ICCV 2023 Open Access Repository

Papers

Back
Towards Attack-tolerant Federated Learning via Critical Parameter Analysis: Sungwon Han,

Sungwon Park,

Fangzhao Wu,

Sundong Kim,

Bin Zhu,

Xing Xie,

Meeyoung Cha; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Han_2023_ICCV, author = {Han, Sungwon and Park, Sungwon and Wu, Fangzhao and Kim, Sundong and Zhu, Bin and Xie, Xing and Cha, Meeyoung}, title = {Towards Attack-tolerant Federated Learning via Critical Parameter Analysis}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {4999-5008} }
Stochastic Segmentation with Conditional Categorical Diffusion Models: Lukas Zbinden,

Lars Doorenbos,

Theodoros Pissas,

Adrian Thomas Huber,

Raphael Sznitman,

Pablo Márquez-Neila; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zbinden_2023_ICCV, author = {Zbinden, Lukas and Doorenbos, Lars and Pissas, Theodoros and Huber, Adrian Thomas and Sznitman, Raphael and M\'arquez-Neila, Pablo}, title = {Stochastic Segmentation with Conditional Categorical Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {1119-1129} }
Diff-Retinex: Rethinking Low-light Image Enhancement with A Generative Diffusion Model: Xunpeng Yi,

Han Xu,

Hao Zhang,

Linfeng Tang,

Jiayi Ma; [pdf]
[bibtex]
@InProceedings{Yi_2023_ICCV, author = {Yi, Xunpeng and Xu, Han and Zhang, Hao and Tang, Linfeng and Ma, Jiayi}, title = {Diff-Retinex: Rethinking Low-light Image Enhancement with A Generative Diffusion Model}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {12302-12311} }
Bird's-Eye-View Scene Graph for Vision-Language Navigation: Rui Liu,

Xiaohan Wang,

Wenguan Wang,

Yi Yang; [pdf] [supp]
[bibtex]
@InProceedings{Liu_2023_ICCV, author = {Liu, Rui and Wang, Xiaohan and Wang, Wenguan and Yang, Yi}, title = {Bird's-Eye-View Scene Graph for Vision-Language Navigation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {10968-10980} }
PVT++: A Simple End-to-End Latency-Aware Visual Tracking Framework: Bowen Li,

Ziyuan Huang,

Junjie Ye,

Yiming Li,

Sebastian Scherer,

Hang Zhao,

Changhong Fu; [pdf] [supp]
[bibtex]
@InProceedings{Li_2023_ICCV, author = {Li, Bowen and Huang, Ziyuan and Ye, Junjie and Li, Yiming and Scherer, Sebastian and Zhao, Hang and Fu, Changhong}, title = {PVT++: A Simple End-to-End Latency-Aware Visual Tracking Framework}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {10006-10016} }
A Dynamic Dual-Processing Object Detection Framework Inspired by the Brain's Recognition Mechanism: Minying Zhang,

Tianpeng Bu,

Lulu Hu; [pdf]
[bibtex]
@InProceedings{Zhang_2023_ICCV, author = {Zhang, Minying and Bu, Tianpeng and Hu, Lulu}, title = {A Dynamic Dual-Processing Object Detection Framework Inspired by the Brain's Recognition Mechanism}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {6264-6274} }
Hard No-Box Adversarial Attack on Skeleton-Based Human Action Recognition with Skeleton-Motion-Informed Gradient: Zhengzhi Lu,

He Wang,

Ziyi Chang,

Guoan Yang,

Hubert P. H. Shum; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Lu_2023_ICCV, author = {Lu, Zhengzhi and Wang, He and Chang, Ziyi and Yang, Guoan and Shum, Hubert P. H.}, title = {Hard No-Box Adversarial Attack on Skeleton-Based Human Action Recognition with Skeleton-Motion-Informed Gradient}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {4597-4606} }
GameFormer: Game-theoretic Modeling and Learning of Transformer-based Interactive Prediction and Planning for Autonomous Driving: Zhiyu Huang,

Haochen Liu,

Chen Lv; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Huang_2023_ICCV, author = {Huang, Zhiyu and Liu, Haochen and Lv, Chen}, title = {GameFormer: Game-theoretic Modeling and Learning of Transformer-based Interactive Prediction and Planning for Autonomous Driving}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {3903-3913} }
Towards Better Robustness against Common Corruptions for Unsupervised Domain Adaptation: Zhiqiang Gao,

Kaizhu Huang,

Rui Zhang,

Dawei Liu,

Jieming Ma; [pdf] [supp]
[bibtex]
@InProceedings{Gao_2023_ICCV, author = {Gao, Zhiqiang and Huang, Kaizhu and Zhang, Rui and Liu, Dawei and Ma, Jieming}, title = {Towards Better Robustness against Common Corruptions for Unsupervised Domain Adaptation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {18882-18893} }
Learning in Imperfect Environment: Multi-Label Classification with Long-Tailed Distribution and Partial Labels: Wenqiao Zhang,

Changshuo Liu,

Lingze Zeng,

Bengchin Ooi,

Siliang Tang,

Yueting Zhuang; [pdf] [arXiv]
[bibtex]
@InProceedings{Zhang_2023_ICCV, author = {Zhang, Wenqiao and Liu, Changshuo and Zeng, Lingze and Ooi, Bengchin and Tang, Siliang and Zhuang, Yueting}, title = {Learning in Imperfect Environment: Multi-Label Classification with Long-Tailed Distribution and Partial Labels}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {1423-1432} }
Flexible Visual Recognition by Evidential Modeling of Confusion and Ignorance: Lei Fan,

Bo Liu,

Haoxiang Li,

Ying Wu,

Gang Hua; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Fan_2023_ICCV, author = {Fan, Lei and Liu, Bo and Li, Haoxiang and Wu, Ying and Hua, Gang}, title = {Flexible Visual Recognition by Evidential Modeling of Confusion and Ignorance}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {1338-1347} }
Texture Generation on 3D Meshes with Point-UV Diffusion: Xin Yu,

Peng Dai,

Wenbo Li,

Lan Ma,

Zhengzhe Liu,

Xiaojuan Qi; [pdf] [arXiv]
[bibtex]
@InProceedings{Yu_2023_ICCV, author = {Yu, Xin and Dai, Peng and Li, Wenbo and Ma, Lan and Liu, Zhengzhe and Qi, Xiaojuan}, title = {Texture Generation on 3D Meshes with Point-UV Diffusion}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {4206-4216} }
Supervised Homography Learning with Realistic Dataset Generation: Hai Jiang,

Haipeng Li,

Songchen Han,

Haoqiang Fan,

Bing Zeng,

Shuaicheng Liu; [pdf] [arXiv]
[bibtex]
@InProceedings{Jiang_2023_ICCV, author = {Jiang, Hai and Li, Haipeng and Han, Songchen and Fan, Haoqiang and Zeng, Bing and Liu, Shuaicheng}, title = {Supervised Homography Learning with Realistic Dataset Generation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {9806-9815} }
E2E-LOAD: End-to-End Long-form Online Action Detection: Shuqiang Cao,

Weixin Luo,

Bairui Wang,

Wei Zhang,

Lin Ma; [pdf] [supp]
[bibtex]
@InProceedings{Cao_2023_ICCV, author = {Cao, Shuqiang and Luo, Weixin and Wang, Bairui and Zhang, Wei and Ma, Lin}, title = {E2E-LOAD: End-to-End Long-form Online Action Detection}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {10422-10432} }
TALL: Thumbnail Layout for Deepfake Video Detection: Yuting Xu,

Jian Liang,

Gengyun Jia,

Ziming Yang,

Yanhao Zhang,

Ran He; [pdf] [arXiv]
[bibtex]
@InProceedings{Xu_2023_ICCV, author = {Xu, Yuting and Liang, Jian and Jia, Gengyun and Yang, Ziming and Zhang, Yanhao and He, Ran}, title = {TALL: Thumbnail Layout for Deepfake Video Detection}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {22658-22668} }
Enhanced Soft Label for Semi-Supervised Semantic Segmentation: Jie Ma,

Chuan Wang,

Yang Liu,

Liang Lin,

Guanbin Li; [pdf] [supp]
[bibtex]
@InProceedings{Ma_2023_ICCV, author = {Ma, Jie and Wang, Chuan and Liu, Yang and Lin, Liang and Li, Guanbin}, title = {Enhanced Soft Label for Semi-Supervised Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {1185-1195} }
Self-supervised Monocular Depth Estimation: Let's Talk About The Weather: Kieran Saunders,

George Vogiatzis,

Luis J. Manso; [pdf] [supp]
[bibtex]
@InProceedings{Saunders_2023_ICCV, author = {Saunders, Kieran and Vogiatzis, George and Manso, Luis J.}, title = {Self-supervised Monocular Depth Estimation: Let's Talk About The Weather}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {8907-8917} }
Bidirectional Alignment for Domain Adaptive Detection with Transformers: Liqiang He,

Wei Wang,

Albert Chen,

Min Sun,

Cheng-Hao Kuo,

Sinisa Todorovic; [pdf] [supp]
[bibtex]
@InProceedings{He_2023_ICCV, author = {He, Liqiang and Wang, Wei and Chen, Albert and Sun, Min and Kuo, Cheng-Hao and Todorovic, Sinisa}, title = {Bidirectional Alignment for Domain Adaptive Detection with Transformers}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {18775-18785} }
Fast Neural Scene Flow: Xueqian Li,

Jianqiao Zheng,

Francesco Ferroni,

Jhony Kaesemodel Pontes,

Simon Lucey; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Li_2023_ICCV, author = {Li, Xueqian and Zheng, Jianqiao and Ferroni, Francesco and Pontes, Jhony Kaesemodel and Lucey, Simon}, title = {Fast Neural Scene Flow}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {9878-9890} }
CAME: Contrastive Automated Model Evaluation: Ru Peng,

Qiuyang Duan,

Haobo Wang,

Jiachen Ma,

Yanbo Jiang,

Yongjun Tu,

Xiu Jiang,

Junbo Zhao; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Peng_2023_ICCV, author = {Peng, Ru and Duan, Qiuyang and Wang, Haobo and Ma, Jiachen and Jiang, Yanbo and Tu, Yongjun and Jiang, Xiu and Zhao, Junbo}, title = {CAME: Contrastive Automated Model Evaluation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {20121-20132} }
ExposureDiffusion: Learning to Expose for Low-light Image Enhancement: Yufei Wang,

Yi Yu,

Wenhan Yang,

Lanqing Guo,

Lap-Pui Chau,

Alex C. Kot,

Bihan Wen; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2023_ICCV, author = {Wang, Yufei and Yu, Yi and Yang, Wenhan and Guo, Lanqing and Chau, Lap-Pui and Kot, Alex C. and Wen, Bihan}, title = {ExposureDiffusion: Learning to Expose for Low-light Image Enhancement}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {12438-12448} }
HM-ViT: Hetero-Modal Vehicle-to-Vehicle Cooperative Perception with Vision Transformer: Hao Xiang,

Runsheng Xu,

Jiaqi Ma; [pdf] [supp]
[bibtex]
@InProceedings{Xiang_2023_ICCV, author = {Xiang, Hao and Xu, Runsheng and Ma, Jiaqi}, title = {HM-ViT: Hetero-Modal Vehicle-to-Vehicle Cooperative Perception with Vision Transformer}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {284-295} }
HyperReenact: One-Shot Reenactment via Jointly Learning to Refine and Retarget Faces: Stella Bounareli,

Christos Tzelepis,

Vasileios Argyriou,

Ioannis Patras,

Georgios Tzimiropoulos; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Bounareli_2023_ICCV, author = {Bounareli, Stella and Tzelepis, Christos and Argyriou, Vasileios and Patras, Ioannis and Tzimiropoulos, Georgios}, title = {HyperReenact: One-Shot Reenactment via Jointly Learning to Refine and Retarget Faces}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {7149-7159} }
Order-preserving Consistency Regularization for Domain Adaptation and Generalization: Mengmeng Jing,

Xiantong Zhen,

Jingjing Li,

Cees G. M. Snoek; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Jing_2023_ICCV, author = {Jing, Mengmeng and Zhen, Xiantong and Li, Jingjing and Snoek, Cees G. M.}, title = {Order-preserving Consistency Regularization for Domain Adaptation and Generalization}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {18916-18927} }
RefEgo: Referring Expression Comprehension Dataset from First-Person Perception of Ego4D: Shuhei Kurita,

Naoki Katsura,

Eri Onami; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kurita_2023_ICCV, author = {Kurita, Shuhei and Katsura, Naoki and Onami, Eri}, title = {RefEgo: Referring Expression Comprehension Dataset from First-Person Perception of Ego4D}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {15214-15224} }
Exploring Temporal Frequency Spectrum in Deep Video Deblurring: Qi Zhu,

Man Zhou,

Naishan Zheng,

Chongyi Li,

Jie Huang,

Feng Zhao; [pdf]
[bibtex]
@InProceedings{Zhu_2023_ICCV, author = {Zhu, Qi and Zhou, Man and Zheng, Naishan and Li, Chongyi and Huang, Jie and Zhao, Feng}, title = {Exploring Temporal Frequency Spectrum in Deep Video Deblurring}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {12428-12437} }
Unified Visual Relationship Detection with Vision and Language Models: Long Zhao,

Liangzhe Yuan,

Boqing Gong,

Yin Cui,

Florian Schroff,

Ming-Hsuan Yang,

Hartwig Adam,

Ting Liu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhao_2023_ICCV, author = {Zhao, Long and Yuan, Liangzhe and Gong, Boqing and Cui, Yin and Schroff, Florian and Yang, Ming-Hsuan and Adam, Hartwig and Liu, Ting}, title = {Unified Visual Relationship Detection with Vision and Language Models}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {6962-6973} }
Occ^2Net: Robust Image Matching Based on 3D Occupancy Estimation for Occluded Regions: Miao Fan,

Mingrui Chen,

Chen Hu,

Shuchang Zhou; [pdf]
[bibtex]
@InProceedings{Fan_2023_ICCV, author = {Fan, Miao and Chen, Mingrui and Hu, Chen and Zhou, Shuchang}, title = {Occ{\textasciicircum}2Net: Robust Image Matching Based on 3D Occupancy Estimation for Occluded Regions}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {9652-9662} }
Make-An-Animation: Large-Scale Text-conditional 3D Human Motion Generation: Samaneh Azadi,

Akbar Shah,

Thomas Hayes,

Devi Parikh,

Sonal Gupta; [pdf]
[bibtex]
@InProceedings{Azadi_2023_ICCV, author = {Azadi, Samaneh and Shah, Akbar and Hayes, Thomas and Parikh, Devi and Gupta, Sonal}, title = {Make-An-Animation: Large-Scale Text-conditional 3D Human Motion Generation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {15039-15048} }
Rickrolling the Artist: Injecting Backdoors into Text Encoders for Text-to-Image Synthesis: Lukas Struppek,

Dominik Hintersdorf,

Kristian Kersting; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Struppek_2023_ICCV, author = {Struppek, Lukas and Hintersdorf, Dominik and Kersting, Kristian}, title = {Rickrolling the Artist: Injecting Backdoors into Text Encoders for Text-to-Image Synthesis}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {4584-4596} }
LD-ZNet: A Latent Diffusion Approach for Text-Based Image Segmentation: Koutilya PNVR,

Bharat Singh,

Pallabi Ghosh,

Behjat Siddiquie,

David Jacobs; [pdf] [supp]
[bibtex]
@InProceedings{PNVR_2023_ICCV, author = {PNVR, Koutilya and Singh, Bharat and Ghosh, Pallabi and Siddiquie, Behjat and Jacobs, David}, title = {LD-ZNet: A Latent Diffusion Approach for Text-Based Image Segmentation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {4157-4168} }
Workie-Talkie: Accelerating Federated Learning by Overlapping Computing and Communications via Contrastive Regularization: Rui Chen,

Qiyu Wan,

Pavana Prakash,

Lan Zhang,

Xu Yuan,

Yanmin Gong,

Xin Fu,

Miao Pan; [pdf] [supp]
[bibtex]
@InProceedings{Chen_2023_ICCV, author = {Chen, Rui and Wan, Qiyu and Prakash, Pavana and Zhang, Lan and Yuan, Xu and Gong, Yanmin and Fu, Xin and Pan, Miao}, title = {Workie-Talkie: Accelerating Federated Learning by Overlapping Computing and Communications via Contrastive Regularization}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {16999-17009} }
Downstream-agnostic Adversarial Examples: Ziqi Zhou,

Shengshan Hu,

Ruizhi Zhao,

Qian Wang,

Leo Yu Zhang,

Junhui Hou,

Hai Jin; [pdf] [arXiv]
[bibtex]
@InProceedings{Zhou_2023_ICCV, author = {Zhou, Ziqi and Hu, Shengshan and Zhao, Ruizhi and Wang, Qian and Zhang, Leo Yu and Hou, Junhui and Jin, Hai}, title = {Downstream-agnostic Adversarial Examples}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {4345-4355} }
Late Stopping: Avoiding Confidently Learning from Mislabeled Examples: Suqin Yuan,

Lei Feng,

Tongliang Liu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yuan_2023_ICCV, author = {Yuan, Suqin and Feng, Lei and Liu, Tongliang}, title = {Late Stopping: Avoiding Confidently Learning from Mislabeled Examples}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {16079-16088} }
AerialVLN: Vision-and-Language Navigation for UAVs: Shubo Liu,

Hongsheng Zhang,

Yuankai Qi,

Peng Wang,

Yanning Zhang,

Qi Wu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Liu_2023_ICCV, author = {Liu, Shubo and Zhang, Hongsheng and Qi, Yuankai and Wang, Peng and Zhang, Yanning and Wu, Qi}, title = {AerialVLN: Vision-and-Language Navigation for UAVs}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {15384-15394} }
On the Robustness of Open-World Test-Time Training: Self-Training with Dynamic Prototype Expansion: Yushu Li,

Xun Xu,

Yongyi Su,

Kui Jia; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Li_2023_ICCV, author = {Li, Yushu and Xu, Xun and Su, Yongyi and Jia, Kui}, title = {On the Robustness of Open-World Test-Time Training: Self-Training with Dynamic Prototype Expansion}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {11836-11846} }
Studying How to Efficiently and Effectively Guide Models with Explanations: Sukrut Rao,

Moritz Böhle,

Amin Parchami-Araghi,

Bernt Schiele; [pdf] [supp]
[bibtex]
@InProceedings{Rao_2023_ICCV, author = {Rao, Sukrut and B\"ohle, Moritz and Parchami-Araghi, Amin and Schiele, Bernt}, title = {Studying How to Efficiently and Effectively Guide Models with Explanations}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {1922-1933} }
Most Important Person-Guided Dual-Branch Cross-Patch Attention for Group Affect Recognition: Hongxia Xie,

Ming-Xian Lee,

Tzu-Jui Chen,

Hung-Jen Chen,

Hou-I Liu,

Hong-Han Shuai,

Wen-Huang Cheng; [pdf]
[bibtex]
@InProceedings{Xie_2023_ICCV, author = {Xie, Hongxia and Lee, Ming-Xian and Chen, Tzu-Jui and Chen, Hung-Jen and Liu, Hou-I and Shuai, Hong-Han and Cheng, Wen-Huang}, title = {Most Important Person-Guided Dual-Branch Cross-Patch Attention for Group Affect Recognition}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {20598-20608} }
SkeletonMAE: Graph-based Masked Autoencoder for Skeleton Sequence Pre-training: Hong Yan,

Yang Liu,

Yushen Wei,

Zhen Li,

Guanbin Li,

Liang Lin; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yan_2023_ICCV, author = {Yan, Hong and Liu, Yang and Wei, Yushen and Li, Zhen and Li, Guanbin and Lin, Liang}, title = {SkeletonMAE: Graph-based Masked Autoencoder for Skeleton Sequence Pre-training}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {5606-5618} }
Achievement-Based Training Progress Balancing for Multi-Task Learning: Hayoung Yun,

Hanjoo Cho; [pdf] [supp]
[bibtex]
@InProceedings{Yun_2023_ICCV, author = {Yun, Hayoung and Cho, Hanjoo}, title = {Achievement-Based Training Progress Balancing for Multi-Task Learning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {16935-16944} }
Pose-Free Neural Radiance Fields via Implicit Pose Regularization: Jiahui Zhang,

Fangneng Zhan,

Yingchen Yu,

Kunhao Liu,

Rongliang Wu,

Xiaoqin Zhang,

Ling Shao,

Shijian Lu; [pdf] [arXiv]
[bibtex]
@InProceedings{Zhang_2023_ICCV, author = {Zhang, Jiahui and Zhan, Fangneng and Yu, Yingchen and Liu, Kunhao and Wu, Rongliang and Zhang, Xiaoqin and Shao, Ling and Lu, Shijian}, title = {Pose-Free Neural Radiance Fields via Implicit Pose Regularization}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {3534-3543} }
Self-supervised Learning to Bring Dual Reversed Rolling Shutter Images Alive: Wei Shang,

Dongwei Ren,

Chaoyu Feng,

Xiaotao Wang,

Lei Lei,

Wangmeng Zuo; [pdf] [arXiv]
[bibtex]
@InProceedings{Shang_2023_ICCV, author = {Shang, Wei and Ren, Dongwei and Feng, Chaoyu and Wang, Xiaotao and Lei, Lei and Zuo, Wangmeng}, title = {Self-supervised Learning to Bring Dual Reversed Rolling Shutter Images Alive}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {13086-13094} }
Logic-induced Diagnostic Reasoning for Semi-supervised Semantic Segmentation: Chen Liang,

Wenguan Wang,

Jiaxu Miao,

Yi Yang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Liang_2023_ICCV, author = {Liang, Chen and Wang, Wenguan and Miao, Jiaxu and Yang, Yi}, title = {Logic-induced Diagnostic Reasoning for Semi-supervised Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {16197-16208} }
Self-Supervised Monocular Depth Estimation by Direction-aware Cumulative Convolution Network: Wencheng Han,

Junbo Yin,

Jianbing Shen; [pdf] [arXiv]
[bibtex]
@InProceedings{Han_2023_ICCV, author = {Han, Wencheng and Yin, Junbo and Shen, Jianbing}, title = {Self-Supervised Monocular Depth Estimation by Direction-aware Cumulative Convolution Network}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {8613-8623} }
Encyclopedic VQA: Visual Questions About Detailed Properties of Fine-Grained Categories: Thomas Mensink,

Jasper Uijlings,

Lluis Castrejon,

Arushi Goel,

Felipe Cadar,

Howard Zhou,

Fei Sha,

André Araujo,

Vittorio Ferrari; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Mensink_2023_ICCV, author = {Mensink, Thomas and Uijlings, Jasper and Castrejon, Lluis and Goel, Arushi and Cadar, Felipe and Zhou, Howard and Sha, Fei and Araujo, Andr\'e and Ferrari, Vittorio}, title = {Encyclopedic VQA: Visual Questions About Detailed Properties of Fine-Grained Categories}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {3113-3124} }
Towards Understanding the Generalization of Deepfake Detectors from a Game-Theoretical View: Kelu Yao,

Jin Wang,

Boyu Diao,

Chao Li; [pdf] [supp]
[bibtex]
@InProceedings{Yao_2023_ICCV, author = {Yao, Kelu and Wang, Jin and Diao, Boyu and Li, Chao}, title = {Towards Understanding the Generalization of Deepfake Detectors from a Game-Theoretical View}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {2031-2041} }
Few-Shot Common Action Localization via Cross-Attentional Fusion of Context and Temporal Dynamics: Juntae Lee,

Mihir Jain,

Sungrack Yun; [pdf]
[bibtex]
@InProceedings{Lee_2023_ICCV, author = {Lee, Juntae and Jain, Mihir and Yun, Sungrack}, title = {Few-Shot Common Action Localization via Cross-Attentional Fusion of Context and Temporal Dynamics}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {10214-10223} }
Physically-Plausible Illumination Distribution Estimation: Egor Ershov,

Vasily Tesalin,

Ivan Ermakov,

Michael S. Brown; [pdf]
[bibtex]
@InProceedings{Ershov_2023_ICCV, author = {Ershov, Egor and Tesalin, Vasily and Ermakov, Ivan and Brown, Michael S.}, title = {Physically-Plausible Illumination Distribution Estimation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {12928-12936} }
3DPPE: 3D Point Positional Encoding for Transformer-based Multi-Camera 3D Object Detection: Changyong Shu,

Jiajun Deng,

Fisher Yu,

Yifan Liu; [pdf] [supp]
[bibtex]
@InProceedings{Shu_2023_ICCV, author = {Shu, Changyong and Deng, Jiajun and Yu, Fisher and Liu, Yifan}, title = {3DPPE: 3D Point Positional Encoding for Transformer-based Multi-Camera 3D Object Detection}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {3580-3589} }
Revisiting Foreground and Background Separation in Weakly-supervised Temporal Action Localization: A Clustering-based Approach: Qinying Liu,

Zilei Wang,

Shenghai Rong,

Junjie Li,

Yixin Zhang; [pdf] [supp]
[bibtex]
@InProceedings{Liu_2023_ICCV, author = {Liu, Qinying and Wang, Zilei and Rong, Shenghai and Li, Junjie and Zhang, Yixin}, title = {Revisiting Foreground and Background Separation in Weakly-supervised Temporal Action Localization: A Clustering-based Approach}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {10433-10443} }
VertexSerum: Poisoning Graph Neural Networks for Link Inference: Ruyi Ding,

Shijin Duan,

Xiaolin Xu,

Yunsi Fei; [pdf] [arXiv]
[bibtex]
@InProceedings{Ding_2023_ICCV, author = {Ding, Ruyi and Duan, Shijin and Xu, Xiaolin and Fei, Yunsi}, title = {VertexSerum: Poisoning Graph Neural Networks for Link Inference}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {4532-4541} }
NeRF-Det: Learning Geometry-Aware Volumetric Representation for Multi-View 3D Object Detection: Chenfeng Xu,

Bichen Wu,

Ji Hou,

Sam Tsai,

Ruilong Li,

Jialiang Wang,

Wei Zhan,

Zijian He,

Peter Vajda,

Kurt Keutzer,

Masayoshi Tomizuka; [pdf] [supp]
[bibtex]
@InProceedings{Xu_2023_ICCV, author = {Xu, Chenfeng and Wu, Bichen and Hou, Ji and Tsai, Sam and Li, Ruilong and Wang, Jialiang and Zhan, Wei and He, Zijian and Vajda, Peter and Keutzer, Kurt and Tomizuka, Masayoshi}, title = {NeRF-Det: Learning Geometry-Aware Volumetric Representation for Multi-View 3D Object Detection}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {23320-23330} }
Spatio-Temporal Domain Awareness for Multi-Agent Collaborative Perception: Kun Yang,

Dingkang Yang,

Jingyu Zhang,

Mingcheng Li,

Yang Liu,

Jing Liu,

Hanqi Wang,

Peng Sun,

Liang Song; [pdf] [arXiv]
[bibtex]
@InProceedings{Yang_2023_ICCV, author = {Yang, Kun and Yang, Dingkang and Zhang, Jingyu and Li, Mingcheng and Liu, Yang and Liu, Jing and Wang, Hanqi and Sun, Peng and Song, Liang}, title = {Spatio-Temporal Domain Awareness for Multi-Agent Collaborative Perception}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {23383-23392} }
LPFF: A Portrait Dataset for Face Generators Across Large Poses: Yiqian Wu,

Jing Zhang,

Hongbo Fu,

Xiaogang Jin; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wu_2023_ICCV, author = {Wu, Yiqian and Zhang, Jing and Fu, Hongbo and Jin, Xiaogang}, title = {LPFF: A Portrait Dataset for Face Generators Across Large Poses}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {20327-20337} }
Pseudo-label Alignment for Semi-supervised Instance Segmentation: Jie Hu,

Chen Chen,

Liujuan Cao,

Shengchuan Zhang,

Annan Shu,

Guannan Jiang,

Rongrong Ji; [pdf] [arXiv]
[bibtex]
@InProceedings{Hu_2023_ICCV, author = {Hu, Jie and Chen, Chen and Cao, Liujuan and Zhang, Shengchuan and Shu, Annan and Jiang, Guannan and Ji, Rongrong}, title = {Pseudo-label Alignment for Semi-supervised Instance Segmentation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {16337-16347} }
Deep Geometrized Cartoon Line Inbetweening: Li Siyao,

Tianpei Gu,

Weiye Xiao,

Henghui Ding,

Ziwei Liu,

Chen Change Loy; [pdf] [supp]
[bibtex]
@InProceedings{Siyao_2023_ICCV, author = {Siyao, Li and Gu, Tianpei and Xiao, Weiye and Ding, Henghui and Liu, Ziwei and Loy, Chen Change}, title = {Deep Geometrized Cartoon Line Inbetweening}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {7291-7300} }
MixBag: Bag-Level Data Augmentation for Learning from Label Proportions: Takanori Asanomi,

Shinnosuke Matsuo,

Daiki Suehiro,

Ryoma Bise; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Asanomi_2023_ICCV, author = {Asanomi, Takanori and Matsuo, Shinnosuke and Suehiro, Daiki and Bise, Ryoma}, title = {MixBag: Bag-Level Data Augmentation for Learning from Label Proportions}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {16570-16579} }
Effective Real Image Editing with Accelerated Iterative Diffusion Inversion: Zhihong Pan,

Riccardo Gherardi,

Xiufeng Xie,

Stephen Huang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Pan_2023_ICCV, author = {Pan, Zhihong and Gherardi, Riccardo and Xie, Xiufeng and Huang, Stephen}, title = {Effective Real Image Editing with Accelerated Iterative Diffusion Inversion}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {15912-15921} }
3D-Aware Neural Body Fitting for Occlusion Robust 3D Human Pose Estimation: Yi Zhang,

Pengliang Ji,

Angtian Wang,

Jieru Mei,

Adam Kortylewski,

Alan Yuille; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhang_2023_ICCV, author = {Zhang, Yi and Ji, Pengliang and Wang, Angtian and Mei, Jieru and Kortylewski, Adam and Yuille, Alan}, title = {3D-Aware Neural Body Fitting for Occlusion Robust 3D Human Pose Estimation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {9399-9410} }
Chinese Text Recognition with A Pre-Trained CLIP-Like Model Through Image-IDS Aligning: Haiyang Yu,

Xiaocong Wang,

Bin Li,

Xiangyang Xue; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yu_2023_ICCV, author = {Yu, Haiyang and Wang, Xiaocong and Li, Bin and Xue, Xiangyang}, title = {Chinese Text Recognition with A Pre-Trained CLIP-Like Model Through Image-IDS Aligning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {11943-11952} }
MatrixCity: A Large-scale City Dataset for City-scale Neural Rendering and Beyond: Yixuan Li,

Lihan Jiang,

Linning Xu,

Yuanbo Xiangli,

Zhenzhi Wang,

Dahua Lin,

Bo Dai; [pdf] [supp]
[bibtex]
@InProceedings{Li_2023_ICCV, author = {Li, Yixuan and Jiang, Lihan and Xu, Linning and Xiangli, Yuanbo and Wang, Zhenzhi and Lin, Dahua and Dai, Bo}, title = {MatrixCity: A Large-scale City Dataset for City-scale Neural Rendering and Beyond}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {3205-3215} }
LinkGAN: Linking GAN Latents to Pixels for Controllable Image Synthesis: Jiapeng Zhu,

Ceyuan Yang,

Yujun Shen,

Zifan Shi,

Bo Dai,

Deli Zhao,

Qifeng Chen; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhu_2023_ICCV, author = {Zhu, Jiapeng and Yang, Ceyuan and Shen, Yujun and Shi, Zifan and Dai, Bo and Zhao, Deli and Chen, Qifeng}, title = {LinkGAN: Linking GAN Latents to Pixels for Controllable Image Synthesis}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {7656-7666} }
Exploiting Proximity-Aware Tasks for Embodied Social Navigation: Enrico Cancelli,

Tommaso Campari,

Luciano Serafini,

Angel X. Chang,

Lamberto Ballan; [pdf] [arXiv]
[bibtex]
@InProceedings{Cancelli_2023_ICCV, author = {Cancelli, Enrico and Campari, Tommaso and Serafini, Luciano and Chang, Angel X. and Ballan, Lamberto}, title = {Exploiting Proximity-Aware Tasks for Embodied Social Navigation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {10957-10967} }
SVDiff: Compact Parameter Space for Diffusion Fine-Tuning: Ligong Han,

Yinxiao Li,

Han Zhang,

Peyman Milanfar,

Dimitris Metaxas,

Feng Yang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Han_2023_ICCV, author = {Han, Ligong and Li, Yinxiao and Zhang, Han and Milanfar, Peyman and Metaxas, Dimitris and Yang, Feng}, title = {SVDiff: Compact Parameter Space for Diffusion Fine-Tuning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {7323-7334} }
UniFace: Unified Cross-Entropy Loss for Deep Face Recognition: Jiancan Zhou,

Xi Jia,

Qiufu Li,

Linlin Shen,

Jinming Duan; [pdf] [supp]
[bibtex]
@InProceedings{Zhou_2023_ICCV, author = {Zhou, Jiancan and Jia, Xi and Li, Qiufu and Shen, Linlin and Duan, Jinming}, title = {UniFace: Unified Cross-Entropy Loss for Deep Face Recognition}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {20730-20739} }
Jumping through Local Minima: Quantization in the Loss Landscape of Vision Transformers: Natalia Frumkin,

Dibakar Gope,

Diana Marculescu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Frumkin_2023_ICCV, author = {Frumkin, Natalia and Gope, Dibakar and Marculescu, Diana}, title = {Jumping through Local Minima: Quantization in the Loss Landscape of Vision Transformers}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {16978-16988} }
Hierarchical Contrastive Learning for Pattern-Generalizable Image Corruption Detection: Xin Feng,

Yifeng Xu,

Guangming Lu,

Wenjie Pei; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Feng_2023_ICCV, author = {Feng, Xin and Xu, Yifeng and Lu, Guangming and Pei, Wenjie}, title = {Hierarchical Contrastive Learning for Pattern-Generalizable Image Corruption Detection}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {12076-12085} }
Learning Optical Flow from Event Camera with Rendered Dataset: Xinglong Luo,

Kunming Luo,

Ao Luo,

Zhengning Wang,

Ping Tan,

Shuaicheng Liu; [pdf] [arXiv]
[bibtex]
@InProceedings{Luo_2023_ICCV, author = {Luo, Xinglong and Luo, Kunming and Luo, Ao and Wang, Zhengning and Tan, Ping and Liu, Shuaicheng}, title = {Learning Optical Flow from Event Camera with Rendered Dataset}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {9847-9857} }
EPiC: Ensemble of Partial Point Clouds for Robust Classification: Meir Yossef Levi,

Guy Gilboa; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Levi_2023_ICCV, author = {Levi, Meir Yossef and Gilboa, Guy}, title = {EPiC: Ensemble of Partial Point Clouds for Robust Classification}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {14475-14484} }
Distilling Large Vision-Language Model with Out-of-Distribution Generalizability: Xuanlin Li,

Yunhao Fang,

Minghua Liu,

Zhan Ling,

Zhuowen Tu,

Hao Su; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Li_2023_ICCV, author = {Li, Xuanlin and Fang, Yunhao and Liu, Minghua and Ling, Zhan and Tu, Zhuowen and Su, Hao}, title = {Distilling Large Vision-Language Model with Out-of-Distribution Generalizability}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {2492-2503} }
Cross-Modal Learning with 3D Deformable Attention for Action Recognition: Sangwon Kim,

Dasom Ahn,

Byoung Chul Ko; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kim_2023_ICCV, author = {Kim, Sangwon and Ahn, Dasom and Ko, Byoung Chul}, title = {Cross-Modal Learning with 3D Deformable Attention for Action Recognition}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {10265-10275} }
What do neural networks learn in image classification? A frequency shortcut perspective: Shunxin Wang,

Raymond Veldhuis,

Christoph Brune,

Nicola Strisciuglio; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2023_ICCV, author = {Wang, Shunxin and Veldhuis, Raymond and Brune, Christoph and Strisciuglio, Nicola}, title = {What do neural networks learn in image classification? A frequency shortcut perspective}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {1433-1442} }
Tracking by 3D Model Estimation of Unknown Objects in Videos: Denys Rozumnyi,

Jiří Matas,

Marc Pollefeys,

Vittorio Ferrari,

Martin R. Oswald; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Rozumnyi_2023_ICCV, author = {Rozumnyi, Denys and Matas, Ji\v{r}{\'\i} and Pollefeys, Marc and Ferrari, Vittorio and Oswald, Martin R.}, title = {Tracking by 3D Model Estimation of Unknown Objects in Videos}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {14086-14096} }
ScatterNeRF: Seeing Through Fog with Physically-Based Inverse Neural Rendering: Andrea Ramazzina,

Mario Bijelic,

Stefanie Walz,

Alessandro Sanvito,

Dominik Scheuble,

Felix Heide; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ramazzina_2023_ICCV, author = {Ramazzina, Andrea and Bijelic, Mario and Walz, Stefanie and Sanvito, Alessandro and Scheuble, Dominik and Heide, Felix}, title = {ScatterNeRF: Seeing Through Fog with Physically-Based Inverse Neural Rendering}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {17957-17968} }
Sigmoid Loss for Language Image Pre-Training: Xiaohua Zhai,

Basil Mustafa,

Alexander Kolesnikov,

Lucas Beyer; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhai_2023_ICCV, author = {Zhai, Xiaohua and Mustafa, Basil and Kolesnikov, Alexander and Beyer, Lucas}, title = {Sigmoid Loss for Language Image Pre-Training}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {11975-11986} }
PromptCap: Prompt-Guided Image Captioning for VQA with GPT-3: Yushi Hu,

Hang Hua,

Zhengyuan Yang,

Weijia Shi,

Noah A. Smith,

Jiebo Luo; [pdf] [supp]
[bibtex]
@InProceedings{Hu_2023_ICCV, author = {Hu, Yushi and Hua, Hang and Yang, Zhengyuan and Shi, Weijia and Smith, Noah A. and Luo, Jiebo}, title = {PromptCap: Prompt-Guided Image Captioning for VQA with GPT-3}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {2963-2975} }
Neural Video Depth Stabilizer: Yiran Wang,

Min Shi,

Jiaqi Li,

Zihao Huang,

Zhiguo Cao,

Jianming Zhang,

Ke Xian,

Guosheng Lin; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2023_ICCV, author = {Wang, Yiran and Shi, Min and Li, Jiaqi and Huang, Zihao and Cao, Zhiguo and Zhang, Jianming and Xian, Ke and Lin, Guosheng}, title = {Neural Video Depth Stabilizer}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {9466-9476} }
Learning Symmetry-Aware Geometry Correspondences for 6D Object Pose Estimation: Heng Zhao,

Shenxing Wei,

Dahu Shi,

Wenming Tan,

Zheyang Li,

Ye Ren,

Xing Wei,

Yi Yang,

Shiliang Pu; [pdf]
[bibtex]
@InProceedings{Zhao_2023_ICCV, author = {Zhao, Heng and Wei, Shenxing and Shi, Dahu and Tan, Wenming and Li, Zheyang and Ren, Ye and Wei, Xing and Yang, Yi and Pu, Shiliang}, title = {Learning Symmetry-Aware Geometry Correspondences for 6D Object Pose Estimation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {14045-14054} }
TrackFlow: Multi-Object tracking with Normalizing Flows: Gianluca Mancusi,

Aniello Panariello,

Angelo Porrello,

Matteo Fabbri,

Simone Calderara,

Rita Cucchiara; [pdf] [arXiv]
[bibtex]
@InProceedings{Mancusi_2023_ICCV, author = {Mancusi, Gianluca and Panariello, Aniello and Porrello, Angelo and Fabbri, Matteo and Calderara, Simone and Cucchiara, Rita}, title = {TrackFlow: Multi-Object tracking with Normalizing Flows}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {9531-9543} }
Towards Generic Image Manipulation Detection with Weakly-Supervised Self-Consistency Learning: Yuanhao Zhai,

Tianyu Luan,

David Doermann,

Junsong Yuan; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhai_2023_ICCV, author = {Zhai, Yuanhao and Luan, Tianyu and Doermann, David and Yuan, Junsong}, title = {Towards Generic Image Manipulation Detection with Weakly-Supervised Self-Consistency Learning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {22390-22400} }
PARF: Primitive-Aware Radiance Fusion for Indoor Scene Novel View Synthesis: Haiyang Ying,

Baowei Jiang,

Jinzhi Zhang,

Di Xu,

Tao Yu,

Qionghai Dai,

Lu Fang; [pdf] [supp]
[bibtex]
@InProceedings{Ying_2023_ICCV, author = {Ying, Haiyang and Jiang, Baowei and Zhang, Jinzhi and Xu, Di and Yu, Tao and Dai, Qionghai and Fang, Lu}, title = {PARF: Primitive-Aware Radiance Fusion for Indoor Scene Novel View Synthesis}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {17706-17716} }
DeePoint: Visual Pointing Recognition and Direction Estimation: Shu Nakamura,

Yasutomo Kawanishi,

Shohei Nobuhara,

Ko Nishino; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Nakamura_2023_ICCV, author = {Nakamura, Shu and Kawanishi, Yasutomo and Nobuhara, Shohei and Nishino, Ko}, title = {DeePoint: Visual Pointing Recognition and Direction Estimation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {20577-20587} }
Periodically Exchange Teacher-Student for Source-Free Object Detection: Qipeng Liu,

Luojun Lin,

Zhifeng Shen,

Zhifeng Yang; [pdf]
[bibtex]
@InProceedings{Liu_2023_ICCV, author = {Liu, Qipeng and Lin, Luojun and Shen, Zhifeng and Yang, Zhifeng}, title = {Periodically Exchange Teacher-Student for Source-Free Object Detection}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {6414-6424} }
Generating Instance-level Prompts for Rehearsal-free Continual Learning: Dahuin Jung,

Dongyoon Han,

Jihwan Bang,

Hwanjun Song; [pdf] [supp]
[bibtex]
@InProceedings{Jung_2023_ICCV, author = {Jung, Dahuin and Han, Dongyoon and Bang, Jihwan and Song, Hwanjun}, title = {Generating Instance-level Prompts for Rehearsal-free Continual Learning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {11847-11857} }
Deformer: Dynamic Fusion Transformer for Robust Hand Pose Estimation: Qichen Fu,

Xingyu Liu,

Ran Xu,

Juan Carlos Niebles,

Kris M. Kitani; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Fu_2023_ICCV, author = {Fu, Qichen and Liu, Xingyu and Xu, Ran and Niebles, Juan Carlos and Kitani, Kris M.}, title = {Deformer: Dynamic Fusion Transformer for Robust Hand Pose Estimation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {23600-23611} }
HSE: Hybrid Species Embedding for Deep Metric Learning: Bailin Yang,

Haoqiang Sun,

Frederick W. B. Li,

Zheng Chen,

Jianlu Cai,

Chao Song; [pdf]
[bibtex]
@InProceedings{Yang_2023_ICCV, author = {Yang, Bailin and Sun, Haoqiang and Li, Frederick W. B. and Chen, Zheng and Cai, Jianlu and Song, Chao}, title = {HSE: Hybrid Species Embedding for Deep Metric Learning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {11047-11057} }
Online Continual Learning on Hierarchical Label Expansion: Byung Hyun Lee,

Okchul Jung,

Jonghyun Choi,

Se Young Chun; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Lee_2023_ICCV, author = {Lee, Byung Hyun and Jung, Okchul and Choi, Jonghyun and Chun, Se Young}, title = {Online Continual Learning on Hierarchical Label Expansion}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {11761-11770} }
iDAG: Invariant DAG Searching for Domain Generalization: Zenan Huang,

Haobo Wang,

Junbo Zhao,

Nenggan Zheng; [pdf] [supp]
[bibtex]
@InProceedings{Huang_2023_ICCV, author = {Huang, Zenan and Wang, Haobo and Zhao, Junbo and Zheng, Nenggan}, title = {iDAG: Invariant DAG Searching for Domain Generalization}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {19169-19179} }
Spacetime Surface Regularization for Neural Dynamic Scene Reconstruction: Jaesung Choe,

Christopher Choy,

Jaesik Park,

In So Kweon,

Anima Anandkumar; [pdf] [supp]
[bibtex]
@InProceedings{Choe_2023_ICCV, author = {Choe, Jaesung and Choy, Christopher and Park, Jaesik and Kweon, In So and Anandkumar, Anima}, title = {Spacetime Surface Regularization for Neural Dynamic Scene Reconstruction}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {17871-17881} }
GasMono: Geometry-Aided Self-Supervised Monocular Depth Estimation for Indoor Scenes: Chaoqiang Zhao,

Matteo Poggi,

Fabio Tosi,

Lei Zhou,

Qiyu Sun,

Yang Tang,

Stefano Mattoccia; [pdf] [supp]
[bibtex]
@InProceedings{Zhao_2023_ICCV, author = {Zhao, Chaoqiang and Poggi, Matteo and Tosi, Fabio and Zhou, Lei and Sun, Qiyu and Tang, Yang and Mattoccia, Stefano}, title = {GasMono: Geometry-Aided Self-Supervised Monocular Depth Estimation for Indoor Scenes}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {16209-16220} }
3D Motion Magnification: Visualizing Subtle Motions from Time-Varying Radiance Fields: Brandon Y. Feng,

Hadi Alzayer,

Michael Rubinstein,

William T. Freeman,

Jia-bin Huang; [pdf]
[bibtex]
@InProceedings{Feng_2023_ICCV, author = {Feng, Brandon Y. and Alzayer, Hadi and Rubinstein, Michael and Freeman, William T. and Huang, Jia-bin}, title = {3D Motion Magnification: Visualizing Subtle Motions from Time-Varying Radiance Fields}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {9837-9846} }
Learning to Transform for Generalizable Instance-wise Invariance: Utkarsh Singhal,

Carlos Esteves,

Ameesh Makadia,

Stella X. Yu; [pdf]
[bibtex]
@InProceedings{Singhal_2023_ICCV, author = {Singhal, Utkarsh and Esteves, Carlos and Makadia, Ameesh and Yu, Stella X.}, title = {Learning to Transform for Generalizable Instance-wise Invariance}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {6211-6221} }
Audio-Visual Deception Detection: DOLOS Dataset and Parameter-Efficient Crossmodal Learning: Xiaobao Guo,

Nithish Muthuchamy Selvaraj,

Zitong Yu,

Adams Wai-Kin Kong,

Bingquan Shen,

Alex Kot; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Guo_2023_ICCV, author = {Guo, Xiaobao and Selvaraj, Nithish Muthuchamy and Yu, Zitong and Kong, Adams Wai-Kin and Shen, Bingquan and Kot, Alex}, title = {Audio-Visual Deception Detection: DOLOS Dataset and Parameter-Efficient Crossmodal Learning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {22135-22145} }
Multiple Instance Learning Framework with Masked Hard Instance Mining for Whole Slide Image Classification: Wenhao Tang,

Sheng Huang,

Xiaoxian Zhang,

Fengtao Zhou,

Yi Zhang,

Bo Liu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Tang_2023_ICCV, author = {Tang, Wenhao and Huang, Sheng and Zhang, Xiaoxian and Zhou, Fengtao and Zhang, Yi and Liu, Bo}, title = {Multiple Instance Learning Framework with Masked Hard Instance Mining for Whole Slide Image Classification}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {4078-4087} }
Unsupervised Compositional Concepts Discovery with Text-to-Image Generative Models: Nan Liu,

Yilun Du,

Shuang Li,

Joshua B. Tenenbaum,

Antonio Torralba; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Liu_2023_ICCV, author = {Liu, Nan and Du, Yilun and Li, Shuang and Tenenbaum, Joshua B. and Torralba, Antonio}, title = {Unsupervised Compositional Concepts Discovery with Text-to-Image Generative Models}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {2085-2095} }
Partition-And-Debias: Agnostic Biases Mitigation via a Mixture of Biases-Specific Experts: Jiaxuan Li,

Duc Minh Vo,

Hideki Nakayama; [pdf] [supp]
[bibtex]
@InProceedings{Li_2023_ICCV, author = {Li, Jiaxuan and Vo, Duc Minh and Nakayama, Hideki}, title = {Partition-And-Debias: Agnostic Biases Mitigation via a Mixture of Biases-Specific Experts}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {4924-4934} }
Spatial Self-Distillation for Object Detection with Inaccurate Bounding Boxes: Di Wu,

Pengfei Chen,

Xuehui Yu,

Guorong Li,

Zhenjun Han,

Jianbin Jiao; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wu_2023_ICCV, author = {Wu, Di and Chen, Pengfei and Yu, Xuehui and Li, Guorong and Han, Zhenjun and Jiao, Jianbin}, title = {Spatial Self-Distillation for Object Detection with Inaccurate Bounding Boxes}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {6855-6865} }
CC3D: Layout-Conditioned Generation of Compositional 3D Scenes: Sherwin Bahmani,

Jeong Joon Park,

Despoina Paschalidou,

Xingguang Yan,

Gordon Wetzstein,

Leonidas Guibas,

Andrea Tagliasacchi; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Bahmani_2023_ICCV, author = {Bahmani, Sherwin and Park, Jeong Joon and Paschalidou, Despoina and Yan, Xingguang and Wetzstein, Gordon and Guibas, Leonidas and Tagliasacchi, Andrea}, title = {CC3D: Layout-Conditioned Generation of Compositional 3D Scenes}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {7171-7181} }
Alleviating Catastrophic Forgetting of Incremental Object Detection via Within-Class and Between-Class Knowledge Distillation: Mengxue Kang,

Jinpeng Zhang,

Jinming Zhang,

Xiashuang Wang,

Yang Chen,

Zhe Ma,

Xuhui Huang; [pdf] [supp]
[bibtex]
@InProceedings{Kang_2023_ICCV, author = {Kang, Mengxue and Zhang, Jinpeng and Zhang, Jinming and Wang, Xiashuang and Chen, Yang and Ma, Zhe and Huang, Xuhui}, title = {Alleviating Catastrophic Forgetting of Incremental Object Detection via Within-Class and Between-Class Knowledge Distillation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {18894-18904} }
TextPSG: Panoptic Scene Graph Generation from Textual Descriptions: Chengyang Zhao,

Yikang Shen,

Zhenfang Chen,

Mingyu Ding,

Chuang Gan; [pdf] [supp]
[bibtex]
@InProceedings{Zhao_2023_ICCV, author = {Zhao, Chengyang and Shen, Yikang and Chen, Zhenfang and Ding, Mingyu and Gan, Chuang}, title = {TextPSG: Panoptic Scene Graph Generation from Textual Descriptions}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {2839-2850} }
Revisiting the Parameter Efficiency of Adapters from the Perspective of Precision Redundancy: Shibo Jie,

Haoqing Wang,

Zhi-Hong Deng; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Jie_2023_ICCV, author = {Jie, Shibo and Wang, Haoqing and Deng, Zhi-Hong}, title = {Revisiting the Parameter Efficiency of Adapters from the Perspective of Precision Redundancy}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {17217-17226} }
EMQ: Evolving Training-free Proxies for Automated Mixed Precision Quantization: Peijie Dong,

Lujun Li,

Zimian Wei,

Xin Niu,

Zhiliang Tian,

Hengyue Pan; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Dong_2023_ICCV, author = {Dong, Peijie and Li, Lujun and Wei, Zimian and Niu, Xin and Tian, Zhiliang and Pan, Hengyue}, title = {EMQ: Evolving Training-free Proxies for Automated Mixed Precision Quantization}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {17076-17086} }
Face Clustering via Graph Convolutional Networks with Confidence Edges: Yang Wu,

Zhiwei Ge,

Yuhao Luo,

Lin Liu,

Sulong Xu; [pdf]
[bibtex]
@InProceedings{Wu_2023_ICCV, author = {Wu, Yang and Ge, Zhiwei and Luo, Yuhao and Liu, Lin and Xu, Sulong}, title = {Face Clustering via Graph Convolutional Networks with Confidence Edges}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {20990-20999} }
Learning Spatial-context-aware Global Visual Feature Representation for Instance Image Retrieval: Zhongyan Zhang,

Lei Wang,

Luping Zhou,

Piotr Koniusz; [pdf] [supp]
[bibtex]
@InProceedings{Zhang_2023_ICCV, author = {Zhang, Zhongyan and Wang, Lei and Zhou, Luping and Koniusz, Piotr}, title = {Learning Spatial-context-aware Global Visual Feature Representation for Instance Image Retrieval}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {11250-11259} }
Cross-modal Latent Space Alignment for Image to Avatar Translation: Manuel Ladron de Guevara,

Jose Echevarria,

Yijun Li,

Yannick Hold-Geoffroy,

Cameron Smith,

Daichi Ito; [pdf] [supp]
[bibtex]
@InProceedings{de_Guevara_2023_ICCV, author = {de Guevara, Manuel Ladron and Echevarria, Jose and Li, Yijun and Hold-Geoffroy, Yannick and Smith, Cameron and Ito, Daichi}, title = {Cross-modal Latent Space Alignment for Image to Avatar Translation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {520-529} }
Inspecting the Geographical Representativeness of Images from Text-to-Image Models: Abhipsa Basu,

R. Venkatesh Babu,

Danish Pruthi; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Basu_2023_ICCV, author = {Basu, Abhipsa and Babu, R. Venkatesh and Pruthi, Danish}, title = {Inspecting the Geographical Representativeness of Images from Text-to-Image Models}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {5136-5147} }
Space-time Prompting for Video Class-incremental Learning: Yixuan Pei,

Zhiwu Qing,

Shiwei Zhang,

Xiang Wang,

Yingya Zhang,

Deli Zhao,

Xueming Qian; [pdf] [supp]
[bibtex]
@InProceedings{Pei_2023_ICCV, author = {Pei, Yixuan and Qing, Zhiwu and Zhang, Shiwei and Wang, Xiang and Zhang, Yingya and Zhao, Deli and Qian, Xueming}, title = {Space-time Prompting for Video Class-incremental Learning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {11932-11942} }
Multimodal Garment Designer: Human-Centric Latent Diffusion Models for Fashion Image Editing: Alberto Baldrati,

Davide Morelli,

Giuseppe Cartella,

Marcella Cornia,

Marco Bertini,

Rita Cucchiara; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Baldrati_2023_ICCV, author = {Baldrati, Alberto and Morelli, Davide and Cartella, Giuseppe and Cornia, Marcella and Bertini, Marco and Cucchiara, Rita}, title = {Multimodal Garment Designer: Human-Centric Latent Diffusion Models for Fashion Image Editing}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {23393-23402} }
Time-to-Contact Map by Joint Estimation of Up-to-Scale Inverse Depth and Global Motion using a Single Event Camera: Urbano Miguel Nunes,

Laurent Udo Perrinet,

Sio-Hoi Ieng; [pdf] [supp]
[bibtex]
@InProceedings{Nunes_2023_ICCV, author = {Nunes, Urbano Miguel and Perrinet, Laurent Udo and Ieng, Sio-Hoi}, title = {Time-to-Contact Map by Joint Estimation of Up-to-Scale Inverse Depth and Global Motion using a Single Event Camera}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {23653-23663} }
Sparse Sampling Transformer with Uncertainty-Driven Ranking for Unified Removal of Raindrops and Rain Streaks: Sixiang Chen,

Tian Ye,

Jinbin Bai,

Erkang Chen,

Jun Shi,

Lei Zhu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chen_2023_ICCV, author = {Chen, Sixiang and Ye, Tian and Bai, Jinbin and Chen, Erkang and Shi, Jun and Zhu, Lei}, title = {Sparse Sampling Transformer with Uncertainty-Driven Ranking for Unified Removal of Raindrops and Rain Streaks}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {13106-13117} }
A Benchmark for Chinese-English Scene Text Image Super-Resolution: Jianqi Ma,

Zhetong Liang,

Wangmeng Xiang,

Xi Yang,

Lei Zhang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ma_2023_ICCV, author = {Ma, Jianqi and Liang, Zhetong and Xiang, Wangmeng and Yang, Xi and Zhang, Lei}, title = {A Benchmark for Chinese-English Scene Text Image Super-Resolution}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {19452-19461} }
HSR-Diff: Hyperspectral Image Super-Resolution via Conditional Diffusion Models: Chanyue Wu,

Dong Wang,

Yunpeng Bai,

Hanyu Mao,

Ying Li,

Qiang Shen; [pdf] [supp]
[bibtex]
@InProceedings{Wu_2023_ICCV, author = {Wu, Chanyue and Wang, Dong and Bai, Yunpeng and Mao, Hanyu and Li, Ying and Shen, Qiang}, title = {HSR-Diff: Hyperspectral Image Super-Resolution via Conditional Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {7083-7093} }
Replay: Multi-modal Multi-view Acted Videos for Casual Holography: Roman Shapovalov,

Yanir Kleiman,

Ignacio Rocco,

David Novotny,

Andrea Vedaldi,

Changan Chen,

Filippos Kokkinos,

Ben Graham,

Natalia Neverova; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Shapovalov_2023_ICCV, author = {Shapovalov, Roman and Kleiman, Yanir and Rocco, Ignacio and Novotny, David and Vedaldi, Andrea and Chen, Changan and Kokkinos, Filippos and Graham, Ben and Neverova, Natalia}, title = {Replay: Multi-modal Multi-view Acted Videos for Casual Holography}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {20338-20348} }
Advancing Example Exploitation Can Alleviate Critical Challenges in Adversarial Training: Yao Ge,

Yun Li,

Keji Han,

Junyi Zhu,

Xianzhong Long; [pdf] [supp]
[bibtex]
@InProceedings{Ge_2023_ICCV, author = {Ge, Yao and Li, Yun and Han, Keji and Zhu, Junyi and Long, Xianzhong}, title = {Advancing Example Exploitation Can Alleviate Critical Challenges in Adversarial Training}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {145-154} }
Affine-Consistent Transformer for Multi-Class Cell Nuclei Detection: Junjia Huang,

Haofeng Li,

Xiang Wan,

Guanbin Li; [pdf] [supp]
[bibtex]
@InProceedings{Huang_2023_ICCV, author = {Huang, Junjia and Li, Haofeng and Wan, Xiang and Li, Guanbin}, title = {Affine-Consistent Transformer for Multi-Class Cell Nuclei Detection}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {21384-21393} }
Removing Anomalies as Noises for Industrial Defect Localization: Fanbin Lu,

Xufeng Yao,

Chi-Wing Fu,

Jiaya Jia; [pdf]
[bibtex]
@InProceedings{Lu_2023_ICCV, author = {Lu, Fanbin and Yao, Xufeng and Fu, Chi-Wing and Jia, Jiaya}, title = {Removing Anomalies as Noises for Industrial Defect Localization}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {16166-16175} }
GPGait: Generalized Pose-based Gait Recognition: Yang Fu,

Shibei Meng,

Saihui Hou,

Xuecai Hu,

Yongzhen Huang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Fu_2023_ICCV, author = {Fu, Yang and Meng, Shibei and Hou, Saihui and Hu, Xuecai and Huang, Yongzhen}, title = {GPGait: Generalized Pose-based Gait Recognition}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {19595-19604} }
Stable and Causal Inference for Discriminative Self-supervised Deep Visual Representations: Yuewei Yang,

Hai Li,

Yiran Chen; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yang_2023_ICCV, author = {Yang, Yuewei and Li, Hai and Chen, Yiran}, title = {Stable and Causal Inference for Discriminative Self-supervised Deep Visual Representations}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {16109-16120} }
ShiftNAS: Improving One-shot NAS via Probability Shift: Mingyang Zhang,

Xinyi Yu,

Haodong Zhao,

Linlin Ou; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhang_2023_ICCV, author = {Zhang, Mingyang and Yu, Xinyi and Zhao, Haodong and Ou, Linlin}, title = {ShiftNAS: Improving One-shot NAS via Probability Shift}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {5919-5928} }
Semantic Attention Flow Fields for Monocular Dynamic Scene Decomposition: Yiqing Liang,

Eliot Laidlaw,

Alexander Meyerowitz,

Srinath Sridhar,

James Tompkin; [pdf] [supp]
[bibtex]
@InProceedings{Liang_2023_ICCV, author = {Liang, Yiqing and Laidlaw, Eliot and Meyerowitz, Alexander and Sridhar, Srinath and Tompkin, James}, title = {Semantic Attention Flow Fields for Monocular Dynamic Scene Decomposition}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {21797-21806} }
LexLIP: Lexicon-Bottlenecked Language-Image Pre-Training for Large-Scale Image-Text Sparse Retrieval: Ziyang Luo,

Pu Zhao,

Can Xu,

Xiubo Geng,

Tao Shen,

Chongyang Tao,

Jing Ma,

Qingwei Lin,

Daxin Jiang; [pdf] [supp]
[bibtex]
@InProceedings{Luo_2023_ICCV, author = {Luo, Ziyang and Zhao, Pu and Xu, Can and Geng, Xiubo and Shen, Tao and Tao, Chongyang and Ma, Jing and Lin, Qingwei and Jiang, Daxin}, title = {LexLIP: Lexicon-Bottlenecked Language-Image Pre-Training for Large-Scale Image-Text Sparse Retrieval}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {11206-11217} }
A Fast Unified System for 3D Object Detection and Tracking: Thomas Heitzinger,

Martin Kampel; [pdf] [supp]
[bibtex]
@InProceedings{Heitzinger_2023_ICCV, author = {Heitzinger, Thomas and Kampel, Martin}, title = {A Fast Unified System for 3D Object Detection and Tracking}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {17044-17054} }
Adaptive Testing of Computer Vision Models: Irena Gao,

Gabriel Ilharco,

Scott Lundberg,

Marco Tulio Ribeiro; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Gao_2023_ICCV, author = {Gao, Irena and Ilharco, Gabriel and Lundberg, Scott and Ribeiro, Marco Tulio}, title = {Adaptive Testing of Computer Vision Models}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {4003-4014} }
LFS-GAN: Lifelong Few-Shot Image Generation: Juwon Seo,

Ji-Su Kang,

Gyeong-Moon Park; [pdf] [supp]
[bibtex]
@InProceedings{Seo_2023_ICCV, author = {Seo, Juwon and Kang, Ji-Su and Park, Gyeong-Moon}, title = {LFS-GAN: Lifelong Few-Shot Image Generation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {11356-11366} }
AIDE: A Vision-Driven Multi-View, Multi-Modal, Multi-Tasking Dataset for Assistive Driving Perception: Dingkang Yang,

Shuai Huang,

Zhi Xu,

Zhenpeng Li,

Shunli Wang,

Mingcheng Li,

Yuzheng Wang,

Yang Liu,

Kun Yang,

Zhaoyu Chen,

Yan Wang,

Jing Liu,

Peixuan Zhang,

Peng Zhai,

Lihua Zhang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yang_2023_ICCV, author = {Yang, Dingkang and Huang, Shuai and Xu, Zhi and Li, Zhenpeng and Wang, Shunli and Li, Mingcheng and Wang, Yuzheng and Liu, Yang and Yang, Kun and Chen, Zhaoyu and Wang, Yan and Liu, Jing and Zhang, Peixuan and Zhai, Peng and Zhang, Lihua}, title = {AIDE: A Vision-Driven Multi-View, Multi-Modal, Multi-Tasking Dataset for Assistive Driving Perception}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {20459-20470} }
Feature Proliferation -- the "Cancer" in StyleGAN and its Treatments: Shuang Song,

Yuanbang Liang,

Jing Wu,

Yu-Kun Lai,

Yipeng Qin; [pdf] [supp]
[bibtex]
@InProceedings{Song_2023_ICCV, author = {Song, Shuang and Liang, Yuanbang and Wu, Jing and Lai, Yu-Kun and Qin, Yipeng}, title = {Feature Proliferation -- the ''Cancer'' in StyleGAN and its Treatments}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {2360-2370} }
Self-Supervised Character-to-Character Distillation for Text Recognition: Tongkun Guan,

Wei Shen,

Xue Yang,

Qi Feng,

Zekun Jiang,

Xiaokang Yang; [pdf] [arXiv]
[bibtex]
@InProceedings{Guan_2023_ICCV, author = {Guan, Tongkun and Shen, Wei and Yang, Xue and Feng, Qi and Jiang, Zekun and Yang, Xiaokang}, title = {Self-Supervised Character-to-Character Distillation for Text Recognition}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {19473-19484} }
MixCycle: Mixup Assisted Semi-Supervised 3D Single Object Tracking with Cycle Consistency: Qiao Wu,

Jiaqi Yang,

Kun Sun,

Chu'ai Zhang,

Yanning Zhang,

Mathieu Salzmann; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wu_2023_ICCV, author = {Wu, Qiao and Yang, Jiaqi and Sun, Kun and Zhang, Chu'ai and Zhang, Yanning and Salzmann, Mathieu}, title = {MixCycle: Mixup Assisted Semi-Supervised 3D Single Object Tracking with Cycle Consistency}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {13956-13966} }
Multi-Label Self-Supervised Learning with Scene Images: Ke Zhu,

Minghao Fu,

Jianxin Wu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhu_2023_ICCV, author = {Zhu, Ke and Fu, Minghao and Wu, Jianxin}, title = {Multi-Label Self-Supervised Learning with Scene Images}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {6694-6703} }
Domain Adaptive Few-Shot Open-Set Learning: Debabrata Pal,

Deeptej More,

Sai Bhargav,

Dipesh Tamboli,

Vaneet Aggarwal,

Biplab Banerjee; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Pal_2023_ICCV, author = {Pal, Debabrata and More, Deeptej and Bhargav, Sai and Tamboli, Dipesh and Aggarwal, Vaneet and Banerjee, Biplab}, title = {Domain Adaptive Few-Shot Open-Set Learning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {18831-18840} }
DiffFacto: Controllable Part-Based 3D Point Cloud Generation with Cross Diffusion: George Kiyohiro Nakayama,

Mikaela Angelina Uy,

Jiahui Huang,

Shi-Min Hu,

Ke Li,

Leonidas Guibas; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Nakayama_2023_ICCV, author = {Nakayama, George Kiyohiro and Uy, Mikaela Angelina and Huang, Jiahui and Hu, Shi-Min and Li, Ke and Guibas, Leonidas}, title = {DiffFacto: Controllable Part-Based 3D Point Cloud Generation with Cross Diffusion}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {14257-14267} }
Interactive Class-Agnostic Object Counting: Yifeng Huang,

Viresh Ranjan,

Minh Hoai; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Huang_2023_ICCV, author = {Huang, Yifeng and Ranjan, Viresh and Hoai, Minh}, title = {Interactive Class-Agnostic Object Counting}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {22312-22322} }
Spatio-temporal Prompting Network for Robust Video Feature Extraction: Guanxiong Sun,

Chi Wang,

Zhaoyu Zhang,

Jiankang Deng,

Stefanos Zafeiriou,

Yang Hua; [pdf] [supp]
[bibtex]
@InProceedings{Sun_2023_ICCV, author = {Sun, Guanxiong and Wang, Chi and Zhang, Zhaoyu and Deng, Jiankang and Zafeiriou, Stefanos and Hua, Yang}, title = {Spatio-temporal Prompting Network for Robust Video Feature Extraction}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {13587-13597} }
Enhancing Fine-Tuning Based Backdoor Defense with Sharpness-Aware Minimization: Mingli Zhu,

Shaokui Wei,

Li Shen,

Yanbo Fan,

Baoyuan Wu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhu_2023_ICCV, author = {Zhu, Mingli and Wei, Shaokui and Shen, Li and Fan, Yanbo and Wu, Baoyuan}, title = {Enhancing Fine-Tuning Based Backdoor Defense with Sharpness-Aware Minimization}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {4466-4477} }
Deep Geometry-Aware Camera Self-Calibration from Video: Annika Hagemann,

Moritz Knorr,

Christoph Stiller; [pdf] [supp]
[bibtex]
@InProceedings{Hagemann_2023_ICCV, author = {Hagemann, Annika and Knorr, Moritz and Stiller, Christoph}, title = {Deep Geometry-Aware Camera Self-Calibration from Video}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {3438-3448} }
A Simple Vision Transformer for Weakly Semi-supervised 3D Object Detection: Dingyuan Zhang,

Dingkang Liang,

Zhikang Zou,

Jingyu Li,

Xiaoqing Ye,

Zhe Liu,

Xiao Tan,

Xiang Bai; [pdf] [supp]
[bibtex]
@InProceedings{Zhang_2023_ICCV, author = {Zhang, Dingyuan and Liang, Dingkang and Zou, Zhikang and Li, Jingyu and Ye, Xiaoqing and Liu, Zhe and Tan, Xiao and Bai, Xiang}, title = {A Simple Vision Transformer for Weakly Semi-supervised 3D Object Detection}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {8373-8383} }
Estimator Meets Equilibrium Perspective: A Rectified Straight Through Estimator for Binary Neural Networks Training: Xiao-Ming Wu,

Dian Zheng,

Zuhao Liu,

Wei-Shi Zheng; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wu_2023_ICCV, author = {Wu, Xiao-Ming and Zheng, Dian and Liu, Zuhao and Zheng, Wei-Shi}, title = {Estimator Meets Equilibrium Perspective: A Rectified Straight Through Estimator for Binary Neural Networks Training}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {17055-17064} }
Exploring Object-Centric Temporal Modeling for Efficient Multi-View 3D Object Detection: Shihao Wang,

Yingfei Liu,

Tiancai Wang,

Ying Li,

Xiangyu Zhang; [pdf] [arXiv]
[bibtex]
@InProceedings{Wang_2023_ICCV, author = {Wang, Shihao and Liu, Yingfei and Wang, Tiancai and Li, Ying and Zhang, Xiangyu}, title = {Exploring Object-Centric Temporal Modeling for Efficient Multi-View 3D Object Detection}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {3621-3631} }
Open-domain Visual Entity Recognition: Towards Recognizing Millions of Wikipedia Entities: Hexiang Hu,

Yi Luan,

Yang Chen,

Urvashi Khandelwal,

Mandar Joshi,

Kenton Lee,

Kristina Toutanova,

Ming-Wei Chang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Hu_2023_ICCV, author = {Hu, Hexiang and Luan, Yi and Chen, Yang and Khandelwal, Urvashi and Joshi, Mandar and Lee, Kenton and Toutanova, Kristina and Chang, Ming-Wei}, title = {Open-domain Visual Entity Recognition: Towards Recognizing Millions of Wikipedia Entities}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {12065-12075} }
MedKLIP: Medical Knowledge Enhanced Language-Image Pre-Training for X-ray Diagnosis: Chaoyi Wu,

Xiaoman Zhang,

Ya Zhang,

Yanfeng Wang,

Weidi Xie; [pdf] [supp]
[bibtex]
@InProceedings{Wu_2023_ICCV, author = {Wu, Chaoyi and Zhang, Xiaoman and Zhang, Ya and Wang, Yanfeng and Xie, Weidi}, title = {MedKLIP: Medical Knowledge Enhanced Language-Image Pre-Training for X-ray Diagnosis}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {21372-21383} }
Automated Knowledge Distillation via Monte Carlo Tree Search: Lujun Li,

Peijie Dong,

Zimian Wei,

Ya Yang; [pdf] [supp]
[bibtex]
@InProceedings{Li_2023_ICCV, author = {Li, Lujun and Dong, Peijie and Wei, Zimian and Yang, Ya}, title = {Automated Knowledge Distillation via Monte Carlo Tree Search}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {17413-17424} }
EmoTalk: Speech-Driven Emotional Disentanglement for 3D Face Animation: Ziqiao Peng,

Haoyu Wu,

Zhenbo Song,

Hao Xu,

Xiangyu Zhu,

Jun He,

Hongyan Liu,

Zhaoxin Fan; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Peng_2023_ICCV, author = {Peng, Ziqiao and Wu, Haoyu and Song, Zhenbo and Xu, Hao and Zhu, Xiangyu and He, Jun and Liu, Hongyan and Fan, Zhaoxin}, title = {EmoTalk: Speech-Driven Emotional Disentanglement for 3D Face Animation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {20687-20697} }
A Soft Nearest-Neighbor Framework for Continual Semi-Supervised Learning: Zhiqi Kang,

Enrico Fini,

Moin Nabi,

Elisa Ricci,

Karteek Alahari; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kang_2023_ICCV, author = {Kang, Zhiqi and Fini, Enrico and Nabi, Moin and Ricci, Elisa and Alahari, Karteek}, title = {A Soft Nearest-Neighbor Framework for Continual Semi-Supervised Learning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {11868-11877} }
Text-Conditioned Sampling Framework for Text-to-Image Generation with Masked Generative Models: Jaewoong Lee,

Sangwon Jang,

Jaehyeong Jo,

Jaehong Yoon,

Yunji Kim,

Jin-Hwa Kim,

Jung-Woo Ha,

Sung Ju Hwang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Lee_2023_ICCV, author = {Lee, Jaewoong and Jang, Sangwon and Jo, Jaehyeong and Yoon, Jaehong and Kim, Yunji and Kim, Jin-Hwa and Ha, Jung-Woo and Hwang, Sung Ju}, title = {Text-Conditioned Sampling Framework for Text-to-Image Generation with Masked Generative Models}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {23252-23262} }
ScanNet++: A High-Fidelity Dataset of 3D Indoor Scenes: Chandan Yeshwanth,

Yueh-Cheng Liu,

Matthias Nießner,

Angela Dai; [pdf] [supp]
[bibtex]
@InProceedings{Yeshwanth_2023_ICCV, author = {Yeshwanth, Chandan and Liu, Yueh-Cheng and Nie{\ss}ner, Matthias and Dai, Angela}, title = {ScanNet++: A High-Fidelity Dataset of 3D Indoor Scenes}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {12-22} }
Minimal Solutions to Uncalibrated Two-view Geometry with Known Epipoles: Gaku Nakano; [pdf]
[bibtex]
@InProceedings{Nakano_2023_ICCV, author = {Nakano, Gaku}, title = {Minimal Solutions to Uncalibrated Two-view Geometry with Known Epipoles}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {13361-13370} }
Improving Diversity in Zero-Shot GAN Adaptation with Semantic Variations: Seogkyu Jeon,

Bei Liu,

Pilhyeon Lee,

Kibeom Hong,

Jianlong Fu,

Hyeran Byun; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Jeon_2023_ICCV, author = {Jeon, Seogkyu and Liu, Bei and Lee, Pilhyeon and Hong, Kibeom and Fu, Jianlong and Byun, Hyeran}, title = {Improving Diversity in Zero-Shot GAN Adaptation with Semantic Variations}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {7258-7267} }
Context-Aware Planning and Environment-Aware Memory for Instruction Following Embodied Agents: Byeonghwi Kim,

Jinyeon Kim,

Yuyeong Kim,

Cheolhong Min,

Jonghyun Choi; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kim_2023_ICCV, author = {Kim, Byeonghwi and Kim, Jinyeon and Kim, Yuyeong and Min, Cheolhong and Choi, Jonghyun}, title = {Context-Aware Planning and Environment-Aware Memory for Instruction Following Embodied Agents}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {10936-10946} }
Vox-E: Text-Guided Voxel Editing of 3D Objects: Etai Sella,

Gal Fiebelman,

Peter Hedman,

Hadar Averbuch-Elor; [pdf] [supp]
[bibtex]
@InProceedings{Sella_2023_ICCV, author = {Sella, Etai and Fiebelman, Gal and Hedman, Peter and Averbuch-Elor, Hadar}, title = {Vox-E: Text-Guided Voxel Editing of 3D Objects}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {430-440} }
Inverse Problem Regularization with Hierarchical Variational Autoencoders: Jean Prost,

Antoine Houdard,

Andrés Almansa,

Nicolas Papadakis; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Prost_2023_ICCV, author = {Prost, Jean and Houdard, Antoine and Almansa, Andr\'es and Papadakis, Nicolas}, title = {Inverse Problem Regularization with Hierarchical Variational Autoencoders}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {22894-22905} }
Unpaired Multi-domain Attribute Translation of 3D Facial Shapes with a Square and Symmetric Geometric Map: Zhenfeng Fan,

Zhiheng Zhang,

Shuang Yang,

Chongyang Zhong,

Min Cao,

Shihong Xia; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Fan_2023_ICCV, author = {Fan, Zhenfeng and Zhang, Zhiheng and Yang, Shuang and Zhong, Chongyang and Cao, Min and Xia, Shihong}, title = {Unpaired Multi-domain Attribute Translation of 3D Facial Shapes with a Square and Symmetric Geometric Map}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {20828-20838} }
Passive Ultra-Wideband Single-Photon Imaging: Mian Wei,

Sotiris Nousias,

Rahul Gulve,

David B. Lindell,

Kiriakos N. Kutulakos; [pdf] [supp]
[bibtex]
@InProceedings{Wei_2023_ICCV, author = {Wei, Mian and Nousias, Sotiris and Gulve, Rahul and Lindell, David B. and Kutulakos, Kiriakos N.}, title = {Passive Ultra-Wideband Single-Photon Imaging}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {8135-8146} }
Template Inversion Attack against Face Recognition Systems using 3D Face Reconstruction: Hatef Otroshi Shahreza,

Sébastien Marcel; [pdf] [supp]
[bibtex]
@InProceedings{Shahreza_2023_ICCV, author = {Shahreza, Hatef Otroshi and Marcel, S\'ebastien}, title = {Template Inversion Attack against Face Recognition Systems using 3D Face Reconstruction}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {19662-19672} }
ETran: Energy-Based Transferability Estimation: Mohsen Gholami,

Mohammad Akbari,

Xinglu Wang,

Behnam Kamranian,

Yong Zhang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Gholami_2023_ICCV, author = {Gholami, Mohsen and Akbari, Mohammad and Wang, Xinglu and Kamranian, Behnam and Zhang, Yong}, title = {ETran: Energy-Based Transferability Estimation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {18613-18622} }
Predict to Detect: Prediction-guided 3D Object Detection using Sequential Images: Sanmin Kim,

Youngseok Kim,

In-Jae Lee,

Dongsuk Kum; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kim_2023_ICCV, author = {Kim, Sanmin and Kim, Youngseok and Lee, In-Jae and Kum, Dongsuk}, title = {Predict to Detect: Prediction-guided 3D Object Detection using Sequential Images}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {18057-18066} }
Unilaterally Aggregated Contrastive Learning with Hierarchical Augmentation for Anomaly Detection: Guodong Wang,

Yunhong Wang,

Jie Qin,

Dongming Zhang,

Xiuguo Bao,

Di Huang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2023_ICCV, author = {Wang, Guodong and Wang, Yunhong and Qin, Jie and Zhang, Dongming and Bao, Xiuguo and Huang, Di}, title = {Unilaterally Aggregated Contrastive Learning with Hierarchical Augmentation for Anomaly Detection}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {6888-6897} }
Learning Image-Adaptive Codebooks for Class-Agnostic Image Restoration: Kechun Liu,

Yitong Jiang,

Inchang Choi,

Jinwei Gu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Liu_2023_ICCV, author = {Liu, Kechun and Jiang, Yitong and Choi, Inchang and Gu, Jinwei}, title = {Learning Image-Adaptive Codebooks for Class-Agnostic Image Restoration}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {5373-5383} }
3D Segmentation of Humans in Point Clouds with Synthetic Data: Ayça Takmaz,

Jonas Schult,

Irem Kaftan,

Mertcan Akçay,

Bastian Leibe,

Robert Sumner,

Francis Engelmann,

Siyu Tang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Takmaz_2023_ICCV, author = {Takmaz, Ay\c{c}a and Schult, Jonas and Kaftan, Irem and Ak\c{c}ay, Mertcan and Leibe, Bastian and Sumner, Robert and Engelmann, Francis and Tang, Siyu}, title = {3D Segmentation of Humans in Point Clouds with Synthetic Data}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {1292-1304} }
Mastering Spatial Graph Prediction of Road Networks: Anagnostidis Sotiris,

Aurelien Lucchi,

Thomas Hofmann; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Sotiris_2023_ICCV, author = {Sotiris, Anagnostidis and Lucchi, Aurelien and Hofmann, Thomas}, title = {Mastering Spatial Graph Prediction of Road Networks}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {5408-5418} }
IDiff-Face: Synthetic-based Face Recognition through Fizzy Identity-Conditioned Diffusion Model: Fadi Boutros,

Jonas Henry Grebe,

Arjan Kuijper,

Naser Damer; [pdf]
[bibtex]
@InProceedings{Boutros_2023_ICCV, author = {Boutros, Fadi and Grebe, Jonas Henry and Kuijper, Arjan and Damer, Naser}, title = {IDiff-Face: Synthetic-based Face Recognition through Fizzy Identity-Conditioned Diffusion Model}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {19650-19661} }
Deep Video Demoireing via Compact Invertible Dyadic Decomposition: Yuhui Quan,

Haoran Huang,

Shengfeng He,

Ruotao Xu; [pdf] [supp]
[bibtex]
@InProceedings{Quan_2023_ICCV, author = {Quan, Yuhui and Huang, Haoran and He, Shengfeng and Xu, Ruotao}, title = {Deep Video Demoireing via Compact Invertible Dyadic Decomposition}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {12677-12686} }
Rethinking Multi-Contrast MRI Super-Resolution: Rectangle-Window Cross-Attention Transformer and Arbitrary-Scale Upsampling: Guangyuan Li,

Lei Zhao,

Jiakai Sun,

Zehua Lan,

Zhanjie Zhang,

Jiafu Chen,

Zhijie Lin,

Huaizhong Lin,

Wei Xing; [pdf]
[bibtex]
@InProceedings{Li_2023_ICCV, author = {Li, Guangyuan and Zhao, Lei and Sun, Jiakai and Lan, Zehua and Zhang, Zhanjie and Chen, Jiafu and Lin, Zhijie and Lin, Huaizhong and Xing, Wei}, title = {Rethinking Multi-Contrast MRI Super-Resolution: Rectangle-Window Cross-Attention Transformer and Arbitrary-Scale Upsampling}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {21230-21240} }
Domain Generalization via Rationale Invariance: Liang Chen,

Yong Zhang,

Yibing Song,

Anton van den Hengel,

Lingqiao Liu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chen_2023_ICCV, author = {Chen, Liang and Zhang, Yong and Song, Yibing and van den Hengel, Anton and Liu, Lingqiao}, title = {Domain Generalization via Rationale Invariance}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {1751-1760} }
ProbVLM: Probabilistic Adapter for Frozen Vison-Language Models: Uddeshya Upadhyay,

Shyamgopal Karthik,

Massimiliano Mancini,

Zeynep Akata; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Upadhyay_2023_ICCV, author = {Upadhyay, Uddeshya and Karthik, Shyamgopal and Mancini, Massimiliano and Akata, Zeynep}, title = {ProbVLM: Probabilistic Adapter for Frozen Vison-Language Models}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {1899-1910} }
Towards Open-Set Test-Time Adaptation Utilizing the Wisdom of Crowds in Entropy Minimization: Jungsoo Lee,

Debasmit Das,

Jaegul Choo,

Sungha Choi; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Lee_2023_ICCV, author = {Lee, Jungsoo and Das, Debasmit and Choo, Jaegul and Choi, Sungha}, title = {Towards Open-Set Test-Time Adaptation Utilizing the Wisdom of Crowds in Entropy Minimization}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {16380-16389} }
Scene Graph Contrastive Learning for Embodied Navigation: Kunal Pratap Singh,

Jordi Salvador,

Luca Weihs,

Aniruddha Kembhavi; [pdf] [supp]
[bibtex]
@InProceedings{Singh_2023_ICCV, author = {Singh, Kunal Pratap and Salvador, Jordi and Weihs, Luca and Kembhavi, Aniruddha}, title = {Scene Graph Contrastive Learning for Embodied Navigation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {10884-10894} }
Long-Range Grouping Transformer for Multi-View 3D Reconstruction: Liying Yang,

Zhenwei Zhu,

Xuxin Lin,

Jian Nong,

Yanyan Liang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yang_2023_ICCV, author = {Yang, Liying and Zhu, Zhenwei and Lin, Xuxin and Nong, Jian and Liang, Yanyan}, title = {Long-Range Grouping Transformer for Multi-View 3D Reconstruction}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {18257-18267} }
Latent-OFER: Detect, Mask, and Reconstruct with Latent Vectors for Occluded Facial Expression Recognition: Isack Lee,

Eungi Lee,

Seok Bong Yoo; [pdf] [supp]
[bibtex]
@InProceedings{Lee_2023_ICCV, author = {Lee, Isack and Lee, Eungi and Yoo, Seok Bong}, title = {Latent-OFER: Detect, Mask, and Reconstruct with Latent Vectors for Occluded Facial Expression Recognition}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {1536-1546} }
DenseShift: Towards Accurate and Efficient Low-Bit Power-of-Two Quantization: Xinlin Li,

Bang Liu,

Rui Heng Yang,

Vanessa Courville,

Chao Xing,

Vahid Partovi Nia; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Li_2023_ICCV, author = {Li, Xinlin and Liu, Bang and Yang, Rui Heng and Courville, Vanessa and Xing, Chao and Nia, Vahid Partovi}, title = {DenseShift: Towards Accurate and Efficient Low-Bit Power-of-Two Quantization}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {17010-17020} }
Preparing the Future for Continual Semantic Segmentation: Zihan Lin,

Zilei Wang,

Yixin Zhang; [pdf]
[bibtex]
@InProceedings{Lin_2023_ICCV, author = {Lin, Zihan and Wang, Zilei and Zhang, Yixin}, title = {Preparing the Future for Continual Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {11910-11920} }
Efficient Computation Sharing for Multi-Task Visual Scene Understanding: Sara Shoouri,

Mingyu Yang,

Zichen Fan,

Hun-Seok Kim; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Shoouri_2023_ICCV, author = {Shoouri, Sara and Yang, Mingyu and Fan, Zichen and Kim, Hun-Seok}, title = {Efficient Computation Sharing for Multi-Task Visual Scene Understanding}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {17130-17141} }
Self-supervised Cross-view Representation Reconstruction for Change Captioning: Yunbin Tu,

Liang Li,

Li Su,

Zheng-Jun Zha,

Chenggang Yan,

Qingming Huang; [pdf] [supp]
[bibtex]
@InProceedings{Tu_2023_ICCV, author = {Tu, Yunbin and Li, Liang and Su, Li and Zha, Zheng-Jun and Yan, Chenggang and Huang, Qingming}, title = {Self-supervised Cross-view Representation Reconstruction for Change Captioning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {2805-2815} }
Unify, Align and Refine: Multi-Level Semantic Alignment for Radiology Report Generation: Yaowei Li,

Bang Yang,

Xuxin Cheng,

Zhihong Zhu,

Hongxiang Li,

Yuexian Zou; [pdf] [arXiv]
[bibtex]
@InProceedings{Li_2023_ICCV, author = {Li, Yaowei and Yang, Bang and Cheng, Xuxin and Zhu, Zhihong and Li, Hongxiang and Zou, Yuexian}, title = {Unify, Align and Refine: Multi-Level Semantic Alignment for Radiology Report Generation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {2863-2874} }
Synthesizing Diverse Human Motions in 3D Indoor Scenes: Kaifeng Zhao,

Yan Zhang,

Shaofei Wang,

Thabo Beeler,

Siyu Tang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhao_2023_ICCV, author = {Zhao, Kaifeng and Zhang, Yan and Wang, Shaofei and Beeler, Thabo and Tang, Siyu}, title = {Synthesizing Diverse Human Motions in 3D Indoor Scenes}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {14738-14749} }
Deep Optics for Video Snapshot Compressive Imaging: Ping Wang,

Lishun Wang,

Xin Yuan; [pdf] [supp]
[bibtex]
@InProceedings{Wang_2023_ICCV, author = {Wang, Ping and Wang, Lishun and Yuan, Xin}, title = {Deep Optics for Video Snapshot Compressive Imaging}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {10646-10656} }
DDIT: Semantic Scene Completion via Deformable Deep Implicit Templates: Haoang Li,

Jinhu Dong,

Binghui Wen,

Ming Gao,

Tianyu Huang,

Yun-Hui Liu,

Daniel Cremers; [pdf] [supp]
[bibtex]
@InProceedings{Li_2023_ICCV, author = {Li, Haoang and Dong, Jinhu and Wen, Binghui and Gao, Ming and Huang, Tianyu and Liu, Yun-Hui and Cremers, Daniel}, title = {DDIT: Semantic Scene Completion via Deformable Deep Implicit Templates}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {21894-21904} }
Joint Demosaicing and Deghosting of Time-Varying Exposures for Single-Shot HDR Imaging: Jungwoo Kim,

Min H. Kim; [pdf] [supp]
[bibtex]
@InProceedings{Kim_2023_ICCV, author = {Kim, Jungwoo and Kim, Min H.}, title = {Joint Demosaicing and Deghosting of Time-Varying Exposures for Single-Shot HDR Imaging}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {12292-12301} }
Scene-Aware Feature Matching: Xiaoyong Lu,

Yaping Yan,

Tong Wei,

Songlin Du; [pdf] [arXiv]
[bibtex]
@InProceedings{Lu_2023_ICCV, author = {Lu, Xiaoyong and Yan, Yaping and Wei, Tong and Du, Songlin}, title = {Scene-Aware Feature Matching}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {3704-3713} }
FDViT: Improve the Hierarchical Architecture of Vision Transformer: Yixing Xu,

Chao Li,

Dong Li,

Xiao Sheng,

Fan Jiang,

Lu Tian,

Ashish Sirasao; [pdf]
[bibtex]
@InProceedings{Xu_2023_ICCV, author = {Xu, Yixing and Li, Chao and Li, Dong and Sheng, Xiao and Jiang, Fan and Tian, Lu and Sirasao, Ashish}, title = {FDViT: Improve the Hierarchical Architecture of Vision Transformer}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {5950-5960} }
Tuning Pre-trained Model via Moment Probing: Mingze Gao,

Qilong Wang,

Zhenyi Lin,

Pengfei Zhu,

Qinghua Hu,

Jingbo Zhou; [pdf] [supp] [arXiv ]
[bibtex]
@InProceedings{Gao_2023_ICCV, author = {Gao, Mingze and Wang, Qilong and Lin, Zhenyi and Zhu, Pengfei and Hu, Qinghua and Zhou, Jingbo}, title = {Tuning Pre-trained Model via Moment Probing}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {11803-11813} }
Attention Where It Matters: Rethinking Visual Document Understanding with Selective Region Concentration: Haoyu Cao,

Changcun Bao,

Chaohu Liu,

Huang Chen,

Kun Yin,

Hao Liu,

Yinsong Liu,

Deqiang Jiang,

Xing Sun; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Cao_2023_ICCV, author = {Cao, Haoyu and Bao, Changcun and Liu, Chaohu and Chen, Huang and Yin, Kun and Liu, Hao and Liu, Yinsong and Jiang, Deqiang and Sun, Xing}, title = {Attention Where It Matters: Rethinking Visual Document Understanding with Selective Region Concentration}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {19517-19527} }
Task Agnostic Restoration of Natural Video Dynamics: Muhammad Kashif Ali,

Dongjin Kim,

Tae Hyun Kim; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ali_2023_ICCV, author = {Ali, Muhammad Kashif and Kim, Dongjin and Kim, Tae Hyun}, title = {Task Agnostic Restoration of Natural Video Dynamics}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {13534-13544} }
TMR: Text-to-Motion Retrieval Using Contrastive 3D Human Motion Synthesis: Mathis Petrovich,

Michael J. Black,

Gül Varol; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Petrovich_2023_ICCV, author = {Petrovich, Mathis and Black, Michael J. and Varol, G\"ul}, title = {TMR: Text-to-Motion Retrieval Using Contrastive 3D Human Motion Synthesis}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {9488-9497} }
3D Neural Embedding Likelihood: Probabilistic Inverse Graphics for Robust 6D Pose Estimation: Guangyao Zhou,

Nishad Gothoskar,

Lirui Wang,

Joshua B. Tenenbaum,

Dan Gutfreund,

Miguel Lázaro-Gredilla,

Dileep George,

Vikash K. Mansinghka; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhou_2023_ICCV, author = {Zhou, Guangyao and Gothoskar, Nishad and Wang, Lirui and Tenenbaum, Joshua B. and Gutfreund, Dan and L\'azaro-Gredilla, Miguel and George, Dileep and Mansinghka, Vikash K.}, title = {3D Neural Embedding Likelihood: Probabilistic Inverse Graphics for Robust 6D Pose Estimation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {21625-21636} }
Towards Robust Model Watermark via Reducing Parametric Vulnerability: Guanhao Gan,

Yiming Li,

Dongxian Wu,

Shu-Tao Xia; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Gan_2023_ICCV, author = {Gan, Guanhao and Li, Yiming and Wu, Dongxian and Xia, Shu-Tao}, title = {Towards Robust Model Watermark via Reducing Parametric Vulnerability}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {4751-4761} }
SupFusion: Supervised LiDAR-Camera Fusion for 3D Object Detection: Yiran Qin,

Chaoqun Wang,

Zijian Kang,

Ningning Ma,

Zhen Li,

Ruimao Zhang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Qin_2023_ICCV, author = {Qin, Yiran and Wang, Chaoqun and Kang, Zijian and Ma, Ningning and Li, Zhen and Zhang, Ruimao}, title = {SupFusion: Supervised LiDAR-Camera Fusion for 3D Object Detection}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {22014-22024} }
EMMN: Emotional Motion Memory Network for Audio-driven Emotional Talking Face Generation: Shuai Tan,

Bin Ji,

Ye Pan; [pdf] [supp]
[bibtex]
@InProceedings{Tan_2023_ICCV, author = {Tan, Shuai and Ji, Bin and Pan, Ye}, title = {EMMN: Emotional Motion Memory Network for Audio-driven Emotional Talking Face Generation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {22146-22156} }
Rethinking Vision Transformers for MobileNet Size and Speed: Yanyu Li,

Ju Hu,

Yang Wen,

Georgios Evangelidis,

Kamyar Salahi,

Yanzhi Wang,

Sergey Tulyakov,

Jian Ren; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Li_2023_ICCV, author = {Li, Yanyu and Hu, Ju and Wen, Yang and Evangelidis, Georgios and Salahi, Kamyar and Wang, Yanzhi and Tulyakov, Sergey and Ren, Jian}, title = {Rethinking Vision Transformers for MobileNet Size and Speed}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {16889-16900} }
Implicit Identity Representation Conditioned Memory Compensation Network for Talking Head video Generation: Fa-Ting Hong,

Dan Xu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Hong_2023_ICCV, author = {Hong, Fa-Ting and Xu, Dan}, title = {Implicit Identity Representation Conditioned Memory Compensation Network for Talking Head video Generation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {23062-23072} }
SINC: Self-Supervised In-Context Learning for Vision-Language Tasks: Yi-Syuan Chen,

Yun-Zhu Song,

Cheng Yu Yeo,

Bei Liu,

Jianlong Fu,

Hong-Han Shuai; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chen_2023_ICCV, author = {Chen, Yi-Syuan and Song, Yun-Zhu and Yeo, Cheng Yu and Liu, Bei and Fu, Jianlong and Shuai, Hong-Han}, title = {SINC: Self-Supervised In-Context Learning for Vision-Language Tasks}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {15430-15442} }
LEA2: A Lightweight Ensemble Adversarial Attack via Non-overlapping Vulnerable Frequency Regions: Yaguan Qian,

Shuke He,

Chenyu Zhao,

Jiaqiang Sha,

Wei Wang,

Bin Wang; [pdf] [supp]
[bibtex]
@InProceedings{Qian_2023_ICCV, author = {Qian, Yaguan and He, Shuke and Zhao, Chenyu and Sha, Jiaqiang and Wang, Wei and Wang, Bin}, title = {LEA2: A Lightweight Ensemble Adversarial Attack via Non-overlapping Vulnerable Frequency Regions}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {4510-4521} }
Chupa: Carving 3D Clothed Humans from Skinned Shape Priors using 2D Diffusion Probabilistic Models: Byungjun Kim,

Patrick Kwon,

Kwangho Lee,

Myunggi Lee,

Sookwan Han,

Daesik Kim,

Hanbyul Joo; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kim_2023_ICCV, author = {Kim, Byungjun and Kwon, Patrick and Lee, Kwangho and Lee, Myunggi and Han, Sookwan and Kim, Daesik and Joo, Hanbyul}, title = {Chupa: Carving 3D Clothed Humans from Skinned Shape Priors using 2D Diffusion Probabilistic Models}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {15965-15976} }
Unsupervised Domain Adaptive Detection with Network Stability Analysis: Wenzhang Zhou,

Heng Fan,

Tiejian Luo,

Libo Zhang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhou_2023_ICCV, author = {Zhou, Wenzhang and Fan, Heng and Luo, Tiejian and Zhang, Libo}, title = {Unsupervised Domain Adaptive Detection with Network Stability Analysis}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {6986-6995} }
Learning a Room with the Occ-SDF Hybrid: Signed Distance Function Mingled with Occupancy Aids Scene Representation: Xiaoyang Lyu,

Peng Dai,

Zizhang Li,

Dongyu Yan,

Yi Lin,

Yifan Peng,

Xiaojuan Qi; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Lyu_2023_ICCV, author = {Lyu, Xiaoyang and Dai, Peng and Li, Zizhang and Yan, Dongyu and Lin, Yi and Peng, Yifan and Qi, Xiaojuan}, title = {Learning a Room with the Occ-SDF Hybrid: Signed Distance Function Mingled with Occupancy Aids Scene Representation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {8940-8950} }
Cloth2Body: Generating 3D Human Body Mesh from 2D Clothing: Lu Dai,

Liqian Ma,

Shenhan Qian,

Hao Liu,

Ziwei Liu,

Hui Xiong; [pdf]
[bibtex]
@InProceedings{Dai_2023_ICCV, author = {Dai, Lu and Ma, Liqian and Qian, Shenhan and Liu, Hao and Liu, Ziwei and Xiong, Hui}, title = {Cloth2Body: Generating 3D Human Body Mesh from 2D Clothing}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {15007-15017} }
Spatially and Spectrally Consistent Deep Functional Maps: Mingze Sun,

Shiwei Mao,

Puhua Jiang,

Maks Ovsjanikov,

Ruqi Huang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Sun_2023_ICCV, author = {Sun, Mingze and Mao, Shiwei and Jiang, Puhua and Ovsjanikov, Maks and Huang, Ruqi}, title = {Spatially and Spectrally Consistent Deep Functional Maps}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {14497-14507} }
Sparse Point Guided 3D Lane Detection: Chengtang Yao,

Lidong Yu,

Yuwei Wu,

Yunde Jia; [pdf] [supp]
[bibtex]
@InProceedings{Yao_2023_ICCV, author = {Yao, Chengtang and Yu, Lidong and Wu, Yuwei and Jia, Yunde}, title = {Sparse Point Guided 3D Lane Detection}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {8363-8372} }
Event-based Temporally Dense Optical Flow Estimation with Sequential Learning: Wachirawit Ponghiran,

Chamika Mihiranga Liyanagedera,

Kaushik Roy; [pdf] [supp]
[bibtex]
@InProceedings{Ponghiran_2023_ICCV, author = {Ponghiran, Wachirawit and Liyanagedera, Chamika Mihiranga and Roy, Kaushik}, title = {Event-based Temporally Dense Optical Flow Estimation with Sequential Learning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {9827-9836} }
Going Beyond Nouns With Vision & Language Models Using Synthetic Data: Paola Cascante-Bonilla,

Khaled Shehada,

James Seale Smith,

Sivan Doveh,

Donghyun Kim,

Rameswar Panda,

Gul Varol,

Aude Oliva,

Vicente Ordonez,

Rogerio Feris,

Leonid Karlinsky; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Cascante-Bonilla_2023_ICCV, author = {Cascante-Bonilla, Paola and Shehada, Khaled and Smith, James Seale and Doveh, Sivan and Kim, Donghyun and Panda, Rameswar and Varol, Gul and Oliva, Aude and Ordonez, Vicente and Feris, Rogerio and Karlinsky, Leonid}, title = {Going Beyond Nouns With Vision \& Language Models Using Synthetic Data}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {20155-20165} }
Continual Zero-Shot Learning through Semantically Guided Generative Random Walks: Wenxuan Zhang,

Paul Janson,

Kai Yi,

Ivan Skorokhodov,

Mohamed Elhoseiny; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhang_2023_ICCV, author = {Zhang, Wenxuan and Janson, Paul and Yi, Kai and Skorokhodov, Ivan and Elhoseiny, Mohamed}, title = {Continual Zero-Shot Learning through Semantically Guided Generative Random Walks}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {11574-11585} }
Foreground-Background Distribution Modeling Transformer for Visual Object Tracking: Dawei Yang,

Jianfeng He,

Yinchao Ma,

Qianjin Yu,

Tianzhu Zhang; [pdf] [supp]
[bibtex]
@InProceedings{Yang_2023_ICCV, author = {Yang, Dawei and He, Jianfeng and Ma, Yinchao and Yu, Qianjin and Zhang, Tianzhu}, title = {Foreground-Background Distribution Modeling Transformer for Visual Object Tracking}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {10117-10127} }
MeViS: A Large-scale Benchmark for Video Segmentation with Motion Expressions: Henghui Ding,

Chang Liu,

Shuting He,

Xudong Jiang,

Chen Change Loy; [pdf] [arXiv]
[bibtex]
@InProceedings{Ding_2023_ICCV, author = {Ding, Henghui and Liu, Chang and He, Shuting and Jiang, Xudong and Loy, Chen Change}, title = {MeViS: A Large-scale Benchmark for Video Segmentation with Motion Expressions}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {2694-2703} }
OPERA: Omni-Supervised Representation Learning with Hierarchical Supervisions: Chengkun Wang,

Wenzhao Zheng,

Zheng Zhu,

Jie Zhou,

Jiwen Lu; [pdf] [arXiv]
[bibtex]
@InProceedings{Wang_2023_ICCV, author = {Wang, Chengkun and Zheng, Wenzhao and Zhu, Zheng and Zhou, Jie and Lu, Jiwen}, title = {OPERA: Omni-Supervised Representation Learning with Hierarchical Supervisions}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {5559-5570} }
GPFL: Simultaneously Learning Global and Personalized Feature Information for Personalized Federated Learning: Jianqing Zhang,

Yang Hua,

Hao Wang,

Tao Song,

Zhengui Xue,

Ruhui Ma,

Jian Cao,

Haibing Guan; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhang_2023_ICCV, author = {Zhang, Jianqing and Hua, Yang and Wang, Hao and Song, Tao and Xue, Zhengui and Ma, Ruhui and Cao, Jian and Guan, Haibing}, title = {GPFL: Simultaneously Learning Global and Personalized Feature Information for Personalized Federated Learning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {5041-5051} }
Zero-Shot Contrastive Loss for Text-Guided Diffusion Image Style Transfer: Serin Yang,

Hyunmin Hwang,

Jong Chul Ye; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yang_2023_ICCV, author = {Yang, Serin and Hwang, Hyunmin and Ye, Jong Chul}, title = {Zero-Shot Contrastive Loss for Text-Guided Diffusion Image Style Transfer}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {22873-22882} }
Efficient Region-Aware Neural Radiance Fields for High-Fidelity Talking Portrait Synthesis: Jiahe Li,

Jiawei Zhang,

Xiao Bai,

Jun Zhou,

Lin Gu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Li_2023_ICCV, author = {Li, Jiahe and Zhang, Jiawei and Bai, Xiao and Zhou, Jun and Gu, Lin}, title = {Efficient Region-Aware Neural Radiance Fields for High-Fidelity Talking Portrait Synthesis}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {7568-7578} }
End2End Multi-View Feature Matching with Differentiable Pose Optimization: Barbara Roessle,

Matthias Nießner; [pdf] [supp]
[bibtex]
@InProceedings{Roessle_2023_ICCV, author = {Roessle, Barbara and Nie{\ss}ner, Matthias}, title = {End2End Multi-View Feature Matching with Differentiable Pose Optimization}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {477-487} }
Low-Light Image Enhancement with Illumination-Aware Gamma Correction and Complete Image Modelling Network: Yinglong Wang,

Zhen Liu,

Jianzhuang Liu,

Songcen Xu,

Shuaicheng Liu; [pdf] [arXiv]
[bibtex]
@InProceedings{Wang_2023_ICCV, author = {Wang, Yinglong and Liu, Zhen and Liu, Jianzhuang and Xu, Songcen and Liu, Shuaicheng}, title = {Low-Light Image Enhancement with Illumination-Aware Gamma Correction and Complete Image Modelling Network}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {13128-13137} }
Both Diverse and Realism Matter: Physical Attribute and Style Alignment for Rainy Image Generation: Changfeng Yu,

Shiming Chen,

Yi Chang,

Yibing Song,

Luxin Yan; [pdf] [supp]
[bibtex]
@InProceedings{Yu_2023_ICCV, author = {Yu, Changfeng and Chen, Shiming and Chang, Yi and Song, Yibing and Yan, Luxin}, title = {Both Diverse and Realism Matter: Physical Attribute and Style Alignment for Rainy Image Generation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {12387-12397} }
Exploring the Benefits of Visual Prompting in Differential Privacy: Yizhe Li,

Yu-Lin Tsai,

Chia-Mu Yu,

Pin-Yu Chen,

Xuebin Ren; [pdf] [arXiv]
[bibtex]
@InProceedings{Li_2023_ICCV, author = {Li, Yizhe and Tsai, Yu-Lin and Yu, Chia-Mu and Chen, Pin-Yu and Ren, Xuebin}, title = {Exploring the Benefits of Visual Prompting in Differential Privacy}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {5158-5167} }
Single Image Reflection Separation via Component Synergy: Qiming Hu,

Xiaojie Guo; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Hu_2023_ICCV, author = {Hu, Qiming and Guo, Xiaojie}, title = {Single Image Reflection Separation via Component Synergy}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {13138-13147} }
Mining bias-target Alignment from Voronoi Cells: Rémi Nahon,

Van-Tam Nguyen,

Enzo Tartaglione; [pdf] [arXiv]
[bibtex]
@InProceedings{Nahon_2023_ICCV, author = {Nahon, R\'emi and Nguyen, Van-Tam and Tartaglione, Enzo}, title = {Mining bias-target Alignment from Voronoi Cells}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {4946-4955} }
The Victim and The Beneficiary: Exploiting a Poisoned Model to Train a Clean Model on Poisoned Data: Zixuan Zhu,

Rui Wang,

Cong Zou,

Lihua Jing; [pdf] [supp]
[bibtex]
@InProceedings{Zhu_2023_ICCV, author = {Zhu, Zixuan and Wang, Rui and Zou, Cong and Jing, Lihua}, title = {The Victim and The Beneficiary: Exploiting a Poisoned Model to Train a Clean Model on Poisoned Data}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {155-164} }
DIFFGUARD: Semantic Mismatch-Guided Out-of-Distribution Detection Using Pre-Trained Diffusion Models: Ruiyuan Gao,

Chenchen Zhao,

Lanqing Hong,

Qiang Xu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Gao_2023_ICCV, author = {Gao, Ruiyuan and Zhao, Chenchen and Hong, Lanqing and Xu, Qiang}, title = {DIFFGUARD: Semantic Mismatch-Guided Out-of-Distribution Detection Using Pre-Trained Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {1579-1589} }
Identity-Seeking Self-Supervised Representation Learning for Generalizable Person Re-Identification: Zhaopeng Dou,

Zhongdao Wang,

Yali Li,

Shengjin Wang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Dou_2023_ICCV, author = {Dou, Zhaopeng and Wang, Zhongdao and Li, Yali and Wang, Shengjin}, title = {Identity-Seeking Self-Supervised Representation Learning for Generalizable Person Re-Identification}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {15847-15858} }
3D-Aware Generative Model for Improved Side-View Image Synthesis: Kyungmin Jo,

Wonjoon Jin,

Jaegul Choo,

Hyunjoon Lee,

Sunghyun Cho; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Jo_2023_ICCV, author = {Jo, Kyungmin and Jin, Wonjoon and Choo, Jaegul and Lee, Hyunjoon and Cho, Sunghyun}, title = {3D-Aware Generative Model for Improved Side-View Image Synthesis}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {22862-22872} }
Tracking Anything with Decoupled Video Segmentation: Ho Kei Cheng,

Seoung Wug Oh,

Brian Price,

Alexander Schwing,

Joon-Young Lee; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Cheng_2023_ICCV, author = {Cheng, Ho Kei and Oh, Seoung Wug and Price, Brian and Schwing, Alexander and Lee, Joon-Young}, title = {Tracking Anything with Decoupled Video Segmentation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {1316-1326} }
Generative Gradient Inversion via Over-Parameterized Networks in Federated Learning: Chi Zhang,

Zhang Xiaoman,

Ekanut Sotthiwat,

Yanyu Xu,

Ping Liu,

Liangli Zhen,

Yong Liu; [pdf] [supp]
[bibtex]
@InProceedings{Zhang_2023_ICCV, author = {Zhang, Chi and Xiaoman, Zhang and Sotthiwat, Ekanut and Xu, Yanyu and Liu, Ping and Zhen, Liangli and Liu, Yong}, title = {Generative Gradient Inversion via Over-Parameterized Networks in Federated Learning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {5126-5135} }
EQ-Net: Elastic Quantization Neural Networks: Ke Xu,

Lei Han,

Ye Tian,

Shangshang Yang,

Xingyi Zhang; [pdf] [supp]
[bibtex]
@InProceedings{Xu_2023_ICCV, author = {Xu, Ke and Han, Lei and Tian, Ye and Yang, Shangshang and Zhang, Xingyi}, title = {EQ-Net: Elastic Quantization Neural Networks}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {1505-1514} }
OxfordTVG-HIC: Can Machine Make Humorous Captions from Images?: Runjia Li,

Shuyang Sun,

Mohamed Elhoseiny,

Philip Torr; [pdf] [supp]
[bibtex]
@InProceedings{Li_2023_ICCV, author = {Li, Runjia and Sun, Shuyang and Elhoseiny, Mohamed and Torr, Philip}, title = {OxfordTVG-HIC: Can Machine Make Humorous Captions from Images?}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {20293-20303} }
Exploring Open-Vocabulary Semantic Segmentation from CLIP Vision Encoder Distillation Only: Jun Chen,

Deyao Zhu,

Guocheng Qian,

Bernard Ghanem,

Zhicheng Yan,

Chenchen Zhu,

Fanyi Xiao,

Sean Chang Culatana,

Mohamed Elhoseiny; [pdf] [supp]
[bibtex]
@InProceedings{Chen_2023_ICCV, author = {Chen, Jun and Zhu, Deyao and Qian, Guocheng and Ghanem, Bernard and Yan, Zhicheng and Zhu, Chenchen and Xiao, Fanyi and Culatana, Sean Chang and Elhoseiny, Mohamed}, title = {Exploring Open-Vocabulary Semantic Segmentation from CLIP Vision Encoder Distillation Only}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {699-710} }
EDAPS: Enhanced Domain-Adaptive Panoptic Segmentation: Suman Saha,

Lukas Hoyer,

Anton Obukhov,

Dengxin Dai,

Luc Van Gool; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Saha_2023_ICCV, author = {Saha, Suman and Hoyer, Lukas and Obukhov, Anton and Dai, Dengxin and Van Gool, Luc}, title = {EDAPS: Enhanced Domain-Adaptive Panoptic Segmentation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {19234-19245} }
Parallax-Tolerant Unsupervised Deep Image Stitching: Lang Nie,

Chunyu Lin,

Kang Liao,

Shuaicheng Liu,

Yao Zhao; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Nie_2023_ICCV, author = {Nie, Lang and Lin, Chunyu and Liao, Kang and Liu, Shuaicheng and Zhao, Yao}, title = {Parallax-Tolerant Unsupervised Deep Image Stitching}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {7399-7408} }
Scratch Each Other's Back: Incomplete Multi-Modal Brain Tumor Segmentation via Category Aware Group Self-Support Learning: Yansheng Qiu,

Delin Chen,

Hongdou Yao,

Yongchao Xu,

Zheng Wang; [pdf]
[bibtex]
@InProceedings{Qiu_2023_ICCV, author = {Qiu, Yansheng and Chen, Delin and Yao, Hongdou and Xu, Yongchao and Wang, Zheng}, title = {Scratch Each Other's Back: Incomplete Multi-Modal Brain Tumor Segmentation via Category Aware Group Self-Support Learning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {21317-21326} }
SFHarmony: Source Free Domain Adaptation for Distributed Neuroimaging Analysis: Nicola K Dinsdale,

Mark Jenkinson,

Ana IL Namburete; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Dinsdale_2023_ICCV, author = {Dinsdale, Nicola K and Jenkinson, Mark and Namburete, Ana IL}, title = {SFHarmony: Source Free Domain Adaptation for Distributed Neuroimaging Analysis}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {11494-11505} }
M2T: Masking Transformers Twice for Faster Decoding: Fabian Mentzer,

Eirikur Agustson,

Michael Tschannen; [pdf] [supp]
[bibtex]
@InProceedings{Mentzer_2023_ICCV, author = {Mentzer, Fabian and Agustson, Eirikur and Tschannen, Michael}, title = {M2T: Masking Transformers Twice for Faster Decoding}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {5340-5349} }
CoIn: Contrastive Instance Feature Mining for Outdoor 3D Object Detection with Very Limited Annotations: Qiming Xia,

Jinhao Deng,

Chenglu Wen,

Hai Wu,

Shaoshuai Shi,

Xin Li,

Cheng Wang; [pdf] [supp]
[bibtex]
@InProceedings{Xia_2023_ICCV, author = {Xia, Qiming and Deng, Jinhao and Wen, Chenglu and Wu, Hai and Shi, Shaoshuai and Li, Xin and Wang, Cheng}, title = {CoIn: Contrastive Instance Feature Mining for Outdoor 3D Object Detection with Very Limited Annotations}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {6254-6263} }
3D Human Mesh Recovery with Sequentially Global Rotation Estimation: Dongkai Wang,

Shiliang Zhang; [pdf]
[bibtex]
@InProceedings{Wang_2023_ICCV, author = {Wang, Dongkai and Zhang, Shiliang}, title = {3D Human Mesh Recovery with Sequentially Global Rotation Estimation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {14953-14962} }
DREAMWALKER: Mental Planning for Continuous Vision-Language Navigation: Hanqing Wang,

Wei Liang,

Luc Van Gool,

Wenguan Wang; [pdf] [arXiv]
[bibtex]
@InProceedings{Wang_2023_ICCV, author = {Wang, Hanqing and Liang, Wei and Van Gool, Luc and Wang, Wenguan}, title = {DREAMWALKER: Mental Planning for Continuous Vision-Language Navigation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {10873-10883} }
Computation and Data Efficient Backdoor Attacks: Yutong Wu,

Xingshuo Han,

Han Qiu,

Tianwei Zhang; [pdf]
[bibtex]
@InProceedings{Wu_2023_ICCV, author = {Wu, Yutong and Han, Xingshuo and Qiu, Han and Zhang, Tianwei}, title = {Computation and Data Efficient Backdoor Attacks}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {4805-4814} }
Agglomerative Transformer for Human-Object Interaction Detection: Danyang Tu,

Wei Sun,

Guangtao Zhai,

Wei Shen; [pdf] [arXiv]
[bibtex]
@InProceedings{Tu_2023_ICCV, author = {Tu, Danyang and Sun, Wei and Zhai, Guangtao and Shen, Wei}, title = {Agglomerative Transformer for Human-Object Interaction Detection}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {21614-21624} }
Decouple Before Interact: Multi-Modal Prompt Learning for Continual Visual Question Answering: Zi Qian,

Xin Wang,

Xuguang Duan,

Pengda Qin,

Yuhong Li,

Wenwu Zhu; [pdf] [supp]
[bibtex]
@InProceedings{Qian_2023_ICCV, author = {Qian, Zi and Wang, Xin and Duan, Xuguang and Qin, Pengda and Li, Yuhong and Zhu, Wenwu}, title = {Decouple Before Interact: Multi-Modal Prompt Learning for Continual Visual Question Answering}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {2953-2962} }
Rethinking Fast Fourier Convolution in Image Inpainting: Tianyi Chu,

Jiafu Chen,

Jiakai Sun,

Shuobin Lian,

Zhizhong Wang,

Zhiwen Zuo,

Lei Zhao,

Wei Xing,

Dongming Lu; [pdf] [supp]
[bibtex]
@InProceedings{Chu_2023_ICCV, author = {Chu, Tianyi and Chen, Jiafu and Sun, Jiakai and Lian, Shuobin and Wang, Zhizhong and Zuo, Zhiwen and Zhao, Lei and Xing, Wei and Lu, Dongming}, title = {Rethinking Fast Fourier Convolution in Image Inpainting}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {23195-23205} }
Learning Robust Representations with Information Bottleneck and Memory Network for RGB-D-based Gesture Recognition: Yunan Li,

Huizhou Chen,

Guanwen Feng,

Qiguang Miao; [pdf] [supp]
[bibtex]
@InProceedings{Li_2023_ICCV, author = {Li, Yunan and Chen, Huizhou and Feng, Guanwen and Miao, Qiguang}, title = {Learning Robust Representations with Information Bottleneck and Memory Network for RGB-D-based Gesture Recognition}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {20968-20978} }
P1AC: Revisiting Absolute Pose From a Single Affine Correspondence: Jonathan Ventura,

Zuzana Kukelova,

Torsten Sattler,

Dániel Baráth; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ventura_2023_ICCV, author = {Ventura, Jonathan and Kukelova, Zuzana and Sattler, Torsten and Bar\'ath, D\'aniel}, title = {P1AC: Revisiting Absolute Pose From a Single Affine Correspondence}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {19751-19761} }
LAN-HDR: Luminance-based Alignment Network for High Dynamic Range Video Reconstruction: Haesoo Chung,

Nam Ik Cho; [pdf]
[bibtex]
@InProceedings{Chung_2023_ICCV, author = {Chung, Haesoo and Cho, Nam Ik}, title = {LAN-HDR: Luminance-based Alignment Network for High Dynamic Range Video Reconstruction}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {12760-12769} }
Dancing in the Dark: A Benchmark towards General Low-light Video Enhancement: Huiyuan Fu,

Wenkai Zheng,

Xicong Wang,

Jiaxuan Wang,

Heng Zhang,

Huadong Ma; [pdf]
[bibtex]
@InProceedings{Fu_2023_ICCV, author = {Fu, Huiyuan and Zheng, Wenkai and Wang, Xicong and Wang, Jiaxuan and Zhang, Heng and Ma, Huadong}, title = {Dancing in the Dark: A Benchmark towards General Low-light Video Enhancement}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {12877-12886} }
RED-PSM: Regularization by Denoising of Partially Separable Models for Dynamic Imaging: Berk Iskender,

Marc L. Klasky,

Yoram Bresler; [pdf] [supp]
[bibtex]
@InProceedings{Iskender_2023_ICCV, author = {Iskender, Berk and Klasky, Marc L. and Bresler, Yoram}, title = {RED-PSM: Regularization by Denoising of Partially Separable Models for Dynamic Imaging}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {10595-10604} }
Unsupervised Manifold Linearizing and Clustering: Tianjiao Ding,

Shengbang Tong,

Kwan Ho Ryan Chan,

Xili Dai,

Yi Ma,

Benjamin D. Haeffele; [pdf] [arXiv]
[bibtex]
@InProceedings{Ding_2023_ICCV, author = {Ding, Tianjiao and Tong, Shengbang and Chan, Kwan Ho Ryan and Dai, Xili and Ma, Yi and Haeffele, Benjamin D.}, title = {Unsupervised Manifold Linearizing and Clustering}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {5450-5461} }
Lossy and Lossless (L2) Post-training Model Size Compression: Yumeng Shi,

Shihao Bai,

Xiuying Wei,

Ruihao Gong,

Jianlei Yang; [pdf] [supp]
[bibtex]
@InProceedings{Shi_2023_ICCV, author = {Shi, Yumeng and Bai, Shihao and Wei, Xiuying and Gong, Ruihao and Yang, Jianlei}, title = {Lossy and Lossless (L2) Post-training Model Size Compression}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {17546-17556} }
C2ST: Cross-Modal Contextualized Sequence Transduction for Continuous Sign Language Recognition: Huaiwen Zhang,

Zihang Guo,

Yang Yang,

Xin Liu,

De Hu; [pdf]
[bibtex]
@InProceedings{Zhang_2023_ICCV, author = {Zhang, Huaiwen and Guo, Zihang and Yang, Yang and Liu, Xin and Hu, De}, title = {C2ST: Cross-Modal Contextualized Sequence Transduction for Continuous Sign Language Recognition}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {21053-21062} }
ObjectFusion: Multi-modal 3D Object Detection with Object-Centric Fusion: Qi Cai,

Yingwei Pan,

Ting Yao,

Chong-Wah Ngo,

Tao Mei; [pdf] [supp]
[bibtex]
@InProceedings{Cai_2023_ICCV, author = {Cai, Qi and Pan, Yingwei and Yao, Ting and Ngo, Chong-Wah and Mei, Tao}, title = {ObjectFusion: Multi-modal 3D Object Detection with Object-Centric Fusion}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {18067-18076} }
D-IF: Uncertainty-aware Human Digitization via Implicit Distribution Field: Xueting Yang,

Yihao Luo,

Yuliang Xiu,

Wei Wang,

Hao Xu,

Zhaoxin Fan; [pdf]
[bibtex]
@InProceedings{Yang_2023_ICCV, author = {Yang, Xueting and Luo, Yihao and Xiu, Yuliang and Wang, Wei and Xu, Hao and Fan, Zhaoxin}, title = {D-IF: Uncertainty-aware Human Digitization via Implicit Distribution Field}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {9122-9132} }
MMVP: Motion-Matrix-Based Video Prediction: Yiqi Zhong,

Luming Liang,

Ilya Zharkov,

Ulrich Neumann; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhong_2023_ICCV, author = {Zhong, Yiqi and Liang, Luming and Zharkov, Ilya and Neumann, Ulrich}, title = {MMVP: Motion-Matrix-Based Video Prediction}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {4273-4283} }
Human Preference Score: Better Aligning Text-to-Image Models with Human Preference: Xiaoshi Wu,

Keqiang Sun,

Feng Zhu,

Rui Zhao,

Hongsheng Li; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wu_2023_ICCV, author = {Wu, Xiaoshi and Sun, Keqiang and Zhu, Feng and Zhao, Rui and Li, Hongsheng}, title = {Human Preference Score: Better Aligning Text-to-Image Models with Human Preference}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {2096-2105} }
Guided Motion Diffusion for Controllable Human Motion Synthesis: Korrawe Karunratanakul,

Konpat Preechakul,

Supasorn Suwajanakorn,

Siyu Tang; [pdf] [supp]
[bibtex]
@InProceedings{Karunratanakul_2023_ICCV, author = {Karunratanakul, Korrawe and Preechakul, Konpat and Suwajanakorn, Supasorn and Tang, Siyu}, title = {Guided Motion Diffusion for Controllable Human Motion Synthesis}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {2151-2162} }
AffordPose: A Large-Scale Dataset of Hand-Object Interactions with Affordance-Driven Hand Pose: Juntao Jian,

Xiuping Liu,

Manyi Li,

Ruizhen Hu,

Jian Liu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Jian_2023_ICCV, author = {Jian, Juntao and Liu, Xiuping and Li, Manyi and Hu, Ruizhen and Liu, Jian}, title = {AffordPose: A Large-Scale Dataset of Hand-Object Interactions with Affordance-Driven Hand Pose}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {14713-14724} }
Locomotion-Action-Manipulation: Synthesizing Human-Scene Interactions in Complex 3D Environments: Jiye Lee,

Hanbyul Joo; [pdf] [supp]
[bibtex]
@InProceedings{Lee_2023_ICCV, author = {Lee, Jiye and Joo, Hanbyul}, title = {Locomotion-Action-Manipulation: Synthesizing Human-Scene Interactions in Complex 3D Environments}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {9663-9674} }
NDDepth: Normal-Distance Assisted Monocular Depth Estimation: Shuwei Shao,

Zhongcai Pei,

Weihai Chen,

Xingming Wu,

Zhengguo Li; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Shao_2023_ICCV, author = {Shao, Shuwei and Pei, Zhongcai and Chen, Weihai and Wu, Xingming and Li, Zhengguo}, title = {NDDepth: Normal-Distance Assisted Monocular Depth Estimation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {7931-7940} }
Sequential Texts Driven Cohesive Motions Synthesis with Natural Transitions: Shuai Li,

Sisi Zhuang,

Wenfeng Song,

Xinyu Zhang,

Hejia Chen,

Aimin Hao; [pdf] [supp]
[bibtex]
@InProceedings{Li_2023_ICCV, author = {Li, Shuai and Zhuang, Sisi and Song, Wenfeng and Zhang, Xinyu and Chen, Hejia and Hao, Aimin}, title = {Sequential Texts Driven Cohesive Motions Synthesis with Natural Transitions}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {9498-9508} }
Efficient Converted Spiking Neural Network for 3D and 2D Classification: Yuxiang Lan,

Yachao Zhang,

Xu Ma,

Yanyun Qu,

Yun Fu; [pdf]
[bibtex]
@InProceedings{Lan_2023_ICCV, author = {Lan, Yuxiang and Zhang, Yachao and Ma, Xu and Qu, Yanyun and Fu, Yun}, title = {Efficient Converted Spiking Neural Network for 3D and 2D Classification}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {9211-9220} }
Eulerian Single-Photon Vision: Shantanu Gupta,

Mohit Gupta; [pdf] [supp]
[bibtex]
@InProceedings{Gupta_2023_ICCV, author = {Gupta, Shantanu and Gupta, Mohit}, title = {Eulerian Single-Photon Vision}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {10465-10476} }
Adaptive Calibrator Ensemble: Navigating Test Set Difficulty in Out-of-Distribution Scenarios: Yuli Zou,

Weijian Deng,

Liang Zheng; [pdf] [supp]
[bibtex]
@InProceedings{Zou_2023_ICCV, author = {Zou, Yuli and Deng, Weijian and Zheng, Liang}, title = {Adaptive Calibrator Ensemble: Navigating Test Set Difficulty in Out-of-Distribution Scenarios}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {19333-19342} }
Contrastive Learning Relies More on Spatial Inductive Bias Than Supervised Learning: An Empirical Study: Yuanyi Zhong,

Haoran Tang,

Jun-Kun Chen,

Yu-Xiong Wang; [pdf] [supp]
[bibtex]
@InProceedings{Zhong_2023_ICCV, author = {Zhong, Yuanyi and Tang, Haoran and Chen, Jun-Kun and Wang, Yu-Xiong}, title = {Contrastive Learning Relies More on Spatial Inductive Bias Than Supervised Learning: An Empirical Study}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {16327-16336} }
DiffuMask: Synthesizing Images with Pixel-level Annotations for Semantic Segmentation Using Diffusion Models: Weijia Wu,

Yuzhong Zhao,

Mike Zheng Shou,

Hong Zhou,

Chunhua Shen; [pdf] [arXiv]
[bibtex]
@InProceedings{Wu_2023_ICCV, author = {Wu, Weijia and Zhao, Yuzhong and Shou, Mike Zheng and Zhou, Hong and Shen, Chunhua}, title = {DiffuMask: Synthesizing Images with Pixel-level Annotations for Semantic Segmentation Using Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {1206-1217} }
NSF: Neural Surface Fields for Human Modeling from Monocular Depth: Yuxuan Xue,

Bharat Lal Bhatnagar,

Riccardo Marin,

Nikolaos Sarafianos,

Yuanlu Xu,

Gerard Pons-Moll,

Tony Tung; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Xue_2023_ICCV, author = {Xue, Yuxuan and Bhatnagar, Bharat Lal and Marin, Riccardo and Sarafianos, Nikolaos and Xu, Yuanlu and Pons-Moll, Gerard and Tung, Tony}, title = {NSF: Neural Surface Fields for Human Modeling from Monocular Depth}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {15049-15060} }
Unaligned 2D to 3D Translation with Conditional Vector-Quantized Code Diffusion using Transformers: Abril Corona-Figueroa,

Sam Bond-Taylor,

Neelanjan Bhowmik,

Yona Falinie A. Gaus,

Toby P. Breckon,

Hubert P. H. Shum,

Chris G. Willcocks; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Corona-Figueroa_2023_ICCV, author = {Corona-Figueroa, Abril and Bond-Taylor, Sam and Bhowmik, Neelanjan and Gaus, Yona Falinie A. and Breckon, Toby P. and Shum, Hubert P. H. and Willcocks, Chris G.}, title = {Unaligned 2D to 3D Translation with Conditional Vector-Quantized Code Diffusion using Transformers}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {14585-14594} }
DMNet: Delaunay Meshing Network for 3D Shape Representation: Chen Zhang,

Ganzhangqin Yuan,

Wenbing Tao; [pdf] [supp]
[bibtex]
@InProceedings{Zhang_2023_ICCV, author = {Zhang, Chen and Yuan, Ganzhangqin and Tao, Wenbing}, title = {DMNet: Delaunay Meshing Network for 3D Shape Representation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {14418-14428} }
StyleDomain: Efficient and Lightweight Parameterizations of StyleGAN for One-shot and Few-shot Domain Adaptation: Aibek Alanov,

Vadim Titov,

Maksim Nakhodnov,

Dmitry Vetrov; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Alanov_2023_ICCV, author = {Alanov, Aibek and Titov, Vadim and Nakhodnov, Maksim and Vetrov, Dmitry}, title = {StyleDomain: Efficient and Lightweight Parameterizations of StyleGAN for One-shot and Few-shot Domain Adaptation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {2184-2194} }
RankMixup: Ranking-Based Mixup Training for Network Calibration: Jongyoun Noh,

Hyekang Park,

Junghyup Lee,

Bumsub Ham; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Noh_2023_ICCV, author = {Noh, Jongyoun and Park, Hyekang and Lee, Junghyup and Ham, Bumsub}, title = {RankMixup: Ranking-Based Mixup Training for Network Calibration}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {1358-1368} }
Body Knowledge and Uncertainty Modeling for Monocular 3D Human Body Reconstruction: Yufei Zhang,

Hanjing Wang,

Jeffrey O. Kephart,

Qiang Ji; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhang_2023_ICCV, author = {Zhang, Yufei and Wang, Hanjing and Kephart, Jeffrey O. and Ji, Qiang}, title = {Body Knowledge and Uncertainty Modeling for Monocular 3D Human Body Reconstruction}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {9020-9032} }
Randomized Quantization: A Generic Augmentation for Data Agnostic Self-supervised Learning: Huimin Wu,

Chenyang Lei,

Xiao Sun,

Peng-Shuai Wang,

Qifeng Chen,

Kwang-Ting Cheng,

Stephen Lin,

Zhirong Wu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wu_2023_ICCV, author = {Wu, Huimin and Lei, Chenyang and Sun, Xiao and Wang, Peng-Shuai and Chen, Qifeng and Cheng, Kwang-Ting and Lin, Stephen and Wu, Zhirong}, title = {Randomized Quantization: A Generic Augmentation for Data Agnostic Self-supervised Learning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {16305-16316} }
Learning to Generate Semantic Layouts for Higher Text-Image Correspondence in Text-to-Image Synthesis: Minho Park,

Jooyeol Yun,

Seunghwan Choi,

Jaegul Choo; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Park_2023_ICCV, author = {Park, Minho and Yun, Jooyeol and Choi, Seunghwan and Choo, Jaegul}, title = {Learning to Generate Semantic Layouts for Higher Text-Image Correspondence in Text-to-Image Synthesis}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {7591-7600} }
Neural Radiance Field with LiDAR maps: MingFang Chang,

Akash Sharma,

Michael Kaess,

Simon Lucey; [pdf] [supp]
[bibtex]
@InProceedings{Chang_2023_ICCV, author = {Chang, MingFang and Sharma, Akash and Kaess, Michael and Lucey, Simon}, title = {Neural Radiance Field with LiDAR maps}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {17914-17923} }
AREA: Adaptive Reweighting via Effective Area for Long-Tailed Classification: Xiaohua Chen,

Yucan Zhou,

Dayan Wu,

Chule Yang,

Bo Li,

Qinghua Hu,

Weiping Wang; [pdf] [supp]
[bibtex]
@InProceedings{Chen_2023_ICCV, author = {Chen, Xiaohua and Zhou, Yucan and Wu, Dayan and Yang, Chule and Li, Bo and Hu, Qinghua and Wang, Weiping}, title = {AREA: Adaptive Reweighting via Effective Area for Long-Tailed Classification}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {19277-19287} }
Erasing Concepts from Diffusion Models: Rohit Gandikota,

Joanna Materzynska,

Jaden Fiotto-Kaufman,

David Bau; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Gandikota_2023_ICCV, author = {Gandikota, Rohit and Materzynska, Joanna and Fiotto-Kaufman, Jaden and Bau, David}, title = {Erasing Concepts from Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {2426-2436} }
Fully Attentional Networks with Self-emerging Token Labeling: Bingyin Zhao,

Zhiding Yu,

Shiyi Lan,

Yutao Cheng,

Anima Anandkumar,

Yingjie Lao,

Jose M. Alvarez; [pdf]
[bibtex]
@InProceedings{Zhao_2023_ICCV, author = {Zhao, Bingyin and Yu, Zhiding and Lan, Shiyi and Cheng, Yutao and Anandkumar, Anima and Lao, Yingjie and Alvarez, Jose M.}, title = {Fully Attentional Networks with Self-emerging Token Labeling}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {5585-5595} }
ACTIVE: Towards Highly Transferable 3D Physical Camouflage for Universal and Robust Vehicle Evasion: Naufal Suryanto,

Yongsu Kim,

Harashta Tatimma Larasati,

Hyoeun Kang,

Thi-Thu-Huong Le,

Yoonyoung Hong,

Hunmin Yang,

Se-Yoon Oh,

Howon Kim; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Suryanto_2023_ICCV, author = {Suryanto, Naufal and Kim, Yongsu and Larasati, Harashta Tatimma and Kang, Hyoeun and Le, Thi-Thu-Huong and Hong, Yoonyoung and Yang, Hunmin and Oh, Se-Yoon and Kim, Howon}, title = {ACTIVE: Towards Highly Transferable 3D Physical Camouflage for Universal and Robust Vehicle Evasion}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {4305-4314} }
Learning Adaptive Neighborhoods for Graph Neural Networks: Avishkar Saha,

Oscar Mendez,

Chris Russell,

Richard Bowden; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Saha_2023_ICCV, author = {Saha, Avishkar and Mendez, Oscar and Russell, Chris and Bowden, Richard}, title = {Learning Adaptive Neighborhoods for Graph Neural Networks}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {22541-22550} }
Equivariant Similarity for Vision-Language Foundation Models: Tan Wang,

Kevin Lin,

Linjie Li,

Chung-Ching Lin,

Zhengyuan Yang,

Hanwang Zhang,

Zicheng Liu,

Lijuan Wang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2023_ICCV, author = {Wang, Tan and Lin, Kevin and Li, Linjie and Lin, Chung-Ching and Yang, Zhengyuan and Zhang, Hanwang and Liu, Zicheng and Wang, Lijuan}, title = {Equivariant Similarity for Vision-Language Foundation Models}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {11998-12008} }
ReST: A Reconfigurable Spatial-Temporal Graph Model for Multi-Camera Multi-Object Tracking: Cheng-Che Cheng,

Min-Xuan Qiu,

Chen-Kuo Chiang,

Shang-Hong Lai; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Cheng_2023_ICCV, author = {Cheng, Cheng-Che and Qiu, Min-Xuan and Chiang, Chen-Kuo and Lai, Shang-Hong}, title = {ReST: A Reconfigurable Spatial-Temporal Graph Model for Multi-Camera Multi-Object Tracking}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {10051-10060} }
Too Large; Data Reduction for Vision-Language Pre-Training: Alex Jinpeng Wang,

Kevin Qinghong Lin,

David Junhao Zhang,

Stan Weixian Lei,

Mike Zheng Shou; [pdf] [arXiv]
[bibtex]
@InProceedings{Wang_2023_ICCV, author = {Wang, Alex Jinpeng and Lin, Kevin Qinghong and Zhang, David Junhao and Lei, Stan Weixian and Shou, Mike Zheng}, title = {Too Large; Data Reduction for Vision-Language Pre-Training}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {3147-3157} }
Make-It-3D: High-fidelity 3D Creation from A Single Image with Diffusion Prior: Junshu Tang,

Tengfei Wang,

Bo Zhang,

Ting Zhang,

Ran Yi,

Lizhuang Ma,

Dong Chen; [pdf] [supp]
[bibtex]
@InProceedings{Tang_2023_ICCV, author = {Tang, Junshu and Wang, Tengfei and Zhang, Bo and Zhang, Ting and Yi, Ran and Ma, Lizhuang and Chen, Dong}, title = {Make-It-3D: High-fidelity 3D Creation from A Single Image with Diffusion Prior}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {22819-22829} }
Towards Deeply Unified Depth-aware Panoptic Segmentation with Bi-directional Guidance Learning: Junwen He,

Yifan Wang,

Lijun Wang,

Huchuan Lu,

Bin Luo,

Jun-Yan He,

Jin-Peng Lan,

Yifeng Geng,

Xuansong Xie; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{He_2023_ICCV, author = {He, Junwen and Wang, Yifan and Wang, Lijun and Lu, Huchuan and Luo, Bin and He, Jun-Yan and Lan, Jin-Peng and Geng, Yifeng and Xie, Xuansong}, title = {Towards Deeply Unified Depth-aware Panoptic Segmentation with Bi-directional Guidance Learning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {4111-4121} }
Taxonomy Adaptive Cross-Domain Adaptation in Medical Imaging via Optimization Trajectory Distillation: Jianan Fan,

Dongnan Liu,

Hang Chang,

Heng Huang,

Mei Chen,

Weidong Cai; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Fan_2023_ICCV, author = {Fan, Jianan and Liu, Dongnan and Chang, Hang and Huang, Heng and Chen, Mei and Cai, Weidong}, title = {Taxonomy Adaptive Cross-Domain Adaptation in Medical Imaging via Optimization Trajectory Distillation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {21174-21184} }
DiffTAD: Temporal Action Detection with Proposal Denoising Diffusion: Sauradip Nag,

Xiatian Zhu,

Jiankang Deng,

Yi-Zhe Song,

Tao Xiang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Nag_2023_ICCV, author = {Nag, Sauradip and Zhu, Xiatian and Deng, Jiankang and Song, Yi-Zhe and Xiang, Tao}, title = {DiffTAD: Temporal Action Detection with Proposal Denoising Diffusion}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {10362-10374} }
Ray Conditioning: Trading Photo-consistency for Photo-realism in Multi-view Image Generation: Eric Ming Chen,

Sidhanth Holalkere,

Ruyu Yan,

Kai Zhang,

Abe Davis; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chen_2023_ICCV, author = {Chen, Eric Ming and Holalkere, Sidhanth and Yan, Ruyu and Zhang, Kai and Davis, Abe}, title = {Ray Conditioning: Trading Photo-consistency for Photo-realism in Multi-view Image Generation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {23242-23251} }
SCOB: Universal Text Understanding via Character-wise Supervised Contrastive Learning with Online Text Rendering for Bridging Domain Gap: Daehee Kim,

Yoonsik Kim,

DongHyun Kim,

Yumin Lim,

Geewook Kim,

Taeho Kil; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kim_2023_ICCV, author = {Kim, Daehee and Kim, Yoonsik and Kim, DongHyun and Lim, Yumin and Kim, Geewook and Kil, Taeho}, title = {SCOB: Universal Text Understanding via Character-wise Supervised Contrastive Learning with Online Text Rendering for Bridging Domain Gap}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {19562-19573} }
Point-Query Quadtree for Crowd Counting, Localization, and More: Chengxin Liu,

Hao Lu,

Zhiguo Cao,

Tongliang Liu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Liu_2023_ICCV, author = {Liu, Chengxin and Lu, Hao and Cao, Zhiguo and Liu, Tongliang}, title = {Point-Query Quadtree for Crowd Counting, Localization, and More}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {1676-1685} }
Heterogeneous Diversity Driven Active Learning for Multi-Object Tracking: Rui Li,

Baopeng Zhang,

Jun Liu,

Wei Liu,

Jian Zhao,

Zhu Teng; [pdf] [supp]
[bibtex]
@InProceedings{Li_2023_ICCV, author = {Li, Rui and Zhang, Baopeng and Liu, Jun and Liu, Wei and Zhao, Jian and Teng, Zhu}, title = {Heterogeneous Diversity Driven Active Learning for Multi-Object Tracking}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {9932-9941} }
Domain Generalization of 3D Semantic Segmentation in Autonomous Driving: Jules Sanchez,

Jean-Emmanuel Deschaud,

François Goulette; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Sanchez_2023_ICCV, author = {Sanchez, Jules and Deschaud, Jean-Emmanuel and Goulette, Fran\c{c}ois}, title = {Domain Generalization of 3D Semantic Segmentation in Autonomous Driving}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {18077-18087} }
HaMuCo: Hand Pose Estimation via Multiview Collaborative Self-Supervised Learning: Xiaozheng Zheng,

Chao Wen,

Zhou Xue,

Pengfei Ren,

Jingyu Wang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zheng_2023_ICCV, author = {Zheng, Xiaozheng and Wen, Chao and Xue, Zhou and Ren, Pengfei and Wang, Jingyu}, title = {HaMuCo: Hand Pose Estimation via Multiview Collaborative Self-Supervised Learning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {20763-20773} }
Efficient Model Personalization in Federated Learning via Client-Specific Prompt Generation: Fu-En Yang,

Chien-Yi Wang,

Yu-Chiang Frank Wang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yang_2023_ICCV, author = {Yang, Fu-En and Wang, Chien-Yi and Wang, Yu-Chiang Frank}, title = {Efficient Model Personalization in Federated Learning via Client-Specific Prompt Generation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {19159-19168} }
Dual Aggregation Transformer for Image Super-Resolution: Zheng Chen,

Yulun Zhang,

Jinjin Gu,

Linghe Kong,

Xiaokang Yang,

Fisher Yu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chen_2023_ICCV, author = {Chen, Zheng and Zhang, Yulun and Gu, Jinjin and Kong, Linghe and Yang, Xiaokang and Yu, Fisher}, title = {Dual Aggregation Transformer for Image Super-Resolution}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {12312-12321} }
Zero-Shot Spatial Layout Conditioning for Text-to-Image Diffusion Models: Guillaume Couairon,

Marlène Careil,

Matthieu Cord,

Stéphane Lathuilière,

Jakob Verbeek; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Couairon_2023_ICCV, author = {Couairon, Guillaume and Careil, Marl\`ene and Cord, Matthieu and Lathuili\`ere, St\'ephane and Verbeek, Jakob}, title = {Zero-Shot Spatial Layout Conditioning for Text-to-Image Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {2174-2183} }
SegGPT: Towards Segmenting Everything in Context: Xinlong Wang,

Xiaosong Zhang,

Yue Cao,

Wen Wang,

Chunhua Shen,

Tiejun Huang; [pdf] [supp]
[bibtex]
@InProceedings{Wang_2023_ICCV, author = {Wang, Xinlong and Zhang, Xiaosong and Cao, Yue and Wang, Wen and Shen, Chunhua and Huang, Tiejun}, title = {SegGPT: Towards Segmenting Everything in Context}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {1130-1140} }
Semantify: Simplifying the Control of 3D Morphable Models Using CLIP: Omer Gralnik,

Guy Gafni,

Ariel Shamir; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Gralnik_2023_ICCV, author = {Gralnik, Omer and Gafni, Guy and Shamir, Ariel}, title = {Semantify: Simplifying the Control of 3D Morphable Models Using CLIP}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {14554-14564} }
From Sky to the Ground: A Large-scale Benchmark and Simple Baseline Towards Real Rain Removal: Yun Guo,

Xueyao Xiao,

Yi Chang,

Shumin Deng,

Luxin Yan; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Guo_2023_ICCV, author = {Guo, Yun and Xiao, Xueyao and Chang, Yi and Deng, Shumin and Yan, Luxin}, title = {From Sky to the Ground: A Large-scale Benchmark and Simple Baseline Towards Real Rain Removal}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {12097-12107} }
Knowledge Restore and Transfer for Multi-Label Class-Incremental Learning: Songlin Dong,

Haoyu Luo,

Yuhang He,

Xing Wei,

Jie Cheng,

Yihong Gong; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Dong_2023_ICCV, author = {Dong, Songlin and Luo, Haoyu and He, Yuhang and Wei, Xing and Cheng, Jie and Gong, Yihong}, title = {Knowledge Restore and Transfer for Multi-Label Class-Incremental Learning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {18711-18720} }
DDColor: Towards Photo-Realistic Image Colorization via Dual Decoders: Xiaoyang Kang,

Tao Yang,

Wenqi Ouyang,

Peiran Ren,

Lingzhi Li,

Xuansong Xie; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kang_2023_ICCV, author = {Kang, Xiaoyang and Yang, Tao and Ouyang, Wenqi and Ren, Peiran and Li, Lingzhi and Xie, Xuansong}, title = {DDColor: Towards Photo-Realistic Image Colorization via Dual Decoders}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {328-338} }
Visual Explanations via Iterated Integrated Attributions: Oren Barkan,

‪Yehonatan Elisha‬‏,

Yuval Asher,

Amit Eshel,

Noam Koenigstein; [pdf] [supp]
[bibtex]
@InProceedings{Barkan_2023_ICCV, author = {Barkan, Oren and Elisha‬‏, ‪Yehonatan and Asher, Yuval and Eshel, Amit and Koenigstein, Noam}, title = {Visual Explanations via Iterated Integrated Attributions}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {2073-2084} }
PanFlowNet: A Flow-Based Deep Network for Pan-Sharpening: Gang Yang,

Xiangyong Cao,

Wenzhe Xiao,

Man Zhou,

Aiping Liu,

Xun Chen,

Deyu Meng; [pdf] [arXiv]
[bibtex]
@InProceedings{Yang_2023_ICCV, author = {Yang, Gang and Cao, Xiangyong and Xiao, Wenzhe and Zhou, Man and Liu, Aiping and Chen, Xun and Meng, Deyu}, title = {PanFlowNet: A Flow-Based Deep Network for Pan-Sharpening}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {16857-16867} }
Domain Generalization via Balancing Training Difficulty and Model Capability: Xueying Jiang,

Jiaxing Huang,

Sheng Jin,

Shijian Lu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Jiang_2023_ICCV, author = {Jiang, Xueying and Huang, Jiaxing and Jin, Sheng and Lu, Shijian}, title = {Domain Generalization via Balancing Training Difficulty and Model Capability}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {18993-19003} }
Pairwise Similarity Learning is SimPLE: Yandong Wen,

Weiyang Liu,

Yao Feng,

Bhiksha Raj,

Rita Singh,

Adrian Weller,

Michael J. Black,

Bernhard Schölkopf; [pdf] [supp]
[bibtex]
@InProceedings{Wen_2023_ICCV, author = {Wen, Yandong and Liu, Weiyang and Feng, Yao and Raj, Bhiksha and Singh, Rita and Weller, Adrian and Black, Michael J. and Sch\"olkopf, Bernhard}, title = {Pairwise Similarity Learning is SimPLE}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {5308-5318} }
GO-SLAM: Global Optimization for Consistent 3D Instant Reconstruction: Youmin Zhang,

Fabio Tosi,

Stefano Mattoccia,

Matteo Poggi; [pdf] [supp]
[bibtex]
@InProceedings{Zhang_2023_ICCV, author = {Zhang, Youmin and Tosi, Fabio and Mattoccia, Stefano and Poggi, Matteo}, title = {GO-SLAM: Global Optimization for Consistent 3D Instant Reconstruction}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {3727-3737} }
JOTR: 3D Joint Contrastive Learning with Transformers for Occluded Human Mesh Recovery: Jiahao Li,

Zongxin Yang,

Xiaohan Wang,

Jianxin Ma,

Chang Zhou,

Yi Yang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Li_2023_ICCV, author = {Li, Jiahao and Yang, Zongxin and Wang, Xiaohan and Ma, Jianxin and Zhou, Chang and Yang, Yi}, title = {JOTR: 3D Joint Contrastive Learning with Transformers for Occluded Human Mesh Recovery}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {9110-9121} }
CLIP-Driven Universal Model for Organ Segmentation and Tumor Detection: Jie Liu,

Yixiao Zhang,

Jie-Neng Chen,

Junfei Xiao,

Yongyi Lu,

Bennett A Landman,

Yixuan Yuan,

Alan Yuille,

Yucheng Tang,

Zongwei Zhou; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Liu_2023_ICCV, author = {Liu, Jie and Zhang, Yixiao and Chen, Jie-Neng and Xiao, Junfei and Lu, Yongyi and A Landman, Bennett and Yuan, Yixuan and Yuille, Alan and Tang, Yucheng and Zhou, Zongwei}, title = {CLIP-Driven Universal Model for Organ Segmentation and Tumor Detection}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {21152-21164} }
NIR-assisted Video Enhancement via Unpaired 24-hour Data: Muyao Niu,

Zhihang Zhong,

Yinqiang Zheng; [pdf] [supp]
[bibtex]
@InProceedings{Niu_2023_ICCV, author = {Niu, Muyao and Zhong, Zhihang and Zheng, Yinqiang}, title = {NIR-assisted Video Enhancement via Unpaired 24-hour Data}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {10778-10788} }
FACTS: First Amplify Correlations and Then Slice to Discover Bias: Sriram Yenamandra,

Pratik Ramesh,

Viraj Prabhu,

Judy Hoffman; [pdf] [supp]
[bibtex]
@InProceedings{Yenamandra_2023_ICCV, author = {Yenamandra, Sriram and Ramesh, Pratik and Prabhu, Viraj and Hoffman, Judy}, title = {FACTS: First Amplify Correlations and Then Slice to Discover Bias}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {4794-4804} }
Anchor Structure Regularization Induced Multi-view Subspace Clustering via Enhanced Tensor Rank Minimization: Jintian Ji,

Songhe Feng; [pdf] [supp]
[bibtex]
@InProceedings{Ji_2023_ICCV, author = {Ji, Jintian and Feng, Songhe}, title = {Anchor Structure Regularization Induced Multi-view Subspace Clustering via Enhanced Tensor Rank Minimization}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {19343-19352} }
VeRi3D: Generative Vertex-based Radiance Fields for 3D Controllable Human Image Synthesis: Xinya Chen,

Jiaxin Huang,

Yanrui Bin,

Lu Yu,

Yiyi Liao; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chen_2023_ICCV, author = {Chen, Xinya and Huang, Jiaxin and Bin, Yanrui and Yu, Lu and Liao, Yiyi}, title = {VeRi3D: Generative Vertex-based Radiance Fields for 3D Controllable Human Image Synthesis}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {8986-8997} }
MOSE: A New Dataset for Video Object Segmentation in Complex Scenes: Henghui Ding,

Chang Liu,

Shuting He,

Xudong Jiang,

Philip H.S. Torr,

Song Bai; [pdf] [arXiv]
[bibtex]
@InProceedings{Ding_2023_ICCV, author = {Ding, Henghui and Liu, Chang and He, Shuting and Jiang, Xudong and Torr, Philip H.S. and Bai, Song}, title = {MOSE: A New Dataset for Video Object Segmentation in Complex Scenes}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {20224-20234} }
BoMD: Bag of Multi-label Descriptors for Noisy Chest X-ray Classification: Yuanhong Chen,

Fengbei Liu,

Hu Wang,

Chong Wang,

Yuyuan Liu,

Yu Tian,

Gustavo Carneiro; [pdf] [supp]
[bibtex]
@InProceedings{Chen_2023_ICCV, author = {Chen, Yuanhong and Liu, Fengbei and Wang, Hu and Wang, Chong and Liu, Yuyuan and Tian, Yu and Carneiro, Gustavo}, title = {BoMD: Bag of Multi-label Descriptors for Noisy Chest X-ray Classification}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {21284-21295} }
Mask-Attention-Free Transformer for 3D Instance Segmentation: Xin Lai,

Yuhui Yuan,

Ruihang Chu,

Yukang Chen,

Han Hu,

Jiaya Jia; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Lai_2023_ICCV, author = {Lai, Xin and Yuan, Yuhui and Chu, Ruihang and Chen, Yukang and Hu, Han and Jia, Jiaya}, title = {Mask-Attention-Free Transformer for 3D Instance Segmentation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {3693-3703} }
SHIFT3D: Synthesizing Hard Inputs For Tricking 3D Detectors: Hongge Chen,

Zhao Chen,

Gregory P. Meyer,

Dennis Park,

Carl Vondrick,

Ashish Shrivastava,

Yuning Chai; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chen_2023_ICCV, author = {Chen, Hongge and Chen, Zhao and Meyer, Gregory P. and Park, Dennis and Vondrick, Carl and Shrivastava, Ashish and Chai, Yuning}, title = {SHIFT3D: Synthesizing Hard Inputs For Tricking 3D Detectors}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {8493-8503} }
EgoLoc: Revisiting 3D Object Localization from Egocentric Videos with Visual Queries: Jinjie Mai,

Abdullah Hamdi,

Silvio Giancola,

Chen Zhao,

Bernard Ghanem; [pdf] [arXiv]
[bibtex]
@InProceedings{Mai_2023_ICCV, author = {Mai, Jinjie and Hamdi, Abdullah and Giancola, Silvio and Zhao, Chen and Ghanem, Bernard}, title = {EgoLoc: Revisiting 3D Object Localization from Egocentric Videos with Visual Queries}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {45-57} }
Coordinate Transformer: Achieving Single-stage Multi-person Mesh Recovery from Videos: Haoyuan Li,

Haoye Dong,

Hanchao Jia,

Dong Huang,

Michael C. Kampffmeyer,

Liang Lin,

Xiaodan Liang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Li_2023_ICCV, author = {Li, Haoyuan and Dong, Haoye and Jia, Hanchao and Huang, Dong and Kampffmeyer, Michael C. and Lin, Liang and Liang, Xiaodan}, title = {Coordinate Transformer: Achieving Single-stage Multi-person Mesh Recovery from Videos}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {8744-8753} }
FLatten Transformer: Vision Transformer using Focused Linear Attention: Dongchen Han,

Xuran Pan,

Yizeng Han,

Shiji Song,

Gao Huang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Han_2023_ICCV, author = {Han, Dongchen and Pan, Xuran and Han, Yizeng and Song, Shiji and Huang, Gao}, title = {FLatten Transformer: Vision Transformer using Focused Linear Attention}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {5961-5971} }
Q-Diffusion: Quantizing Diffusion Models: Xiuyu Li,

Yijiang Liu,

Long Lian,

Huanrui Yang,

Zhen Dong,

Daniel Kang,

Shanghang Zhang,

Kurt Keutzer; [pdf] [supp]
[bibtex]
@InProceedings{Li_2023_ICCV, author = {Li, Xiuyu and Liu, Yijiang and Lian, Long and Yang, Huanrui and Dong, Zhen and Kang, Daniel and Zhang, Shanghang and Keutzer, Kurt}, title = {Q-Diffusion: Quantizing Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {17535-17545} }
Robustifying Token Attention for Vision Transformers: Yong Guo,

David Stutz,

Bernt Schiele; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Guo_2023_ICCV, author = {Guo, Yong and Stutz, David and Schiele, Bernt}, title = {Robustifying Token Attention for Vision Transformers}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {17557-17568} }
Boosting Positive Segments for Weakly-Supervised Audio-Visual Video Parsing: Kranthi Kumar Rachavarapu,

Rajagopalan A. N.; [pdf] [supp]
[bibtex]
@InProceedings{Rachavarapu_2023_ICCV, author = {Rachavarapu, Kranthi Kumar and N., Rajagopalan A.}, title = {Boosting Positive Segments for Weakly-Supervised Audio-Visual Video Parsing}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {10192-10202} }
ADNet: Lane Shape Prediction via Anchor Decomposition: Lingyu Xiao,

Xiang Li,

Sen Yang,

Wankou Yang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Xiao_2023_ICCV, author = {Xiao, Lingyu and Li, Xiang and Yang, Sen and Yang, Wankou}, title = {ADNet: Lane Shape Prediction via Anchor Decomposition}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {6404-6413} }
UniSeg: A Unified Multi-Modal LiDAR Segmentation Network and the OpenPCSeg Codebase: Youquan Liu,

Runnan Chen,

Xin Li,

Lingdong Kong,

Yuchen Yang,

Zhaoyang Xia,

Yeqi Bai,

Xinge Zhu,

Yuexin Ma,

Yikang Li,

Yu Qiao,

Yuenan Hou; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Liu_2023_ICCV, author = {Liu, Youquan and Chen, Runnan and Li, Xin and Kong, Lingdong and Yang, Yuchen and Xia, Zhaoyang and Bai, Yeqi and Zhu, Xinge and Ma, Yuexin and Li, Yikang and Qiao, Yu and Hou, Yuenan}, title = {UniSeg: A Unified Multi-Modal LiDAR Segmentation Network and the OpenPCSeg Codebase}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {21662-21673} }
Sign Language Translation with Iterative Prototype: Huijie Yao,

Wengang Zhou,

Hao Feng,

Hezhen Hu,

Hao Zhou,

Houqiang Li; [pdf] [arXiv]
[bibtex]
@InProceedings{Yao_2023_ICCV, author = {Yao, Huijie and Zhou, Wengang and Feng, Hao and Hu, Hezhen and Zhou, Hao and Li, Houqiang}, title = {Sign Language Translation with Iterative Prototype}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {15592-15601} }
Pixel-Wise Contrastive Distillation: Junqiang Huang,

Zichao Guo; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Huang_2023_ICCV, author = {Huang, Junqiang and Guo, Zichao}, title = {Pixel-Wise Contrastive Distillation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {16359-16369} }
Efficient Deep Space Filling Curve: Wanli Chen,

Xufeng Yao,

Xinyun Zhang,

Bei Yu; [pdf] [supp]
[bibtex]
@InProceedings{Chen_2023_ICCV, author = {Chen, Wanli and Yao, Xufeng and Zhang, Xinyun and Yu, Bei}, title = {Efficient Deep Space Filling Curve}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {17525-17534} }
GlueGen: Plug and Play Multi-modal Encoders for X-to-image Generation: Can Qin,

Ning Yu,

Chen Xing,

Shu Zhang,

Zeyuan Chen,

Stefano Ermon,

Yun Fu,

Caiming Xiong,

Ran Xu; [pdf] [supp]
[bibtex]
@InProceedings{Qin_2023_ICCV, author = {Qin, Can and Yu, Ning and Xing, Chen and Zhang, Shu and Chen, Zeyuan and Ermon, Stefano and Fu, Yun and Xiong, Caiming and Xu, Ran}, title = {GlueGen: Plug and Play Multi-modal Encoders for X-to-image Generation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {23085-23096} }
Humans in 4D: Reconstructing and Tracking Humans with Transformers: Shubham Goel,

Georgios Pavlakos,

Jathushan Rajasegaran,

Angjoo Kanazawa,

Jitendra Malik; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Goel_2023_ICCV, author = {Goel, Shubham and Pavlakos, Georgios and Rajasegaran, Jathushan and Kanazawa, Angjoo and Malik, Jitendra}, title = {Humans in 4D: Reconstructing and Tracking Humans with Transformers}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {14783-14794} }
Ponder: Point Cloud Pre-training via Neural Rendering: Di Huang,

Sida Peng,

Tong He,

Honghui Yang,

Xiaowei Zhou,

Wanli Ouyang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Huang_2023_ICCV, author = {Huang, Di and Peng, Sida and He, Tong and Yang, Honghui and Zhou, Xiaowei and Ouyang, Wanli}, title = {Ponder: Point Cloud Pre-training via Neural Rendering}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {16089-16098} }
Perpetual Humanoid Control for Real-time Simulated Avatars: Zhengyi Luo,

Jinkun Cao,

AlexanderWinkler,

Kris Kitani,

Weipeng Xu; [pdf] [supp]
[bibtex]
@InProceedings{Luo_2023_ICCV, author = {Luo, Zhengyi and Cao, Jinkun and AlexanderWinkler and Kitani, Kris and Xu, Weipeng}, title = {Perpetual Humanoid Control for Real-time Simulated Avatars}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {10895-10904} }
HollowNeRF: Pruning Hashgrid-Based NeRFs with Trainable Collision Mitigation: Xiufeng Xie,

Riccardo Gherardi,

Zhihong Pan,

Stephen Huang; [pdf] [arXiv]
[bibtex]
@InProceedings{Xie_2023_ICCV, author = {Xie, Xiufeng and Gherardi, Riccardo and Pan, Zhihong and Huang, Stephen}, title = {HollowNeRF: Pruning Hashgrid-Based NeRFs with Trainable Collision Mitigation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {3480-3490} }
A Complete Recipe for Diffusion Generative Models: Kushagra Pandey,

Stephan Mandt; [pdf] [supp]
[bibtex]
@InProceedings{Pandey_2023_ICCV, author = {Pandey, Kushagra and Mandt, Stephan}, title = {A Complete Recipe for Diffusion Generative Models}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {4261-4272} }
The Devil is in the Crack Orientation: A New Perspective for Crack Detection: Zhuangzhuang Chen,

Jin Zhang,

Zhuonan Lai,

Guanming Zhu,

Zun Liu,

Jie Chen,

Jianqiang Li; [pdf]
[bibtex]
@InProceedings{Chen_2023_ICCV, author = {Chen, Zhuangzhuang and Zhang, Jin and Lai, Zhuonan and Zhu, Guanming and Liu, Zun and Chen, Jie and Li, Jianqiang}, title = {The Devil is in the Crack Orientation: A New Perspective for Crack Detection}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {6653-6663} }
FedPD: Federated Open Set Recognition with Parameter Disentanglement: Chen Yang,

Meilu Zhu,

Yifan Liu,

Yixuan Yuan; [pdf]
[bibtex]
@InProceedings{Yang_2023_ICCV, author = {Yang, Chen and Zhu, Meilu and Liu, Yifan and Yuan, Yixuan}, title = {FedPD: Federated Open Set Recognition with Parameter Disentanglement}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {4882-4891} }
WaterMask: Instance Segmentation for Underwater Imagery: Shijie Lian,

Hua Li,

Runmin Cong,

Suqi Li,

Wei Zhang,

Sam Kwong; [pdf]
[bibtex]
@InProceedings{Lian_2023_ICCV, author = {Lian, Shijie and Li, Hua and Cong, Runmin and Li, Suqi and Zhang, Wei and Kwong, Sam}, title = {WaterMask: Instance Segmentation for Underwater Imagery}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {1305-1315} }
Score Priors Guided Deep Variational Inference for Unsupervised Real-World Single Image Denoising: Jun Cheng,

Tao Liu,

Shan Tan; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Cheng_2023_ICCV, author = {Cheng, Jun and Liu, Tao and Tan, Shan}, title = {Score Priors Guided Deep Variational Inference for Unsupervised Real-World Single Image Denoising}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {12937-12948} }
L-DAWA: Layer-wise Divergence Aware Weight Aggregation in Federated Self-Supervised Visual Representation Learning: Yasar Abbas Ur Rehman,

Yan Gao,

Pedro Porto Buarque de Gusmao,

Mina Alibeigi,

Jiajun Shen,

Nicholas D. Lane; [pdf] [supp]
[bibtex]
@InProceedings{Rehman_2023_ICCV, author = {Rehman, Yasar Abbas Ur and Gao, Yan and de Gusmao, Pedro Porto Buarque and Alibeigi, Mina and Shen, Jiajun and Lane, Nicholas D.}, title = {L-DAWA: Layer-wise Divergence Aware Weight Aggregation in Federated Self-Supervised Visual Representation Learning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {16464-16473} }
Improving Transformer-based Image Matching by Cascaded Capturing Spatially Informative Keypoints: Chenjie Cao,

Yanwei Fu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Cao_2023_ICCV, author = {Cao, Chenjie and Fu, Yanwei}, title = {Improving Transformer-based Image Matching by Cascaded Capturing Spatially Informative Keypoints}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {12129-12139} }
Controllable Guide-Space for Generalizable Face Forgery Detection: Ying Guo,

Cheng Zhen,

Pengfei Yan; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Guo_2023_ICCV, author = {Guo, Ying and Zhen, Cheng and Yan, Pengfei}, title = {Controllable Guide-Space for Generalizable Face Forgery Detection}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {20818-20827} }
Calibrating Uncertainty for Semi-Supervised Crowd Counting: Chen LI,

Xiaoling Hu,

Shahira Abousamra,

Chao Chen; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{LI_2023_ICCV, author = {LI, Chen and Hu, Xiaoling and Abousamra, Shahira and Chen, Chao}, title = {Calibrating Uncertainty for Semi-Supervised Crowd Counting}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {16731-16741} }
MosaiQ: Quantum Generative Adversarial Networks for Image Generation on NISQ Computers: Daniel Silver,

Tirthak Patel,

William Cutler,

Aditya Ranjan,

Harshitta Gandhi,

Devesh Tiwari; [pdf] [arXiv]
[bibtex]
@InProceedings{Silver_2023_ICCV, author = {Silver, Daniel and Patel, Tirthak and Cutler, William and Ranjan, Aditya and Gandhi, Harshitta and Tiwari, Devesh}, title = {MosaiQ: Quantum Generative Adversarial Networks for Image Generation on NISQ Computers}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {7030-7039} }
DVIS: Decoupled Video Instance Segmentation Framework: Tao Zhang,

Xingye Tian,

Yu Wu,

Shunping Ji,

Xuebo Wang,

Yuan Zhang,

Pengfei Wan; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhang_2023_ICCV, author = {Zhang, Tao and Tian, Xingye and Wu, Yu and Ji, Shunping and Wang, Xuebo and Zhang, Yuan and Wan, Pengfei}, title = {DVIS: Decoupled Video Instance Segmentation Framework}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {1282-1291} }
Segmentation of Tubular Structures Using Iterative Training with Tailored Samples: Wei Liao; [pdf] [arXiv]
[bibtex]
@InProceedings{Liao_2023_ICCV, author = {Liao, Wei}, title = {Segmentation of Tubular Structures Using Iterative Training with Tailored Samples}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {23643-23652} }
Boundary-Aware Divide and Conquer: A Diffusion-Based Solution for Unsupervised Shadow Removal: Lanqing Guo,

Chong Wang,

Wenhan Yang,

Yufei Wang,

Bihan Wen; [pdf] [supp]
[bibtex]
@InProceedings{Guo_2023_ICCV, author = {Guo, Lanqing and Wang, Chong and Yang, Wenhan and Wang, Yufei and Wen, Bihan}, title = {Boundary-Aware Divide and Conquer: A Diffusion-Based Solution for Unsupervised Shadow Removal}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {13045-13054} }
Towards Nonlinear-Motion-Aware and Occlusion-Robust Rolling Shutter Correction: Delin Qu,

Yizhen Lao,

Zhigang Wang,

Dong Wang,

Bin Zhao,

Xuelong Li; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Qu_2023_ICCV, author = {Qu, Delin and Lao, Yizhen and Wang, Zhigang and Wang, Dong and Zhao, Bin and Li, Xuelong}, title = {Towards Nonlinear-Motion-Aware and Occlusion-Robust Rolling Shutter Correction}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {10680-10688} }
Surface Extraction from Neural Unsigned Distance Fields: Congyi Zhang,

Guying Lin,

Lei Yang,

Xin Li,

Taku Komura,

Scott Schaefer,

John Keyser,

Wenping Wang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhang_2023_ICCV, author = {Zhang, Congyi and Lin, Guying and Yang, Lei and Li, Xin and Komura, Taku and Schaefer, Scott and Keyser, John and Wang, Wenping}, title = {Surface Extraction from Neural Unsigned Distance Fields}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {22531-22540} }
CBA: Improving Online Continual Learning via Continual Bias Adaptor: Quanziang Wang,

Renzhen Wang,

Yichen Wu,

Xixi Jia,

Deyu Meng; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2023_ICCV, author = {Wang, Quanziang and Wang, Renzhen and Wu, Yichen and Jia, Xixi and Meng, Deyu}, title = {CBA: Improving Online Continual Learning via Continual Bias Adaptor}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {19082-19092} }
GraphEcho: Graph-Driven Unsupervised Domain Adaptation for Echocardiogram Video Segmentation: Jiewen Yang,

Xinpeng Ding,

Ziyang Zheng,

Xiaowei Xu,

Xiaomeng Li; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yang_2023_ICCV, author = {Yang, Jiewen and Ding, Xinpeng and Zheng, Ziyang and Xu, Xiaowei and Li, Xiaomeng}, title = {GraphEcho: Graph-Driven Unsupervised Domain Adaptation for Echocardiogram Video Segmentation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {11878-11887} }
Multi-view Spectral Polarization Propagation for Video Glass Segmentation: Yu Qiao,

Bo Dong,

Ao Jin,

Yu Fu,

Seung-Hwan Baek,

Felix Heide,

Pieter Peers,

Xiaopeng Wei,

Xin Yang; [pdf] [supp]
[bibtex]
@InProceedings{Qiao_2023_ICCV, author = {Qiao, Yu and Dong, Bo and Jin, Ao and Fu, Yu and Baek, Seung-Hwan and Heide, Felix and Peers, Pieter and Wei, Xiaopeng and Yang, Xin}, title = {Multi-view Spectral Polarization Propagation for Video Glass Segmentation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {23218-23228} }
Rethinking Amodal Video Segmentation from Learning Supervised Signals with Object-centric Representation: Ke Fan,

Jingshi Lei,

Xuelin Qian,

Miaopeng Yu,

Tianjun Xiao,

Tong He,

Zheng Zhang,

Yanwei Fu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Fan_2023_ICCV, author = {Fan, Ke and Lei, Jingshi and Qian, Xuelin and Yu, Miaopeng and Xiao, Tianjun and He, Tong and Zhang, Zheng and Fu, Yanwei}, title = {Rethinking Amodal Video Segmentation from Learning Supervised Signals with Object-centric Representation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {1272-1281} }
Augmented Box Replay: Overcoming Foreground Shift for Incremental Object Detection: Yuyang Liu,

Yang Cong,

Dipam Goswami,

Xialei Liu,

Joost van de Weijer; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Liu_2023_ICCV, author = {Liu, Yuyang and Cong, Yang and Goswami, Dipam and Liu, Xialei and van de Weijer, Joost}, title = {Augmented Box Replay: Overcoming Foreground Shift for Incremental Object Detection}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {11367-11377} }
Distilled Reverse Attention Network for Open-world Compositional Zero-Shot Learning: Yun Li,

Zhe Liu,

Saurav Jha,

Lina Yao; [pdf] [arXiv]
[bibtex]
@InProceedings{Li_2023_ICCV, author = {Li, Yun and Liu, Zhe and Jha, Saurav and Yao, Lina}, title = {Distilled Reverse Attention Network for Open-world Compositional Zero-Shot Learning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {1782-1791} }
DandelionNet: Domain Composition with Instance Adaptive Classification for Domain Generalization: Lanqing Hu,

Meina Kan,

Shiguang Shan,

Xilin Chen; [pdf] [supp]
[bibtex]
@InProceedings{Hu_2023_ICCV, author = {Hu, Lanqing and Kan, Meina and Shan, Shiguang and Chen, Xilin}, title = {DandelionNet: Domain Composition with Instance Adaptive Classification for Domain Generalization}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {19050-19059} }
TexFusion: Synthesizing 3D Textures with Text-Guided Image Diffusion Models: Tianshi Cao,

Karsten Kreis,

Sanja Fidler,

Nicholas Sharp,

Kangxue Yin; [pdf] [supp]
[bibtex]
@InProceedings{Cao_2023_ICCV, author = {Cao, Tianshi and Kreis, Karsten and Fidler, Sanja and Sharp, Nicholas and Yin, Kangxue}, title = {TexFusion: Synthesizing 3D Textures with Text-Guided Image Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {4169-4181} }
Shift from Texture-bias to Shape-bias: Edge Deformation-based Augmentation for Robust Object Recognition: Xilin He,

Qinliang Lin,

Cheng Luo,

Weicheng Xie,

Siyang Song,

Feng Liu,

Linlin Shen; [pdf] [supp]
[bibtex]
@InProceedings{He_2023_ICCV, author = {He, Xilin and Lin, Qinliang and Luo, Cheng and Xie, Weicheng and Song, Siyang and Liu, Feng and Shen, Linlin}, title = {Shift from Texture-bias to Shape-bias: Edge Deformation-based Augmentation for Robust Object Recognition}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {1526-1535} }
Lighting Every Darkness in Two Pairs: A Calibration-Free Pipeline for RAW Denoising: Xin Jin,

Jia-Wen Xiao,

Ling-Hao Han,

Chunle Guo,

Ruixun Zhang,

Xialei Liu,

Chongyi Li; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Jin_2023_ICCV, author = {Jin, Xin and Xiao, Jia-Wen and Han, Ling-Hao and Guo, Chunle and Zhang, Ruixun and Liu, Xialei and Li, Chongyi}, title = {Lighting Every Darkness in Two Pairs: A Calibration-Free Pipeline for RAW Denoising}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {13275-13284} }
Data-free Knowledge Distillation for Fine-grained Visual Categorization: Renrong Shao,

Wei Zhang,

Jianhua Yin,

Jun Wang; [pdf] [supp]
[bibtex]
@InProceedings{Shao_2023_ICCV, author = {Shao, Renrong and Zhang, Wei and Yin, Jianhua and Wang, Jun}, title = {Data-free Knowledge Distillation for Fine-grained Visual Categorization}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {1515-1525} }
MotionBERT: A Unified Perspective on Learning Human Motion Representations: Wentao Zhu,

Xiaoxuan Ma,

Zhaoyang Liu,

Libin Liu,

Wayne Wu,

Yizhou Wang; [pdf] [arXiv]
[bibtex]
@InProceedings{Zhu_2023_ICCV, author = {Zhu, Wentao and Ma, Xiaoxuan and Liu, Zhaoyang and Liu, Libin and Wu, Wayne and Wang, Yizhou}, title = {MotionBERT: A Unified Perspective on Learning Human Motion Representations}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {15085-15099} }
PASTA: Proportional Amplitude Spectrum Training Augmentation for Syn-to-Real Domain Generalization: Prithvijit Chattopadhyay,

Kartik Sarangmath,

Vivek Vijaykumar,

Judy Hoffman; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chattopadhyay_2023_ICCV, author = {Chattopadhyay, Prithvijit and Sarangmath, Kartik and Vijaykumar, Vivek and Hoffman, Judy}, title = {PASTA: Proportional Amplitude Spectrum Training Augmentation for Syn-to-Real Domain Generalization}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {19288-19300} }
EgoPCA: A New Framework for Egocentric Hand-Object Interaction Understanding: Yue Xu,

Yong-Lu Li,

Zhemin Huang,

Michael Xu Liu,

Cewu Lu,

Yu-Wing Tai,

Chi-Keung Tang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Xu_2023_ICCV, author = {Xu, Yue and Li, Yong-Lu and Huang, Zhemin and Liu, Michael Xu and Lu, Cewu and Tai, Yu-Wing and Tang, Chi-Keung}, title = {EgoPCA: A New Framework for Egocentric Hand-Object Interaction Understanding}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {5273-5284} }
Metric3D: Towards Zero-shot Metric 3D Prediction from A Single Image: Wei Yin,

Chi Zhang,

Hao Chen,

Zhipeng Cai,

Gang Yu,

Kaixuan Wang,

Xiaozhi Chen,

Chunhua Shen; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yin_2023_ICCV, author = {Yin, Wei and Zhang, Chi and Chen, Hao and Cai, Zhipeng and Yu, Gang and Wang, Kaixuan and Chen, Xiaozhi and Shen, Chunhua}, title = {Metric3D: Towards Zero-shot Metric 3D Prediction from A Single Image}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {9043-9053} }
I Can't Believe There's No Images! Learning Visual Tasks Using only Language Supervision: Sophia Gu,

Christopher Clark,

Aniruddha Kembhavi; [pdf] [supp]
[bibtex]
@InProceedings{Gu_2023_ICCV, author = {Gu, Sophia and Clark, Christopher and Kembhavi, Aniruddha}, title = {I Can't Believe There's No Images! Learning Visual Tasks Using only Language Supervision}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {2672-2683} }
Lightweight Image Super-Resolution with Superpixel Token Interaction: Aiping Zhang,

Wenqi Ren,

Yi Liu,

Xiaochun Cao; [pdf]
[bibtex]
@InProceedings{Zhang_2023_ICCV, author = {Zhang, Aiping and Ren, Wenqi and Liu, Yi and Cao, Xiaochun}, title = {Lightweight Image Super-Resolution with Superpixel Token Interaction}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {12728-12737} }
Feature Prediction Diffusion Model for Video Anomaly Detection: Cheng Yan,

Shiyu Zhang,

Yang Liu,

Guansong Pang,

Wenjun Wang; [pdf]
[bibtex]
@InProceedings{Yan_2023_ICCV, author = {Yan, Cheng and Zhang, Shiyu and Liu, Yang and Pang, Guansong and Wang, Wenjun}, title = {Feature Prediction Diffusion Model for Video Anomaly Detection}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {5527-5537} }
RANA: Relightable Articulated Neural Avatars: Umar Iqbal,

Akin Caliskan,

Koki Nagano,

Sameh Khamis,

Pavlo Molchanov,

Jan Kautz; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Iqbal_2023_ICCV, author = {Iqbal, Umar and Caliskan, Akin and Nagano, Koki and Khamis, Sameh and Molchanov, Pavlo and Kautz, Jan}, title = {RANA: Relightable Articulated Neural Avatars}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {23142-23153} }
Iterative Denoiser and Noise Estimator for Self-Supervised Image Denoising: Yunhao Zou,

Chenggang Yan,

Ying Fu; [pdf]
[bibtex]
@InProceedings{Zou_2023_ICCV, author = {Zou, Yunhao and Yan, Chenggang and Fu, Ying}, title = {Iterative Denoiser and Noise Estimator for Self-Supervised Image Denoising}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {13265-13274} }
MasQCLIP for Open-Vocabulary Universal Image Segmentation: Xin Xu,

Tianyi Xiong,

Zheng Ding,

Zhuowen Tu; [pdf]
[bibtex]
@InProceedings{Xu_2023_ICCV, author = {Xu, Xin and Xiong, Tianyi and Ding, Zheng and Tu, Zhuowen}, title = {MasQCLIP for Open-Vocabulary Universal Image Segmentation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {887-898} }
Memory-and-Anticipation Transformer for Online Action Understanding: Jiahao Wang,

Guo Chen,

Yifei Huang,

Limin Wang,

Tong Lu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2023_ICCV, author = {Wang, Jiahao and Chen, Guo and Huang, Yifei and Wang, Limin and Lu, Tong}, title = {Memory-and-Anticipation Transformer for Online Action Understanding}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {13824-13835} }
Self-similarity Driven Scale-invariant Learning for Weakly Supervised Person Search: Benzhi Wang,

Yang Yang,

Jinlin Wu,

Guo-jun Qi,

Zhen Lei; [pdf] [arXiv]
[bibtex]
@InProceedings{Wang_2023_ICCV, author = {Wang, Benzhi and Yang, Yang and Wu, Jinlin and Qi, Guo-jun and Lei, Zhen}, title = {Self-similarity Driven Scale-invariant Learning for Weakly Supervised Person Search}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {1813-1822} }
MODA: Mapping-Once Audio-driven Portrait Animation with Dual Attentions: Yunfei Liu,

Lijian Lin,

Fei Yu,

Changyin Zhou,

Yu Li; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Liu_2023_ICCV, author = {Liu, Yunfei and Lin, Lijian and Yu, Fei and Zhou, Changyin and Li, Yu}, title = {MODA: Mapping-Once Audio-driven Portrait Animation with Dual Attentions}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {23020-23029} }
Realistic Full-Body Tracking from Sparse Observations via Joint-Level Modeling: Xiaozheng Zheng,

Zhuo Su,

Chao Wen,

Zhou Xue,

Xiaojie Jin; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zheng_2023_ICCV, author = {Zheng, Xiaozheng and Su, Zhuo and Wen, Chao and Xue, Zhou and Jin, Xiaojie}, title = {Realistic Full-Body Tracking from Sparse Observations via Joint-Level Modeling}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {14678-14688} }
MetaF2N: Blind Image Super-Resolution by Learning Efficient Model Adaptation from Faces: Zhicun Yin,

Ming Liu,

Xiaoming Li,

Hui Yang,

Longan Xiao,

Wangmeng Zuo; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yin_2023_ICCV, author = {Yin, Zhicun and Liu, Ming and Li, Xiaoming and Yang, Hui and Xiao, Longan and Zuo, Wangmeng}, title = {MetaF2N: Blind Image Super-Resolution by Learning Efficient Model Adaptation from Faces}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {13033-13044} }
Lighting up NeRF via Unsupervised Decomposition and Enhancement: Haoyuan Wang,

Xiaogang Xu,

Ke Xu,

Rynson W.H. Lau; [pdf] [arXiv]
[bibtex]
@InProceedings{Wang_2023_ICCV, author = {Wang, Haoyuan and Xu, Xiaogang and Xu, Ke and Lau, Rynson W.H.}, title = {Lighting up NeRF via Unsupervised Decomposition and Enhancement}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {12632-12641} }
ViM: Vision Middleware for Unified Downstream Transferring: Yutong Feng,

Biao Gong,

Jianwen Jiang,

Yiliang Lv,

Yujun Shen,

Deli Zhao,

Jingren Zhou; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Feng_2023_ICCV, author = {Feng, Yutong and Gong, Biao and Jiang, Jianwen and Lv, Yiliang and Shen, Yujun and Zhao, Deli and Zhou, Jingren}, title = {ViM: Vision Middleware for Unified Downstream Transferring}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {11696-11707} }
DIRE for Diffusion-Generated Image Detection: Zhendong Wang,

Jianmin Bao,

Wengang Zhou,

Weilun Wang,

Hezhen Hu,

Hong Chen,

Houqiang Li; [pdf] [arXiv]
[bibtex]
@InProceedings{Wang_2023_ICCV, author = {Wang, Zhendong and Bao, Jianmin and Zhou, Wengang and Wang, Weilun and Hu, Hezhen and Chen, Hong and Li, Houqiang}, title = {DIRE for Diffusion-Generated Image Detection}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {22445-22455} }
Ord2Seq: Regarding Ordinal Regression as Label Sequence Prediction: Jinhong Wang,

Yi Cheng,

Jintai Chen,

TingTing Chen,

Danny Chen,

Jian Wu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2023_ICCV, author = {Wang, Jinhong and Cheng, Yi and Chen, Jintai and Chen, TingTing and Chen, Danny and Wu, Jian}, title = {Ord2Seq: Regarding Ordinal Regression as Label Sequence Prediction}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {5865-5875} }
Bring Clipart to Life: Nanxuan Zhao,

Shengqi Dang,

Hexun Lin,

Yang Shi,

Nan Cao; [pdf] [supp]
[bibtex]
@InProceedings{Zhao_2023_ICCV, author = {Zhao, Nanxuan and Dang, Shengqi and Lin, Hexun and Shi, Yang and Cao, Nan}, title = {Bring Clipart to Life}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {23341-23350} }
Co-Evolution of Pose and Mesh for 3D Human Body Estimation from Video: Yingxuan You,

Hong Liu,

Ti Wang,

Wenhao Li,

Runwei Ding,

Xia Li; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{You_2023_ICCV, author = {You, Yingxuan and Liu, Hong and Wang, Ti and Li, Wenhao and Ding, Runwei and Li, Xia}, title = {Co-Evolution of Pose and Mesh for 3D Human Body Estimation from Video}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {14963-14973} }
Noise2Info: Noisy Image to Information of Noise for Self-Supervised Image Denoising: Jiachuan Wang,

Shimin Di,

Lei Chen,

Charles Wang Wai Ng; [pdf] [supp]
[bibtex]
@InProceedings{Wang_2023_ICCV, author = {Wang, Jiachuan and Di, Shimin and Chen, Lei and Ng, Charles Wang Wai}, title = {Noise2Info: Noisy Image to Information of Noise for Self-Supervised Image Denoising}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {16034-16043} }
Controllable Visual-Tactile Synthesis: Ruihan Gao,

Wenzhen Yuan,

Jun-Yan Zhu; [pdf] [arXiv]
[bibtex]
@InProceedings{Gao_2023_ICCV, author = {Gao, Ruihan and Yuan, Wenzhen and Zhu, Jun-Yan}, title = {Controllable Visual-Tactile Synthesis}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {7040-7052} }
Keep It SimPool: Who Said Supervised Transformers Suffer from Attention Deficit?: Bill Psomas,

Ioannis Kakogeorgiou,

Konstantinos Karantzalos,

Yannis Avrithis; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Psomas_2023_ICCV, author = {Psomas, Bill and Kakogeorgiou, Ioannis and Karantzalos, Konstantinos and Avrithis, Yannis}, title = {Keep It SimPool: Who Said Supervised Transformers Suffer from Attention Deficit?}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {5350-5360} }
SynBody: Synthetic Dataset with Layered Human Models for 3D Human Perception and Modeling: Zhitao Yang,

Zhongang Cai,

Haiyi Mei,

Shuai Liu,

Zhaoxi Chen,

Weiye Xiao,

Yukun Wei,

Zhongfei Qing,

Chen Wei,

Bo Dai,

Wayne Wu,

Chen Qian,

Dahua Lin,

Ziwei Liu,

Lei Yang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yang_2023_ICCV, author = {Yang, Zhitao and Cai, Zhongang and Mei, Haiyi and Liu, Shuai and Chen, Zhaoxi and Xiao, Weiye and Wei, Yukun and Qing, Zhongfei and Wei, Chen and Dai, Bo and Wu, Wayne and Qian, Chen and Lin, Dahua and Liu, Ziwei and Yang, Lei}, title = {SynBody: Synthetic Dataset with Layered Human Models for 3D Human Perception and Modeling}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {20282-20292} }
Viewset Diffusion: (0-)Image-Conditioned 3D Generative Models from 2D Data: Stanislaw Szymanowicz,

Christian Rupprecht,

Andrea Vedaldi; [pdf] [supp]
[bibtex]
@InProceedings{Szymanowicz_2023_ICCV, author = {Szymanowicz, Stanislaw and Rupprecht, Christian and Vedaldi, Andrea}, title = {Viewset Diffusion: (0-)Image-Conditioned 3D Generative Models from 2D Data}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {8863-8873} }
LoGoPrompt: Synthetic Text Images Can Be Good Visual Prompts for Vision-Language Models: Cheng Shi,

Sibei Yang; [pdf] [arXiv]
[bibtex]
@InProceedings{Shi_2023_ICCV, author = {Shi, Cheng and Yang, Sibei}, title = {LoGoPrompt: Synthetic Text Images Can Be Good Visual Prompts for Vision-Language Models}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {2932-2941} }
EP2P-Loc: End-to-End 3D Point to 2D Pixel Localization for Large-Scale Visual Localization: Minjung Kim,

Junseo Koo,

Gunhee Kim; [pdf] [supp]
[bibtex]
@InProceedings{Kim_2023_ICCV, author = {Kim, Minjung and Koo, Junseo and Kim, Gunhee}, title = {EP2P-Loc: End-to-End 3D Point to 2D Pixel Localization for Large-Scale Visual Localization}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {21527-21537} }
SIRA-PCR: Sim-to-Real Adaptation for 3D Point Cloud Registration: Suyi Chen,

Hao Xu,

Ru Li,

Guanghui Liu,

Chi-Wing Fu,

Shuaicheng Liu; [pdf] [supp]
[bibtex]
@InProceedings{Chen_2023_ICCV, author = {Chen, Suyi and Xu, Hao and Li, Ru and Liu, Guanghui and Fu, Chi-Wing and Liu, Shuaicheng}, title = {SIRA-PCR: Sim-to-Real Adaptation for 3D Point Cloud Registration}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {14394-14405} }
FeatEnHancer: Enhancing Hierarchical Features for Object Detection and Beyond Under Low-Light Vision: Khurram Azeem Hashmi,

Goutham Kallempudi,

Didier Stricker,

Muhammad Zeshan Afzal; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Hashmi_2023_ICCV, author = {Hashmi, Khurram Azeem and Kallempudi, Goutham and Stricker, Didier and Afzal, Muhammad Zeshan}, title = {FeatEnHancer: Enhancing Hierarchical Features for Object Detection and Beyond Under Low-Light Vision}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {6725-6735} }
SOAR: Scene-debiasing Open-set Action Recognition: Yuanhao Zhai,

Ziyi Liu,

Zhenyu Wu,

Yi Wu,

Chunluan Zhou,

David Doermann,

Junsong Yuan,

Gang Hua; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhai_2023_ICCV, author = {Zhai, Yuanhao and Liu, Ziyi and Wu, Zhenyu and Wu, Yi and Zhou, Chunluan and Doermann, David and Yuan, Junsong and Hua, Gang}, title = {SOAR: Scene-debiasing Open-set Action Recognition}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {10244-10254} }
Physics-Augmented Autoencoder for 3D Skeleton-Based Gait Recognition: Hongji Guo,

Qiang Ji; [pdf] [supp]
[bibtex]
@InProceedings{Guo_2023_ICCV, author = {Guo, Hongji and Ji, Qiang}, title = {Physics-Augmented Autoencoder for 3D Skeleton-Based Gait Recognition}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {19627-19638} }
Regularized Primitive Graph Learning for Unified Vector Mapping: Lei Wang,

Min Dai,

Jianan He,

Jingwei Huang; [pdf] [supp]
[bibtex]
@InProceedings{Wang_2023_ICCV, author = {Wang, Lei and Dai, Min and He, Jianan and Huang, Jingwei}, title = {Regularized Primitive Graph Learning for Unified Vector Mapping}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {16817-16826} }
Saliency Regularization for Self-Training with Partial Annotations: Shouwen Wang,

Qian Wan,

Xiang Xiang,

Zhigang Zeng; [pdf] [supp]
[bibtex]
@InProceedings{Wang_2023_ICCV, author = {Wang, Shouwen and Wan, Qian and Xiang, Xiang and Zeng, Zhigang}, title = {Saliency Regularization for Self-Training with Partial Annotations}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {1611-1620} }
Stabilizing Visual Reinforcement Learning via Asymmetric Interactive Cooperation: Yunpeng Zhai,

Peixi Peng,

Yifan Zhao,

Yangru Huang,

Yonghong Tian; [pdf]
[bibtex]
@InProceedings{Zhai_2023_ICCV, author = {Zhai, Yunpeng and Peng, Peixi and Zhao, Yifan and Huang, Yangru and Tian, Yonghong}, title = {Stabilizing Visual Reinforcement Learning via Asymmetric Interactive Cooperation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {207-216} }
FlipNeRF: Flipped Reflection Rays for Few-shot Novel View Synthesis: Seunghyeon Seo,

Yeonjin Chang,

Nojun Kwak; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Seo_2023_ICCV, author = {Seo, Seunghyeon and Chang, Yeonjin and Kwak, Nojun}, title = {FlipNeRF: Flipped Reflection Rays for Few-shot Novel View Synthesis}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {22883-22893} }
Discovering Spatio-Temporal Rationales for Video Question Answering: Yicong Li,

Junbin Xiao,

Chun Feng,

Xiang Wang,

Tat-Seng Chua; [pdf] [arXiv]
[bibtex]
@InProceedings{Li_2023_ICCV, author = {Li, Yicong and Xiao, Junbin and Feng, Chun and Wang, Xiang and Chua, Tat-Seng}, title = {Discovering Spatio-Temporal Rationales for Video Question Answering}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {13869-13878} }
Iterative Soft Shrinkage Learning for Efficient Image Super-Resolution: Jiamian Wang,

Huan Wang,

Yulun Zhang,

Yun Fu,

Zhiqiang Tao; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2023_ICCV, author = {Wang, Jiamian and Wang, Huan and Zhang, Yulun and Fu, Yun and Tao, Zhiqiang}, title = {Iterative Soft Shrinkage Learning for Efficient Image Super-Resolution}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {12590-12599} }
Learning Hierarchical Features with Joint Latent Space Energy-Based Prior: Jiali Cui,

Ying Nian Wu,

Tian Han; [pdf] [supp]
[bibtex]
@InProceedings{Cui_2023_ICCV, author = {Cui, Jiali and Wu, Ying Nian and Han, Tian}, title = {Learning Hierarchical Features with Joint Latent Space Energy-Based Prior}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {2218-2227} }
UniFormerV2: Unlocking the Potential of Image ViTs for Video Understanding: Kunchang Li,

Yali Wang,

Yinan He,

Yizhuo Li,

Yi Wang,

Limin Wang,

Yu Qiao; [pdf] [supp]
[bibtex]
@InProceedings{Li_2023_ICCV, author = {Li, Kunchang and Wang, Yali and He, Yinan and Li, Yizhuo and Wang, Yi and Wang, Limin and Qiao, Yu}, title = {UniFormerV2: Unlocking the Potential of Image ViTs for Video Understanding}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {1632-1643} }
G2L: Semantically Aligned and Uniform Video Grounding via Geodesic and Game Theory: Hongxiang Li,

Meng Cao,

Xuxin Cheng,

Yaowei Li,

Zhihong Zhu,

Yuexian Zou; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Li_2023_ICCV, author = {Li, Hongxiang and Cao, Meng and Cheng, Xuxin and Li, Yaowei and Zhu, Zhihong and Zou, Yuexian}, title = {G2L: Semantically Aligned and Uniform Video Grounding via Geodesic and Game Theory}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {12032-12042} }
TARGET: Federated Class-Continual Learning via Exemplar-Free Distillation: Jie Zhang,

Chen Chen,

Weiming Zhuang,

Lingjuan Lyu; [pdf] [arXiv]
[bibtex]
@InProceedings{Zhang_2023_ICCV, author = {Zhang, Jie and Chen, Chen and Zhuang, Weiming and Lyu, Lingjuan}, title = {TARGET: Federated Class-Continual Learning via Exemplar-Free Distillation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {4782-4793} }
FashionNTM: Multi-turn Fashion Image Retrieval via Cascaded Memory: Anwesan Pal,

Sahil Wadhwa,

Ayush Jaiswal,

Xu Zhang,

Yue Wu,

Rakesh Chada,

Pradeep Natarajan,

Henrik I. Christensen; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Pal_2023_ICCV, author = {Pal, Anwesan and Wadhwa, Sahil and Jaiswal, Ayush and Zhang, Xu and Wu, Yue and Chada, Rakesh and Natarajan, Pradeep and Christensen, Henrik I.}, title = {FashionNTM: Multi-turn Fashion Image Retrieval via Cascaded Memory}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {11323-11334} }
MolGrapher: Graph-based Visual Recognition of Chemical Structures: Lucas Morin,

Martin Danelljan,

Maria Isabel Agea,

Ahmed Nassar,

Valery Weber,

Ingmar Meijer,

Peter Staar,

Fisher Yu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Morin_2023_ICCV, author = {Morin, Lucas and Danelljan, Martin and Agea, Maria Isabel and Nassar, Ahmed and Weber, Valery and Meijer, Ingmar and Staar, Peter and Yu, Fisher}, title = {MolGrapher: Graph-based Visual Recognition of Chemical Structures}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {19552-19561} }
SAMPLING: Scene-adaptive Hierarchical Multiplane Images Representation for Novel View Synthesis from a Single Image: Xiaoyu Zhou,

Zhiwei Lin,

Xiaojun Shan,

Yongtao Wang,

Deqing Sun,

Ming-Hsuan Yang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhou_2023_ICCV, author = {Zhou, Xiaoyu and Lin, Zhiwei and Shan, Xiaojun and Wang, Yongtao and Sun, Deqing and Yang, Ming-Hsuan}, title = {SAMPLING: Scene-adaptive Hierarchical Multiplane Images Representation for Novel View Synthesis from a Single Image}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {22830-22840} }
DiffV2S: Diffusion-Based Video-to-Speech Synthesis with Vision-Guided Speaker Embedding: Jeongsoo Choi,

Joanna Hong,

Yong Man Ro; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Choi_2023_ICCV, author = {Choi, Jeongsoo and Hong, Joanna and Ro, Yong Man}, title = {DiffV2S: Diffusion-Based Video-to-Speech Synthesis with Vision-Guided Speaker Embedding}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {7812-7821} }
PointOdyssey: A Large-Scale Synthetic Dataset for Long-Term Point Tracking: Yang Zheng,

Adam W. Harley,

Bokui Shen,

Gordon Wetzstein,

Leonidas J. Guibas; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zheng_2023_ICCV, author = {Zheng, Yang and Harley, Adam W. and Shen, Bokui and Wetzstein, Gordon and Guibas, Leonidas J.}, title = {PointOdyssey: A Large-Scale Synthetic Dataset for Long-Term Point Tracking}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {19855-19865} }
The Effectiveness of MAE Pre-Pretraining for Billion-Scale Pretraining: Mannat Singh,

Quentin Duval,

Kalyan Vasudev Alwala,

Haoqi Fan,

Vaibhav Aggarwal,

Aaron Adcock,

Armand Joulin,

Piotr Dollar,

Christoph Feichtenhofer,

Ross Girshick,

Rohit Girdhar,

Ishan Misra; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Singh_2023_ICCV, author = {Singh, Mannat and Duval, Quentin and Alwala, Kalyan Vasudev and Fan, Haoqi and Aggarwal, Vaibhav and Adcock, Aaron and Joulin, Armand and Dollar, Piotr and Feichtenhofer, Christoph and Girshick, Ross and Girdhar, Rohit and Misra, Ishan}, title = {The Effectiveness of MAE Pre-Pretraining for Billion-Scale Pretraining}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {5484-5494} }
Towards Zero Domain Gap: A Comprehensive Study of Realistic LiDAR Simulation for Autonomy Testing: Sivabalan Manivasagam,

Ioan Andrei Bârsan,

Jingkang Wang,

Ze Yang,

Raquel Urtasun; [pdf] [supp]
[bibtex]
@InProceedings{Manivasagam_2023_ICCV, author = {Manivasagam, Sivabalan and B\^arsan, Ioan Andrei and Wang, Jingkang and Yang, Ze and Urtasun, Raquel}, title = {Towards Zero Domain Gap: A Comprehensive Study of Realistic LiDAR Simulation for Autonomy Testing}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {8272-8282} }
GPA-3D: Geometry-aware Prototype Alignment for Unsupervised Domain Adaptive 3D Object Detection from Point Clouds: Ziyu Li,

Jingming Guo,

Tongtong Cao,

Liu Bingbing,

Wankou Yang; [pdf] [supp]
[bibtex]
@InProceedings{Li_2023_ICCV, author = {Li, Ziyu and Guo, Jingming and Cao, Tongtong and Bingbing, Liu and Yang, Wankou}, title = {GPA-3D: Geometry-aware Prototype Alignment for Unsupervised Domain Adaptive 3D Object Detection from Point Clouds}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {6394-6403} }
TransHuman: A Transformer-based Human Representation for Generalizable Neural Human Rendering: Xiao Pan,

Zongxin Yang,

Jianxin Ma,

Chang Zhou,

Yi Yang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Pan_2023_ICCV, author = {Pan, Xiao and Yang, Zongxin and Ma, Jianxin and Zhou, Chang and Yang, Yi}, title = {TransHuman: A Transformer-based Human Representation for Generalizable Neural Human Rendering}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {3544-3555} }
LNPL-MIL: Learning from Noisy Pseudo Labels for Promoting Multiple Instance Learning in Whole Slide Image: Zhuchen Shao,

Yifeng Wang,

Yang Chen,

Hao Bian,

Shaohui Liu,

Haoqian Wang,

Yongbing Zhang; [pdf] [supp]
[bibtex]
@InProceedings{Shao_2023_ICCV, author = {Shao, Zhuchen and Wang, Yifeng and Chen, Yang and Bian, Hao and Liu, Shaohui and Wang, Haoqian and Zhang, Yongbing}, title = {LNPL-MIL: Learning from Noisy Pseudo Labels for Promoting Multiple Instance Learning in Whole Slide Image}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {21495-21505} }
Few-Shot Dataset Distillation via Translative Pre-Training: Songhua Liu,

Xinchao Wang; [pdf] [supp]
[bibtex]
@InProceedings{Liu_2023_ICCV, author = {Liu, Songhua and Wang, Xinchao}, title = {Few-Shot Dataset Distillation via Translative Pre-Training}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {18654-18664} }
Random Sub-Samples Generation for Self-Supervised Real Image Denoising: Yizhong Pan,

Xiao Liu,

Xiangyu Liao,

Yuanzhouhan Cao,

Chao Ren; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Pan_2023_ICCV, author = {Pan, Yizhong and Liu, Xiao and Liao, Xiangyu and Cao, Yuanzhouhan and Ren, Chao}, title = {Random Sub-Samples Generation for Self-Supervised Real Image Denoising}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {12150-12159} }
Waffling Around for Performance: Visual Classification with Random Words and Broad Concepts: Karsten Roth,

Jae Myung Kim,

A. Sophia Koepke,

Oriol Vinyals,

Cordelia Schmid,

Zeynep Akata; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Roth_2023_ICCV, author = {Roth, Karsten and Kim, Jae Myung and Koepke, A. Sophia and Vinyals, Oriol and Schmid, Cordelia and Akata, Zeynep}, title = {Waffling Around for Performance: Visual Classification with Random Words and Broad Concepts}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {15746-15757} }
Unsupervised Surface Anomaly Detection with Diffusion Probabilistic Model: Xinyi Zhang,

Naiqi Li,

Jiawei Li,

Tao Dai,

Yong Jiang,

Shu-Tao Xia; [pdf] [supp]
[bibtex]
@InProceedings{Zhang_2023_ICCV, author = {Zhang, Xinyi and Li, Naiqi and Li, Jiawei and Dai, Tao and Jiang, Yong and Xia, Shu-Tao}, title = {Unsupervised Surface Anomaly Detection with Diffusion Probabilistic Model}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {6782-6791} }
AutoAD II: The Sequel - Who, When, and What in Movie Audio Description: Tengda Han,

Max Bain,

Arsha Nagrani,

Gul Varol,

Weidi Xie,

Andrew Zisserman; [pdf] [supp]
[bibtex]
@InProceedings{Han_2023_ICCV, author = {Han, Tengda and Bain, Max and Nagrani, Arsha and Varol, Gul and Xie, Weidi and Zisserman, Andrew}, title = {AutoAD II: The Sequel - Who, When, and What in Movie Audio Description}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {13645-13655} }
TinyCLIP: CLIP Distillation via Affinity Mimicking and Weight Inheritance: Kan Wu,

Houwen Peng,

Zhenghong Zhou,

Bin Xiao,