. Brostow,

Michael Firman,

Sara Vicente; [pdf] [arXiv]
[bibtex]
@InProceedings{Weder_2023_CVPR, author = {Weder, Silvan and Garcia-Hernando, Guillermo and Monszpart, \'Aron and Pollefeys, Marc and Brostow, Gabriel J. and Firman, Michael and Vicente, Sara}, title = {Removing Objects From Neural Radiance Fields}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16528-16538} }
Structural Multiplane Image: Bridging Neural View Synthesis and 3D Reconstruction: Mingfang Zhang,

Jinglu Wang,

Xiao Li,

Yifei Huang,

Yoichi Sato,

Yan Lu; [pdf] [arXiv]
[bibtex]
@InProceedings{Zhang_2023_CVPR, author = {Zhang, Mingfang and Wang, Jinglu and Li, Xiao and Huang, Yifei and Sato, Yoichi and Lu, Yan}, title = {Structural Multiplane Image: Bridging Neural View Synthesis and 3D Reconstruction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16707-16716} }
Harmonious Teacher for Cross-Domain Object Detection: Jinhong Deng,

Dongli Xu,

Wen Li,

Lixin Duan; [pdf] [supp]
[bibtex]
@InProceedings{Deng_2023_CVPR, author = {Deng, Jinhong and Xu, Dongli and Li, Wen and Duan, Lixin}, title = {Harmonious Teacher for Cross-Domain Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {23829-23838} }
Learning To Predict Scene-Level Implicit 3D From Posed RGBD Data: Nilesh Kulkarni,

Linyi Jin,

Justin Johnson,

David F. Fouhey; [pdf] [supp]
[bibtex]
@InProceedings{Kulkarni_2023_CVPR, author = {Kulkarni, Nilesh and Jin, Linyi and Johnson, Justin and Fouhey, David F.}, title = {Learning To Predict Scene-Level Implicit 3D From Posed RGBD Data}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {17256-17265} }
Physical-World Optical Adversarial Attacks on 3D Face Recognition: Yanjie Li,

Yiquan Li,

Xuelong Dai,

Songtao Guo,

Bin Xiao; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Li_2023_CVPR, author = {Li, Yanjie and Li, Yiquan and Dai, Xuelong and Guo, Songtao and Xiao, Bin}, title = {Physical-World Optical Adversarial Attacks on 3D Face Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {24699-24708} }
Raw Image Reconstruction With Learned Compact Metadata: Yufei Wang,

Yi Yu,

Wenhan Yang,

Lanqing Guo,

Lap-Pui Chau,

Alex C. Kot,

Bihan Wen; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2023_CVPR, author = {Wang, Yufei and Yu, Yi and Yang, Wenhan and Guo, Lanqing and Chau, Lap-Pui and Kot, Alex C. and Wen, Bihan}, title = {Raw Image Reconstruction With Learned Compact Metadata}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {18206-18215} }
Semi-Supervised Video Inpainting With Cycle Consistency Constraints: Zhiliang Wu,

Hanyu Xuan,

Changchang Sun,

Weili Guan,

Kang Zhang,

Yan Yan; [pdf] [arXiv]
[bibtex]
@InProceedings{Wu_2023_CVPR, author = {Wu, Zhiliang and Xuan, Hanyu and Sun, Changchang and Guan, Weili and Zhang, Kang and Yan, Yan}, title = {Semi-Supervised Video Inpainting With Cycle Consistency Constraints}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {22586-22595} }
Level-S$^2$fM: Structure From Motion on Neural Level Set of Implicit Surfaces: Yuxi Xiao,

Nan Xue,

Tianfu Wu,

Gui-Song Xia; [pdf] [supp]
[bibtex]
@InProceedings{Xiao_2023_CVPR, author = {Xiao, Yuxi and Xue, Nan and Wu, Tianfu and Xia, Gui-Song}, title = {Level-S\${\textasciicircum}2\$fM: Structure From Motion on Neural Level Set of Implicit Surfaces}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {17205-17214} }
Neuron Structure Modeling for Generalizable Remote Physiological Measurement: Hao Lu,

Zitong Yu,

Xuesong Niu,

Ying-Cong Chen; [pdf] [arXiv]
[bibtex]
@InProceedings{Lu_2023_CVPR, author = {Lu, Hao and Yu, Zitong and Niu, Xuesong and Chen, Ying-Cong}, title = {Neuron Structure Modeling for Generalizable Remote Physiological Measurement}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {18589-18599} }
Out-of-Candidate Rectification for Weakly Supervised Semantic Segmentation: Zesen Cheng,

Pengchong Qiao,

Kehan Li,

Siheng Li,

Pengxu Wei,

Xiangyang Ji,

Li Yuan,

Chang Liu,

Jie Chen; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Cheng_2023_CVPR, author = {Cheng, Zesen and Qiao, Pengchong and Li, Kehan and Li, Siheng and Wei, Pengxu and Ji, Xiangyang and Yuan, Li and Liu, Chang and Chen, Jie}, title = {Out-of-Candidate Rectification for Weakly Supervised Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {23673-23684} }
MonoATT: Online Monocular 3D Object Detection With Adaptive Token Transformer: Yunsong Zhou,

Hongzi Zhu,

Quan Liu,

Shan Chang,

Minyi Guo; [pdf] [arXiv]
[bibtex]
@InProceedings{Zhou_2023_CVPR, author = {Zhou, Yunsong and Zhu, Hongzi and Liu, Quan and Chang, Shan and Guo, Minyi}, title = {MonoATT: Online Monocular 3D Object Detection With Adaptive Token Transformer}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {17493-17503} }
Image Quality-Aware Diagnosis via Meta-Knowledge Co-Embedding: Haoxuan Che,

Siyu Chen,

Hao Chen; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Che_2023_CVPR, author = {Che, Haoxuan and Chen, Siyu and Chen, Hao}, title = {Image Quality-Aware Diagnosis via Meta-Knowledge Co-Embedding}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {19819-19829} }
Learning 3D Representations From 2D Pre-Trained Models via Image-to-Point Masked Autoencoders: Renrui Zhang,

Liuhui Wang,

Yu Qiao,

Peng Gao,

Hongsheng Li; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhang_2023_CVPR, author = {Zhang, Renrui and Wang, Liuhui and Qiao, Yu and Gao, Peng and Li, Hongsheng}, title = {Learning 3D Representations From 2D Pre-Trained Models via Image-to-Point Masked Autoencoders}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {21769-21780} }
BEVFormer v2: Adapting Modern Image Backbones to Bird's-Eye-View Recognition via Perspective Supervision: Chenyu Yang,

Yuntao Chen,

Hao Tian,

Chenxin Tao,

Xizhou Zhu,

Zhaoxiang Zhang,

Gao Huang,

Hongyang Li,

Yu Qiao,

Lewei Lu,

Jie Zhou,

Jifeng Dai; [pdf] [supp]
[bibtex]
@InProceedings{Yang_2023_CVPR, author = {Yang, Chenyu and Chen, Yuntao and Tian, Hao and Tao, Chenxin and Zhu, Xizhou and Zhang, Zhaoxiang and Huang, Gao and Li, Hongyang and Qiao, Yu and Lu, Lewei and Zhou, Jie and Dai, Jifeng}, title = {BEVFormer v2: Adapting Modern Image Backbones to Bird's-Eye-View Recognition via Perspective Supervision}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {17830-17839} }
Object Discovery From Motion-Guided Tokens: Zhipeng Bao,

Pavel Tokmakov,

Yu-Xiong Wang,

Adrien Gaidon,

Martial Hebert; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Bao_2023_CVPR, author = {Bao, Zhipeng and Tokmakov, Pavel and Wang, Yu-Xiong and Gaidon, Adrien and Hebert, Martial}, title = {Object Discovery From Motion-Guided Tokens}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {22972-22981} }
Event-Based Video Frame Interpolation With Cross-Modal Asymmetric Bidirectional Motion Fields: Taewoo Kim,

Yujeong Chae,

Hyun-Kurl Jang,

Kuk-Jin Yoon; [pdf] [supp]
[bibtex]
@InProceedings{Kim_2023_CVPR, author = {Kim, Taewoo and Chae, Yujeong and Jang, Hyun-Kurl and Yoon, Kuk-Jin}, title = {Event-Based Video Frame Interpolation With Cross-Modal Asymmetric Bidirectional Motion Fields}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {18032-18042} }
VolRecon: Volume Rendering of Signed Ray Distance Functions for Generalizable Multi-View Reconstruction: Yufan Ren,

Fangjinhua Wang,

Tong Zhang,

Marc Pollefeys,

Sabine Süsstrunk; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ren_2023_CVPR, author = {Ren, Yufan and Wang, Fangjinhua and Zhang, Tong and Pollefeys, Marc and S\"usstrunk, Sabine}, title = {VolRecon: Volume Rendering of Signed Ray Distance Functions for Generalizable Multi-View Reconstruction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16685-16695} }
DA-DETR: Domain Adaptive Detection Transformer With Information Fusion: Jingyi Zhang,

Jiaxing Huang,

Zhipeng Luo,

Gongjie Zhang,

Xiaoqin Zhang,

Shijian Lu; [pdf] [supp]
[bibtex]
@InProceedings{Zhang_2023_CVPR, author = {Zhang, Jingyi and Huang, Jiaxing and Luo, Zhipeng and Zhang, Gongjie and Zhang, Xiaoqin and Lu, Shijian}, title = {DA-DETR: Domain Adaptive Detection Transformer With Information Fusion}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {23787-23798} }
Vision Transformers Are Good Mask Auto-Labelers: Shiyi Lan,

Xitong Yang,

Zhiding Yu,

Zuxuan Wu,

Jose M. Alvarez,

Anima Anandkumar; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Lan_2023_CVPR, author = {Lan, Shiyi and Yang, Xitong and Yu, Zhiding and Wu, Zuxuan and Alvarez, Jose M. and Anandkumar, Anima}, title = {Vision Transformers Are Good Mask Auto-Labelers}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {23745-23755} }
Neural Transformation Fields for Arbitrary-Styled Font Generation: Bin Fu,

Junjun He,

Jianjun Wang,

Yu Qiao; [pdf] [supp]
[bibtex]
@InProceedings{Fu_2023_CVPR, author = {Fu, Bin and He, Junjun and Wang, Jianjun and Qiao, Yu}, title = {Neural Transformation Fields for Arbitrary-Styled Font Generation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {22438-22447} }
EDICT: Exact Diffusion Inversion via Coupled Transformations: Bram Wallace,

Akash Gokul,

Nikhil Naik; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wallace_2023_CVPR, author = {Wallace, Bram and Gokul, Akash and Naik, Nikhil}, title = {EDICT: Exact Diffusion Inversion via Coupled Transformations}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {22532-22541} }
AeDet: Azimuth-Invariant Multi-View 3D Object Detection: Chengjian Feng,

Zequn Jie,

Yujie Zhong,

Xiangxiang Chu,

Lin Ma; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Feng_2023_CVPR, author = {Feng, Chengjian and Jie, Zequn and Zhong, Yujie and Chu, Xiangxiang and Ma, Lin}, title = {AeDet: Azimuth-Invariant Multi-View 3D Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {21580-21588} }
OCELOT: Overlapped Cell on Tissue Dataset for Histopathology: Jeongun Ryu,

Aaron Valero Puche,

JaeWoong Shin,

Seonwook Park,

Biagio Brattoli,

Jinhee Lee,

Wonkyung Jung,

Soo Ick Cho,

Kyunghyun Paeng,

Chan-Young Ock,

Donggeun Yoo,

Sérgio Pereira; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ryu_2023_CVPR, author = {Ryu, Jeongun and Puche, Aaron Valero and Shin, JaeWoong and Park, Seonwook and Brattoli, Biagio and Lee, Jinhee and Jung, Wonkyung and Cho, Soo Ick and Paeng, Kyunghyun and Ock, Chan-Young and Yoo, Donggeun and Pereira, S\'ergio}, title = {OCELOT: Overlapped Cell on Tissue Dataset for Histopathology}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {23902-23912} }
Unsupervised Sampling Promoting for Stochastic Human Trajectory Prediction: Guangyi Chen,

Zhenhao Chen,

Shunxing Fan,

Kun Zhang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chen_2023_CVPR, author = {Chen, Guangyi and Chen, Zhenhao and Fan, Shunxing and Zhang, Kun}, title = {Unsupervised Sampling Promoting for Stochastic Human Trajectory Prediction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {17874-17884} }
Safe Latent Diffusion: Mitigating Inappropriate Degeneration in Diffusion Models: Patrick Schramowski,

Manuel Brack,

Björn Deiseroth,

Kristian Kersting; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Schramowski_2023_CVPR, author = {Schramowski, Patrick and Brack, Manuel and Deiseroth, Bj\"orn and Kersting, Kristian}, title = {Safe Latent Diffusion: Mitigating Inappropriate Degeneration in Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {22522-22531} }
Superclass Learning With Representation Enhancement: Zeyu Gan,

Suyun Zhao,

Jinlong Kang,

Liyuan Shang,

Hong Chen,

Cuiping Li; [pdf] [supp]
[bibtex]
@InProceedings{Gan_2023_CVPR, author = {Gan, Zeyu and Zhao, Suyun and Kang, Jinlong and Shang, Liyuan and Chen, Hong and Li, Cuiping}, title = {Superclass Learning With Representation Enhancement}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {24060-24069} }
Visual Prompt Tuning for Generative Transfer Learning: Kihyuk Sohn,

Huiwen Chang,

José Lezama,

Luisa Polania,

Han Zhang,

Yuan Hao,

Irfan Essa,

Lu Jiang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Sohn_2023_CVPR, author = {Sohn, Kihyuk and Chang, Huiwen and Lezama, Jos\'e and Polania, Luisa and Zhang, Han and Hao, Yuan and Essa, Irfan and Jiang, Lu}, title = {Visual Prompt Tuning for Generative Transfer Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {19840-19851} }
ReLight My NeRF: A Dataset for Novel View Synthesis and Relighting of Real World Objects: Marco Toschi,

Riccardo De Matteo,

Riccardo Spezialetti,

Daniele De Gregorio,

Luigi Di Stefano,

Samuele Salti; [pdf] [arXiv]
[bibtex]
@InProceedings{Toschi_2023_CVPR, author = {Toschi, Marco and De Matteo, Riccardo and Spezialetti, Riccardo and De Gregorio, Daniele and Di Stefano, Luigi and Salti, Samuele}, title = {ReLight My NeRF: A Dataset for Novel View Synthesis and Relighting of Real World Objects}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {20762-20772} }
Content-Aware Token Sharing for Efficient Semantic Segmentation With Vision Transformers: Chenyang Lu,

Daan de Geus,

Gijs Dubbelman; [pdf] [supp]
[bibtex]
@InProceedings{Lu_2023_CVPR, author = {Lu, Chenyang and de Geus, Daan and Dubbelman, Gijs}, title = {Content-Aware Token Sharing for Efficient Semantic Segmentation With Vision Transformers}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {23631-23640} }
Are Binary Annotations Sufficient? Video Moment Retrieval via Hierarchical Uncertainty-Based Active Learning: Wei Ji,

Renjie Liang,

Zhedong Zheng,

Wenqiao Zhang,

Shengyu Zhang,

Juncheng Li,

Mengze Li,

Tat-seng Chua; [pdf]
[bibtex]
@InProceedings{Ji_2023_CVPR, author = {Ji, Wei and Liang, Renjie and Zheng, Zhedong and Zhang, Wenqiao and Zhang, Shengyu and Li, Juncheng and Li, Mengze and Chua, Tat-seng}, title = {Are Binary Annotations Sufficient? Video Moment Retrieval via Hierarchical Uncertainty-Based Active Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {23013-23022} }
VGFlow: Visibility Guided Flow Network for Human Reposing: Rishabh Jain,

Krishna Kumar Singh,

Mayur Hemani,

Jingwan Lu,

Mausoom Sarkar,

Duygu Ceylan,

Balaji Krishnamurthy; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Jain_2023_CVPR, author = {Jain, Rishabh and Singh, Krishna Kumar and Hemani, Mayur and Lu, Jingwan and Sarkar, Mausoom and Ceylan, Duygu and Krishnamurthy, Balaji}, title = {VGFlow: Visibility Guided Flow Network for Human Reposing}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {21088-21097} }
Improving Selective Visual Question Answering by Learning From Your Peers: Corentin Dancette,

Spencer Whitehead,

Rishabh Maheshwary,

Ramakrishna Vedantam,

Stefan Scherer,

Xinlei Chen,

Matthieu Cord,

Marcus Rohrbach; [pdf] [supp]
[bibtex]
@InProceedings{Dancette_2023_CVPR, author = {Dancette, Corentin and Whitehead, Spencer and Maheshwary, Rishabh and Vedantam, Ramakrishna and Scherer, Stefan and Chen, Xinlei and Cord, Matthieu and Rohrbach, Marcus}, title = {Improving Selective Visual Question Answering by Learning From Your Peers}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {24049-24059} }
Look, Radiate, and Learn: Self-Supervised Localisation via Radio-Visual Correspondence: Mohammed Alloulah,

Maximilian Arnold; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Alloulah_2023_CVPR, author = {Alloulah, Mohammed and Arnold, Maximilian}, title = {Look, Radiate, and Learn: Self-Supervised Localisation via Radio-Visual Correspondence}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {17430-17440} }
Shape-Erased Feature Learning for Visible-Infrared Person Re-Identification: Jiawei Feng,

Ancong Wu,

Wei-Shi Zheng; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Feng_2023_CVPR, author = {Feng, Jiawei and Wu, Ancong and Zheng, Wei-Shi}, title = {Shape-Erased Feature Learning for Visible-Infrared Person Re-Identification}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {22752-22761} }
On Calibrating Semantic Segmentation Models: Analyses and an Algorithm: Dongdong Wang,

Boqing Gong,

Liqiang Wang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2023_CVPR, author = {Wang, Dongdong and Gong, Boqing and Wang, Liqiang}, title = {On Calibrating Semantic Segmentation Models: Analyses and an Algorithm}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {23652-23662} }
Visual Atoms: Pre-Training Vision Transformers With Sinusoidal Waves: Sora Takashima,

Ryo Hayamizu,

Nakamasa Inoue,

Hirokatsu Kataoka,

Rio Yokota; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Takashima_2023_CVPR, author = {Takashima, Sora and Hayamizu, Ryo and Inoue, Nakamasa and Kataoka, Hirokatsu and Yokota, Rio}, title = {Visual Atoms: Pre-Training Vision Transformers With Sinusoidal Waves}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {18579-18588} }
Masked Autoencoding Does Not Help Natural Language Supervision at Scale: Floris Weers,

Vaishaal Shankar,

Angelos Katharopoulos,

Yinfei Yang,

Tom Gunter; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Weers_2023_CVPR, author = {Weers, Floris and Shankar, Vaishaal and Katharopoulos, Angelos and Yang, Yinfei and Gunter, Tom}, title = {Masked Autoencoding Does Not Help Natural Language Supervision at Scale}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {23432-23444} }
Transductive Few-Shot Learning With Prototype-Based Label Propagation by Iterative Graph Refinement: Hao Zhu,

Piotr Koniusz; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhu_2023_CVPR, author = {Zhu, Hao and Koniusz, Piotr}, title = {Transductive Few-Shot Learning With Prototype-Based Label Propagation by Iterative Graph Refinement}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {23996-24006} }
Binary Latent Diffusion: Ze Wang,

Jiang Wang,

Zicheng Liu,

Qiang Qiu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2023_CVPR, author = {Wang, Ze and Wang, Jiang and Liu, Zicheng and Qiu, Qiang}, title = {Binary Latent Diffusion}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {22576-22585} }
FLAG3D: A 3D Fitness Activity Dataset With Language Instruction: Yansong Tang,

Jinpeng Liu,

Aoyang Liu,

Bin Yang,

Wenxun Dai,

Yongming Rao,

Jiwen Lu,

Jie Zhou,

Xiu Li; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Tang_2023_CVPR, author = {Tang, Yansong and Liu, Jinpeng and Liu, Aoyang and Yang, Bin and Dai, Wenxun and Rao, Yongming and Lu, Jiwen and Zhou, Jie and Li, Xiu}, title = {FLAG3D: A 3D Fitness Activity Dataset With Language Instruction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {22106-22117} }
NeuralUDF: Learning Unsigned Distance Fields for Multi-View Reconstruction of Surfaces With Arbitrary Topologies: Xiaoxiao Long,

Cheng Lin,

Lingjie Liu,

Yuan Liu,

Peng Wang,

Christian Theobalt,

Taku Komura,

Wenping Wang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Long_2023_CVPR, author = {Long, Xiaoxiao and Lin, Cheng and Liu, Lingjie and Liu, Yuan and Wang, Peng and Theobalt, Christian and Komura, Taku and Wang, Wenping}, title = {NeuralUDF: Learning Unsigned Distance Fields for Multi-View Reconstruction of Surfaces With Arbitrary Topologies}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {20834-20843} }
Collaborative Static and Dynamic Vision-Language Streams for Spatio-Temporal Video Grounding: Zihang Lin,

Chaolei Tan,

Jian-Fang Hu,

Zhi Jin,

Tiancai Ye,

Wei-Shi Zheng; [pdf] [supp]
[bibtex]
@InProceedings{Lin_2023_CVPR, author = {Lin, Zihang and Tan, Chaolei and Hu, Jian-Fang and Jin, Zhi and Ye, Tiancai and Zheng, Wei-Shi}, title = {Collaborative Static and Dynamic Vision-Language Streams for Spatio-Temporal Video Grounding}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {23100-23109} }
Residual Degradation Learning Unfolding Framework With Mixing Priors Across Spectral and Spatial for Compressive Spectral Imaging: Yubo Dong,

Dahua Gao,

Tian Qiu,

Yuyan Li,

Minxi Yang,

Guangming Shi; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Dong_2023_CVPR, author = {Dong, Yubo and Gao, Dahua and Qiu, Tian and Li, Yuyan and Yang, Minxi and Shi, Guangming}, title = {Residual Degradation Learning Unfolding Framework With Mixing Priors Across Spectral and Spatial for Compressive Spectral Imaging}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {22262-22271} }
GamutMLP: A Lightweight MLP for Color Loss Recovery: Hoang M. Le,

Brian Price,

Scott Cohen,

Michael S. Brown; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Le_2023_CVPR, author = {Le, Hoang M. and Price, Brian and Cohen, Scott and Brown, Michael S.}, title = {GamutMLP: A Lightweight MLP for Color Loss Recovery}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {18268-18277} }
Instance-Aware Domain Generalization for Face Anti-Spoofing: Qianyu Zhou,

Ke-Yue Zhang,

Taiping Yao,

Xuequan Lu,

Ran Yi,

Shouhong Ding,

Lizhuang Ma; [pdf] [arXiv]
[bibtex]
@InProceedings{Zhou_2023_CVPR, author = {Zhou, Qianyu and Zhang, Ke-Yue and Yao, Taiping and Lu, Xuequan and Yi, Ran and Ding, Shouhong and Ma, Lizhuang}, title = {Instance-Aware Domain Generalization for Face Anti-Spoofing}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {20453-20463} }
Robust and Scalable Gaussian Process Regression and Its Applications: Yifan Lu,

Jiayi Ma,

Leyuan Fang,

Xin Tian,

Junjun Jiang; [pdf] [supp]
[bibtex]
@InProceedings{Lu_2023_CVPR, author = {Lu, Yifan and Ma, Jiayi and Fang, Leyuan and Tian, Xin and Jiang, Junjun}, title = {Robust and Scalable Gaussian Process Regression and Its Applications}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {21950-21959} }
Shepherding Slots to Objects: Towards Stable and Robust Object-Centric Learning: Jinwoo Kim,

Janghyuk Choi,

Ho-Jin Choi,

Seon Joo Kim; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kim_2023_CVPR, author = {Kim, Jinwoo and Choi, Janghyuk and Choi, Ho-Jin and Kim, Seon Joo}, title = {Shepherding Slots to Objects: Towards Stable and Robust Object-Centric Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {19198-19207} }
High-Fidelity Event-Radiance Recovery via Transient Event Frequency: Jin Han,

Yuta Asano,

Boxin Shi,

Yinqiang Zheng,

Imari Sato; [pdf] [supp]
[bibtex]
@InProceedings{Han_2023_CVPR, author = {Han, Jin and Asano, Yuta and Shi, Boxin and Zheng, Yinqiang and Sato, Imari}, title = {High-Fidelity Event-Radiance Recovery via Transient Event Frequency}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {20616-20625} }
NeMo: Learning 3D Neural Motion Fields From Multiple Video Instances of the Same Action: Kuan-Chieh Wang,

Zhenzhen Weng,

Maria Xenochristou,

João Pedro Araújo,

Jeffrey Gu,

Karen Liu,

Serena Yeung; [pdf] [supp]
[bibtex]
@InProceedings{Wang_2023_CVPR, author = {Wang, Kuan-Chieh and Weng, Zhenzhen and Xenochristou, Maria and Ara\'ujo, Jo\~ao Pedro and Gu, Jeffrey and Liu, Karen and Yeung, Serena}, title = {NeMo: Learning 3D Neural Motion Fields From Multiple Video Instances of the Same Action}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {22129-22138} }
RIATIG: Reliable and Imperceptible Adversarial Text-to-Image Generation With Natural Prompts: Han Liu,

Yuhao Wu,

Shixuan Zhai,

Bo Yuan,

Ning Zhang; [pdf]
[bibtex]
@InProceedings{Liu_2023_CVPR, author = {Liu, Han and Wu, Yuhao and Zhai, Shixuan and Yuan, Bo and Zhang, Ning}, title = {RIATIG: Reliable and Imperceptible Adversarial Text-to-Image Generation With Natural Prompts}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {20585-20594} }
GLIGEN: Open-Set Grounded Text-to-Image Generation: Yuheng Li,

Haotian Liu,

Qingyang Wu,

Fangzhou Mu,

Jianwei Yang,

Jianfeng Gao,

Chunyuan Li,

Yong Jae Lee; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Li_2023_CVPR, author = {Li, Yuheng and Liu, Haotian and Wu, Qingyang and Mu, Fangzhou and Yang, Jianwei and Gao, Jianfeng and Li, Chunyuan and Lee, Yong Jae}, title = {GLIGEN: Open-Set Grounded Text-to-Image Generation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {22511-22521} }
Learning Geometry-Aware Representations by Sketching: Hyundo Lee,

Inwoo Hwang,

Hyunsung Go,

Won-Seok Choi,

Kibeom Kim,

Byoung-Tak Zhang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Lee_2023_CVPR, author = {Lee, Hyundo and Hwang, Inwoo and Go, Hyunsung and Choi, Won-Seok and Kim, Kibeom and Zhang, Byoung-Tak}, title = {Learning Geometry-Aware Representations by Sketching}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {23315-23326} }
SVFormer: Semi-Supervised Video Transformer for Action Recognition: Zhen Xing,

Qi Dai,

Han Hu,

Jingjing Chen,

Zuxuan Wu,

Yu-Gang Jiang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Xing_2023_CVPR, author = {Xing, Zhen and Dai, Qi and Hu, Han and Chen, Jingjing and Wu, Zuxuan and Jiang, Yu-Gang}, title = {SVFormer: Semi-Supervised Video Transformer for Action Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {18816-18826} }
X-Avatar: Expressive Human Avatars: Kaiyue Shen,

Chen Guo,

Manuel Kaufmann,

Juan Jose Zarate,

Julien Valentin,

Jie Song,

Otmar Hilliges; [pdf] [supp]
[bibtex]
@InProceedings{Shen_2023_CVPR, author = {Shen, Kaiyue and Guo, Chen and Kaufmann, Manuel and Zarate, Juan Jose and Valentin, Julien and Song, Jie and Hilliges, Otmar}, title = {X-Avatar: Expressive Human Avatars}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16911-16921} }
AccelIR: Task-Aware Image Compression for Accelerating Neural Restoration: Juncheol Ye,

Hyunho Yeo,

Jinwoo Park,

Dongsu Han; [pdf] [supp]
[bibtex]
@InProceedings{Ye_2023_CVPR, author = {Ye, Juncheol and Yeo, Hyunho and Park, Jinwoo and Han, Dongsu}, title = {AccelIR: Task-Aware Image Compression for Accelerating Neural Restoration}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {18216-18226} }
BEV-Guided Multi-Modality Fusion for Driving Perception: Yunze Man,

Liang-Yan Gui,

Yu-Xiong Wang; [pdf] [supp]
[bibtex]
@InProceedings{Man_2023_CVPR, author = {Man, Yunze and Gui, Liang-Yan and Wang, Yu-Xiong}, title = {BEV-Guided Multi-Modality Fusion for Driving Perception}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {21960-21969} }
Proximal Splitting Adversarial Attack for Semantic Segmentation: Jérôme Rony,

Jean-Christophe Pesquet,

Ismail Ben Ayed; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Rony_2023_CVPR, author = {Rony, J\'er\^ome and Pesquet, Jean-Christophe and Ben Ayed, Ismail}, title = {Proximal Splitting Adversarial Attack for Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {20524-20533} }
Improved Test-Time Adaptation for Domain Generalization: Liang Chen,

Yong Zhang,

Yibing Song,

Ying Shan,

Lingqiao Liu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chen_2023_CVPR, author = {Chen, Liang and Zhang, Yong and Song, Yibing and Shan, Ying and Liu, Lingqiao}, title = {Improved Test-Time Adaptation for Domain Generalization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {24172-24182} }
Correspondence Transformers With Asymmetric Feature Learning and Matching Flow Super-Resolution: Yixuan Sun,

Dongyang Zhao,

Zhangyue Yin,

Yiwen Huang,

Tao Gui,

Wenqiang Zhang,

Weifeng Ge; [pdf] [supp]
[bibtex]
@InProceedings{Sun_2023_CVPR, author = {Sun, Yixuan and Zhao, Dongyang and Yin, Zhangyue and Huang, Yiwen and Gui, Tao and Zhang, Wenqiang and Ge, Weifeng}, title = {Correspondence Transformers With Asymmetric Feature Learning and Matching Flow Super-Resolution}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {17787-17796} }
Adjustment and Alignment for Unbiased Open Set Domain Adaptation: Wuyang Li,

Jie Liu,

Bo Han,

Yixuan Yuan; [pdf] [supp]
[bibtex]
@InProceedings{Li_2023_CVPR, author = {Li, Wuyang and Liu, Jie and Han, Bo and Yuan, Yixuan}, title = {Adjustment and Alignment for Unbiased Open Set Domain Adaptation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {24110-24119} }
ESLAM: Efficient Dense SLAM System Based on Hybrid Representation of Signed Distance Fields: Mohammad Mahdi Johari,

Camilla Carta,

François Fleuret; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Johari_2023_CVPR, author = {Johari, Mohammad Mahdi and Carta, Camilla and Fleuret, Fran\c{c}ois}, title = {ESLAM: Efficient Dense SLAM System Based on Hybrid Representation of Signed Distance Fields}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {17408-17419} }
Unsupervised Space-Time Network for Temporally-Consistent Segmentation of Multiple Motions: Etienne Meunier,

Patrick Bouthemy; [pdf] [supp]
[bibtex]
@InProceedings{Meunier_2023_CVPR, author = {Meunier, Etienne and Bouthemy, Patrick}, title = {Unsupervised Space-Time Network for Temporally-Consistent Segmentation of Multiple Motions}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {22139-22148} }
iDisc: Internal Discretization for Monocular Depth Estimation: Luigi Piccinelli,

Christos Sakaridis,

Fisher Yu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Piccinelli_2023_CVPR, author = {Piccinelli, Luigi and Sakaridis, Christos and Yu, Fisher}, title = {iDisc: Internal Discretization for Monocular Depth Estimation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {21477-21487} }
Balancing Logit Variation for Long-Tailed Semantic Segmentation: Yuchao Wang,

Jingjing Fei,

Haochen Wang,

Wei Li,

Tianpeng Bao,

Liwei Wu,

Rui Zhao,

Yujun Shen; [pdf] [supp]
[bibtex]
@InProceedings{Wang_2023_CVPR, author = {Wang, Yuchao and Fei, Jingjing and Wang, Haochen and Li, Wei and Bao, Tianpeng and Wu, Liwei and Zhao, Rui and Shen, Yujun}, title = {Balancing Logit Variation for Long-Tailed Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {19561-19573} }
Single Image Depth Prediction Made Better: A Multivariate Gaussian Take: Ce Liu,

Suryansh Kumar,

Shuhang Gu,

Radu Timofte,

Luc Van Gool; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Liu_2023_CVPR, author = {Liu, Ce and Kumar, Suryansh and Gu, Shuhang and Timofte, Radu and Van Gool, Luc}, title = {Single Image Depth Prediction Made Better: A Multivariate Gaussian Take}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {17346-17356} }
Query-Centric Trajectory Prediction: Zikang Zhou,

Jianping Wang,

Yung-Hui Li,

Yu-Kai Huang; [pdf] [supp]
[bibtex]
@InProceedings{Zhou_2023_CVPR, author = {Zhou, Zikang and Wang, Jianping and Li, Yung-Hui and Huang, Yu-Kai}, title = {Query-Centric Trajectory Prediction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {17863-17873} }
The Enemy of My Enemy Is My Friend: Exploring Inverse Adversaries for Improving Adversarial Training: Junhao Dong,

Seyed-Mohsen Moosavi-Dezfooli,

Jianhuang Lai,

Xiaohua Xie; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Dong_2023_CVPR, author = {Dong, Junhao and Moosavi-Dezfooli, Seyed-Mohsen and Lai, Jianhuang and Xie, Xiaohua}, title = {The Enemy of My Enemy Is My Friend: Exploring Inverse Adversaries for Improving Adversarial Training}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {24678-24687} }
Exploring Motion Ambiguity and Alignment for High-Quality Video Frame Interpolation: Kun Zhou,

Wenbo Li,

Xiaoguang Han,

Jiangbo Lu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhou_2023_CVPR, author = {Zhou, Kun and Li, Wenbo and Han, Xiaoguang and Lu, Jiangbo}, title = {Exploring Motion Ambiguity and Alignment for High-Quality Video Frame Interpolation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {22169-22179} }
Knowledge Distillation for 6D Pose Estimation by Aligning Distributions of Local Predictions: Shuxuan Guo,

Yinlin Hu,

Jose M. Alvarez,

Mathieu Salzmann; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Guo_2023_CVPR, author = {Guo, Shuxuan and Hu, Yinlin and Alvarez, Jose M. and Salzmann, Mathieu}, title = {Knowledge Distillation for 6D Pose Estimation by Aligning Distributions of Local Predictions}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {18633-18642} }
Adaptive Annealing for Robust Geometric Estimation: Chitturi Sidhartha,

Lalit Manam,

Venu Madhav Govindu; [pdf] [supp]
[bibtex]
@InProceedings{Sidhartha_2023_CVPR, author = {Sidhartha, Chitturi and Manam, Lalit and Govindu, Venu Madhav}, title = {Adaptive Annealing for Robust Geometric Estimation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {21929-21939} }
PointListNet: Deep Learning on 3D Point Lists: Hehe Fan,

Linchao Zhu,

Yi Yang,

Mohan Kankanhalli; [pdf] [supp]
[bibtex]
@InProceedings{Fan_2023_CVPR, author = {Fan, Hehe and Zhu, Linchao and Yang, Yi and Kankanhalli, Mohan}, title = {PointListNet: Deep Learning on 3D Point Lists}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {17692-17701} }
Upcycling Models Under Domain and Category Shift: Sanqing Qu,

Tianpei Zou,

Florian Röhrbein,

Cewu Lu,

Guang Chen,

Dacheng Tao,

Changjun Jiang; [pdf] [supp]
[bibtex]
@InProceedings{Qu_2023_CVPR, author = {Qu, Sanqing and Zou, Tianpei and R\"ohrbein, Florian and Lu, Cewu and Chen, Guang and Tao, Dacheng and Jiang, Changjun}, title = {Upcycling Models Under Domain and Category Shift}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {20019-20028} }
Single Domain Generalization for LiDAR Semantic Segmentation: Hyeonseong Kim,

Yoonsu Kang,

Changgyoon Oh,

Kuk-Jin Yoon; [pdf] [supp]
[bibtex]
@InProceedings{Kim_2023_CVPR, author = {Kim, Hyeonseong and Kang, Yoonsu and Oh, Changgyoon and Yoon, Kuk-Jin}, title = {Single Domain Generalization for LiDAR Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {17587-17598} }
SLACK: Stable Learning of Augmentations With Cold-Start and KL Regularization: Juliette Marrie,

Michael Arbel,

Diane Larlus,

Julien Mairal; [pdf] [supp]
[bibtex]
@InProceedings{Marrie_2023_CVPR, author = {Marrie, Juliette and Arbel, Michael and Larlus, Diane and Mairal, Julien}, title = {SLACK: Stable Learning of Augmentations With Cold-Start and KL Regularization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {24306-24314} }
Gradient Norm Aware Minimization Seeks First-Order Flatness and Improves Generalization: Xingxuan Zhang,

Renzhe Xu,

Han Yu,

Hao Zou,

Peng Cui; [pdf] [arXiv]
[bibtex]
@InProceedings{Zhang_2023_CVPR, author = {Zhang, Xingxuan and Xu, Renzhe and Yu, Han and Zou, Hao and Cui, Peng}, title = {Gradient Norm Aware Minimization Seeks First-Order Flatness and Improves Generalization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {20247-20257} }
Latency Matters: Real-Time Action Forecasting Transformer: Harshayu Girase,

Nakul Agarwal,

Chiho Choi,

Karttikeya Mangalam; [pdf] [supp]
[bibtex]
@InProceedings{Girase_2023_CVPR, author = {Girase, Harshayu and Agarwal, Nakul and Choi, Chiho and Mangalam, Karttikeya}, title = {Latency Matters: Real-Time Action Forecasting Transformer}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {18759-18769} }
HierVL: Learning Hierarchical Video-Language Embeddings: Kumar Ashutosh,

Rohit Girdhar,

Lorenzo Torresani,

Kristen Grauman; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ashutosh_2023_CVPR, author = {Ashutosh, Kumar and Girdhar, Rohit and Torresani, Lorenzo and Grauman, Kristen}, title = {HierVL: Learning Hierarchical Video-Language Embeddings}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {23066-23078} }
GraVoS: Voxel Selection for 3D Point-Cloud Detection: Oren Shrout,

Yizhak Ben-Shabat,

Ayellet Tal; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Shrout_2023_CVPR, author = {Shrout, Oren and Ben-Shabat, Yizhak and Tal, Ayellet}, title = {GraVoS: Voxel Selection for 3D Point-Cloud Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {21684-21693} }
RobustNeRF: Ignoring Distractors With Robust Losses: Sara Sabour,

Suhani Vora,

Daniel Duckworth,

Ivan Krasin,

David J. Fleet,

Andrea Tagliasacchi; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Sabour_2023_CVPR, author = {Sabour, Sara and Vora, Suhani and Duckworth, Daniel and Krasin, Ivan and Fleet, David J. and Tagliasacchi, Andrea}, title = {RobustNeRF: Ignoring Distractors With Robust Losses}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {20626-20636} }
Spherical Transformer for LiDAR-Based 3D Recognition: Xin Lai,

Yukang Chen,

Fanbin Lu,

Jianhui Liu,

Jiaya Jia; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Lai_2023_CVPR, author = {Lai, Xin and Chen, Yukang and Lu, Fanbin and Liu, Jianhui and Jia, Jiaya}, title = {Spherical Transformer for LiDAR-Based 3D Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {17545-17555} }
Watch or Listen: Robust Audio-Visual Speech Recognition With Visual Corruption Modeling and Reliability Scoring: Joanna Hong,

Minsu Kim,

Jeongsoo Choi,

Yong Man Ro; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Hong_2023_CVPR, author = {Hong, Joanna and Kim, Minsu and Choi, Jeongsoo and Ro, Yong Man}, title = {Watch or Listen: Robust Audio-Visual Speech Recognition With Visual Corruption Modeling and Reliability Scoring}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {18783-18794} }
VisFusion: Visibility-Aware Online 3D Scene Reconstruction From Videos: Huiyu Gao,

Wei Mao,

Miaomiao Liu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Gao_2023_CVPR, author = {Gao, Huiyu and Mao, Wei and Liu, Miaomiao}, title = {VisFusion: Visibility-Aware Online 3D Scene Reconstruction From Videos}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {17317-17326} }
Towards Transferable Targeted Adversarial Examples: Zhibo Wang,

Hongshan Yang,

Yunhe Feng,

Peng Sun,

Hengchang Guo,

Zhifei Zhang,

Kui Ren; [pdf]
[bibtex]
@InProceedings{Wang_2023_CVPR, author = {Wang, Zhibo and Yang, Hongshan and Feng, Yunhe and Sun, Peng and Guo, Hengchang and Zhang, Zhifei and Ren, Kui}, title = {Towards Transferable Targeted Adversarial Examples}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {20534-20543} }
C-SFDA: A Curriculum Learning Aided Self-Training Framework for Efficient Source Free Domain Adaptation: Nazmul Karim,

Niluthpol Chowdhury Mithun,

Abhinav Rajvanshi,

Han-pang Chiu,

Supun Samarasekera,

Nazanin Rahnavard; [pdf] [supp]
[bibtex]
@InProceedings{Karim_2023_CVPR, author = {Karim, Nazmul and Mithun, Niluthpol Chowdhury and Rajvanshi, Abhinav and Chiu, Han-pang and Samarasekera, Supun and Rahnavard, Nazanin}, title = {C-SFDA: A Curriculum Learning Aided Self-Training Framework for Efficient Source Free Domain Adaptation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {24120-24131} }
Modeling the Distributional Uncertainty for Salient Object Detection Models: Xinyu Tian,

Jing Zhang,

Mochu Xiang,

Yuchao Dai; [pdf]
[bibtex]
@InProceedings{Tian_2023_CVPR, author = {Tian, Xinyu and Zhang, Jing and Xiang, Mochu and Dai, Yuchao}, title = {Modeling the Distributional Uncertainty for Salient Object Detection Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {19660-19670} }
Kernel Aware Resampler: Michael Bernasconi,

Abdelaziz Djelouah,

Farnood Salehi,

Markus Gross,

Christopher Schroers; [pdf] [supp]
[bibtex]
@InProceedings{Bernasconi_2023_CVPR, author = {Bernasconi, Michael and Djelouah, Abdelaziz and Salehi, Farnood and Gross, Markus and Schroers, Christopher}, title = {Kernel Aware Resampler}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {22347-22355} }
LaserMix for Semi-Supervised LiDAR Semantic Segmentation: Lingdong Kong,

Jiawei Ren,

Liang Pan,

Ziwei Liu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kong_2023_CVPR, author = {Kong, Lingdong and Ren, Jiawei and Pan, Liang and Liu, Ziwei}, title = {LaserMix for Semi-Supervised LiDAR Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {21705-21715} }
Complementary Intrinsics From Neural Radiance Fields and CNNs for Outdoor Scene Relighting: Siqi Yang,

Xuanning Cui,

Yongjie Zhu,

Jiajun Tang,

Si Li,

Zhaofei Yu,

Boxin Shi; [pdf] [supp]
[bibtex]
@InProceedings{Yang_2023_CVPR, author = {Yang, Siqi and Cui, Xuanning and Zhu, Yongjie and Tang, Jiajun and Li, Si and Yu, Zhaofei and Shi, Boxin}, title = {Complementary Intrinsics From Neural Radiance Fields and CNNs for Outdoor Scene Relighting}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16600-16609} }
Azimuth Super-Resolution for FMCW Radar in Autonomous Driving: Yu-Jhe Li,

Shawn Hunt,

Jinhyung Park,

Matthew O’Toole,

Kris Kitani; [pdf]
[bibtex]
@InProceedings{Li_2023_CVPR, author = {Li, Yu-Jhe and Hunt, Shawn and Park, Jinhyung and O{\textquoteright}Toole, Matthew and Kitani, Kris}, title = {Azimuth Super-Resolution for FMCW Radar in Autonomous Driving}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {17504-17513} }
VQACL: A Novel Visual Question Answering Continual Learning Setting: Xi Zhang,

Feifei Zhang,

Changsheng Xu; [pdf] [supp]
[bibtex]
@InProceedings{Zhang_2023_CVPR, author = {Zhang, Xi and Zhang, Feifei and Xu, Changsheng}, title = {VQACL: A Novel Visual Question Answering Continual Learning Setting}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {19102-19112} }
High-Res Facial Appearance Capture From Polarized Smartphone Images: Dejan Azinović,

Olivier Maury,

Christophe Hery,

Matthias Nießner,

Justus Thies; [pdf] [supp]
[bibtex]
@InProceedings{Azinovic_2023_CVPR, author = {Azinovi\'c, Dejan and Maury, Olivier and Hery, Christophe and Nie{\ss}ner, Matthias and Thies, Justus}, title = {High-Res Facial Appearance Capture From Polarized Smartphone Images}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16836-16846} }
JAWS: Just a Wild Shot for Cinematic Transfer in Neural Radiance Fields: Xi Wang,

Robin Courant,

Jinglei Shi,

Eric Marchand,

Marc Christie; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2023_CVPR, author = {Wang, Xi and Courant, Robin and Shi, Jinglei and Marchand, Eric and Christie, Marc}, title = {JAWS: Just a Wild Shot for Cinematic Transfer in Neural Radiance Fields}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16933-16942} }
EfficientSCI: Densely Connected Network With Space-Time Factorization for Large-Scale Video Snapshot Compressive Imaging: Lishun Wang,

Miao Cao,

Xin Yuan; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2023_CVPR, author = {Wang, Lishun and Cao, Miao and Yuan, Xin}, title = {EfficientSCI: Densely Connected Network With Space-Time Factorization for Large-Scale Video Snapshot Compressive Imaging}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {18477-18486} }
MotionTrack: Learning Robust Short-Term and Long-Term Motions for Multi-Object Tracking: Zheng Qin,

Sanping Zhou,

Le Wang,

Jinghai Duan,

Gang Hua,

Wei Tang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Qin_2023_CVPR, author = {Qin, Zheng and Zhou, Sanping and Wang, Le and Duan, Jinghai and Hua, Gang and Tang, Wei}, title = {MotionTrack: Learning Robust Short-Term and Long-Term Motions for Multi-Object Tracking}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {17939-17948} }
3D Registration With Maximal Cliques: Xiyu Zhang,

Jiaqi Yang,

Shikun Zhang,

Yanning Zhang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhang_2023_CVPR, author = {Zhang, Xiyu and Yang, Jiaqi and Zhang, Shikun and Zhang, Yanning}, title = {3D Registration With Maximal Cliques}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {17745-17754} }
MetaPortrait: Identity-Preserving Talking Head Generation With Fast Personalized Adaptation: Bowen Zhang,

Chenyang Qi,

Pan Zhang,

Bo Zhang,

HsiangTao Wu,

Dong Chen,

Qifeng Chen,

Yong Wang,

Fang Wen; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhang_2023_CVPR, author = {Zhang, Bowen and Qi, Chenyang and Zhang, Pan and Zhang, Bo and Wu, HsiangTao and Chen, Dong and Chen, Qifeng and Wang, Yong and Wen, Fang}, title = {MetaPortrait: Identity-Preserving Talking Head Generation With Fast Personalized Adaptation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {22096-22105} }
UniHCP: A Unified Model for Human-Centric Perceptions: Yuanzheng Ci,

Yizhou Wang,

Meilin Chen,

Shixiang Tang,

Lei Bai,

Feng Zhu,

Rui Zhao,

Fengwei Yu,

Donglian Qi,

Wanli Ouyang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ci_2023_CVPR, author = {Ci, Yuanzheng and Wang, Yizhou and Chen, Meilin and Tang, Shixiang and Bai, Lei and Zhu, Feng and Zhao, Rui and Yu, Fengwei and Qi, Donglian and Ouyang, Wanli}, title = {UniHCP: A Unified Model for Human-Centric Perceptions}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {17840-17852} }
VoxelNeXt: Fully Sparse VoxelNet for 3D Object Detection and Tracking: Yukang Chen,

Jianhui Liu,

Xiangyu Zhang,

Xiaojuan Qi,

Jiaya Jia; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chen_2023_CVPR, author = {Chen, Yukang and Liu, Jianhui and Zhang, Xiangyu and Qi, Xiaojuan and Jia, Jiaya}, title = {VoxelNeXt: Fully Sparse VoxelNet for 3D Object Detection and Tracking}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {21674-21683} }
Bias in Pruned Vision Models: In-Depth Analysis and Countermeasures: Eugenia Iofinova,

Alexandra Peste,

Dan Alistarh; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Iofinova_2023_CVPR, author = {Iofinova, Eugenia and Peste, Alexandra and Alistarh, Dan}, title = {Bias in Pruned Vision Models: In-Depth Analysis and Countermeasures}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {24364-24373} }
AttentionShift: Iteratively Estimated Part-Based Attention Map for Pointly Supervised Instance Segmentation: Mingxiang Liao,

Zonghao Guo,

Yuze Wang,

Peng Yuan,

Bailan Feng,

Fang Wan; [pdf] [supp]
[bibtex]
@InProceedings{Liao_2023_CVPR, author = {Liao, Mingxiang and Guo, Zonghao and Wang, Yuze and Yuan, Peng and Feng, Bailan and Wan, Fang}, title = {AttentionShift: Iteratively Estimated Part-Based Attention Map for Pointly Supervised Instance Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {19519-19528} }
PlaneDepth: Self-Supervised Depth Estimation via Orthogonal Planes: Ruoyu Wang,

Zehao Yu,

Shenghua Gao; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2023_CVPR, author = {Wang, Ruoyu and Yu, Zehao and Gao, Shenghua}, title = {PlaneDepth: Self-Supervised Depth Estimation via Orthogonal Planes}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {21425-21434} }
Semantic-Conditional Diffusion Networks for Image Captioning: Jianjie Luo,

Yehao Li,

Yingwei Pan,

Ting Yao,

Jianlin Feng,

Hongyang Chao,

Tao Mei; [pdf] [arXiv]
[bibtex]
@InProceedings{Luo_2023_CVPR, author = {Luo, Jianjie and Li, Yehao and Pan, Yingwei and Yao, Ting and Feng, Jianlin and Chao, Hongyang and Mei, Tao}, title = {Semantic-Conditional Diffusion Networks for Image Captioning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {23359-23368} }
TranSG: Transformer-Based Skeleton Graph Prototype Contrastive Learning With Structure-Trajectory Prompted Reconstruction for Person Re-Identification: Haocong Rao,

Chunyan Miao; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Rao_2023_CVPR, author = {Rao, Haocong and Miao, Chunyan}, title = {TranSG: Transformer-Based Skeleton Graph Prototype Contrastive Learning With Structure-Trajectory Prompted Reconstruction for Person Re-Identification}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {22118-22128} }
All Are Worth Words: A ViT Backbone for Diffusion Models: Fan Bao,

Shen Nie,

Kaiwen Xue,

Yue Cao,

Chongxuan Li,

Hang Su,

Jun Zhu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Bao_2023_CVPR, author = {Bao, Fan and Nie, Shen and Xue, Kaiwen and Cao, Yue and Li, Chongxuan and Su, Hang and Zhu, Jun}, title = {All Are Worth Words: A ViT Backbone for Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {22669-22679} }
SteerNeRF: Accelerating NeRF Rendering via Smooth Viewpoint Trajectory: Sicheng Li,

Hao Li,

Yue Wang,

Yiyi Liao,

Lu Yu; [pdf] [arXiv]
[bibtex]
@InProceedings{Li_2023_CVPR, author = {Li, Sicheng and Li, Hao and Wang, Yue and Liao, Yiyi and Yu, Lu}, title = {SteerNeRF: Accelerating NeRF Rendering via Smooth Viewpoint Trajectory}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {20701-20711} }
Spatial-Frequency Mutual Learning for Face Super-Resolution: Chenyang Wang,

Junjun Jiang,

Zhiwei Zhong,

Xianming Liu; [pdf]
[bibtex]
@InProceedings{Wang_2023_CVPR, author = {Wang, Chenyang and Jiang, Junjun and Zhong, Zhiwei and Liu, Xianming}, title = {Spatial-Frequency Mutual Learning for Face Super-Resolution}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {22356-22366} }
Being Comes From Not-Being: Open-Vocabulary Text-to-Motion Generation With Wordless Training: Junfan Lin,

Jianlong Chang,

Lingbo Liu,

Guanbin Li,

Liang Lin,

Qi Tian,

Chang-Wen Chen; [pdf] [supp]
[bibtex]
@InProceedings{Lin_2023_CVPR, author = {Lin, Junfan and Chang, Jianlong and Liu, Lingbo and Li, Guanbin and Lin, Liang and Tian, Qi and Chen, Chang-Wen}, title = {Being Comes From Not-Being: Open-Vocabulary Text-to-Motion Generation With Wordless Training}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {23222-23231} }
MonoHuman: Animatable Human Neural Field From Monocular Video: Zhengming Yu,

Wei Cheng,

Xian Liu,

Wayne Wu,

Kwan-Yee Lin; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yu_2023_CVPR, author = {Yu, Zhengming and Cheng, Wei and Liu, Xian and Wu, Wayne and Lin, Kwan-Yee}, title = {MonoHuman: Animatable Human Neural Field From Monocular Video}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16943-16953} }
SINE: Semantic-Driven Image-Based NeRF Editing With Prior-Guided Editing Field: Chong Bao,

Yinda Zhang,

Bangbang Yang,

Tianxing Fan,

Zesong Yang,

Hujun Bao,

Guofeng Zhang,

Zhaopeng Cui; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Bao_2023_CVPR, author = {Bao, Chong and Zhang, Yinda and Yang, Bangbang and Fan, Tianxing and Yang, Zesong and Bao, Hujun and Zhang, Guofeng and Cui, Zhaopeng}, title = {SINE: Semantic-Driven Image-Based NeRF Editing With Prior-Guided Editing Field}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {20919-20929} }
MetaCLUE: Towards Comprehensive Visual Metaphors Research: Arjun R. Akula,

Brendan Driscoll,

Pradyumna Narayana,

Soravit Changpinyo,

Zhiwei Jia,

Suyash Damle,

Garima Pruthi,

Sugato Basu,

Leonidas Guibas,

William T. Freeman,

Yuanzhen Li,

Varun Jampani; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Akula_2023_CVPR, author = {Akula, Arjun R. and Driscoll, Brendan and Narayana, Pradyumna and Changpinyo, Soravit and Jia, Zhiwei and Damle, Suyash and Pruthi, Garima and Basu, Sugato and Guibas, Leonidas and Freeman, William T. and Li, Yuanzhen and Jampani, Varun}, title = {MetaCLUE: Towards Comprehensive Visual Metaphors Research}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {23201-23211} }
Towards End-to-End Generative Modeling of Long Videos With Memory-Efficient Bidirectional Transformers: Jaehoon Yoo,

Semin Kim,

Doyup Lee,

Chiheon Kim,

Seunghoon Hong; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yoo_2023_CVPR, author = {Yoo, Jaehoon and Kim, Semin and Lee, Doyup and Kim, Chiheon and Hong, Seunghoon}, title = {Towards End-to-End Generative Modeling of Long Videos With Memory-Efficient Bidirectional Transformers}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {22888-22897} }
HaLP: Hallucinating Latent Positives for Skeleton-Based Self-Supervised Learning of Actions: Anshul Shah,

Aniket Roy,

Ketul Shah,

Shlok Mishra,

David Jacobs,

Anoop Cherian,

Rama Chellappa; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Shah_2023_CVPR, author = {Shah, Anshul and Roy, Aniket and Shah, Ketul and Mishra, Shlok and Jacobs, David and Cherian, Anoop and Chellappa, Rama}, title = {HaLP: Hallucinating Latent Positives for Skeleton-Based Self-Supervised Learning of Actions}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {18846-18856} }
FLEX: Full-Body Grasping Without Full-Body Grasps: Purva Tendulkar,

Dídac Surís,

Carl Vondrick; [pdf] [supp]
[bibtex]
@InProceedings{Tendulkar_2023_CVPR, author = {Tendulkar, Purva and Sur{\'\i}s, D{\'\i}dac and Vondrick, Carl}, title = {FLEX: Full-Body Grasping Without Full-Body Grasps}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {21179-21189} }
EVA: Exploring the Limits of Masked Visual Representation Learning at Scale: Yuxin Fang,

Wen Wang,

Binhui Xie,

Quan Sun,

Ledell Wu,

Xinggang Wang,

Tiejun Huang,

Xinlong Wang,

Yue Cao; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Fang_2023_CVPR, author = {Fang, Yuxin and Wang, Wen and Xie, Binhui and Sun, Quan and Wu, Ledell and Wang, Xinggang and Huang, Tiejun and Wang, Xinlong and Cao, Yue}, title = {EVA: Exploring the Limits of Masked Visual Representation Learning at Scale}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {19358-19369} }
Discrete Point-Wise Attack Is Not Enough: Generalized Manifold Adversarial Attack for Face Recognition: Qian Li,

Yuxiao Hu,

Ye Liu,

Dongxiao Zhang,

Xin Jin,

Yuntian Chen; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Li_2023_CVPR, author = {Li, Qian and Hu, Yuxiao and Liu, Ye and Zhang, Dongxiao and Jin, Xin and Chen, Yuntian}, title = {Discrete Point-Wise Attack Is Not Enough: Generalized Manifold Adversarial Attack for Face Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {20575-20584} }
FREDOM: Fairness Domain Adaptation Approach to Semantic Scene Understanding: Thanh-Dat Truong,

Ngan Le,

Bhiksha Raj,

Jackson Cothren,

Khoa Luu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Truong_2023_CVPR, author = {Truong, Thanh-Dat and Le, Ngan and Raj, Bhiksha and Cothren, Jackson and Luu, Khoa}, title = {FREDOM: Fairness Domain Adaptation Approach to Semantic Scene Understanding}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {19988-19997} }
IMP: Iterative Matching and Pose Estimation With Adaptive Pooling: Fei Xue,

Ignas Budvytis,

Roberto Cipolla; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Xue_2023_CVPR, author = {Xue, Fei and Budvytis, Ignas and Cipolla, Roberto}, title = {IMP: Iterative Matching and Pose Estimation With Adaptive Pooling}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {21317-21326} }
PATS: Patch Area Transportation With Subdivision for Local Feature Matching: Junjie Ni,

Yijin Li,

Zhaoyang Huang,

Hongsheng Li,

Hujun Bao,

Zhaopeng Cui,

Guofeng Zhang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ni_2023_CVPR, author = {Ni, Junjie and Li, Yijin and Huang, Zhaoyang and Li, Hongsheng and Bao, Hujun and Cui, Zhaopeng and Zhang, Guofeng}, title = {PATS: Patch Area Transportation With Subdivision for Local Feature Matching}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {17776-17786} }
MEDIC: Remove Model Backdoors via Importance Driven Cloning: Qiuling Xu,

Guanhong Tao,

Jean Honorio,

Yingqi Liu,

Shengwei An,

Guangyu Shen,

Siyuan Cheng,

Xiangyu Zhang; [pdf] [supp]
[bibtex]
@InProceedings{Xu_2023_CVPR, author = {Xu, Qiuling and Tao, Guanhong and Honorio, Jean and Liu, Yingqi and An, Shengwei and Shen, Guangyu and Cheng, Siyuan and Zhang, Xiangyu}, title = {MEDIC: Remove Model Backdoors via Importance Driven Cloning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {20485-20494} }
SimpleNet: A Simple Network for Image Anomaly Detection and Localization: Zhikang Liu,

Yiming Zhou,

Yuansheng Xu,

Zilei Wang; [pdf] [arXiv]
[bibtex]
@InProceedings{Liu_2023_CVPR, author = {Liu, Zhikang and Zhou, Yiming and Xu, Yuansheng and Wang, Zilei}, title = {SimpleNet: A Simple Network for Image Anomaly Detection and Localization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {20402-20411} }
G-MSM: Unsupervised Multi-Shape Matching With Graph-Based Affinity Priors: Marvin Eisenberger,

Aysim Toker,

Laura Leal-Taixé,

Daniel Cremers; [pdf] [supp]
[bibtex]
@InProceedings{Eisenberger_2023_CVPR, author = {Eisenberger, Marvin and Toker, Aysim and Leal-Taix\'e, Laura and Cremers, Daniel}, title = {G-MSM: Unsupervised Multi-Shape Matching With Graph-Based Affinity Priors}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {22762-22772} }
Mixed Autoencoder for Self-Supervised Visual Representation Learning: Kai Chen,

Zhili Liu,

Lanqing Hong,

Hang Xu,

Zhenguo Li,

Dit-Yan Yeung; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chen_2023_CVPR, author = {Chen, Kai and Liu, Zhili and Hong, Lanqing and Xu, Hang and Li, Zhenguo and Yeung, Dit-Yan}, title = {Mixed Autoencoder for Self-Supervised Visual Representation Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {22742-22751} }
ProphNet: Efficient Agent-Centric Motion Forecasting With Anchor-Informed Proposals: Xishun Wang,

Tong Su,

Fang Da,

Xiaodong Yang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2023_CVPR, author = {Wang, Xishun and Su, Tong and Da, Fang and Yang, Xiaodong}, title = {ProphNet: Efficient Agent-Centric Motion Forecasting With Anchor-Informed Proposals}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {21995-22003} }
Learning Multi-Modal Class-Specific Tokens for Weakly Supervised Dense Object Localization: Lian Xu,

Wanli Ouyang,

Mohammed Bennamoun,

Farid Boussaid,

Dan Xu; [pdf] [supp]
[bibtex]
@InProceedings{Xu_2023_CVPR, author = {Xu, Lian and Ouyang, Wanli and Bennamoun, Mohammed and Boussaid, Farid and Xu, Dan}, title = {Learning Multi-Modal Class-Specific Tokens for Weakly Supervised Dense Object Localization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {19596-19605} }
GlassesGAN: Eyewear Personalization Using Synthetic Appearance Discovery and Targeted Subspace Modeling: Richard Plesh,

Peter Peer,

Vitomir Struc; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Plesh_2023_CVPR, author = {Plesh, Richard and Peer, Peter and Struc, Vitomir}, title = {GlassesGAN: Eyewear Personalization Using Synthetic Appearance Discovery and Targeted Subspace Modeling}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16847-16857} }
Deep Hashing With Minimal-Distance-Separated Hash Centers: Liangdao Wang,

Yan Pan,

Cong Liu,

Hanjiang Lai,

Jian Yin,

Ye Liu; [pdf] [supp]
[bibtex]
@InProceedings{Wang_2023_CVPR, author = {Wang, Liangdao and Pan, Yan and Liu, Cong and Lai, Hanjiang and Yin, Jian and Liu, Ye}, title = {Deep Hashing With Minimal-Distance-Separated Hash Centers}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {23455-23464} }
VL-SAT: Visual-Linguistic Semantics Assisted Training for 3D Semantic Scene Graph Prediction in Point Cloud: Ziqin Wang,

Bowen Cheng,

Lichen Zhao,

Dong Xu,

Yang Tang,

Lu Sheng; [pdf] [supp]
[bibtex]
@InProceedings{Wang_2023_CVPR, author = {Wang, Ziqin and Cheng, Bowen and Zhao, Lichen and Xu, Dong and Tang, Yang and Sheng, Lu}, title = {VL-SAT: Visual-Linguistic Semantics Assisted Training for 3D Semantic Scene Graph Prediction in Point Cloud}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {21560-21569} }
Learning Emotion Representations From Verbal and Nonverbal Communication: Sitao Zhang,

Yimu Pan,

James Z. Wang; [pdf] [supp]
[bibtex]
@InProceedings{Zhang_2023_CVPR, author = {Zhang, Sitao and Pan, Yimu and Wang, James Z.}, title = {Learning Emotion Representations From Verbal and Nonverbal Communication}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {18993-19004} }
Architectural Backdoors in Neural Networks: Mikel Bober-Irizar,

Ilia Shumailov,

Yiren Zhao,

Robert Mullins,

Nicolas Papernot; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Bober-Irizar_2023_CVPR, author = {Bober-Irizar, Mikel and Shumailov, Ilia and Zhao, Yiren and Mullins, Robert and Papernot, Nicolas}, title = {Architectural Backdoors in Neural Networks}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {24595-24604} }
Semantic Human Parsing via Scalable Semantic Transfer Over Multiple Label Domains: Jie Yang,

Chaoqun Wang,

Zhen Li,

Junle Wang,

Ruimao Zhang; [pdf] [arXiv]
[bibtex]
@InProceedings{Yang_2023_CVPR, author = {Yang, Jie and Wang, Chaoqun and Li, Zhen and Wang, Junle and Zhang, Ruimao}, title = {Semantic Human Parsing via Scalable Semantic Transfer Over Multiple Label Domains}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {19424-19433} }
GEN: Pushing the Limits of Softmax-Based Out-of-Distribution Detection: Xixi Liu,

Yaroslava Lochman,

Christopher Zach; [pdf] [supp]
[bibtex]
@InProceedings{Liu_2023_CVPR, author = {Liu, Xixi and Lochman, Yaroslava and Zach, Christopher}, title = {GEN: Pushing the Limits of Softmax-Based Out-of-Distribution Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {23946-23955} }
Learnable Skeleton-Aware 3D Point Cloud Sampling: Cheng Wen,

Baosheng Yu,

Dacheng Tao; [pdf] [supp]
[bibtex]
@InProceedings{Wen_2023_CVPR, author = {Wen, Cheng and Yu, Baosheng and Tao, Dacheng}, title = {Learnable Skeleton-Aware 3D Point Cloud Sampling}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {17671-17681} }
Boundary-Enhanced Co-Training for Weakly Supervised Semantic Segmentation: Shenghai Rong,

Bohai Tu,

Zilei Wang,

Junjie Li; [pdf] [supp]
[bibtex]
@InProceedings{Rong_2023_CVPR, author = {Rong, Shenghai and Tu, Bohai and Wang, Zilei and Li, Junjie}, title = {Boundary-Enhanced Co-Training for Weakly Supervised Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {19574-19584} }
Sample-Level Multi-View Graph Clustering: Yuze Tan,

Yixi Liu,

Shudong Huang,

Wentao Feng,

Jiancheng Lv; [pdf]
[bibtex]
@InProceedings{Tan_2023_CVPR, author = {Tan, Yuze and Liu, Yixi and Huang, Shudong and Feng, Wentao and Lv, Jiancheng}, title = {Sample-Level Multi-View Graph Clustering}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {23966-23975} }
Next3D: Generative Neural Texture Rasterization for 3D-Aware Head Avatars: Jingxiang Sun,

Xuan Wang,

Lizhen Wang,

Xiaoyu Li,

Yong Zhang,

Hongwen Zhang,

Yebin Liu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Sun_2023_CVPR, author = {Sun, Jingxiang and Wang, Xuan and Wang, Lizhen and Li, Xiaoyu and Zhang, Yong and Zhang, Hongwen and Liu, Yebin}, title = {Next3D: Generative Neural Texture Rasterization for 3D-Aware Head Avatars}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {20991-21002} }
Linking Garment With Person via Semantically Associated Landmarks for Virtual Try-On: Keyu Yan,

Tingwei Gao,

Hui Zhang,

Chengjun Xie; [pdf] [supp]
[bibtex]
@InProceedings{Yan_2023_CVPR, author = {Yan, Keyu and Gao, Tingwei and Zhang, Hui and Xie, Chengjun}, title = {Linking Garment With Person via Semantically Associated Landmarks for Virtual Try-On}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {17194-17204} }
Devil's on the Edges: Selective Quad Attention for Scene Graph Generation: Deunsol Jung,

Sanghyun Kim,

Won Hwa Kim,

Minsu Cho; [pdf] [supp]
[bibtex]
@InProceedings{Jung_2023_CVPR, author = {Jung, Deunsol and Kim, Sanghyun and Kim, Won Hwa and Cho, Minsu}, title = {Devil's on the Edges: Selective Quad Attention for Scene Graph Generation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {18664-18674} }
NIFF: Alleviating Forgetting in Generalized Few-Shot Object Detection via Neural Instance Feature Forging: Karim Guirguis,

Johannes Meier,

George Eskandar,

Matthias Kayser,

Bin Yang,

Jürgen Beyerer; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Guirguis_2023_CVPR, author = {Guirguis, Karim and Meier, Johannes and Eskandar, George and Kayser, Matthias and Yang, Bin and Beyerer, J\"urgen}, title = {NIFF: Alleviating Forgetting in Generalized Few-Shot Object Detection via Neural Instance Feature Forging}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {24193-24202} }
Post-Processing Temporal Action Detection: Sauradip Nag,

Xiatian Zhu,

Yi-Zhe Song,

Tao Xiang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Nag_2023_CVPR, author = {Nag, Sauradip and Zhu, Xiatian and Song, Yi-Zhe and Xiang, Tao}, title = {Post-Processing Temporal Action Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {18837-18845} }
ConZIC: Controllable Zero-Shot Image Captioning by Sampling-Based Polishing: Zequn Zeng,

Hao Zhang,

Ruiying Lu,

Dongsheng Wang,

Bo Chen,

Zhengjue Wang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zeng_2023_CVPR, author = {Zeng, Zequn and Zhang, Hao and Lu, Ruiying and Wang, Dongsheng and Chen, Bo and Wang, Zhengjue}, title = {ConZIC: Controllable Zero-Shot Image Captioning by Sampling-Based Polishing}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {23465-23476} }
Learning From Noisy Labels With Decoupled Meta Label Purifier: Yuanpeng Tu,

Boshen Zhang,

Yuxi Li,

Liang Liu,

Jian Li,

Yabiao Wang,

Chengjie Wang,

Cai Rong Zhao; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Tu_2023_CVPR, author = {Tu, Yuanpeng and Zhang, Boshen and Li, Yuxi and Liu, Liang and Li, Jian and Wang, Yabiao and Wang, Chengjie and Zhao, Cai Rong}, title = {Learning From Noisy Labels With Decoupled Meta Label Purifier}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {19934-19943} }
Language in a Bottle: Language Model Guided Concept Bottlenecks for Interpretable Image Classification: Yue Yang,

Artemis Panagopoulou,

Shenghao Zhou,

Daniel Jin,

Chris Callison-Burch,

Mark Yatskar; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yang_2023_CVPR, author = {Yang, Yue and Panagopoulou, Artemis and Zhou, Shenghao and Jin, Daniel and Callison-Burch, Chris and Yatskar, Mark}, title = {Language in a Bottle: Language Model Guided Concept Bottlenecks for Interpretable Image Classification}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {19187-19197} }
ViPLO: Vision Transformer Based Pose-Conditioned Self-Loop Graph for Human-Object Interaction Detection: Jeeseung Park,

Jin-Woo Park,

Jong-Seok Lee; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Park_2023_CVPR, author = {Park, Jeeseung and Park, Jin-Woo and Lee, Jong-Seok}, title = {ViPLO: Vision Transformer Based Pose-Conditioned Self-Loop Graph for Human-Object Interaction Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {17152-17162} }
MSINet: Twins Contrastive Search of Multi-Scale Interaction for Object ReID: Jianyang Gu,

Kai Wang,

Hao Luo,

Chen Chen,

Wei Jiang,

Yuqiang Fang,

Shanghang Zhang,

Yang You,

Jian Zhao; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Gu_2023_CVPR, author = {Gu, Jianyang and Wang, Kai and Luo, Hao and Chen, Chen and Jiang, Wei and Fang, Yuqiang and Zhang, Shanghang and You, Yang and Zhao, Jian}, title = {MSINet: Twins Contrastive Search of Multi-Scale Interaction for Object ReID}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {19243-19253} }
WIRE: Wavelet Implicit Neural Representations: Vishwanath Saragadam,

Daniel LeJeune,

Jasper Tan,

Guha Balakrishnan,

Ashok Veeraraghavan,

Richard G. Baraniuk; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Saragadam_2023_CVPR, author = {Saragadam, Vishwanath and LeJeune, Daniel and Tan, Jasper and Balakrishnan, Guha and Veeraraghavan, Ashok and Baraniuk, Richard G.}, title = {WIRE: Wavelet Implicit Neural Representations}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {18507-18516} }
Bringing Inputs to Shared Domains for 3D Interacting Hands Recovery in the Wild: Gyeongsik Moon; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Moon_2023_CVPR, author = {Moon, Gyeongsik}, title = {Bringing Inputs to Shared Domains for 3D Interacting Hands Recovery in the Wild}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {17028-17037} }
Deep Deterministic Uncertainty: A New Simple Baseline: Jishnu Mukhoti,

Andreas Kirsch,

Joost van Amersfoort,

Philip H.S. Torr,

Yarin Gal; [pdf] [supp]
[bibtex]
@InProceedings{Mukhoti_2023_CVPR, author = {Mukhoti, Jishnu and Kirsch, Andreas and van Amersfoort, Joost and Torr, Philip H.S. and Gal, Yarin}, title = {Deep Deterministic Uncertainty: A New Simple Baseline}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {24384-24394} }
NeRDi: Single-View NeRF Synthesis With Language-Guided Diffusion As General Image Priors: Congyue Deng,

Chiyu “Max” Jiang,

Charles R. Qi,

Xinchen Yan,

Yin Zhou,

Leonidas Guibas,

Dragomir Anguelov; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Deng_2023_CVPR, author = {Deng, Congyue and Jiang, Chiyu {\textquotedblleft}Max{\textquotedblright} and Qi, Charles R. and Yan, Xinchen and Zhou, Yin and Guibas, Leonidas and Anguelov, Dragomir}, title = {NeRDi: Single-View NeRF Synthesis With Language-Guided Diffusion As General Image Priors}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {20637-20647} }
InstantAvatar: Learning Avatars From Monocular Video in 60 Seconds: Tianjian Jiang,

Xu Chen,

Jie Song,

Otmar Hilliges; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Jiang_2023_CVPR, author = {Jiang, Tianjian and Chen, Xu and Song, Jie and Hilliges, Otmar}, title = {InstantAvatar: Learning Avatars From Monocular Video in 60 Seconds}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16922-16932} }
You Only Segment Once: Towards Real-Time Panoptic Segmentation: Jie Hu,

Linyan Huang,

Tianhe Ren,

Shengchuan Zhang,

Rongrong Ji,

Liujuan Cao; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Hu_2023_CVPR, author = {Hu, Jie and Huang, Linyan and Ren, Tianhe and Zhang, Shengchuan and Ji, Rongrong and Cao, Liujuan}, title = {You Only Segment Once: Towards Real-Time Panoptic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {17819-17829} }
Robust Single Image Reflection Removal Against Adversarial Attacks: Zhenbo Song,

Zhenyuan Zhang,

Kaihao Zhang,

Wenhan Luo,

Zhaoxin Fan,

Wenqi Ren,

Jianfeng Lu; [pdf]
[bibtex]
@InProceedings{Song_2023_CVPR, author = {Song, Zhenbo and Zhang, Zhenyuan and Zhang, Kaihao and Luo, Wenhan and Fan, Zhaoxin and Ren, Wenqi and Lu, Jianfeng}, title = {Robust Single Image Reflection Removal Against Adversarial Attacks}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {24688-24698} }
PartMix: Regularization Strategy To Learn Part Discovery for Visible-Infrared Person Re-Identification: Minsu Kim,

Seungryong Kim,

Jungin Park,

Seongheon Park,

Kwanghoon Sohn; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kim_2023_CVPR, author = {Kim, Minsu and Kim, Seungryong and Park, Jungin and Park, Seongheon and Sohn, Kwanghoon}, title = {PartMix: Regularization Strategy To Learn Part Discovery for Visible-Infrared Person Re-Identification}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {18621-18632} }
Feature Representation Learning With Adaptive Displacement Generation and Transformer Fusion for Micro-Expression Recognition: Zhijun Zhai,

Jianhui Zhao,

Chengjiang Long,

Wenju Xu,

Shuangjiang He,

Huijuan Zhao; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhai_2023_CVPR, author = {Zhai, Zhijun and Zhao, Jianhui and Long, Chengjiang and Xu, Wenju and He, Shuangjiang and Zhao, Huijuan}, title = {Feature Representation Learning With Adaptive Displacement Generation and Transformer Fusion for Micro-Expression Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {22086-22095} }
ViewNet: A Novel Projection-Based Backbone With View Pooling for Few-Shot Point Cloud Classification: Jiajing Chen,

Minmin Yang,

Senem Velipasalar; [pdf]
[bibtex]
@InProceedings{Chen_2023_CVPR, author = {Chen, Jiajing and Yang, Minmin and Velipasalar, Senem}, title = {ViewNet: A Novel Projection-Based Backbone With View Pooling for Few-Shot Point Cloud Classification}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {17652-17660} }
ANetQA: A Large-Scale Benchmark for Fine-Grained Compositional Reasoning Over Untrimmed Videos: Zhou Yu,

Lixiang Zheng,

Zhou Zhao,

Fei Wu,

Jianping Fan,

Kui Ren,

Jun Yu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yu_2023_CVPR, author = {Yu, Zhou and Zheng, Lixiang and Zhao, Zhou and Wu, Fei and Fan, Jianping and Ren, Kui and Yu, Jun}, title = {ANetQA: A Large-Scale Benchmark for Fine-Grained Compositional Reasoning Over Untrimmed Videos}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {23191-23200} }
CLAMP: Prompt-Based Contrastive Learning for Connecting Language and Animal Pose: Xu Zhang,

Wen Wang,

Zhe Chen,

Yufei Xu,

Jing Zhang,

Dacheng Tao; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhang_2023_CVPR, author = {Zhang, Xu and Wang, Wen and Chen, Zhe and Xu, Yufei and Zhang, Jing and Tao, Dacheng}, title = {CLAMP: Prompt-Based Contrastive Learning for Connecting Language and Animal Pose}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {23272-23281} }
Standing Between Past and Future: Spatio-Temporal Modeling for Multi-Camera 3D Multi-Object Tracking: Ziqi Pang,

Jie Li,

Pavel Tokmakov,

Dian Chen,

Sergey Zagoruyko,

Yu-Xiong Wang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Pang_2023_CVPR, author = {Pang, Ziqi and Li, Jie and Tokmakov, Pavel and Chen, Dian and Zagoruyko, Sergey and Wang, Yu-Xiong}, title = {Standing Between Past and Future: Spatio-Temporal Modeling for Multi-Camera 3D Multi-Object Tracking}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {17928-17938} }
TTA-COPE: Test-Time Adaptation for Category-Level Object Pose Estimation: Taeyeop Lee,

Jonathan Tremblay,

Valts Blukis,

Bowen Wen,

Byeong-Uk Lee,

Inkyu Shin,

Stan Birchfield,

In So Kweon,

Kuk-Jin Yoon; [pdf] [supp]
[bibtex]
@InProceedings{Lee_2023_CVPR, author = {Lee, Taeyeop and Tremblay, Jonathan and Blukis, Valts and Wen, Bowen and Lee, Byeong-Uk and Shin, Inkyu and Birchfield, Stan and Kweon, In So and Yoon, Kuk-Jin}, title = {TTA-COPE: Test-Time Adaptation for Category-Level Object Pose Estimation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {21285-21295} }
Geometry and Uncertainty-Aware 3D Point Cloud Class-Incremental Semantic Segmentation: Yuwei Yang,

Munawar Hayat,

Zhao Jin,

Chao Ren,

Yinjie Lei; [pdf] [supp]
[bibtex]
@InProceedings{Yang_2023_CVPR, author = {Yang, Yuwei and Hayat, Munawar and Jin, Zhao and Ren, Chao and Lei, Yinjie}, title = {Geometry and Uncertainty-Aware 3D Point Cloud Class-Incremental Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {21759-21768} }
Cooperation or Competition: Avoiding Player Domination for Multi-Target Robustness via Adaptive Budgets: Yimu Wang,

Dinghuai Zhang,

Yihan Wu,

Heng Huang,

Hongyang Zhang; [pdf] [supp]
[bibtex]
@InProceedings{Wang_2023_CVPR, author = {Wang, Yimu and Zhang, Dinghuai and Wu, Yihan and Huang, Heng and Zhang, Hongyang}, title = {Cooperation or Competition: Avoiding Player Domination for Multi-Target Robustness via Adaptive Budgets}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {20564-20574} }
CAT: LoCalization and IdentificAtion Cascade Detection Transformer for Open-World Object Detection: Shuailei Ma,

Yuefeng Wang,

Ying Wei,

Jiaqi Fan,

Thomas H. Li,

Hongli Liu,

Fanbing Lv; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ma_2023_CVPR, author = {Ma, Shuailei and Wang, Yuefeng and Wei, Ying and Fan, Jiaqi and Li, Thomas H. and Liu, Hongli and Lv, Fanbing}, title = {CAT: LoCalization and IdentificAtion Cascade Detection Transformer for Open-World Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {19681-19690} }
TruFor: Leveraging All-Round Clues for Trustworthy Image Forgery Detection and Localization: Fabrizio Guillaro,

Davide Cozzolino,

Avneesh Sud,

Nicholas Dufour,

Luisa Verdoliva; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Guillaro_2023_CVPR, author = {Guillaro, Fabrizio and Cozzolino, Davide and Sud, Avneesh and Dufour, Nicholas and Verdoliva, Luisa}, title = {TruFor: Leveraging All-Round Clues for Trustworthy Image Forgery Detection and Localization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {20606-20615} }
LANA: A Language-Capable Navigator for Instruction Following and Generation: Xiaohan Wang,

Wenguan Wang,

Jiayi Shao,

Yi Yang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2023_CVPR, author = {Wang, Xiaohan and Wang, Wenguan and Shao, Jiayi and Yang, Yi}, title = {LANA: A Language-Capable Navigator for Instruction Following and Generation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {19048-19058} }
CAPE: Camera View Position Embedding for Multi-View 3D Object Detection: Kaixin Xiong,

Shi Gong,

Xiaoqing Ye,

Xiao Tan,

Ji Wan,

Errui Ding,

Jingdong Wang,

Xiang Bai; [pdf] [arXiv]
[bibtex]
@InProceedings{Xiong_2023_CVPR, author = {Xiong, Kaixin and Gong, Shi and Ye, Xiaoqing and Tan, Xiao and Wan, Ji and Ding, Errui and Wang, Jingdong and Bai, Xiang}, title = {CAPE: Camera View Position Embedding for Multi-View 3D Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {21570-21579} }
Bi-Directional Distribution Alignment for Transductive Zero-Shot Learning: Zhicai Wang,

Yanbin Hao,

Tingting Mu,

Ouxiang Li,

Shuo Wang,

Xiangnan He; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2023_CVPR, author = {Wang, Zhicai and Hao, Yanbin and Mu, Tingting and Li, Ouxiang and Wang, Shuo and He, Xiangnan}, title = {Bi-Directional Distribution Alignment for Transductive Zero-Shot Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {19893-19902} }
FlexNeRF: Photorealistic Free-Viewpoint Rendering of Moving Humans From Sparse Views: Vinoj Jayasundara,

Amit Agrawal,

Nicolas Heron,

Abhinav Shrivastava,

Larry S. Davis; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Jayasundara_2023_CVPR, author = {Jayasundara, Vinoj and Agrawal, Amit and Heron, Nicolas and Shrivastava, Abhinav and Davis, Larry S.}, title = {FlexNeRF: Photorealistic Free-Viewpoint Rendering of Moving Humans From Sparse Views}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {21118-21127} }
Towards Better Gradient Consistency for Neural Signed Distance Functions via Level Set Alignment: Baorui Ma,

Junsheng Zhou,

Yu-Shen Liu,

Zhizhong Han; [pdf] [supp]
[bibtex]
@InProceedings{Ma_2023_CVPR, author = {Ma, Baorui and Zhou, Junsheng and Liu, Yu-Shen and Han, Zhizhong}, title = {Towards Better Gradient Consistency for Neural Signed Distance Functions via Level Set Alignment}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {17724-17734} }
Zero-Shot Everything Sketch-Based Image Retrieval, and in Explainable Style: Fengyin Lin,

Mingkang Li,

Da Li,

Timothy Hospedales,

Yi-Zhe Song,

Yonggang Qi; [pdf] [arXiv]
[bibtex]
@InProceedings{Lin_2023_CVPR, author = {Lin, Fengyin and Li, Mingkang and Li, Da and Hospedales, Timothy and Song, Yi-Zhe and Qi, Yonggang}, title = {Zero-Shot Everything Sketch-Based Image Retrieval, and in Explainable Style}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {23349-23358} }
Graph Representation for Order-Aware Visual Transformation: Yue Qiu,

Yanjun Sun,

Fumiya Matsuzawa,

Kenji Iwata,

Hirokatsu Kataoka; [pdf] [supp]
[bibtex]
@InProceedings{Qiu_2023_CVPR, author = {Qiu, Yue and Sun, Yanjun and Matsuzawa, Fumiya and Iwata, Kenji and Kataoka, Hirokatsu}, title = {Graph Representation for Order-Aware Visual Transformation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {22793-22802} }
StarCraftImage: A Dataset for Prototyping Spatial Reasoning Methods for Multi-Agent Environments: Sean Kulinski,

Nicholas R. Waytowich,

James Z. Hare,

David I. Inouye; [pdf] [supp]
[bibtex]
@InProceedings{Kulinski_2023_CVPR, author = {Kulinski, Sean and Waytowich, Nicholas R. and Hare, James Z. and Inouye, David I.}, title = {StarCraftImage: A Dataset for Prototyping Spatial Reasoning Methods for Multi-Agent Environments}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {22004-22013} }
Quality-Aware Pre-Trained Models for Blind Image Quality Assessment: Kai Zhao,

Kun Yuan,

Ming Sun,

Mading Li,

Xing Wen; [pdf] [arXiv]
[bibtex]
@InProceedings{Zhao_2023_CVPR, author = {Zhao, Kai and Yuan, Kun and Sun, Ming and Li, Mading and Wen, Xing}, title = {Quality-Aware Pre-Trained Models for Blind Image Quality Assessment}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {22302-22313} }
Network Expansion for Practical Training Acceleration: Ning Ding,

Yehui Tang,

Kai Han,

Chao Xu,

Yunhe Wang; [pdf]
[bibtex]
@InProceedings{Ding_2023_CVPR, author = {Ding, Ning and Tang, Yehui and Han, Kai and Xu, Chao and Wang, Yunhe}, title = {Network Expansion for Practical Training Acceleration}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {20269-20279} }
FCC: Feature Clusters Compression for Long-Tailed Visual Recognition: Jian Li,

Ziyao Meng,

Daqian Shi,

Rui Song,

Xiaolei Diao,

Jingwen Wang,

Hao Xu; [pdf] [supp]
[bibtex]
@InProceedings{Li_2023_CVPR, author = {Li, Jian and Meng, Ziyao and Shi, Daqian and Song, Rui and Diao, Xiaolei and Wang, Jingwen and Xu, Hao}, title = {FCC: Feature Clusters Compression for Long-Tailed Visual Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {24080-24089} }
Rethinking the Learning Paradigm for Dynamic Facial Expression Recognition: Hanyang Wang,

Bo Li,

Shuang Wu,

Siyuan Shen,

Feng Liu,

Shouhong Ding,

Aimin Zhou; [pdf]
[bibtex]
@InProceedings{Wang_2023_CVPR, author = {Wang, Hanyang and Li, Bo and Wu, Shuang and Shen, Siyuan and Liu, Feng and Ding, Shouhong and Zhou, Aimin}, title = {Rethinking the Learning Paradigm for Dynamic Facial Expression Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {17958-17968} }
Self-Supervised Learning for Multimodal Non-Rigid 3D Shape Matching: Dongliang Cao,

Florian Bernard; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Cao_2023_CVPR, author = {Cao, Dongliang and Bernard, Florian}, title = {Self-Supervised Learning for Multimodal Non-Rigid 3D Shape Matching}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {17735-17744} }
Ham2Pose: Animating Sign Language Notation Into Pose Sequences: Rotem Shalev Arkushin,

Amit Moryossef,

Ohad Fried; [pdf] [supp]
[bibtex]
@InProceedings{Arkushin_2023_CVPR, author = {Arkushin, Rotem Shalev and Moryossef, Amit and Fried, Ohad}, title = {Ham2Pose: Animating Sign Language Notation Into Pose Sequences}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {21046-21056} }
Open-Set Likelihood Maximization for Few-Shot Learning: Malik Boudiaf,

Etienne Bennequin,

Myriam Tami,

Antoine Toubhans,

Pablo Piantanida,

Celine Hudelot,

Ismail Ben Ayed; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Boudiaf_2023_CVPR, author = {Boudiaf, Malik and Bennequin, Etienne and Tami, Myriam and Toubhans, Antoine and Piantanida, Pablo and Hudelot, Celine and Ben Ayed, Ismail}, title = {Open-Set Likelihood Maximization for Few-Shot Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {24007-24016} }
Boosting Accuracy and Robustness of Student Models via Adaptive Adversarial Distillation: Bo Huang,

Mingyang Chen,

Yi Wang,

Junda Lu,

Minhao Cheng,

Wei Wang; [pdf]
[bibtex]
@InProceedings{Huang_2023_CVPR, author = {Huang, Bo and Chen, Mingyang and Wang, Yi and Lu, Junda and Cheng, Minhao and Wang, Wei}, title = {Boosting Accuracy and Robustness of Student Models via Adaptive Adversarial Distillation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {24668-24677} }
PixHt-Lab: Pixel Height Based Light Effect Generation for Image Compositing: Yichen Sheng,

Jianming Zhang,

Julien Philip,

Yannick Hold-Geoffroy,

Xin Sun,

He Zhang,

Lu Ling,

Bedrich Benes; [pdf] [supp]
[bibtex]
@InProceedings{Sheng_2023_CVPR, author = {Sheng, Yichen and Zhang, Jianming and Philip, Julien and Hold-Geoffroy, Yannick and Sun, Xin and Zhang, He and Ling, Lu and Benes, Bedrich}, title = {PixHt-Lab: Pixel Height Based Light Effect Generation for Image Compositing}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16643-16653} }
RGB No More: Minimally-Decoded JPEG Vision Transformers: Jeongsoo Park,

Justin Johnson; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Park_2023_CVPR, author = {Park, Jeongsoo and Johnson, Justin}, title = {RGB No More: Minimally-Decoded JPEG Vision Transformers}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {22334-22346} }
Hybrid Active Learning via Deep Clustering for Video Action Detection: Aayush J. Rana,

Yogesh S. Rawat; [pdf] [supp]
[bibtex]
@InProceedings{Rana_2023_CVPR, author = {Rana, Aayush J. and Rawat, Yogesh S.}, title = {Hybrid Active Learning via Deep Clustering for Video Action Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {18867-18877} }
Fine-Grained Image-Text Matching by Cross-Modal Hard Aligning Network: Zhengxin Pan,

Fangyu Wu,

Bailing Zhang; [pdf]
[bibtex]
@InProceedings{Pan_2023_CVPR, author = {Pan, Zhengxin and Wu, Fangyu and Zhang, Bailing}, title = {Fine-Grained Image-Text Matching by Cross-Modal Hard Aligning Network}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {19275-19284} }
Sparsifiner: Learning Sparse Instance-Dependent Attention for Efficient Vision Transformers: Cong Wei,

Brendan Duke,

Ruowei Jiang,

Parham Aarabi,

Graham W. Taylor,

Florian Shkurti; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wei_2023_CVPR, author = {Wei, Cong and Duke, Brendan and Jiang, Ruowei and Aarabi, Parham and Taylor, Graham W. and Shkurti, Florian}, title = {Sparsifiner: Learning Sparse Instance-Dependent Attention for Efficient Vision Transformers}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {22680-22689} }
Structured Sparsity Learning for Efficient Video Super-Resolution: Bin Xia,

Jingwen He,

Yulun Zhang,

Yitong Wang,

Yapeng Tian,

Wenming Yang,

Luc Van Gool; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Xia_2023_CVPR, author = {Xia, Bin and He, Jingwen and Zhang, Yulun and Wang, Yitong and Tian, Yapeng and Yang, Wenming and Van Gool, Luc}, title = {Structured Sparsity Learning for Efficient Video Super-Resolution}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {22638-22647} }
"Seeing" Electric Network Frequency From Events: Lexuan Xu,

Guang Hua,

Haijian Zhang,

Lei Yu,

Ning Qiao; [pdf] [arXiv]
[bibtex]
@InProceedings{Xu_2023_CVPR, author = {Xu, Lexuan and Hua, Guang and Zhang, Haijian and Yu, Lei and Qiao, Ning}, title = {''Seeing'' Electric Network Frequency From Events}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {18022-18031} }
MMVC: Learned Multi-Mode Video Compression With Block-Based Prediction Mode Selection and Density-Adaptive Entropy Coding: Bowen Liu,

Yu Chen,

Rakesh Chowdary Machineni,

Shiyu Liu,

Hun-Seok Kim; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Liu_2023_CVPR, author = {Liu, Bowen and Chen, Yu and Machineni, Rakesh Chowdary and Liu, Shiyu and Kim, Hun-Seok}, title = {MMVC: Learned Multi-Mode Video Compression With Block-Based Prediction Mode Selection and Density-Adaptive Entropy Coding}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {18487-18496} }
Omni Aggregation Networks for Lightweight Image Super-Resolution: Hang Wang,

Xuanhong Chen,

Bingbing Ni,

Yutian Liu,

Jinfan Liu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2023_CVPR, author = {Wang, Hang and Chen, Xuanhong and Ni, Bingbing and Liu, Yutian and Liu, Jinfan}, title = {Omni Aggregation Networks for Lightweight Image Super-Resolution}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {22378-22387} }
Exploring the Effect of Primitives for Compositional Generalization in Vision-and-Language: Chuanhao Li,

Zhen Li,

Chenchen Jing,

Yunde Jia,

Yuwei Wu; [pdf] [supp]
[bibtex]
@InProceedings{Li_2023_CVPR, author = {Li, Chuanhao and Li, Zhen and Jing, Chenchen and Jia, Yunde and Wu, Yuwei}, title = {Exploring the Effect of Primitives for Compositional Generalization in Vision-and-Language}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {19092-19101} }
DC2: Dual-Camera Defocus Control by Learning To Refocus: Hadi Alzayer,

Abdullah Abuolaim,

Leung Chun Chan,

Yang Yang,

Ying Chen Lou,

Jia-Bin Huang,

Abhishek Kar; [pdf] [supp]
[bibtex]
@InProceedings{Alzayer_2023_CVPR, author = {Alzayer, Hadi and Abuolaim, Abdullah and Chan, Leung Chun and Yang, Yang and Lou, Ying Chen and Huang, Jia-Bin and Kar, Abhishek}, title = {DC2: Dual-Camera Defocus Control by Learning To Refocus}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {21488-21497} }
Looking Through the Glass: Neural Surface Reconstruction Against High Specular Reflections: Jiaxiong Qiu,

Peng-Tao Jiang,

Yifan Zhu,

Ze-Xin Yin,

Ming-Ming Cheng,

Bo Ren; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Qiu_2023_CVPR, author = {Qiu, Jiaxiong and Jiang, Peng-Tao and Zhu, Yifan and Yin, Ze-Xin and Cheng, Ming-Ming and Ren, Bo}, title = {Looking Through the Glass: Neural Surface Reconstruction Against High Specular Reflections}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {20823-20833} }
PartSLIP: Low-Shot Part Segmentation for 3D Point Clouds via Pretrained Image-Language Models: Minghua Liu,

Yinhao Zhu,

Hong Cai,

Shizhong Han,

Zhan Ling,

Fatih Porikli,

Hao Su; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Liu_2023_CVPR, author = {Liu, Minghua and Zhu, Yinhao and Cai, Hong and Han, Shizhong and Ling, Zhan and Porikli, Fatih and Su, Hao}, title = {PartSLIP: Low-Shot Part Segmentation for 3D Point Clouds via Pretrained Image-Language Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {21736-21746} }
MAGVLT: Masked Generative Vision-and-Language Transformer: Sungwoong Kim,

Daejin Jo,

Donghoon Lee,

Jongmin Kim; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kim_2023_CVPR, author = {Kim, Sungwoong and Jo, Daejin and Lee, Donghoon and Kim, Jongmin}, title = {MAGVLT: Masked Generative Vision-and-Language Transformer}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {23338-23348} }
Decoupling Human and Camera Motion From Videos in the Wild: Vickie Ye,

Georgios Pavlakos,

Jitendra Malik,

Angjoo Kanazawa; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ye_2023_CVPR, author = {Ye, Vickie and Pavlakos, Georgios and Malik, Jitendra and Kanazawa, Angjoo}, title = {Decoupling Human and Camera Motion From Videos in the Wild}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {21222-21232} }
DetCLIPv2: Scalable Open-Vocabulary Object Detection Pre-Training via Word-Region Alignment: Lewei Yao,

Jianhua Han,

Xiaodan Liang,

Dan Xu,

Wei Zhang,

Zhenguo Li,

Hang Xu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yao_2023_CVPR, author = {Yao, Lewei and Han, Jianhua and Liang, Xiaodan and Xu, Dan and Zhang, Wei and Li, Zhenguo and Xu, Hang}, title = {DetCLIPv2: Scalable Open-Vocabulary Object Detection Pre-Training via Word-Region Alignment}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {23497-23506} }
GrowSP: Unsupervised Semantic Segmentation of 3D Point Clouds: Zihui Zhang,

Bo Yang,

Bing Wang,

Bo Li; [pdf] [supp]
[bibtex]
@InProceedings{Zhang_2023_CVPR, author = {Zhang, Zihui and Yang, Bo and Wang, Bing and Li, Bo}, title = {GrowSP: Unsupervised Semantic Segmentation of 3D Point Clouds}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {17619-17629} }
One-Stage 3D Whole-Body Mesh Recovery With Component Aware Transformer: Jing Lin,

Ailing Zeng,

Haoqian Wang,

Lei Zhang,

Yu Li; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Lin_2023_CVPR, author = {Lin, Jing and Zeng, Ailing and Wang, Haoqian and Zhang, Lei and Li, Yu}, title = {One-Stage 3D Whole-Body Mesh Recovery With Component Aware Transformer}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {21159-21168} }
Masked Jigsaw Puzzle: A Versatile Position Embedding for Vision Transformers: Bin Ren,

Yahui Liu,

Yue Song,

Wei Bi,

Rita Cucchiara,

Nicu Sebe,

Wei Wang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ren_2023_CVPR, author = {Ren, Bin and Liu, Yahui and Song, Yue and Bi, Wei and Cucchiara, Rita and Sebe, Nicu and Wang, Wei}, title = {Masked Jigsaw Puzzle: A Versatile Position Embedding for Vision Transformers}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {20382-20391} }
LayoutDiffusion: Controllable Diffusion Model for Layout-to-Image Generation: Guangcong Zheng,

Xianpan Zhou,

Xuewei Li,

Zhongang Qi,

Ying Shan,

Xi Li; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zheng_2023_CVPR, author = {Zheng, Guangcong and Zhou, Xianpan and Li, Xuewei and Qi, Zhongang and Shan, Ying and Li, Xi}, title = {LayoutDiffusion: Controllable Diffusion Model for Layout-to-Image Generation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {22490-22499} }
DISC: Learning From Noisy Labels via Dynamic Instance-Specific Selection and Correction: Yifan Li,

Hu Han,

Shiguang Shan,

Xilin Chen; [pdf] [supp]
[bibtex]
@InProceedings{Li_2023_CVPR, author = {Li, Yifan and Han, Hu and Shan, Shiguang and Chen, Xilin}, title = {DISC: Learning From Noisy Labels via Dynamic Instance-Specific Selection and Correction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {24070-24079} }
Imagen Editor and EditBench: Advancing and Evaluating Text-Guided Image Inpainting: Su Wang,

Chitwan Saharia,

Ceslee Montgomery,

Jordi Pont-Tuset,

Shai Noy,

Stefano Pellegrini,

Yasumasa Onoe,

Sarah Laszlo,

David J. Fleet,

Radu Soricut,

Jason Baldridge,

Mohammad Norouzi,

Peter Anderson,

William Chan; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2023_CVPR, author = {Wang, Su and Saharia, Chitwan and Montgomery, Ceslee and Pont-Tuset, Jordi and Noy, Shai and Pellegrini, Stefano and Onoe, Yasumasa and Laszlo, Sarah and Fleet, David J. and Soricut, Radu and Baldridge, Jason and Norouzi, Mohammad and Anderson, Peter and Chan, William}, title = {Imagen Editor and EditBench: Advancing and Evaluating Text-Guided Image Inpainting}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {18359-18369} }
Text With Knowledge Graph Augmented Transformer for Video Captioning: Xin Gu,

Guang Chen,

Yufei Wang,

Libo Zhang,

Tiejian Luo,

Longyin Wen; [pdf] [arXiv]
[bibtex]
@InProceedings{Gu_2023_CVPR, author = {Gu, Xin and Chen, Guang and Wang, Yufei and Zhang, Libo and Luo, Tiejian and Wen, Longyin}, title = {Text With Knowledge Graph Augmented Transformer for Video Captioning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {18941-18951} }
Devil Is in the Queries: Advancing Mask Transformers for Real-World Medical Image Segmentation and Out-of-Distribution Localization: Mingze Yuan,

Yingda Xia,

Hexin Dong,

Zifan Chen,

Jiawen Yao,

Mingyan Qiu,

Ke Yan,

Xiaoli Yin,

Yu Shi,

Xin Chen,

Zaiyi Liu,

Bin Dong,

Jingren Zhou,

Le Lu,

Ling Zhang,

Li Zhang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yuan_2023_CVPR, author = {Yuan, Mingze and Xia, Yingda and Dong, Hexin and Chen, Zifan and Yao, Jiawen and Qiu, Mingyan and Yan, Ke and Yin, Xiaoli and Shi, Yu and Chen, Xin and Liu, Zaiyi and Dong, Bin and Zhou, Jingren and Lu, Le and Zhang, Ling and Zhang, Li}, title = {Devil Is in the Queries: Advancing Mask Transformers for Real-World Medical Image Segmentation and Out-of-Distribution Localization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {23879-23889} }
T-SEA: Transfer-Based Self-Ensemble Attack on Object Detection: Hao Huang,

Ziyan Chen,

Huanran Chen,

Yongtao Wang,

Kevin Zhang; [pdf]
[bibtex]
@InProceedings{Huang_2023_CVPR, author = {Huang, Hao and Chen, Ziyan and Chen, Huanran and Wang, Yongtao and Zhang, Kevin}, title = {T-SEA: Transfer-Based Self-Ensemble Attack on Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {20514-20523} }
PSVT: End-to-End Multi-Person 3D Pose and Shape Estimation With Progressive Video Transformers: Zhongwei Qiu,

Qiansheng Yang,

Jian Wang,

Haocheng Feng,

Junyu Han,

Errui Ding,

Chang Xu,

Dongmei Fu,

Jingdong Wang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Qiu_2023_CVPR, author = {Qiu, Zhongwei and Yang, Qiansheng and Wang, Jian and Feng, Haocheng and Han, Junyu and Ding, Errui and Xu, Chang and Fu, Dongmei and Wang, Jingdong}, title = {PSVT: End-to-End Multi-Person 3D Pose and Shape Estimation With Progressive Video Transformers}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {21254-21263} }
Unifying Vision, Text, and Layout for Universal Document Processing: Zineng Tang,

Ziyi Yang,

Guoxin Wang,

Yuwei Fang,

Yang Liu,

Chenguang Zhu,

Michael Zeng,

Cha Zhang,

Mohit Bansal; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Tang_2023_CVPR, author = {Tang, Zineng and Yang, Ziyi and Wang, Guoxin and Fang, Yuwei and Liu, Yang and Zhu, Chenguang and Zeng, Michael and Zhang, Cha and Bansal, Mohit}, title = {Unifying Vision, Text, and Layout for Universal Document Processing}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {19254-19264} }
SparsePose: Sparse-View Camera Pose Regression and Refinement: Samarth Sinha,

Jason Y. Zhang,

Andrea Tagliasacchi,

Igor Gilitschenski,

David B. Lindell; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Sinha_2023_CVPR, author = {Sinha, Samarth and Zhang, Jason Y. and Tagliasacchi, Andrea and Gilitschenski, Igor and Lindell, David B.}, title = {SparsePose: Sparse-View Camera Pose Regression and Refinement}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {21349-21359} }
Flow Supervision for Deformable NeRF: Chaoyang Wang,

Lachlan Ewen MacDonald,

László A. Jeni,

Simon Lucey; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2023_CVPR, author = {Wang, Chaoyang and MacDonald, Lachlan Ewen and Jeni, L\'aszl\'o A. and Lucey, Simon}, title = {Flow Supervision for Deformable NeRF}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {21128-21137} }
Zero-Shot Text-to-Parameter Translation for Game Character Auto-Creation: Rui Zhao,

Wei Li,

Zhipeng Hu,

Lincheng Li,

Zhengxia Zou,

Zhenwei Shi,

Changjie Fan; [pdf] [arXiv]
[bibtex]
@InProceedings{Zhao_2023_CVPR, author = {Zhao, Rui and Li, Wei and Hu, Zhipeng and Li, Lincheng and Zou, Zhengxia and Shi, Zhenwei and Fan, Changjie}, title = {Zero-Shot Text-to-Parameter Translation for Game Character Auto-Creation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {21013-21023} }
PIVOT: Prompting for Video Continual Learning: Andrés Villa,

Juan León Alcázar,

Motasem Alfarra,

Kumail Alhamoud,

Julio Hurtado,

Fabian Caba Heilbron,

Alvaro Soto,

Bernard Ghanem; [pdf] [supp]
[bibtex]
@InProceedings{Villa_2023_CVPR, author = {Villa, Andr\'es and Alc\'azar, Juan Le\'on and Alfarra, Motasem and Alhamoud, Kumail and Hurtado, Julio and Heilbron, Fabian Caba and Soto, Alvaro and Ghanem, Bernard}, title = {PIVOT: Prompting for Video Continual Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {24214-24223} }
Panoptic Video Scene Graph Generation: Jingkang Yang,

Wenxuan Peng,

Xiangtai Li,

Zujin Guo,

Liangyu Chen,

Bo Li,

Zheng Ma,

Kaiyang Zhou,

Wayne Zhang,

Chen Change Loy,

Ziwei Liu; [pdf]
[bibtex]
@InProceedings{Yang_2023_CVPR, author = {Yang, Jingkang and Peng, Wenxuan and Li, Xiangtai and Guo, Zujin and Chen, Liangyu and Li, Bo and Ma, Zheng and Zhou, Kaiyang and Zhang, Wayne and Loy, Chen Change and Liu, Ziwei}, title = {Panoptic Video Scene Graph Generation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {18675-18685} }
Understanding Imbalanced Semantic Segmentation Through Neural Collapse: Zhisheng Zhong,

Jiequan Cui,

Yibo Yang,

Xiaoyang Wu,

Xiaojuan Qi,

Xiangyu Zhang,

Jiaya Jia; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhong_2023_CVPR, author = {Zhong, Zhisheng and Cui, Jiequan and Yang, Yibo and Wu, Xiaoyang and Qi, Xiaojuan and Zhang, Xiangyu and Jia, Jiaya}, title = {Understanding Imbalanced Semantic Segmentation Through Neural Collapse}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {19550-19560} }
HOICLIP: Efficient Knowledge Transfer for HOI Detection With Vision-Language Models: Shan Ning,

Longtian Qiu,

Yongfei Liu,

Xuming He; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ning_2023_CVPR, author = {Ning, Shan and Qiu, Longtian and Liu, Yongfei and He, Xuming}, title = {HOICLIP: Efficient Knowledge Transfer for HOI Detection With Vision-Language Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {23507-23517} }
Focused and Collaborative Feedback Integration for Interactive Image Segmentation: Qiaoqiao Wei,

Hui Zhang,

Jun-Hai Yong; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wei_2023_CVPR, author = {Wei, Qiaoqiao and Zhang, Hui and Yong, Jun-Hai}, title = {Focused and Collaborative Feedback Integration for Interactive Image Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {18643-18652} }
Class Prototypes Based Contrastive Learning for Classifying Multi-Label and Fine-Grained Educational Videos: Rohit Gupta,

Anirban Roy,

Claire Christensen,

Sujeong Kim,

Sarah Gerard,

Madeline Cincebeaux,

Ajay Divakaran,

Todd Grindal,

Mubarak Shah; [pdf] [supp]
[bibtex]
@InProceedings{Gupta_2023_CVPR, author = {Gupta, Rohit and Roy, Anirban and Christensen, Claire and Kim, Sujeong and Gerard, Sarah and Cincebeaux, Madeline and Divakaran, Ajay and Grindal, Todd and Shah, Mubarak}, title = {Class Prototypes Based Contrastive Learning for Classifying Multi-Label and Fine-Grained Educational Videos}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {19923-19933} }
Source-Free Adaptive Gaze Estimation by Uncertainty Reduction: Xin Cai,

Jiabei Zeng,

Shiguang Shan,

Xilin Chen; [pdf] [supp]
[bibtex]
@InProceedings{Cai_2023_CVPR, author = {Cai, Xin and Zeng, Jiabei and Shan, Shiguang and Chen, Xilin}, title = {Source-Free Adaptive Gaze Estimation by Uncertainty Reduction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {22035-22045} }
SuperDisco: Super-Class Discovery Improves Visual Recognition for the Long-Tail: Yingjun Du,

Jiayi Shen,

Xiantong Zhen,

Cees G. M. Snoek; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Du_2023_CVPR, author = {Du, Yingjun and Shen, Jiayi and Zhen, Xiantong and Snoek, Cees G. M.}, title = {SuperDisco: Super-Class Discovery Improves Visual Recognition for the Long-Tail}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {19944-19954} }
Im2Hands: Learning Attentive Implicit Representation of Interacting Two-Hand Shapes: Jihyun Lee,

Minhyuk Sung,

Honggyu Choi,

Tae-Kyun Kim; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Lee_2023_CVPR, author = {Lee, Jihyun and Sung, Minhyuk and Choi, Honggyu and Kim, Tae-Kyun}, title = {Im2Hands: Learning Attentive Implicit Representation of Interacting Two-Hand Shapes}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {21169-21178} }
Long-Term Visual Localization With Mobile Sensors: Shen Yan,

Yu Liu,

Long Wang,

Zehong Shen,

Zhen Peng,

Haomin Liu,

Maojun Zhang,

Guofeng Zhang,

Xiaowei Zhou; [pdf] [arXiv]
[bibtex]
@InProceedings{Yan_2023_CVPR, author = {Yan, Shen and Liu, Yu and Wang, Long and Shen, Zehong and Peng, Zhen and Liu, Haomin and Zhang, Maojun and Zhang, Guofeng and Zhou, Xiaowei}, title = {Long-Term Visual Localization With Mobile Sensors}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {17245-17255} }
Data-Efficient Large Scale Place Recognition With Graded Similarity Supervision: María Leyva-Vallina,

Nicola Strisciuglio,

Nicolai Petkov; [pdf] [