ICCV 2023 Open Access Repository

Papers

Back
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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 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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
Hyperbolic Chamfer Distance for Point Cloud Completion: Fangzhou Lin,

Yun Yue,

Songlin Hou,

Xuechu Yu,

Yajun Xu,

Kazunori D Yamada,

Ziming Zhang; [pdf]
[bibtex]
@InProceedings{Lin_2023_ICCV, author = {Lin, Fangzhou and Yue, Yun and Hou, Songlin and Yu, Xuechu and Xu, Yajun and Yamada, Kazunori D and Zhang, Ziming}, title = {Hyperbolic Chamfer Distance for Point Cloud Completion}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {14595-14606} }
AG3D: Learning to Generate 3D Avatars from 2D Image Collections: Zijian Dong,

Xu Chen,

Jinlong Yang,

Michael J. Black,

Otmar Hilliges,

Andreas Geiger; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Dong_2023_ICCV, author = {Dong, Zijian and Chen, Xu and Yang, Jinlong and Black, Michael J. and Hilliges, Otmar and Geiger, Andreas}, title = {AG3D: Learning to Generate 3D Avatars from 2D Image Collections}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {14916-14927} }
Learned Image Reasoning Prior Penetrates Deep Unfolding Network for Panchromatic and Multi-spectral Image Fusion: Man Zhou,

Jie Huang,

Naishan Zheng,

Chongyi Li; [pdf] [arXiv]
[bibtex]
@InProceedings{Zhou_2023_ICCV, author = {Zhou, Man and Huang, Jie and Zheng, Naishan and Li, Chongyi}, title = {Learned Image Reasoning Prior Penetrates Deep Unfolding Network for Panchromatic and Multi-spectral Image Fusion}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {12398-12407} }
NCHO: Unsupervised Learning for Neural 3D Composition of Humans and Objects: Taeksoo Kim,

Shunsuke Saito,

Hanbyul Joo; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kim_2023_ICCV, author = {Kim, Taeksoo and Saito, Shunsuke and Joo, Hanbyul}, title = {NCHO: Unsupervised Learning for Neural 3D Composition of Humans and Objects}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {14817-14828} }
Learning Non-Local Spatial-Angular Correlation for Light Field Image Super-Resolution: Zhengyu Liang,

Yingqian Wang,

Longguang Wang,

Jungang Yang,

Shilin Zhou,

Yulan Guo; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Liang_2023_ICCV, author = {Liang, Zhengyu and Wang, Yingqian and Wang, Longguang and Yang, Jungang and Zhou, Shilin and Guo, Yulan}, title = {Learning Non-Local Spatial-Angular Correlation for Light Field Image Super-Resolution}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {12376-12386} }
MGMAE: Motion Guided Masking for Video Masked Autoencoding: Bingkun Huang,

Zhiyu Zhao,

Guozhen Zhang,

Yu Qiao,

Limin Wang; [pdf] [arXiv]
[bibtex]
@InProceedings{Huang_2023_ICCV, author = {Huang, Bingkun and Zhao, Zhiyu and Zhang, Guozhen and Qiao, Yu and Wang, Limin}, title = {MGMAE: Motion Guided Masking for Video Masked Autoencoding}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {13493-13504} }
ViewRefer: Grasp the Multi-view Knowledge for 3D Visual Grounding: Zoey Guo,

Yiwen Tang,

Ray Zhang,

Dong Wang,

Zhigang Wang,

Bin Zhao,

Xuelong Li; [pdf] [arXiv]
[bibtex]
@InProceedings{Guo_2023_ICCV, author = {Guo, Zoey and Tang, Yiwen and Zhang, Ray and Wang, Dong and Wang, Zhigang and Zhao, Bin and Li, Xuelong}, title = {ViewRefer: Grasp the Multi-view Knowledge for 3D Visual Grounding}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {15372-15383} }
CaPhy: Capturing Physical Properties for Animatable Human Avatars: Zhaoqi Su,

Liangxiao Hu,

Siyou Lin,

Hongwen Zhang,

Shengping Zhang,

Justus Thies,

Yebin Liu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Su_2023_ICCV, author = {Su, Zhaoqi and Hu, Liangxiao and Lin, Siyou and Zhang, Hongwen and Zhang, Shengping and Thies, Justus and Liu, Yebin}, title = {CaPhy: Capturing Physical Properties for Animatable Human Avatars}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {14150-14160} }
Fine-grained Unsupervised Domain Adaptation for Gait Recognition: Kang Ma,

Ying Fu,

Dezhi Zheng,

Yunjie Peng,

Chunshui Cao,

Yongzhen Huang; [pdf]
[bibtex]
@InProceedings{Ma_2023_ICCV, author = {Ma, Kang and Fu, Ying and Zheng, Dezhi and Peng, Yunjie and Cao, Chunshui and Huang, Yongzhen}, title = {Fine-grained Unsupervised Domain Adaptation for Gait Recognition}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {11313-11322} }
Instance-aware Dynamic Prompt Tuning for Pre-trained Point Cloud Models: Yaohua Zha,

Jinpeng Wang,

Tao Dai,

Bin Chen,

Zhi Wang,

Shu-Tao Xia; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zha_2023_ICCV, author = {Zha, Yaohua and Wang, Jinpeng and Dai, Tao and Chen, Bin and Wang, Zhi and Xia, Shu-Tao}, title = {Instance-aware Dynamic Prompt Tuning for Pre-trained Point Cloud Models}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {14161-14170} }
GeoUDF: Surface Reconstruction from 3D Point Clouds via Geometry-guided Distance Representation: Siyu Ren,

Junhui Hou,

Xiaodong Chen,

Ying He,

Wenping Wang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ren_2023_ICCV, author = {Ren, Siyu and Hou, Junhui and Chen, Xiaodong and He, Ying and Wang, Wenping}, title = {GeoUDF: Surface Reconstruction from 3D Point Clouds via Geometry-guided Distance Representation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {14214-14224} }
MeMOTR: Long-Term Memory-Augmented Transformer for Multi-Object Tracking: Ruopeng Gao,

Limin Wang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Gao_2023_ICCV, author = {Gao, Ruopeng and Wang, Limin}, title = {MeMOTR: Long-Term Memory-Augmented Transformer for Multi-Object Tracking}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {9901-9910} }
RawHDR: High Dynamic Range Image Reconstruction from a Single Raw Image: Yunhao Zou,

Chenggang Yan,

Ying Fu; [pdf] [arXiv]
[bibtex]
@InProceedings{Zou_2023_ICCV, author = {Zou, Yunhao and Yan, Chenggang and Fu, Ying}, title = {RawHDR: High Dynamic Range Image Reconstruction from a Single Raw Image}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {12334-12344} }
Robust Object Modeling for Visual Tracking: Yidong Cai,

Jie Liu,

Jie Tang,

Gangshan Wu; [pdf] [arXiv]
[bibtex]
@InProceedings{Cai_2023_ICCV, author = {Cai, Yidong and Liu, Jie and Tang, Jie and Wu, Gangshan}, title = {Robust Object Modeling for Visual Tracking}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {9589-9600} }
FSI: Frequency and Spatial Interactive Learning for Image Restoration in Under-Display Cameras: Chengxu Liu,

Xuan Wang,

Shuai Li,

Yuzhi Wang,

Xueming Qian; [pdf] [supp]
[bibtex]
@InProceedings{Liu_2023_ICCV, author = {Liu, Chengxu and Wang, Xuan and Li, Shuai and Wang, Yuzhi and Qian, Xueming}, title = {FSI: Frequency and Spatial Interactive Learning for Image Restoration in Under-Display Cameras}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {12537-12546} }
Temporal Collection and Distribution for Referring Video Object Segmentation: Jiajin Tang,

Ge Zheng,

Sibei Yang; [pdf] [arXiv]
[bibtex]
@InProceedings{Tang_2023_ICCV, author = {Tang, Jiajin and Zheng, Ge and Yang, Sibei}, title = {Temporal Collection and Distribution for Referring Video Object Segmentation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {15466-15476} }
Variational Degeneration to Structural Refinement: A Unified Framework for Superimposed Image Decomposition: Wenyu Li,

Yan Xu,

Yang Yang,

Haoran Ji,

Yue Lang; [pdf]
[bibtex]
@InProceedings{Li_2023_ICCV, author = {Li, Wenyu and Xu, Yan and Yang, Yang and Ji, Haoran and Lang, Yue}, title = {Variational Degeneration to Structural Refinement: A Unified Framework for Superimposed Image Decomposition}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {12206-12216} }
Focal Network for Image Restoration: Yuning Cui,

Wenqi Ren,

Xiaochun Cao,

Alois Knoll; [pdf] [supp]
[bibtex]
@InProceedings{Cui_2023_ICCV, author = {Cui, Yuning and Ren, Wenqi and Cao, Xiaochun and Knoll, Alois}, title = {Focal Network for Image Restoration}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {13001-13011} }
Indoor Depth Recovery Based on Deep Unfolding with Non-Local Prior: Yuhui Dai,

Junkang Zhang,

Faming Fang,

Guixu Zhang; [pdf]
[bibtex]
@InProceedings{Dai_2023_ICCV, author = {Dai, Yuhui and Zhang, Junkang and Fang, Faming and Zhang, Guixu}, title = {Indoor Depth Recovery Based on Deep Unfolding with Non-Local Prior}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {12355-12364} }
GAFlow: Incorporating Gaussian Attention into Optical Flow: Ao Luo,

Fan Yang,

Xin Li,

Lang Nie,

Chunyu Lin,

Haoqiang Fan,

Shuaicheng Liu; [pdf]
[bibtex]
@InProceedings{Luo_2023_ICCV, author = {Luo, Ao and Yang, Fan and Li, Xin and Nie, Lang and Lin, Chunyu and Fan, Haoqiang and Liu, Shuaicheng}, title = {GAFlow: Incorporating Gaussian Attention into Optical Flow}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {9642-9651} }
SoDaCam: Software-defined Cameras via Single-Photon Imaging: Varun Sundar,

Andrei Ardelean,

Tristan Swedish,

Claudio Bruschini,

Edoardo Charbon,

Mohit Gupta; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Sundar_2023_ICCV, author = {Sundar, Varun and Ardelean, Andrei and Swedish, Tristan and Bruschini, Claudio and Charbon, Edoardo and Gupta, Mohit}, title = {SoDaCam: Software-defined Cameras via Single-Photon Imaging}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {8165-8176} }
Decoupled Iterative Refinement Framework for Interacting Hands Reconstruction from a Single RGB Image: Pengfei Ren,

Chao Wen,

Xiaozheng Zheng,

Zhou Xue,

Haifeng Sun,

Qi Qi,

Jingyu Wang,

Jianxin Liao; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ren_2023_ICCV, author = {Ren, Pengfei and Wen, Chao and Zheng, Xiaozheng and Xue, Zhou and Sun, Haifeng and Qi, Qi and Wang, Jingyu and Liao, Jianxin}, title = {Decoupled Iterative Refinement Framework for Interacting Hands Reconstruction from a Single RGB Image}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {8014-8025} }
Who Are You Referring To? Coreference Resolution In Image Narrations: Arushi Goel,

Basura Fernando,

Frank Keller,

Hakan Bilen; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Goel_2023_ICCV, author = {Goel, Arushi and Fernando, Basura and Keller, Frank and Bilen, Hakan}, title = {Who Are You Referring To? Coreference Resolution In Image Narrations}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {15247-15258} }
Dynamic Hyperbolic Attention Network for Fine Hand-object Reconstruction: Zhiying Leng,

Shun-Cheng Wu,

Mahdi Saleh,

Antonio Montanaro,

Hao Yu,

Yin Wang,

Nassir Navab,

Xiaohui Liang,

Federico Tombari; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Leng_2023_ICCV, author = {Leng, Zhiying and Wu, Shun-Cheng and Saleh, Mahdi and Montanaro, Antonio and Yu, Hao and Wang, Yin and Navab, Nassir and Liang, Xiaohui and Tombari, Federico}, title = {Dynamic Hyperbolic Attention Network for Fine Hand-object Reconstruction}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {14894-14904} }
LivePose: Online 3D Reconstruction from Monocular Video with Dynamic Camera Poses: Noah Stier,

Baptiste Angles,

Liang Yang,

Yajie Yan,

Alex Colburn,

Ming Chuang; [pdf] [arXiv]
[bibtex]
@InProceedings{Stier_2023_ICCV, author = {Stier, Noah and Angles, Baptiste and Yang, Liang and Yan, Yajie and Colburn, Alex and Chuang, Ming}, title = {LivePose: Online 3D Reconstruction from Monocular Video with Dynamic Camera Poses}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {7921-7930} }
Feature Modulation Transformer: Cross-Refinement of Global Representation via High-Frequency Prior for Image Super-Resolution: Ao Li,

Le Zhang,

Yun Liu,

Ce Zhu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Li_2023_ICCV, author = {Li, Ao and Zhang, Le and Liu, Yun and Zhu, Ce}, title = {Feature Modulation Transformer: Cross-Refinement of Global Representation via High-Frequency Prior for Image Super-Resolution}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {12514-12524} }
MPI-Flow: Learning Realistic Optical Flow with Multiplane Images: Yingping Liang,

Jiaming Liu,

Debing Zhang,

Ying Fu; [pdf]
[bibtex]
@InProceedings{Liang_2023_ICCV, author = {Liang, Yingping and Liu, Jiaming and Zhang, Debing and Fu, Ying}, title = {MPI-Flow: Learning Realistic Optical Flow with Multiplane Images}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {13857-13868} }
Learning Depth Estimation for Transparent and Mirror Surfaces: Alex Costanzino,

Pierluigi Zama Ramirez,

Matteo Poggi,

Fabio Tosi,

Stefano Mattoccia,

Luigi Di Stefano; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Costanzino_2023_ICCV, author = {Costanzino, Alex and Ramirez, Pierluigi Zama and Poggi, Matteo and Tosi, Fabio and Mattoccia, Stefano and Di Stefano, Luigi}, title = {Learning Depth Estimation for Transparent and Mirror Surfaces}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {9244-9255} }
Towards Zero-Shot Scale-Aware Monocular Depth Estimation: Vitor Guizilini,

Igor Vasiljevic,

Dian Chen,

Rareș Ambruș,

Adrien Gaidon; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Guizilini_2023_ICCV, author = {Guizilini, Vitor and Vasiljevic, Igor and Chen, Dian and Ambruș, Rareș and Gaidon, Adrien}, title = {Towards Zero-Shot Scale-Aware Monocular Depth Estimation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {9233-9243} }
PromptStyler: Prompt-driven Style Generation for Source-free Domain Generalization: Junhyeong Cho,

Gilhyun Nam,

Sungyeon Kim,

Hunmin Yang,

Suha Kwak; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Cho_2023_ICCV, author = {Cho, Junhyeong and Nam, Gilhyun and Kim, Sungyeon and Yang, Hunmin and Kwak, Suha}, title = {PromptStyler: Prompt-driven Style Generation for Source-free Domain Generalization}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {15702-15712} }
SVQNet: Sparse Voxel-Adjacent Query Network for 4D Spatio-Temporal LiDAR Semantic Segmentation: Xuechao Chen,

Shuangjie Xu,

Xiaoyi Zou,

Tongyi Cao,

Dit-Yan Yeung,

Lu Fang; [pdf] [arXiv]
[bibtex]
@InProceedings{Chen_2023_ICCV, author = {Chen, Xuechao and Xu, Shuangjie and Zou, Xiaoyi and Cao, Tongyi and Yeung, Dit-Yan and Fang, Lu}, title = {SVQNet: Sparse Voxel-Adjacent Query Network for 4D Spatio-Temporal LiDAR Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {8569-8578} }
MEFLUT: Unsupervised 1D Lookup Tables for Multi-exposure Image Fusion: Ting Jiang,

Chuan Wang,

Xinpeng Li,

Ru Li,

Haoqiang Fan,

Shuaicheng Liu; [pdf] [arXiv]
[bibtex]
@InProceedings{Jiang_2023_ICCV, author = {Jiang, Ting and Wang, Chuan and Li, Xinpeng and Li, Ru and Fan, Haoqiang and Liu, Shuaicheng}, title = {MEFLUT: Unsupervised 1D Lookup Tables for Multi-exposure Image Fusion}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {10542-10551} }
The Unreasonable Effectiveness of Large Language-Vision Models for Source-Free Video Domain Adaptation: Giacomo Zara,

Alessandro Conti,

Subhankar Roy,

Stéphane Lathuilière,

Paolo Rota,

Elisa Ricci; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zara_2023_ICCV, author = {Zara, Giacomo and Conti, Alessandro and Roy, Subhankar and Lathuili\`ere, St\'ephane and Rota, Paolo and Ricci, Elisa}, title = {The Unreasonable Effectiveness of Large Language-Vision Models for Source-Free Video Domain Adaptation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {10307-10317} }
Sketch and Text Guided Diffusion Model for Colored Point Cloud Generation: Zijie Wu,

Yaonan Wang,

Mingtao Feng,

He Xie,

Ajmal Mian; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wu_2023_ICCV, author = {Wu, Zijie and Wang, Yaonan and Feng, Mingtao and Xie, He and Mian, Ajmal}, title = {Sketch and Text Guided Diffusion Model for Colored Point Cloud Generation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {8929-8939} }
Leveraging SE(3) Equivariance for Learning 3D Geometric Shape Assembly: Ruihai Wu,

Chenrui Tie,

Yushi Du,

Yan Zhao,

Hao Dong; [pdf] [arXiv]
[bibtex]
@InProceedings{Wu_2023_ICCV, author = {Wu, Ruihai and Tie, Chenrui and Du, Yushi and Zhao, Yan and Dong, Hao}, title = {Leveraging SE(3) Equivariance for Learning 3D Geometric Shape Assembly}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {14311-14320} }
Adversarial Bayesian Augmentation for Single-Source Domain Generalization: Sheng Cheng,

Tejas Gokhale,

Yezhou Yang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Cheng_2023_ICCV, author = {Cheng, Sheng and Gokhale, Tejas and Yang, Yezhou}, title = {Adversarial Bayesian Augmentation for Single-Source Domain Generalization}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {11400-11410} }
Robust Geometry-Preserving Depth Estimation Using Differentiable Rendering: Chi Zhang,

Wei Yin,

Gang Yu,

Zhibin Wang,

Tao Chen,

Bin Fu,

Joey Tianyi Zhou,

Chunhua Shen; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhang_2023_ICCV, author = {Zhang, Chi and Yin, Wei and Yu, Gang and Wang, Zhibin and Chen, Tao and Fu, Bin and Zhou, Joey Tianyi and Shen, Chunhua}, title = {Robust Geometry-Preserving Depth Estimation Using Differentiable Rendering}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {8951-8961} }
Self-regulating Prompts: Foundational Model Adaptation without Forgetting: Muhammad Uzair Khattak,

Syed Talal Wasim,

Muzammal Naseer,

Salman Khan,

Ming-Hsuan Yang,

Fahad Shahbaz Khan; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Khattak_2023_ICCV, author = {Khattak, Muhammad Uzair and Wasim, Syed Talal and Naseer, Muzammal and Khan, Salman and Yang, Ming-Hsuan and Khan, Fahad Shahbaz}, title = {Self-regulating Prompts: Foundational Model Adaptation without Forgetting}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {15190-15200} }
Improving Lens Flare Removal with General-Purpose Pipeline and Multiple Light Sources Recovery: Yuyan Zhou,

Dong Liang,

Songcan Chen,

Sheng-Jun Huang,

Shuo Yang,

Chongyi Li; [pdf] [arXiv]
[bibtex]
@InProceedings{Zhou_2023_ICCV, author = {Zhou, Yuyan and Liang, Dong and Chen, Songcan and Huang, Sheng-Jun and Yang, Shuo and Li, Chongyi}, title = {Improving Lens Flare Removal with General-Purpose Pipeline and Multiple Light Sources Recovery}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {12969-12979} }
DCPB: Deformable Convolution Based on the Poincare Ball for Top-view Fisheye Cameras: Xuan Wei,

Zhidan Ran,

Xiaobo Lu; [pdf]
[bibtex]
@InProceedings{Wei_2023_ICCV, author = {Wei, Xuan and Ran, Zhidan and Lu, Xiaobo}, title = {DCPB: Deformable Convolution Based on the Poincare Ball for Top-view Fisheye Cameras}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {13308-13317} }
Integrating Boxes and Masks: A Multi-Object Framework for Unified Visual Tracking and Segmentation: Yuanyou Xu,

Zongxin Yang,

Yi Yang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Xu_2023_ICCV, author = {Xu, Yuanyou and Yang, Zongxin and Yang, Yi}, title = {Integrating Boxes and Masks: A Multi-Object Framework for Unified Visual Tracking and Segmentation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {9738-9751} }
3DMOTFormer: Graph Transformer for Online 3D Multi-Object Tracking: Shuxiao Ding,

Eike Rehder,

Lukas Schneider,

Marius Cordts,

Juergen Gall; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ding_2023_ICCV, author = {Ding, Shuxiao and Rehder, Eike and Schneider, Lukas and Cordts, Marius and Gall, Juergen}, title = {3DMOTFormer: Graph Transformer for Online 3D Multi-Object Tracking}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {9784-9794} }
ReGen: A good Generative Zero-Shot Video Classifier Should be Rewarded: Adrian Bulat,

Enrique Sanchez,

Brais Martinez,

Georgios Tzimiropoulos; [pdf] [supp]
[bibtex]
@InProceedings{Bulat_2023_ICCV, author = {Bulat, Adrian and Sanchez, Enrique and Martinez, Brais and Tzimiropoulos, Georgios}, title = {ReGen: A good Generative Zero-Shot Video Classifier Should be Rewarded}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {13523-13533} }
Complementary Domain Adaptation and Generalization for Unsupervised Continual Domain Shift Learning: Wonguk Cho,

Jinha Park,

Taesup Kim; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Cho_2023_ICCV, author = {Cho, Wonguk and Park, Jinha and Kim, Taesup}, title = {Complementary Domain Adaptation and Generalization for Unsupervised Continual Domain Shift Learning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {11442-11452} }
Ordered Atomic Activity for Fine-grained Interactive Traffic Scenario Understanding: Nakul Agarwal,

Yi-Ting Chen; [pdf] [supp]
[bibtex]
@InProceedings{Agarwal_2023_ICCV, author = {Agarwal, Nakul and Chen, Yi-Ting}, title = {Ordered Atomic Activity for Fine-grained Interactive Traffic Scenario Understanding}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {8624-8636} }
BEV-DG: Cross-Modal Learning under Bird's-Eye View for Domain Generalization of 3D Semantic Segmentation: Miaoyu Li,

Yachao Zhang,

Xu Ma,

Yanyun Qu,

Yun Fu; [pdf] [supp]
[bibtex]
@InProceedings{Li_2023_ICCV, author = {Li, Miaoyu and Zhang, Yachao and Ma, Xu and Qu, Yanyun and Fu, Yun}, title = {BEV-DG: Cross-Modal Learning under Bird's-Eye View for Domain Generalization of 3D Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {11632-11642} }
Grounded Entity-Landmark Adaptive Pre-Training for Vision-and-Language Navigation: Yibo Cui,

Liang Xie,

Yakun Zhang,

Meishan Zhang,

Ye Yan,

Erwei Yin; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Cui_2023_ICCV, author = {Cui, Yibo and Xie, Liang and Zhang, Yakun and Zhang, Meishan and Yan, Ye and Yin, Erwei}, title = {Grounded Entity-Landmark Adaptive Pre-Training for Vision-and-Language Navigation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {12043-12053} }
Lip Reading for Low-resource Languages by Learning and Combining General Speech Knowledge and Language-specific Knowledge: Minsu Kim,

Jeong Hun Yeo,

Jeongsoo Choi,

Yong Man Ro; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kim_2023_ICCV, author = {Kim, Minsu and Yeo, Jeong Hun and Choi, Jeongsoo and Ro, Yong Man}, title = {Lip Reading for Low-resource Languages by Learning and Combining General Speech Knowledge and Language-specific Knowledge}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {15359-15371} }
HopFIR: Hop-wise GraphFormer with Intragroup Joint Refinement for 3D Human Pose Estimation: Kai Zhai,

Qiang Nie,

Bo Ouyang,

Xiang Li,

Shanlin Yang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhai_2023_ICCV, author = {Zhai, Kai and Nie, Qiang and Ouyang, Bo and Li, Xiang and Yang, Shanlin}, title = {HopFIR: Hop-wise GraphFormer with Intragroup Joint Refinement for 3D Human Pose Estimation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {14985-14995} }
Minimal Solutions to Generalized Three-View Relative Pose Problem: Yaqing Ding,

Chiang-Heng Chien,

Viktor Larsson,

Karl Åström,

Benjamin Kimia; [pdf] [supp]
[bibtex]
@InProceedings{Ding_2023_ICCV, author = {Ding, Yaqing and Chien, Chiang-Heng and Larsson, Viktor and \r{A}str\"om, Karl and Kimia, Benjamin}, title = {Minimal Solutions to Generalized Three-View Relative Pose Problem}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {8156-8164} }
Trajectory Unified Transformer for Pedestrian Trajectory Prediction: Liushuai Shi,

Le Wang,

Sanping Zhou,

Gang Hua; [pdf] [supp]
[bibtex]
@InProceedings{Shi_2023_ICCV, author = {Shi, Liushuai and Wang, Le and Zhou, Sanping and Hua, Gang}, title = {Trajectory Unified Transformer for Pedestrian Trajectory Prediction}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {9675-9684} }
MHEntropy: Entropy Meets Multiple Hypotheses for Pose and Shape Recovery: Rongyu Chen,

Linlin Yang,

Angela Yao; [pdf] [supp]
[bibtex]
@InProceedings{Chen_2023_ICCV, author = {Chen, Rongyu and Yang, Linlin and Yao, Angela}, title = {MHEntropy: Entropy Meets Multiple Hypotheses for Pose and Shape Recovery}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {14840-14849} }
Modeling the Relative Visual Tempo for Self-supervised Skeleton-based Action Recognition: Yisheng Zhu,

Hu Han,

Zhengtao Yu,

Guangcan Liu; [pdf]
[bibtex]
@InProceedings{Zhu_2023_ICCV, author = {Zhu, Yisheng and Han, Hu and Yu, Zhengtao and Liu, Guangcan}, title = {Modeling the Relative Visual Tempo for Self-supervised Skeleton-based Action Recognition}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {13913-13922} }
ImbSAM: A Closer Look at Sharpness-Aware Minimization in Class-Imbalanced Recognition: Yixuan Zhou,

Yi Qu,

Xing Xu,

Hengtao Shen; [pdf] [arXiv]
[bibtex]
@InProceedings{Zhou_2023_ICCV, author = {Zhou, Yixuan and Qu, Yi and Xu, Xing and Shen, Hengtao}, title = {ImbSAM: A Closer Look at Sharpness-Aware Minimization in Class-Imbalanced Recognition}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {11345-11355} }
MonoDETR: Depth-guided Transformer for Monocular 3D Object Detection: Renrui Zhang,

Han Qiu,

Tai Wang,

Ziyu Guo,

Ziteng Cui,

Yu Qiao,

Hongsheng Li,

Peng Gao; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhang_2023_ICCV, author = {Zhang, Renrui and Qiu, Han and Wang, Tai and Guo, Ziyu and Cui, Ziteng and Qiao, Yu and Li, Hongsheng and Gao, Peng}, title = {MonoDETR: Depth-guided Transformer for Monocular 3D Object Detection}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {9155-9166} }
Contrastive Feature Masking Open-Vocabulary Vision Transformer: Dahun Kim,

Anelia Angelova,

Weicheng Kuo; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kim_2023_ICCV, author = {Kim, Dahun and Angelova, Anelia and Kuo, Weicheng}, title = {Contrastive Feature Masking Open-Vocabulary Vision Transformer}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {15602-15612} }
OccFormer: Dual-path Transformer for Vision-based 3D Semantic Occupancy Prediction: Yunpeng Zhang,

Zheng Zhu,

Dalong Du; [pdf] [arXiv]
[bibtex]
@InProceedings{Zhang_2023_ICCV, author = {Zhang, Yunpeng and Zhu, Zheng and Du, Dalong}, title = {OccFormer: Dual-path Transformer for Vision-based 3D Semantic Occupancy Prediction}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {9433-9443} }
Probabilistic Triangulation for Uncalibrated Multi-View 3D Human Pose Estimation: Boyuan Jiang,

Lei Hu,

Shihong Xia; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Jiang_2023_ICCV, author = {Jiang, Boyuan and Hu, Lei and Xia, Shihong}, title = {Probabilistic Triangulation for Uncalibrated Multi-View 3D Human Pose Estimation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {14850-14860} }
TORE: Token Reduction for Efficient Human Mesh Recovery with Transformer: Zhiyang Dou,

Qingxuan Wu,

Cheng Lin,

Zeyu Cao,

Qiangqiang Wu,

Weilin Wan,

Taku Komura,

Wenping Wang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Dou_2023_ICCV, author = {Dou, Zhiyang and Wu, Qingxuan and Lin, Cheng and Cao, Zeyu and Wu, Qiangqiang and Wan, Weilin and Komura, Taku and Wang, Wenping}, title = {TORE: Token Reduction for Efficient Human Mesh Recovery with Transformer}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {15143-15155} }
D3G: Exploring Gaussian Prior for Temporal Sentence Grounding with Glance Annotation: Hanjun Li,

Xiujun Shu,

Sunan He,

Ruizhi Qiao,

Wei Wen,

Taian Guo,

Bei Gan,

Xing Sun; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Li_2023_ICCV, author = {Li, Hanjun and Shu, Xiujun and He, Sunan and Qiao, Ruizhi and Wen, Wei and Guo, Taian and Gan, Bei and Sun, Xing}, title = {D3G: Exploring Gaussian Prior for Temporal Sentence Grounding with Glance Annotation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {13734-13746} }
GEDepth: Ground Embedding for Monocular Depth Estimation: Xiaodong Yang,

Zhuang Ma,

Zhiyu Ji,

Zhe Ren; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yang_2023_ICCV, author = {Yang, Xiaodong and Ma, Zhuang and Ji, Zhiyu and Ren, Zhe}, title = {GEDepth: Ground Embedding for Monocular Depth Estimation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {12719-12727} }
Animal3D: A Comprehensive Dataset of 3D Animal Pose and Shape: Jiacong Xu,

Yi Zhang,

Jiawei Peng,

Wufei Ma,

Artur Jesslen,

Pengliang Ji,

Qixin Hu,

Jiehua Zhang,

Qihao Liu,

Jiahao Wang,

Wei Ji,

Chen Wang,

Xiaoding Yuan,

Prakhar Kaushik,

Guofeng Zhang,

Jie Liu,

Yushan Xie,

Yawen Cui,

Alan Yuille,

Adam Kortylewski; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Xu_2023_ICCV, author = {Xu, Jiacong and Zhang, Yi and Peng, Jiawei and Ma, Wufei and Jesslen, Artur and Ji, Pengliang and Hu, Qixin and Zhang, Jiehua and Liu, Qihao and Wang, Jiahao and Ji, Wei and Wang, Chen and Yuan, Xiaoding and Kaushik, Prakhar and Zhang, Guofeng and Liu, Jie and Xie, Yushan and Cui, Yawen and Yuille, Alan and Kortylewski, Adam}, title = {Animal3D: A Comprehensive Dataset of 3D Animal Pose and Shape}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {9099-9109} }
Rethinking Video Frame Interpolation from Shutter Mode Induced Degradation: Xiang Ji,

Zhixiang Wang,

Zhihang Zhong,

Yinqiang Zheng; [pdf] [supp]
[bibtex]
@InProceedings{Ji_2023_ICCV, author = {Ji, Xiang and Wang, Zhixiang and Zhong, Zhihang and Zheng, Yinqiang}, title = {Rethinking Video Frame Interpolation from Shutter Mode Induced Degradation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {12259-12268} }
Semantic-Aware Dynamic Parameter for Video Inpainting Transformer: Eunhye Lee,

Jinsu Yoo,

Yunjeong Yang,

Sungyong Baik,

Tae Hyun Kim; [pdf] [supp]
[bibtex]
@InProceedings{Lee_2023_ICCV, author = {Lee, Eunhye and Yoo, Jinsu and Yang, Yunjeong and Baik, Sungyong and Kim, Tae Hyun}, title = {Semantic-Aware Dynamic Parameter for Video Inpainting Transformer}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {12949-12958} }
SKED: Sketch-guided Text-based 3D Editing: Aryan Mikaeili,

Or Perel,

Mehdi Safaee,

Daniel Cohen-Or,

Ali Mahdavi-Amiri; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Mikaeili_2023_ICCV, author = {Mikaeili, Aryan and Perel, Or and Safaee, Mehdi and Cohen-Or, Daniel and Mahdavi-Amiri, Ali}, title = {SKED: Sketch-guided Text-based 3D Editing}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {14607-14619} }
MBPTrack: Improving 3D Point Cloud Tracking with Memory Networks and Box Priors: Tian-Xing Xu,

Yuan-Chen Guo,

Yu-Kun Lai,

Song-Hai Zhang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Xu_2023_ICCV, author = {Xu, Tian-Xing and Guo, Yuan-Chen and Lai, Yu-Kun and Zhang, Song-Hai}, title = {MBPTrack: Improving 3D Point Cloud Tracking with Memory Networks and Box Priors}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {9911-9920} }
Novel-View Synthesis and Pose Estimation for Hand-Object Interaction from Sparse Views: Wentian Qu,

Zhaopeng Cui,

Yinda Zhang,

Chenyu Meng,

Cuixia Ma,

Xiaoming Deng,

Hongan Wang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Qu_2023_ICCV, author = {Qu, Wentian and Cui, Zhaopeng and Zhang, Yinda and Meng, Chenyu and Ma, Cuixia and Deng, Xiaoming and Wang, Hongan}, title = {Novel-View Synthesis and Pose Estimation for Hand-Object Interaction from Sparse Views}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {15100-15111} }
Distilling from Similar Tasks for Transfer Learning on a Budget: Kenneth Borup,

Cheng Perng Phoo,

Bharath Hariharan; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Borup_2023_ICCV, author = {Borup, Kenneth and Phoo, Cheng Perng and Hariharan, Bharath}, title = {Distilling from Similar Tasks for Transfer Learning on a Budget}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {11431-11441} }
Self-Supervised Burst Super-Resolution: Goutam Bhat,

Michaël Gharbi,

Jiawen Chen,

Luc Van Gool,

Zhihao Xia; [pdf] [supp]
[bibtex]
@InProceedings{Bhat_2023_ICCV, author = {Bhat, Goutam and Gharbi, Micha\"el and Chen, Jiawen and Van Gool, Luc and Xia, Zhihao}, title = {Self-Supervised Burst Super-Resolution}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {10605-10614} }
PC-Adapter: Topology-Aware Adapter for Efficient Domain Adaption on Point Clouds with Rectified Pseudo-label: Joonhyung Park,

Hyunjin Seo,

Eunho Yang; [pdf] [supp]
[bibtex]
@InProceedings{Park_2023_ICCV, author = {Park, Joonhyung and Seo, Hyunjin and Yang, Eunho}, title = {PC-Adapter: Topology-Aware Adapter for Efficient Domain Adaption on Point Clouds with Rectified Pseudo-label}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {11530-11540} }
Cyclic Test-Time Adaptation on Monocular Video for 3D Human Mesh Reconstruction: Hyeongjin Nam,

Daniel Sungho Jung,

Yeonguk Oh,

Kyoung Mu Lee; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Nam_2023_ICCV, author = {Nam, Hyeongjin and Jung, Daniel Sungho and Oh, Yeonguk and Lee, Kyoung Mu}, title = {Cyclic Test-Time Adaptation on Monocular Video for 3D Human Mesh Reconstruction}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {14829-14839} }
2D3D-MATR: 2D-3D Matching Transformer for Detection-Free Registration Between Images and Point Clouds: Minhao Li,

Zheng Qin,

Zhirui Gao,

Renjiao Yi,

Chenyang Zhu,

Yulan Guo,

Kai Xu; [pdf] [supp]
[bibtex]
@InProceedings{Li_2023_ICCV, author = {Li, Minhao and Qin, Zheng and Gao, Zhirui and Yi, Renjiao and Zhu, Chenyang and Guo, Yulan and Xu, Kai}, title = {2D3D-MATR: 2D-3D Matching Transformer for Detection-Free Registration Between Images and Point Clouds}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {14128-14138} }
Group Pose: A Simple Baseline for End-to-End Multi-Person Pose Estimation: Huan Liu,

Qiang Chen,

Zichang Tan,

Jiang-Jiang Liu,

Jian Wang,

Xiangbo Su,

Xiaolong Li,

Kun Yao,

Junyu Han,

Errui Ding,

Yao Zhao,

Jingdong Wang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Liu_2023_ICCV, author = {Liu, Huan and Chen, Qiang and Tan, Zichang and Liu, Jiang-Jiang and Wang, Jian and Su, Xiangbo and Li, Xiaolong and Yao, Kun and Han, Junyu and Ding, Errui and Zhao, Yao and Wang, Jingdong}, title = {Group Pose: A Simple Baseline for End-to-End Multi-Person Pose Estimation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {15029-15038} }
SkeleTR: Towards Skeleton-based Action Recognition in the Wild: Haodong Duan,

Mingze Xu,

Bing Shuai,

Davide Modolo,

Zhuowen Tu,

Joseph Tighe,

Alessandro Bergamo; [pdf]
[bibtex]
@InProceedings{Duan_2023_ICCV, author = {Duan, Haodong and Xu, Mingze and Shuai, Bing and Modolo, Davide and Tu, Zhuowen and Tighe, Joseph and Bergamo, Alessandro}, title = {SkeleTR: Towards Skeleton-based Action Recognition in the Wild}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {13634-13644} }
Weakly-Supervised Action Localization by Hierarchically-Structured Latent Attention Modeling: Guiqin Wang,

Peng Zhao,

Cong Zhao,

Shusen Yang,

Jie Cheng,

Luziwei Leng,

Jianxing Liao,

Qinghai Guo; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2023_ICCV, author = {Wang, Guiqin and Zhao, Peng and Zhao, Cong and Yang, Shusen and Cheng, Jie and Leng, Luziwei and Liao, Jianxing and Guo, Qinghai}, title = {Weakly-Supervised Action Localization by Hierarchically-Structured Latent Attention Modeling}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {10203-10213} }
Get3DHuman: Lifting StyleGAN-Human into a 3D Generative Model Using Pixel-Aligned Reconstruction Priors: Zhangyang Xiong,

Di Kang,

Derong Jin,

Weikai Chen,

Linchao Bao,

Shuguang Cui,

Xiaoguang Han; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Xiong_2023_ICCV, author = {Xiong, Zhangyang and Kang, Di and Jin, Derong and Chen, Weikai and Bao, Linchao and Cui, Shuguang and Han, Xiaoguang}, title = {Get3DHuman: Lifting StyleGAN-Human into a 3D Generative Model Using Pixel-Aligned Reconstruction Priors}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {9287-9297} }
Query6DoF: Learning Sparse Queries as Implicit Shape Prior for Category-Level 6DoF Pose Estimation: Ruiqi Wang,

Xinggang Wang,

Te Li,

Rong Yang,

Minhong Wan,

Wenyu Liu; [pdf]
[bibtex]
@InProceedings{Wang_2023_ICCV, author = {Wang, Ruiqi and Wang, Xinggang and Li, Te and Yang, Rong and Wan, Minhong and Liu, Wenyu}, title = {Query6DoF: Learning Sparse Queries as Implicit Shape Prior for Category-Level 6DoF Pose Estimation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {14055-14064} }
Towards High-Quality Specular Highlight Removal by Leveraging Large-Scale Synthetic Data: Gang Fu,

Qing Zhang,

Lei Zhu,

Chunxia Xiao,

Ping Li; [pdf] [arXiv]
[bibtex]
@InProceedings{Fu_2023_ICCV, author = {Fu, Gang and Zhang, Qing and Zhu, Lei and Xiao, Chunxia and Li, Ping}, title = {Towards High-Quality Specular Highlight Removal by Leveraging Large-Scale Synthetic Data}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {12857-12865} }
Unsupervised 3D Perception with 2D Vision-Language Distillation for Autonomous Driving: Mahyar Najibi,

Jingwei Ji,

Yin Zhou,

Charles R. Qi,

Xinchen Yan,

Scott Ettinger,

Dragomir Anguelov; [pdf] [supp]
[bibtex]
@InProceedings{Najibi_2023_ICCV, author = {Najibi, Mahyar and Ji, Jingwei and Zhou, Yin and Qi, Charles R. and Yan, Xinchen and Ettinger, Scott and Anguelov, Dragomir}, title = {Unsupervised 3D Perception with 2D Vision-Language Distillation for Autonomous Driving}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {8602-8612} }
Towards Grand Unified Representation Learning for Unsupervised Visible-Infrared Person Re-Identification: Bin Yang,

Jun Chen,

Mang Ye; [pdf] [supp]
[bibtex]
@InProceedings{Yang_2023_ICCV, author = {Yang, Bin and Chen, Jun and Ye, Mang}, title = {Towards Grand Unified Representation Learning for Unsupervised Visible-Infrared Person Re-Identification}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {11069-11079} }
ReFit: Recurrent Fitting Network for 3D Human Recovery: Yufu Wang,

Kostas Daniilidis; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2023_ICCV, author = {Wang, Yufu and Daniilidis, Kostas}, title = {ReFit: Recurrent Fitting Network for 3D Human Recovery}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {14644-14654} }
Verbs in Action: Improving Verb Understanding in Video-Language Models: Liliane Momeni,

Mathilde Caron,

Arsha Nagrani,

Andrew Zisserman,

Cordelia Schmid; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Momeni_2023_ICCV, author = {Momeni, Liliane and Caron, Mathilde and Nagrani, Arsha and Zisserman, Andrew and Schmid, Cordelia}, title = {Verbs in Action: Improving Verb Understanding in Video-Language Models}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {15579-15591} }
Zero-Shot Point Cloud Segmentation by Semantic-Visual Aware Synthesis: Yuwei Yang,

Munawar Hayat,

Zhao Jin,

Hongyuan Zhu,

Yinjie Lei; [pdf] [supp]
[bibtex]
@InProceedings{Yang_2023_ICCV, author = {Yang, Yuwei and Hayat, Munawar and Jin, Zhao and Zhu, Hongyuan and Lei, Yinjie}, title = {Zero-Shot Point Cloud Segmentation by Semantic-Visual Aware Synthesis}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {11586-11596} }
Exploring Predicate Visual Context in Detecting of Human-Object Interactions: Frederic Z Zhang,

Yuhui Yuan,

Dylan Campbell,

Zhuoyao Zhong,

Stephen Gould; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhang_2023_ICCV, author = {Zhang, Frederic Z and Yuan, Yuhui and Campbell, Dylan and Zhong, Zhuoyao and Gould, Stephen}, title = {Exploring Predicate Visual Context in Detecting of Human-Object Interactions}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {10411-10421} }
Towards Saner Deep Image Registration: Bin Duan,

Ming Zhong,

Yan Yan; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Duan_2023_ICCV, author = {Duan, Bin and Zhong, Ming and Yan, Yan}, title = {Towards Saner Deep Image Registration}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {12459-12468} }
Interaction-aware Joint Attention Estimation Using People Attributes: Chihiro Nakatani,

Hiroaki Kawashima,

Norimichi Ukita; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Nakatani_2023_ICCV, author = {Nakatani, Chihiro and Kawashima, Hiroaki and Ukita, Norimichi}, title = {Interaction-aware Joint Attention Estimation Using People Attributes}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {10224-10233} }
Non-Coaxial Event-Guided Motion Deblurring with Spatial Alignment: Hoonhee Cho,

Yuhwan Jeong,

Taewoo Kim,

Kuk-Jin Yoon; [pdf] [supp]
[bibtex]
@InProceedings{Cho_2023_ICCV, author = {Cho, Hoonhee and Jeong, Yuhwan and Kim, Taewoo and Yoon, Kuk-Jin}, title = {Non-Coaxial Event-Guided Motion Deblurring with Spatial Alignment}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {12492-12503} }
Fingerprinting Deep Image Restoration Models: Yuhui Quan,

Huan Teng,

Ruotao Xu,

Jun Huang,

Hui Ji; [pdf] [supp]
[bibtex]
@InProceedings{Quan_2023_ICCV, author = {Quan, Yuhui and Teng, Huan and Xu, Ruotao and Huang, Jun and Ji, Hui}, title = {Fingerprinting Deep Image Restoration Models}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {13285-13295} }
SportsMOT: A Large Multi-Object Tracking Dataset in Multiple Sports Scenes: Yutao Cui,

Chenkai Zeng,

Xiaoyu Zhao,

Yichun Yang,

Gangshan Wu,

Limin Wang; [pdf] [arXiv]
[bibtex]
@InProceedings{Cui_2023_ICCV, author = {Cui, Yutao and Zeng, Chenkai and Zhao, Xiaoyu and Yang, Yichun and Wu, Gangshan and Wang, Limin}, title = {SportsMOT: A Large Multi-Object Tracking Dataset in Multiple Sports Scenes}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {9921-9931} }
Localizing Moments in Long Video Via Multimodal Guidance: Wayner Barrios,

Mattia Soldan,

Alberto Mario Ceballos-Arroyo,

Fabian Caba Heilbron,

Bernard Ghanem; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Barrios_2023_ICCV, author = {Barrios, Wayner and Soldan, Mattia and Ceballos-Arroyo, Alberto Mario and Heilbron, Fabian Caba and Ghanem, Bernard}, title = {Localizing Moments in Long Video Via Multimodal Guidance}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {13667-13678} }
Towards Universal Image Embeddings: A Large-Scale Dataset and Challenge for Generic Image Representations: Nikolaos-Antonios Ypsilantis,

Kaifeng Chen,

Bingyi Cao,

Mário Lipovský,

Pelin Dogan-Schönberger,

Grzegorz Makosa,

Boris Bluntschli,

Mojtaba Seyedhosseini,

Ondřej Chum,

André Araujo; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ypsilantis_2023_ICCV, author = {Ypsilantis, Nikolaos-Antonios and Chen, Kaifeng and Cao, Bingyi and Lipovsk\'y, M\'ario and Dogan-Sch\"onberger, Pelin and Makosa, Grzegorz and Bluntschli, Boris and Seyedhosseini, Mojtaba and Chum, Ond\v{r}ej and Araujo, Andr\'e}, title = {Towards Universal Image Embeddings: A Large-Scale Dataset and Challenge for Generic Image Representations}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {11290-11301} }
SemARFlow: Injecting Semantics into Unsupervised Optical Flow Estimation for Autonomous Driving: Shuai Yuan,

Shuzhi Yu,

Hannah Kim,

Carlo Tomasi; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yuan_2023_ICCV, author = {Yuan, Shuai and Yu, Shuzhi and Kim, Hannah and Tomasi, Carlo}, title = {SemARFlow: Injecting Semantics into Unsupervised Optical Flow Estimation for Autonomous Driving}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {9566-9577} }
Uncertainty-aware Unsupervised Multi-Object Tracking: Kai Liu,

Sheng Jin,

Zhihang Fu,

Ze Chen,

Rongxin Jiang,

Jieping Ye; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Liu_2023_ICCV, author = {Liu, Kai and Jin, Sheng and Fu, Zhihang and Chen, Ze and Jiang, Rongxin and Ye, Jieping}, title = {Uncertainty-aware Unsupervised Multi-Object Tracking}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {9996-10005} }
Designing Phase Masks for Under-Display Cameras: Anqi Yang,

Eunhee Kang,

Hyong-Euk Lee,

Aswin C. Sankaranarayanan; [pdf] [supp]
[bibtex]
@InProceedings{Yang_2023_ICCV, author = {Yang, Anqi and Kang, Eunhee and Lee, Hyong-Euk and Sankaranarayanan, Aswin C.}, title = {Designing Phase Masks for Under-Display Cameras}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {10637-10645} }
Can Language Models Learn to Listen?: Evonne Ng,

Sanjay Subramanian,

Dan Klein,

Angjoo Kanazawa,

Trevor Darrell,

Shiry Ginosar; [pdf] [arXiv]
[bibtex]
@InProceedings{Ng_2023_ICCV, author = {Ng, Evonne and Subramanian, Sanjay and Klein, Dan and Kanazawa, Angjoo and Darrell, Trevor and Ginosar, Shiry}, title = {Can Language Models Learn to Listen?}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {10083-10093} }
SurfsUP: Learning Fluid Simulation for Novel Surfaces: Arjun Mani,

Ishaan Preetam Chandratreya,

Elliot Creager,

Carl Vondrick,

Richard Zemel; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Mani_2023_ICCV, author = {Mani, Arjun and Chandratreya, Ishaan Preetam and Creager, Elliot and Vondrick, Carl and Zemel, Richard}, title = {SurfsUP: Learning Fluid Simulation for Novel Surfaces}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {14225-14235} }
Regularized Mask Tuning: Uncovering Hidden Knowledge in Pre-Trained Vision-Language Models: Kecheng Zheng,

Wei Wu,

Ruili Feng,

Kai Zhu,

Jiawei Liu,

Deli Zhao,

Zheng-Jun Zha,

Wei Chen,

Yujun Shen; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zheng_2023_ICCV, author = {Zheng, Kecheng and Wu, Wei and Feng, Ruili and Zhu, Kai and Liu, Jiawei and Zhao, Deli and Zha, Zheng-Jun and Chen, Wei and Shen, Yujun}, title = {Regularized Mask Tuning: Uncovering Hidden Knowledge in Pre-Trained Vision-Language Models}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {11663-11673} }
Skill Transformer: A Monolithic Policy for Mobile Manipulation: Xiaoyu Huang,

Dhruv Batra,

Akshara Rai,

Andrew Szot; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Huang_2023_ICCV, author = {Huang, Xiaoyu and Batra, Dhruv and Rai, Akshara and Szot, Andrew}, title = {Skill Transformer: A Monolithic Policy for Mobile Manipulation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {10852-10862} }
Adaptive and Background-Aware Vision Transformer for Real-Time UAV Tracking: Shuiwang Li,

Yangxiang Yang,

Dan Zeng,

Xucheng Wang; [pdf] [supp]
[bibtex]
@InProceedings{Li_2023_ICCV, author = {Li, Shuiwang and Yang, Yangxiang and Zeng, Dan and Wang, Xucheng}, title = {Adaptive and Background-Aware Vision Transformer for Real-Time UAV Tracking}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {13989-14000} }
Persistent-Transient Duality: A Multi-Mechanism Approach for Modeling Human-Object Interaction: Hung Tran,

Vuong Le,

Svetha Venkatesh,

Truyen Tran; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Tran_2023_ICCV, author = {Tran, Hung and Le, Vuong and Venkatesh, Svetha and Tran, Truyen}, title = {Persistent-Transient Duality: A Multi-Mechanism Approach for Modeling Human-Object Interaction}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {9858-9867} }
DDS2M: Self-Supervised Denoising Diffusion Spatio-Spectral Model for Hyperspectral Image Restoration: Yuchun Miao,

Lefei Zhang,

Liangpei Zhang,

Dacheng Tao; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Miao_2023_ICCV, author = {Miao, Yuchun and Zhang, Lefei and Zhang, Liangpei and Tao, Dacheng}, title = {DDS2M: Self-Supervised Denoising Diffusion Spatio-Spectral Model for Hyperspectral Image Restoration}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {12086-12096} }
MotionLM: Multi-Agent Motion Forecasting as Language Modeling: Ari Seff,

Brian Cera,

Dian Chen,

Mason Ng,

Aurick Zhou,

Nigamaa Nayakanti,

Khaled S. Refaat,

Rami Al-Rfou,

Benjamin Sapp; [pdf] [supp]
[bibtex]
@InProceedings{Seff_2023_ICCV, author = {Seff, Ari and Cera, Brian and Chen, Dian and Ng, Mason and Zhou, Aurick and Nayakanti, Nigamaa and Refaat, Khaled S. and Al-Rfou, Rami and Sapp, Benjamin}, title = {MotionLM: Multi-Agent Motion Forecasting as Language Modeling}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {8579-8590} }
Black Box Few-Shot Adaptation for Vision-Language Models: Yassine Ouali,

Adrian Bulat,

Brais Matinez,

Georgios Tzimiropoulos; [pdf] [supp]
[bibtex]
@InProceedings{Ouali_2023_ICCV, author = {Ouali, Yassine and Bulat, Adrian and Matinez, Brais and Tzimiropoulos, Georgios}, title = {Black Box Few-Shot Adaptation for Vision-Language Models}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {15534-15546} }
Zero-1-to-3: Zero-shot One Image to 3D Object: Ruoshi Liu,

Rundi Wu,

Basile Van Hoorick,

Pavel Tokmakov,

Sergey Zakharov,

Carl Vondrick; [pdf] [supp]
[bibtex]
@InProceedings{Liu_2023_ICCV, author = {Liu, Ruoshi and Wu, Rundi and Van Hoorick, Basile and Tokmakov, Pavel and Zakharov, Sergey and Vondrick, Carl}, title = {Zero-1-to-3: Zero-shot One Image to 3D Object}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {9298-9309} }
3D Distillation: Improving Self-Supervised Monocular Depth Estimation on Reflective Surfaces: Xuepeng Shi,

Georgi Dikov,

Gerhard Reitmayr,

Tae-Kyun Kim,

Mohsen Ghafoorian; [pdf] [supp]
[bibtex]
@InProceedings{Shi_2023_ICCV, author = {Shi, Xuepeng and Dikov, Georgi and Reitmayr, Gerhard and Kim, Tae-Kyun and Ghafoorian, Mohsen}, title = {3D Distillation: Improving Self-Supervised Monocular Depth Estimation on Reflective Surfaces}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {9133-9143} }
Low-Light Image Enhancement with Multi-Stage Residue Quantization and Brightness-Aware Attention: Yunlong Liu,

Tao Huang,

Weisheng Dong,

Fangfang Wu,

Xin Li,

Guangming Shi; [pdf] [supp]
[bibtex]
@InProceedings{Liu_2023_ICCV, author = {Liu, Yunlong and Huang, Tao and Dong, Weisheng and Wu, Fangfang and Li, Xin and Shi, Guangming}, title = {Low-Light Image Enhancement with Multi-Stage Residue Quantization and Brightness-Aware Attention}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {12140-12149} }
Hierarchically Decomposed Graph Convolutional Networks for Skeleton-Based Action Recognition: Jungho Lee,

Minhyeok Lee,

Dogyoon Lee,

Sangyoun Lee; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Lee_2023_ICCV, author = {Lee, Jungho and Lee, Minhyeok and Lee, Dogyoon and Lee, Sangyoun}, title = {Hierarchically Decomposed Graph Convolutional Networks for Skeleton-Based Action Recognition}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {10444-10453} }
LIST: Learning Implicitly from Spatial Transformers for Single-View 3D Reconstruction: Mohammad Samiul Arshad,

William J. Beksi; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Arshad_2023_ICCV, author = {Arshad, Mohammad Samiul and Beksi, William J.}, title = {LIST: Learning Implicitly from Spatial Transformers for Single-View 3D Reconstruction}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {9321-9330} }
LRRU: Long-short Range Recurrent Updating Networks for Depth Completion: Yufei Wang,

Bo Li,

Ge Zhang,

Qi Liu,

Tao Gao,

Yuchao Dai; [pdf]
[bibtex]
@InProceedings{Wang_2023_ICCV, author = {Wang, Yufei and Li, Bo and Zhang, Ge and Liu, Qi and Gao, Tao and Dai, Yuchao}, title = {LRRU: Long-short Range Recurrent Updating Networks for Depth Completion}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {9422-9432} }
MetaBEV: Solving Sensor Failures for 3D Detection and Map Segmentation: Chongjian Ge,

Junsong Chen,

Enze Xie,

Zhongdao Wang,

Lanqing Hong,

Huchuan Lu,

Zhenguo Li,

Ping Luo; [pdf] [supp]
[bibtex]
@InProceedings{Ge_2023_ICCV, author = {Ge, Chongjian and Chen, Junsong and Xie, Enze and Wang, Zhongdao and Hong, Lanqing and Lu, Huchuan and Li, Zhenguo and Luo, Ping}, title = {MetaBEV: Solving Sensor Failures for 3D Detection and Map Segmentation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {8721-8731} }
Exploring Temporal Concurrency for Video-Language Representation Learning: Heng Zhang,

Daqing Liu,

Zezhong Lv,

Bing Su,

Dacheng Tao; [pdf] [supp]
[bibtex]
@InProceedings{Zhang_2023_ICCV, author = {Zhang, Heng and Liu, Daqing and Lv, Zezhong and Su, Bing and Tao, Dacheng}, title = {Exploring Temporal Concurrency for Video-Language Representation Learning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {15568-15578} }
DynamicISP: Dynamically Controlled Image Signal Processor for Image Recognition: Masakazu Yoshimura,

Junji Otsuka,

Atsushi Irie,

Takeshi Ohashi; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yoshimura_2023_ICCV, author = {Yoshimura, Masakazu and Otsuka, Junji and Irie, Atsushi and Ohashi, Takeshi}, title = {DynamicISP: Dynamically Controlled Image Signal Processor for Image Recognition}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {12866-12876} }
R-Pred: Two-Stage Motion Prediction Via Tube-Query Attention-Based Trajectory Refinement: Sehwan Choi,

Jungho Kim,

Junyong Yun,

Jun Won Choi; [pdf] [supp]
[bibtex]
@InProceedings{Choi_2023_ICCV, author = {Choi, Sehwan and Kim, Jungho and Yun, Junyong and Choi, Jun Won}, title = {R-Pred: Two-Stage Motion Prediction Via Tube-Query Attention-Based Trajectory Refinement}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {8525-8535} }
Aggregating Feature Point Cloud for Depth Completion: Zhu Yu,

Zehua Sheng,

Zili Zhou,

Lun Luo,

Si-Yuan Cao,

Hong Gu,

Huaqi Zhang,

Hui-Liang Shen; [pdf] [supp]
[bibtex]
@InProceedings{Yu_2023_ICCV, author = {Yu, Zhu and Sheng, Zehua and Zhou, Zili and Luo, Lun and Cao, Si-Yuan and Gu, Hong and Zhang, Huaqi and Shen, Hui-Liang}, title = {Aggregating Feature Point Cloud for Depth Completion}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {8732-8743} }
Reconstructed Convolution Module Based Look-Up Tables for Efficient Image Super-Resolution: Guandu Liu,

Yukang Ding,

Mading Li,

Ming Sun,

Xing Wen,

Bin Wang; [pdf] [arXiv]
[bibtex]
@InProceedings{Liu_2023_ICCV, author = {Liu, Guandu and Ding, Yukang and Li, Mading and Sun, Ming and Wen, Xing and Wang, Bin}, title = {Reconstructed Convolution Module Based Look-Up Tables for Efficient Image Super-Resolution}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {12217-12226} }
Action Sensitivity Learning for Temporal Action Localization: Jiayi Shao,

Xiaohan Wang,

Ruijie Quan,

Junjun Zheng,

Jiang Yang,

Yi Yang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Shao_2023_ICCV, author = {Shao, Jiayi and Wang, Xiaohan and Quan, Ruijie and Zheng, Junjun and Yang, Jiang and Yang, Yi}, title = {Action Sensitivity Learning for Temporal Action Localization}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {13457-13469} }
PEANUT: Predicting and Navigating to Unseen Targets: Albert J. Zhai,

Shenlong Wang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhai_2023_ICCV, author = {Zhai, Albert J. and Wang, Shenlong}, title = {PEANUT: Predicting and Navigating to Unseen Targets}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {10926-10935} }
PoseDiffusion: Solving Pose Estimation via Diffusion-aided Bundle Adjustment: Jianyuan Wang,

Christian Rupprecht,

David Novotny; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2023_ICCV, author = {Wang, Jianyuan and Rupprecht, Christian and Novotny, David}, title = {PoseDiffusion: Solving Pose Estimation via Diffusion-aided Bundle Adjustment}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {9773-9783} }
CORE: Cooperative Reconstruction for Multi-Agent Perception: Binglu Wang,

Lei Zhang,

Zhaozhong Wang,

Yongqiang Zhao,

Tianfei Zhou; [pdf] [arXiv]
[bibtex]
@InProceedings{Wang_2023_ICCV, author = {Wang, Binglu and Zhang, Lei and Wang, Zhaozhong and Zhao, Yongqiang and Zhou, Tianfei}, title = {CORE: Cooperative Reconstruction for Multi-Agent Perception}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {8710-8720} }
SEFD: Learning to Distill Complex Pose and Occlusion: ChangHee Yang,

Kyeongbo Kong,

SungJun Min,

Dongyoon Wee,

Ho-Deok Jang,

Geonho Cha,

SukJu Kang; [pdf] [supp]
[bibtex]
@InProceedings{Yang_2023_ICCV, author = {Yang, ChangHee and Kong, Kyeongbo and Min, SungJun and Wee, Dongyoon and Jang, Ho-Deok and Cha, Geonho and Kang, SukJu}, title = {SEFD: Learning to Distill Complex Pose and Occlusion}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {14941-14952} }
CiT: Curation in Training for Effective Vision-Language Data: Hu Xu,

Saining Xie,

Po-Yao Huang,

Licheng Yu,

Russell Howes,

Gargi Ghosh,

Luke Zettlemoyer,

Christoph Feichtenhofer; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Xu_2023_ICCV, author = {Xu, Hu and Xie, Saining and Huang, Po-Yao and Yu, Licheng and Howes, Russell and Ghosh, Gargi and Zettlemoyer, Luke and Feichtenhofer, Christoph}, title = {CiT: Curation in Training for Effective Vision-Language Data}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {15180-15189} }
SparseNeRF: Distilling Depth Ranking for Few-shot Novel View Synthesis: Guangcong Wang,

Zhaoxi Chen,

Chen Change Loy,

Ziwei Liu; [pdf] [arXiv]
[bibtex]
@InProceedings{Wang_2023_ICCV, author = {Wang, Guangcong and Chen, Zhaoxi and Loy, Chen Change and Liu, Ziwei}, title = {SparseNeRF: Distilling Depth Ranking for Few-shot Novel View Synthesis}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {9065-9076} }
ProPainter: Improving Propagation and Transformer for Video Inpainting: Shangchen Zhou,

Chongyi Li,

Kelvin C.K. Chan,

Chen Change Loy; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhou_2023_ICCV, author = {Zhou, Shangchen and Li, Chongyi and Chan, Kelvin C.K. and Loy, Chen Change}, title = {ProPainter: Improving Propagation and Transformer for Video Inpainting}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {10477-10486} }
Root Pose Decomposition Towards Generic Non-rigid 3D Reconstruction with Monocular Videos: Yikai Wang,

Yinpeng Dong,

Fuchun Sun,

Xiao Yang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2023_ICCV, author = {Wang, Yikai and Dong, Yinpeng and Sun, Fuchun and Yang, Xiao}, title = {Root Pose Decomposition Towards Generic Non-rigid 3D Reconstruction with Monocular Videos}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {13890-13900} }
GLA-GCN: Global-local Adaptive Graph Convolutional Network for 3D Human Pose Estimation from Monocular Video: Bruce X.B. Yu,

Zhi Zhang,

Yongxu Liu,

Sheng-hua Zhong,

Yan Liu,

Chang Wen Chen; [pdf]
[bibtex]
@InProceedings{Yu_2023_ICCV, author = {Yu, Bruce X.B. and Zhang, Zhi and Liu, Yongxu and Zhong, Sheng-hua and Liu, Yan and Chen, Chang Wen}, title = {GLA-GCN: Global-local Adaptive Graph Convolutional Network for 3D Human Pose Estimation from Monocular Video}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {8818-8829} }
Snow Removal in Video: A New Dataset and A Novel Method: Haoyu Chen,

Jingjing Ren,

Jinjin Gu,

Hongtao Wu,

Xuequan Lu,

Haoming Cai,

Lei Zhu; [pdf] [supp]
[bibtex]
@InProceedings{Chen_2023_ICCV, author = {Chen, Haoyu and Ren, Jingjing and Gu, Jinjin and Wu, Hongtao and Lu, Xuequan and Cai, Haoming and Zhu, Lei}, title = {Snow Removal in Video: A New Dataset and A Novel Method}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {13211-13222} }
Degradation-Resistant Unfolding Network for Heterogeneous Image Fusion: Chunming He,

Kai Li,

Guoxia Xu,

Yulun Zhang,

Runze Hu,

Zhenhua Guo,

Xiu Li; [pdf] [supp]
[bibtex]
@InProceedings{He_2023_ICCV, author = {He, Chunming and Li, Kai and Xu, Guoxia and Zhang, Yulun and Hu, Runze and Guo, Zhenhua and Li, Xiu}, title = {Degradation-Resistant Unfolding Network for Heterogeneous Image Fusion}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {12611-12621} }
Priority-Centric Human Motion Generation in Discrete Latent Space: Hanyang Kong,

Kehong Gong,

Dongze Lian,

Michael Bi Mi,

Xinchao Wang; [pdf] [arXiv]
[bibtex]
@InProceedings{Kong_2023_ICCV, author = {Kong, Hanyang and Gong, Kehong and Lian, Dongze and Mi, Michael Bi and Wang, Xinchao}, title = {Priority-Centric Human Motion Generation in Discrete Latent Space}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {14806-14816} }
3DHacker: Spectrum-based Decision Boundary Generation for Hard-label 3D Point Cloud Attack: Yunbo Tao,

Daizong Liu,

Pan Zhou,

Yulai Xie,

Wei Du,

Wei Hu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Tao_2023_ICCV, author = {Tao, Yunbo and Liu, Daizong and Zhou, Pan and Xie, Yulai and Du, Wei and Hu, Wei}, title = {3DHacker: Spectrum-based Decision Boundary Generation for Hard-label 3D Point Cloud Attack}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {14340-14350} }
Exploring Lightweight Hierarchical Vision Transformers for Efficient Visual Tracking: Ben Kang,

Xin Chen,

Dong Wang,

Houwen Peng,

Huchuan Lu; [pdf] [arXiv]
[bibtex]
@InProceedings{Kang_2023_ICCV, author = {Kang, Ben and Chen, Xin and Wang, Dong and Peng, Houwen and Lu, Huchuan}, title = {Exploring Lightweight Hierarchical Vision Transformers for Efficient Visual Tracking}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {9612-9621} }
MiniROAD: Minimal RNN Framework for Online Action Detection: Joungbin An,

Hyolim Kang,

Su Ho Han,

Ming-Hsuan Yang,

Seon Joo Kim; [pdf] [supp]
[bibtex]
@InProceedings{An_2023_ICCV, author = {An, Joungbin and Kang, Hyolim and Han, Su Ho and Yang, Ming-Hsuan and Kim, Seon Joo}, title = {MiniROAD: Minimal RNN Framework for Online Action Detection}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {10341-10350} }
NDC-Scene: Boost Monocular 3D Semantic Scene Completion in Normalized Device Coordinates Space: Jiawei Yao,

Chuming Li,

Keqiang Sun,

Yingjie Cai,

Hao Li,

Wanli Ouyang,

Hongsheng Li; [pdf] [supp]
[bibtex]
@InProceedings{Yao_2023_ICCV, author = {Yao, Jiawei and Li, Chuming and Sun, Keqiang and Cai, Yingjie and Li, Hao and Ouyang, Wanli and Li, Hongsheng}, title = {NDC-Scene: Boost Monocular 3D Semantic Scene Completion in Normalized Device Coordinates Space}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {9455-9465} }
SVDFormer: Complementing Point Cloud via Self-view Augmentation and Self-structure Dual-generator: Zhe Zhu,

Honghua Chen,

Xing He,

Weiming Wang,

Jing Qin,

Mingqiang Wei; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhu_2023_ICCV, author = {Zhu, Zhe and Chen, Honghua and He, Xing and Wang, Weiming and Qin, Jing and Wei, Mingqiang}, title = {SVDFormer: Complementing Point Cloud via Self-view Augmentation and Self-structure Dual-generator}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {14508-14518} }
E3Sym: Leveraging E(3) Invariance for Unsupervised 3D Planar Reflective Symmetry Detection: Ren-Wu Li,

Ling-Xiao Zhang,

Chunpeng Li,

Yu-Kun Lai,

Lin Gao; [pdf] [supp]
[bibtex]
@InProceedings{Li_2023_ICCV, author = {Li, Ren-Wu and Zhang, Ling-Xiao and Li, Chunpeng and Lai, Yu-Kun and Gao, Lin}, title = {E3Sym: Leveraging E(3) Invariance for Unsupervised 3D Planar Reflective Symmetry Detection}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {14543-14553} }
Zero-Shot Composed Image Retrieval with Textual Inversion: Alberto Baldrati,

Lorenzo Agnolucci,

Marco Bertini,

Alberto Del Bimbo; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Baldrati_2023_ICCV, author = {Baldrati, Alberto and Agnolucci, Lorenzo and Bertini, Marco and Del Bimbo, Alberto}, title = {Zero-Shot Composed Image Retrieval with Textual Inversion}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {15338-15347} }
BiFF: Bi-level Future Fusion with Polyline-based Coordinate for Interactive Trajectory Prediction: Yiyao Zhu,

Di Luan,

Shaojie Shen; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhu_2023_ICCV, author = {Zhu, Yiyao and Luan, Di and Shen, Shaojie}, title = {BiFF: Bi-level Future Fusion with Polyline-based Coordinate for Interactive Trajectory Prediction}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {8260-8271} }
COOL-CHIC: Coordinate-based Low Complexity Hierarchical Image Codec: Théo Ladune,

Pierrick Philippe,

Félix Henry,

Gordon Clare,

Thomas Leguay; [pdf]
[bibtex]
@InProceedings{Ladune_2023_ICCV, author = {Ladune, Th\'eo and Philippe, Pierrick and Henry, F\'elix and Clare, Gordon and Leguay, Thomas}, title = {COOL-CHIC: Coordinate-based Low Complexity Hierarchical Image Codec}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {13515-13522} }
Normalizing Flows for Human Pose Anomaly Detection: Or Hirschorn,

Shai Avidan; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Hirschorn_2023_ICCV, author = {Hirschorn, Or and Avidan, Shai}, title = {Normalizing Flows for Human Pose Anomaly Detection}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {13545-13554} }
Reconstructing Groups of People with Hypergraph Relational Reasoning: Buzhen Huang,

Jingyi Ju,

Zhihao Li,

Yangang Wang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Huang_2023_ICCV, author = {Huang, Buzhen and Ju, Jingyi and Li, Zhihao and Wang, Yangang}, title = {Reconstructing Groups of People with Hypergraph Relational Reasoning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {14873-14883} }
What Does a Platypus Look Like? Generating Customized Prompts for Zero-Shot Image Classification: Sarah Pratt,

Ian Covert,

Rosanne Liu,

Ali Farhadi; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Pratt_2023_ICCV, author = {Pratt, Sarah and Covert, Ian and Liu, Rosanne and Farhadi, Ali}, title = {What Does a Platypus Look Like? Generating Customized Prompts for Zero-Shot Image Classification}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {15691-15701} }
Scene as Occupancy: Wenwen Tong,

Chonghao Sima,

Tai Wang,

Li Chen,

Silei Wu,

Hanming Deng,

Yi Gu,

Lewei Lu,

Ping Luo,

Dahua Lin,

Hongyang Li; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Tong_2023_ICCV, author = {Tong, Wenwen and Sima, Chonghao and Wang, Tai and Chen, Li and Wu, Silei and Deng, Hanming and Gu, Yi and Lu, Lewei and Luo, Ping and Lin, Dahua and Li, Hongyang}, title = {Scene as Occupancy}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {8406-8415} }
U-RED: Unsupervised 3D Shape Retrieval and Deformation for Partial Point Clouds: Yan Di,

Chenyangguang Zhang,

Ruida Zhang,

Fabian Manhardt,

Yongzhi Su,

Jason Rambach,

Didier Stricker,

Xiangyang Ji,

Federico Tombari; [pdf] [supp]
[bibtex]
@InProceedings{Di_2023_ICCV, author = {Di, Yan and Zhang, Chenyangguang and Zhang, Ruida and Manhardt, Fabian and Su, Yongzhi and Rambach, Jason and Stricker, Didier and Ji, Xiangyang and Tombari, Federico}, title = {U-RED: Unsupervised 3D Shape Retrieval and Deformation for Partial Point Clouds}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {8884-8895} }
PatchCT: Aligning Patch Set and Label Set with Conditional Transport for Multi-Label Image Classification: Miaoge Li,

Dongsheng Wang,

Xinyang Liu,

Zequn Zeng,

Ruiying Lu,

Bo Chen,

Mingyuan Zhou; [pdf] [arXiv]
[bibtex]
@InProceedings{Li_2023_ICCV, author = {Li, Miaoge and Wang, Dongsheng and Liu, Xinyang and Zeng, Zequn and Lu, Ruiying and Chen, Bo and Zhou, Mingyuan}, title = {PatchCT: Aligning Patch Set and Label Set with Conditional Transport for Multi-Label Image Classification}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {15348-15358} }
VI-Net: Boosting Category-level 6D Object Pose Estimation via Learning Decoupled Rotations on the Spherical Representations: Jiehong Lin,

Zewei Wei,

Yabin Zhang,

Kui Jia; [pdf] [supp]
[bibtex]
@InProceedings{Lin_2023_ICCV, author = {Lin, Jiehong and Wei, Zewei and Zhang, Yabin and Jia, Kui}, title = {VI-Net: Boosting Category-level 6D Object Pose Estimation via Learning Decoupled Rotations on the Spherical Representations}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {14001-14011} }
Long-range Multimodal Pretraining for Movie Understanding: Dawit Mureja Argaw,

Joon-Young Lee,

Markus Woodson,

In So Kweon,

Fabian Caba Heilbron; [pdf] [arXiv]
[bibtex]
@InProceedings{Argaw_2023_ICCV, author = {Argaw, Dawit Mureja and Lee, Joon-Young and Woodson, Markus and Kweon, In So and Heilbron, Fabian Caba}, title = {Long-range Multimodal Pretraining for Movie Understanding}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {13392-13403} }
Adverse Weather Removal with Codebook Priors: Tian Ye,

Sixiang Chen,

Jinbin Bai,

Jun Shi,

Chenghao Xue,

Jingxia Jiang,

Junjie Yin,

Erkang Chen,

Yun Liu; [pdf] [supp]
[bibtex]
@InProceedings{Ye_2023_ICCV, author = {Ye, Tian and Chen, Sixiang and Bai, Jinbin and Shi, Jun and Xue, Chenghao and Jiang, Jingxia and Yin, Junjie and Chen, Erkang and Liu, Yun}, title = {Adverse Weather Removal with Codebook Priors}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {12653-12664} }
MAP: Towards Balanced Generalization of IID and OOD through Model-Agnostic Adapters: Min Zhang,

Junkun Yuan,

Yue He,

Wenbin Li,

Zhengyu Chen,

Kun Kuang; [pdf] [supp]
[bibtex]
@InProceedings{Zhang_2023_ICCV, author = {Zhang, Min and Yuan, Junkun and He, Yue and Li, Wenbin and Chen, Zhengyu and Kuang, Kun}, title = {MAP: Towards Balanced Generalization of IID and OOD through Model-Agnostic Adapters}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {11921-11931} }
Exploring Group Video Captioning with Efficient Relational Approximation: Wang Lin,

Tao Jin,

Ye Wang,

Wenwen Pan,

Linjun Li,

Xize Cheng,

Zhou Zhao; [pdf] [supp]
[bibtex]
@InProceedings{Lin_2023_ICCV, author = {Lin, Wang and Jin, Tao and Wang, Ye and Pan, Wenwen and Li, Linjun and Cheng, Xize and Zhao, Zhou}, title = {Exploring Group Video Captioning with Efficient Relational Approximation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {15281-15290} }
ADAPT: Efficient Multi-Agent Trajectory Prediction with Adaptation: Görkay Aydemir,

Adil Kaan Akan,

Fatma Güney; [pdf] [supp]
[bibtex]
@InProceedings{Aydemir_2023_ICCV, author = {Aydemir, G\"orkay and Akan, Adil Kaan and G\"uney, Fatma}, title = {ADAPT: Efficient Multi-Agent Trajectory Prediction with Adaptation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {8295-8305} }
MAPConNet: Self-supervised 3D Pose Transfer with Mesh and Point Contrastive Learning: Jiaze Sun,

Zhixiang Chen,

Tae-Kyun Kim; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Sun_2023_ICCV, author = {Sun, Jiaze and Chen, Zhixiang and Kim, Tae-Kyun}, title = {MAPConNet: Self-supervised 3D Pose Transfer with Mesh and Point Contrastive Learning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {14452-14462} }
DARTH: Holistic Test-time Adaptation for Multiple Object Tracking: Mattia Segu,

Bernt Schiele,

Fisher Yu; [pdf] [supp]
[bibtex]
@InProceedings{Segu_2023_ICCV, author = {Segu, Mattia and Schiele, Bernt and Yu, Fisher}, title = {DARTH: Holistic Test-time Adaptation for Multiple Object Tracking}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {9717-9727} }
Multi-interactive Feature Learning and a Full-time Multi-modality Benchmark for Image Fusion and Segmentation: Jinyuan Liu,

Zhu Liu,

Guanyao Wu,

Long Ma,

Risheng Liu,

Wei Zhong,

Zhongxuan Luo,

Xin Fan; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Liu_2023_ICCV, author = {Liu, Jinyuan and Liu, Zhu and Wu, Guanyao and Ma, Long and Liu, Risheng and Zhong, Wei and Luo, Zhongxuan and Fan, Xin}, title = {Multi-interactive Feature Learning and a Full-time Multi-modality Benchmark for Image Fusion and Segmentation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {8115-8124} }
BaRe-ESA: A Riemannian Framework for Unregistered Human Body Shapes: Emmanuel Hartman,

Emery Pierson,

Martin Bauer,

Nicolas Charon,

Mohamed Daoudi; [pdf] [supp]
[bibtex]
@InProceedings{Hartman_2023_ICCV, author = {Hartman, Emmanuel and Pierson, Emery and Bauer, Martin and Charon, Nicolas and Daoudi, Mohamed}, title = {BaRe-ESA: A Riemannian Framework for Unregistered Human Body Shapes}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {14181-14191} }
Skip-Plan: Procedure Planning in Instructional Videos via Condensed Action Space Learning: Zhiheng Li,

Wenjia Geng,

Muheng Li,

Lei Chen,

Yansong Tang,

Jiwen Lu,

Jie Zhou; [pdf] [supp]
[bibtex]
@InProceedings{Li_2023_ICCV, author = {Li, Zhiheng and Geng, Wenjia and Li, Muheng and Chen, Lei and Tang, Yansong and Lu, Jiwen and Zhou, Jie}, title = {Skip-Plan: Procedure Planning in Instructional Videos via Condensed Action Space Learning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {10297-10306} }
Sparse Instance Conditioned Multimodal Trajectory Prediction: Yonghao Dong,

Le Wang,

Sanping Zhou,

Gang Hua; [pdf]
[bibtex]
@InProceedings{Dong_2023_ICCV, author = {Dong, Yonghao and Wang, Le and Zhou, Sanping and Hua, Gang}, title = {Sparse Instance Conditioned Multimodal Trajectory Prediction}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {9763-9772} }
NAPA-VQ: Neighborhood-Aware Prototype Augmentation with Vector Quantization for Continual Learning: Tamasha Malepathirana,

Damith Senanayake,

Saman Halgamuge; [pdf] [supp]
[bibtex]
@InProceedings{Malepathirana_2023_ICCV, author = {Malepathirana, Tamasha and Senanayake, Damith and Halgamuge, Saman}, title = {NAPA-VQ: Neighborhood-Aware Prototype Augmentation with Vector Quantization for Continual Learning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {11674-11684} }
Unsupervised Open-Vocabulary Object Localization in Videos: Ke Fan,

Zechen Bai,

Tianjun Xiao,

Dominik Zietlow,

Max Horn,

Zixu Zhao,

Carl-Johann Simon-Gabriel,

Mike Zheng Shou,

Francesco Locatello,

Bernt Schiele,

Thomas Brox,

Zheng Zhang,

Yanwei Fu,

Tong He; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Fan_2023_ICCV, author = {Fan, Ke and Bai, Zechen and Xiao, Tianjun and Zietlow, Dominik and Horn, Max and Zhao, Zixu and Simon-Gabriel, Carl-Johann and Shou, Mike Zheng and Locatello, Francesco and Schiele, Bernt and Brox, Thomas and Zhang, Zheng and Fu, Yanwei and He, Tong}, title = {Unsupervised Open-Vocabulary Object Localization in Videos}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {13747-13755} }
Unsupervised Video Deraining with An Event Camera: Jin Wang,

Wenming Weng,

Yueyi Zhang,

Zhiwei Xiong; [pdf] [supp]
[bibtex]
@InProceedings{Wang_2023_ICCV, author = {Wang, Jin and Weng, Wenming and Zhang, Yueyi and Xiong, Zhiwei}, title = {Unsupervised Video Deraining with An Event Camera}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {10831-10840} }
DIME-FM : DIstilling Multimodal and Efficient Foundation Models: Ximeng Sun,

Pengchuan Zhang,

Peizhao Zhang,

Hardik Shah,

Kate Saenko,

Xide Xia; [pdf] [supp]
[bibtex]
@InProceedings{Sun_2023_ICCV, author = {Sun, Ximeng and Zhang, Pengchuan and Zhang, Peizhao and Shah, Hardik and Saenko, Kate and Xia, Xide}, title = {DIME-FM : DIstilling Multimodal and Efficient Foundation Models}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {15521-15533} }
Boosting Single Image Super-Resolution via Partial Channel Shifting: Xiaoming Zhang,

Tianrui Li,

Xiaole Zhao; [pdf] [supp]
[bibtex]
@InProceedings{Zhang_2023_ICCV, author = {Zhang, Xiaoming and Li, Tianrui and Zhao, Xiaole}, title = {Boosting Single Image Super-Resolution via Partial Channel Shifting}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {13223-13232} }
Distracting Downpour: Adversarial Weather Attacks for Motion Estimation: Jenny Schmalfuss,

Lukas Mehl,

Andrés Bruhn; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Schmalfuss_2023_ICCV, author = {Schmalfuss, Jenny and Mehl, Lukas and Bruhn, Andr\'es}, title = {Distracting Downpour: Adversarial Weather Attacks for Motion Estimation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {10106-10116} }
Unfolding Framework with Prior of Convolution-Transformer Mixture and Uncertainty Estimation for Video Snapshot Compressive Imaging: Siming Zheng,

Xin Yuan; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zheng_2023_ICCV, author = {Zheng, Siming and Yuan, Xin}, title = {Unfolding Framework with Prior of Convolution-Transformer Mixture and Uncertainty Estimation for Video Snapshot Compressive Imaging}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {12738-12749} }
Non-Semantics Suppressed Mask Learning for Unsupervised Video Semantic Compression: Yuan Tian,

Guo Lu,

Guangtao Zhai,

Zhiyong Gao; [pdf]
[bibtex]
@InProceedings{Tian_2023_ICCV, author = {Tian, Yuan and Lu, Guo and Zhai, Guangtao and Gao, Zhiyong}, title = {Non-Semantics Suppressed Mask Learning for Unsupervised Video Semantic Compression}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {13610-13622} }
Inverse Compositional Learning for Weakly-supervised Relation Grounding: Huan Li,

Ping Wei,

Zeyu Ma,

Nanning Zheng; [pdf]
[bibtex]
@InProceedings{Li_2023_ICCV, author = {Li, Huan and Wei, Ping and Ma, Zeyu and Zheng, Nanning}, title = {Inverse Compositional Learning for Weakly-supervised Relation Grounding}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {15477-15487} }
Navigating to Objects Specified by Images: Jacob Krantz,

Theophile Gervet,

Karmesh Yadav,

Austin Wang,

Chris Paxton,

Roozbeh Mottaghi,

Dhruv Batra,

Jitendra Malik,

Stefan Lee,

Devendra Singh Chaplot; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Krantz_2023_ICCV, author = {Krantz, Jacob and Gervet, Theophile and Yadav, Karmesh and Wang, Austin and Paxton, Chris and Mottaghi, Roozbeh and Batra, Dhruv and Malik, Jitendra and Lee, Stefan and Chaplot, Devendra Singh}, title = {Navigating to Objects Specified by Images}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {10916-10925} }
LATR: 3D Lane Detection from Monocular Images with Transformer: Yueru Luo,

Chaoda Zheng,

Xu Yan,

Tang Kun,

Chao Zheng,

Shuguang Cui,

Zhen Li; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Luo_2023_ICCV, author = {Luo, Yueru and Zheng, Chaoda and Yan, Xu and Kun, Tang and Zheng, Chao and Cui, Shuguang and Li, Zhen}, title = {LATR: 3D Lane Detection from Monocular Images with Transformer}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {7941-7952} }
Environment-Invariant Curriculum Relation Learning for Fine-Grained Scene Graph Generation: Yukuan Min,

Aming Wu,

Cheng Deng; [pdf] [arXiv]
[bibtex]
@InProceedings{Min_2023_ICCV, author = {Min, Yukuan and Wu, Aming and Deng, Cheng}, title = {Environment-Invariant Curriculum Relation Learning for Fine-Grained Scene Graph Generation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {13296-13307} }
Generalizable Decision Boundaries: Dualistic Meta-Learning for Open Set Domain Generalization: Xiran Wang,

Jian Zhang,

Lei Qi,

Yinghuan Shi; [pdf] [arXiv]
[bibtex]
@InProceedings{Wang_2023_ICCV, author = {Wang, Xiran and Zhang, Jian and Qi, Lei and Shi, Yinghuan}, title = {Generalizable Decision Boundaries: Dualistic Meta-Learning for Open Set Domain Generalization}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {11564-11573} }
SimFIR: A Simple Framework for Fisheye Image Rectification with Self-supervised Representation Learning: Hao Feng,

Wendi Wang,

Jiajun Deng,

Wengang Zhou,

Li Li,

Houqiang Li; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Feng_2023_ICCV, author = {Feng, Hao and Wang, Wendi and Deng, Jiajun and Zhou, Wengang and Li, Li and Li, Houqiang}, title = {SimFIR: A Simple Framework for Fisheye Image Rectification with Self-supervised Representation Learning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {12418-12427} }
Generalized Lightness Adaptation with Channel Selective Normalization: Mingde Yao,

Jie Huang,

Xin Jin,

Ruikang Xu,

Shenglong Zhou,

Man Zhou,

Zhiwei Xiong; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yao_2023_ICCV, author = {Yao, Mingde and Huang, Jie and Jin, Xin and Xu, Ruikang and Zhou, Shenglong and Zhou, Man and Xiong, Zhiwei}, title = {Generalized Lightness Adaptation with Channel Selective Normalization}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {10668-10679} }
Omnidirectional Information Gathering for Knowledge Transfer-Based Audio-Visual Navigation: Jinyu Chen,

Wenguan Wang,

Si Liu,

Hongsheng Li,

Yi Yang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chen_2023_ICCV, author = {Chen, Jinyu and Wang, Wenguan and Liu, Si and Li, Hongsheng and Yang, Yi}, title = {Omnidirectional Information Gathering for Knowledge Transfer-Based Audio-Visual Navigation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {10993-11003} }
Multi-Scale Bidirectional Recurrent Network with Hybrid Correlation for Point Cloud Based Scene Flow Estimation: Wencan Cheng,

Jong Hwan Ko; [pdf]
[bibtex]
@InProceedings{Cheng_2023_ICCV, author = {Cheng, Wencan and Ko, Jong Hwan}, title = {Multi-Scale Bidirectional Recurrent Network with Hybrid Correlation for Point Cloud Based Scene Flow Estimation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {10041-10050} }
VLN-PETL: Parameter-Efficient Transfer Learning for Vision-and-Language Navigation: Yanyuan Qiao,

Zheng Yu,

Qi Wu; [pdf] [supp]
[bibtex]
@InProceedings{Qiao_2023_ICCV, author = {Qiao, Yanyuan and Yu, Zheng and Wu, Qi}, title = {VLN-PETL: Parameter-Efficient Transfer Learning for Vision-and-Language Navigation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {15443-15452} }
Learning Continuous Exposure Value Representations for Single-Image HDR Reconstruction: Su-Kai Chen,

Hung-Lin Yen,

Yu-Lun Liu,

Min-Hung Chen,

Hou-Ning Hu,

Wen-Hsiao Peng,

Yen-Yu Lin; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chen_2023_ICCV, author = {Chen, Su-Kai and Yen, Hung-Lin and Liu, Yu-Lun and Chen, Min-Hung and Hu, Hou-Ning and Peng, Wen-Hsiao and Lin, Yen-Yu}, title = {Learning Continuous Exposure Value Representations for Single-Image HDR Reconstruction}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {12990-13000} }
MixSynthFormer: A Transformer Encoder-like Structure with Mixed Synthetic Self-attention for Efficient Human Pose Estimation: Yuran Sun,

Alan William Dougherty,

Zhuoying Zhang,

Yi King Choi,

Chuan Wu; [pdf] [supp]
[bibtex]
@InProceedings{Sun_2023_ICCV, author = {Sun, Yuran and Dougherty, Alan William and Zhang, Zhuoying and Choi, Yi King and Wu, Chuan}, title = {MixSynthFormer: A Transformer Encoder-like Structure with Mixed Synthetic Self-attention for Efficient Human Pose Estimation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {14884-14893} }
HumanMAC: Masked Motion Completion for Human Motion Prediction: Ling-Hao Chen,

JiaWei Zhang,

Yewen Li,

Yiren Pang,

Xiaobo Xia,

Tongliang Liu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chen_2023_ICCV, author = {Chen, Ling-Hao and Zhang, JiaWei and Li, Yewen and Pang, Yiren and Xia, Xiaobo and Liu, Tongliang}, title = {HumanMAC: Masked Motion Completion for Human Motion Prediction}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {9544-9555} }
Prompt Switch: Efficient CLIP Adaptation for Text-Video Retrieval: Chaorui Deng,

Qi Chen,

Pengda Qin,

Da Chen,

Qi Wu; [pdf] [arXiv]
[bibtex]
@InProceedings{Deng_2023_ICCV, author = {Deng, Chaorui and Chen, Qi and Qin, Pengda and Chen, Da and Wu, Qi}, title = {Prompt Switch: Efficient CLIP Adaptation for Text-Video Retrieval}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {15648-15658} }
Video Action Recognition with Attentive Semantic Units: Yifei Chen,

Dapeng Chen,

Ruijin Liu,

Hao Li,

Wei Peng; [pdf] [arXiv]
[bibtex]
@InProceedings{Chen_2023_ICCV, author = {Chen, Yifei and Chen, Dapeng and Liu, Ruijin and Li, Hao and Peng, Wei}, title = {Video Action Recognition with Attentive Semantic Units}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {10170-10180} }
Scanning Only Once: An End-to-end Framework for Fast Temporal Grounding in Long Videos: Yulin Pan,

Xiangteng He,

Biao Gong,

Yiliang Lv,

Yujun Shen,

Yuxin Peng,

Deli Zhao; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Pan_2023_ICCV, author = {Pan, Yulin and He, Xiangteng and Gong, Biao and Lv, Yiliang and Shen, Yujun and Peng, Yuxin and Zhao, Deli}, title = {Scanning Only Once: An End-to-end Framework for Fast Temporal Grounding in Long Videos}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {13767-13777} }
VoroMesh: Learning Watertight Surface Meshes with Voronoi Diagrams: Nissim Maruani,

Roman Klokov,

Maks Ovsjanikov,

Pierre Alliez,

Mathieu Desbrun; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Maruani_2023_ICCV, author = {Maruani, Nissim and Klokov, Roman and Ovsjanikov, Maks and Alliez, Pierre and Desbrun, Mathieu}, title = {VoroMesh: Learning Watertight Surface Meshes with Voronoi Diagrams}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {14565-14574} }
What does CLIP know about a red circle? Visual prompt engineering for VLMs: Aleksandar Shtedritski,

Christian Rupprecht,

Andrea Vedaldi; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Shtedritski_2023_ICCV, author = {Shtedritski, Aleksandar and Rupprecht, Christian and Vedaldi, Andrea}, title = {What does CLIP know about a red circle? Visual prompt engineering for VLMs}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {11987-11997} }
LoLep: Single-View View Synthesis with Locally-Learned Planes and Self-Attention Occlusion Inference: Cong Wang,

Yu-Ping Wang,

Dinesh Manocha; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2023_ICCV, author = {Wang, Cong and Wang, Yu-Ping and Manocha, Dinesh}, title = {LoLep: Single-View View Synthesis with Locally-Learned Planes and Self-Attention Occlusion Inference}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {10841-10851} }
Exploring Positional Characteristics of Dual-Pixel Data for Camera Autofocus: Myungsub Choi,

Hana Lee,

Hyong-euk Lee; [pdf] [supp]
[bibtex]
@InProceedings{Choi_2023_ICCV, author = {Choi, Myungsub and Lee, Hana and Lee, Hyong-euk}, title = {Exploring Positional Characteristics of Dual-Pixel Data for Camera Autofocus}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {13158-13168} }
Heterogeneous Forgetting Compensation for Class-Incremental Learning: Jiahua Dong,

Wenqi Liang,

Yang Cong,

Gan Sun; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Dong_2023_ICCV, author = {Dong, Jiahua and Liang, Wenqi and Cong, Yang and Sun, Gan}, title = {Heterogeneous Forgetting Compensation for Class-Incremental Learning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {11742-11751} }
FemtoDet: An Object Detection Baseline for Energy Versus Performance Tradeoffs: Peng Tu,

Xu Xie,

Guo Ai,

Yuexiang Li,

Yawen Huang,

Yefeng Zheng; [pdf] [arXiv]
[bibtex]
@InProceedings{Tu_2023_ICCV, author = {Tu, Peng and Xie, Xu and Ai, Guo and Li, Yuexiang and Huang, Yawen and Zheng, Yefeng}, title = {FemtoDet: An Object Detection Baseline for Energy Versus Performance Tradeoffs}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {13318-13327} }
Iterative Prompt Learning for Unsupervised Backlit Image Enhancement: Zhexin Liang,

Chongyi Li,

Shangchen Zhou,

Ruicheng Feng,

Chen Change Loy; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Liang_2023_ICCV, author = {Liang, Zhexin and Li, Chongyi and Zhou, Shangchen and Feng, Ruicheng and Loy, Chen Change}, title = {Iterative Prompt Learning for Unsupervised Backlit Image Enhancement}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {8094-8103} }
UATVR: Uncertainty-Adaptive Text-Video Retrieval: Bo Fang,

Wenhao Wu,

Chang Liu,

Yu Zhou,

Yuxin Song,

Weiping Wang,

Xiangbo Shu,

Xiangyang Ji,

Jingdong Wang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Fang_2023_ICCV, author = {Fang, Bo and Wu, Wenhao and Liu, Chang and Zhou, Yu and Song, Yuxin and Wang, Weiping and Shu, Xiangbo and Ji, Xiangyang and Wang, Jingdong}, title = {UATVR: Uncertainty-Adaptive Text-Video Retrieval}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {13723-13733} }
SALAD: Part-Level Latent Diffusion for 3D Shape Generation and Manipulation: Juil Koo,

Seungwoo Yoo,

Minh Hieu Nguyen,

Minhyuk Sung; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Koo_2023_ICCV, author = {Koo, Juil and Yoo, Seungwoo and Nguyen, Minh Hieu and Sung, Minhyuk}, title = {SALAD: Part-Level Latent Diffusion for 3D Shape Generation and Manipulation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {14441-14451} }
COMPASS: High-Efficiency Deep Image Compression with Arbitrary-scale Spatial Scalability: Jongmin Park,

Jooyoung Lee,

Munchurl Kim; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Park_2023_ICCV, author = {Park, Jongmin and Lee, Jooyoung and Kim, Munchurl}, title = {COMPASS: High-Efficiency Deep Image Compression with Arbitrary-scale Spatial Scalability}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {12826-12835} }
Score-Based Diffusion Models as Principled Priors for Inverse Imaging: Berthy T. Feng,

Jamie Smith,

Michael Rubinstein,

Huiwen Chang,

Katherine L. Bouman,

William T. Freeman; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Feng_2023_ICCV, author = {Feng, Berthy T. and Smith, Jamie and Rubinstein, Michael and Chang, Huiwen and Bouman, Katherine L. and Freeman, William T.}, title = {Score-Based Diffusion Models as Principled Priors for Inverse Imaging}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {10520-10531} }
Multiscale Structure Guided Diffusion for Image Deblurring: Mengwei Ren,

Mauricio Delbracio,

Hossein Talebi,

Guido Gerig,

Peyman Milanfar; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ren_2023_ICCV, author = {Ren, Mengwei and Delbracio, Mauricio and Talebi, Hossein and Gerig, Guido and Milanfar, Peyman}, title = {Multiscale Structure Guided Diffusion for Image Deblurring}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {10721-10733} }
CheckerPose: Progressive Dense Keypoint Localization for Object Pose Estimation with Graph Neural Network: Ruyi Lian,

Haibin Ling; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Lian_2023_ICCV, author = {Lian, Ruyi and Ling, Haibin}, title = {CheckerPose: Progressive Dense Keypoint Localization for Object Pose Estimation with Graph Neural Network}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {14022-14033} }
Event Camera Data Pre-training: Yan Yang,

Liyuan Pan,

Liu Liu; [pdf] [arXiv]
[bibtex]
@InProceedings{Yang_2023_ICCV, author = {Yang, Yan and Pan, Liyuan and Liu, Liu}, title = {Event Camera Data Pre-training}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {10699-10709} }
One-shot Implicit Animatable Avatars with Model-based Priors: Yangyi Huang,

Hongwei Yi,

Weiyang Liu,

Haofan Wang,

Boxi Wu,

Wenxiao Wang,

Binbin Lin,

Debing Zhang,

Deng Cai; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Huang_2023_ICCV, author = {Huang, Yangyi and Yi, Hongwei and Liu, Weiyang and Wang, Haofan and Wu, Boxi and Wang, Wenxiao and Lin, Binbin and Zhang, Debing and Cai, Deng}, title = {One-shot Implicit Animatable Avatars with Model-based Priors}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {8974-8985} }
Unsupervised Feature Representation Learning for Domain-generalized Cross-domain Image Retrieval: Conghui Hu,

Can Zhang,

Gim Hee Lee; [pdf] [supp]
[bibtex]
@InProceedings{Hu_2023_ICCV, author = {Hu, Conghui and Zhang, Can and Lee, Gim Hee}, title = {Unsupervised Feature Representation Learning for Domain-generalized Cross-domain Image Retrieval}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {11016-11025} }
Dec-Adapter: Exploring Efficient Decoder-Side Adapter for Bridging Screen Content and Natural Image Compression: Sheng Shen,

Huanjing Yue,

Jingyu Yang; [pdf] [supp]
[bibtex]
@InProceedings{Shen_2023_ICCV, author = {Shen, Sheng and Yue, Huanjing and Yang, Jingyu}, title = {Dec-Adapter: Exploring Efficient Decoder-Side Adapter for Bridging Screen Content and Natural Image Compression}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {12887-12896} }
Under-Display Camera Image Restoration with Scattering Effect: Binbin Song,

Xiangyu Chen,

Shuning Xu,

Jiantao Zhou; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Song_2023_ICCV, author = {Song, Binbin and Chen, Xiangyu and Xu, Shuning and Zhou, Jiantao}, title = {Under-Display Camera Image Restoration with Scattering Effect}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {12580-12589} }
VideoFlow: Exploiting Temporal Cues for Multi-frame Optical Flow Estimation: Xiaoyu Shi,

Zhaoyang Huang,

Weikang Bian,

Dasong Li,

Manyuan Zhang,

Ka Chun Cheung,

Simon See,

Hongwei Qin,

Jifeng Dai,

Hongsheng Li; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Shi_2023_ICCV, author = {Shi, Xiaoyu and Huang, Zhaoyang and Bian, Weikang and Li, Dasong and Zhang, Manyuan and Cheung, Ka Chun and See, Simon and Qin, Hongwei and Dai, Jifeng and Li, Hongsheng}, title = {VideoFlow: Exploiting Temporal Cues for Multi-frame Optical Flow Estimation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {12469-12480} }
3DMiner: Discovering Shapes from Large-Scale Unannotated Image Datasets: Ta-Ying Cheng,

Matheus Gadelha,

Sören Pirk,

Thibault Groueix,

Radomír Měch,

Andrew Markham,

Niki Trigoni; [pdf]
[bibtex]
@InProceedings{Cheng_2023_ICCV, author = {Cheng, Ta-Ying and Gadelha, Matheus and Pirk, S\"oren and Groueix, Thibault and M\v{e}ch, Radom{\'\i}r and Markham, Andrew and Trigoni, Niki}, title = {3DMiner: Discovering Shapes from Large-Scale Unannotated Image Datasets}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {9331-9341} }
Order-Prompted Tag Sequence Generation for Video Tagging: Zongyang Ma,

Ziqi Zhang,

Yuxin Chen,

Zhongang Qi,

Yingmin Luo,

Zekun Li,

Chunfeng Yuan,

Bing Li,

Xiaohu Qie,

Ying Shan,

Weiming Hu; [pdf] [supp]
[bibtex]
@InProceedings{Ma_2023_ICCV, author = {Ma, Zongyang and Zhang, Ziqi and Chen, Yuxin and Qi, Zhongang and Luo, Yingmin and Li, Zekun and Yuan, Chunfeng and Li, Bing and Qie, Xiaohu and Shan, Ying and Hu, Weiming}, title = {Order-Prompted Tag Sequence Generation for Video Tagging}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {15681-15690} }
XVO: Generalized Visual Odometry via Cross-Modal Self-Training: Lei Lai,

Zhongkai Shangguan,

Jimuyang Zhang,

Eshed Ohn-Bar; [pdf]
[bibtex]
@InProceedings{Lai_2023_ICCV, author = {Lai, Lei and Shangguan, Zhongkai and Zhang, Jimuyang and Ohn-Bar, Eshed}, title = {XVO: Generalized Visual Odometry via Cross-Modal Self-Training}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {10094-10105} }
HMD-NeMo: Online 3D Avatar Motion Generation From Sparse Observations: Sadegh Aliakbarian,

Fatemeh Saleh,

David Collier,

Pashmina Cameron,

Darren Cosker; [pdf] [supp]
[bibtex]
@InProceedings{Aliakbarian_2023_ICCV, author = {Aliakbarian, Sadegh and Saleh, Fatemeh and Collier, David and Cameron, Pashmina and Cosker, Darren}, title = {HMD-NeMo: Online 3D Avatar Motion Generation From Sparse Observations}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {9622-9631} }
Adaptive Illumination Mapping for Shadow Detection in Raw Images: Jiayu Sun,

Ke Xu,

Youwei Pang,

Lihe Zhang,

Huchuan Lu,

Gerhard Hancke,

Rynson Lau; [pdf]
[bibtex]
@InProceedings{Sun_2023_ICCV, author = {Sun, Jiayu and Xu, Ke and Pang, Youwei and Zhang, Lihe and Lu, Huchuan and Hancke, Gerhard and Lau, Rynson}, title = {Adaptive Illumination Mapping for Shadow Detection in Raw Images}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {12709-12718} }
Multi-Scale Residual Low-Pass Filter Network for Image Deblurring: Jiangxin Dong,

Jinshan Pan,

Zhongbao Yang,

Jinhui Tang; [pdf] [supp]
[bibtex]
@InProceedings{Dong_2023_ICCV, author = {Dong, Jiangxin and Pan, Jinshan and Yang, Zhongbao and Tang, Jinhui}, title = {Multi-Scale Residual Low-Pass Filter Network for Image Deblurring}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {12345-12354} }
PhaseMP: Robust 3D Pose Estimation via Phase-conditioned Human Motion Prior: Mingyi Shi,

Sebastian Starke,

Yuting Ye,

Taku Komura,

Jungdam Won; [pdf] [supp]
[bibtex]
@InProceedings{Shi_2023_ICCV, author = {Shi, Mingyi and Starke, Sebastian and Ye, Yuting and Komura, Taku and Won, Jungdam}, title = {PhaseMP: Robust 3D Pose Estimation via Phase-conditioned Human Motion Prior}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {14725-14737} }
NLOS-NeuS: Non-line-of-sight Neural Implicit Surface: Yuki Fujimura,

Takahiro Kushida,

Takuya Funatomi,

Yasuhiro Mukaigawa; [pdf] [supp]
[bibtex]
@InProceedings{Fujimura_2023_ICCV, author = {Fujimura, Yuki and Kushida, Takahiro and Funatomi, Takuya and Mukaigawa, Yasuhiro}, title = {NLOS-NeuS: Non-line-of-sight Neural Implicit Surface}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {10532-10541} }
Augmenting and Aligning Snippets for Few-Shot Video Domain Adaptation: Yuecong Xu,

Jianfei Yang,

Yunjiao Zhou,

Zhenghua Chen,

Min Wu,

Xiaoli Li; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Xu_2023_ICCV, author = {Xu, Yuecong and Yang, Jianfei and Zhou, Yunjiao and Chen, Zhenghua and Wu, Min and Li, Xiaoli}, title = {Augmenting and Aligning Snippets for Few-Shot Video Domain Adaptation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {13445-13456} }
Towards Real-World Burst Image Super-Resolution: Benchmark and Method: Pengxu Wei,

Yujing Sun,

Xingbei Guo,

Chang Liu,

Guanbin Li,

Jie Chen,

Xiangyang Ji,

Liang Lin; [pdf] [supp]
[bibtex]
@InProceedings{Wei_2023_ICCV, author = {Wei, Pengxu and Sun, Yujing and Guo, Xingbei and Liu, Chang and Li, Guanbin and Chen, Jie and Ji, Xiangyang and Lin, Liang}, title = {Towards Real-World Burst Image Super-Resolution: Benchmark and Method}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {13233-13242} }
SYENet: A Simple Yet Effective Network for Multiple Low-Level Vision Tasks with Real-Time Performance on Mobile Device: Weiran Gou,

Ziyao Yi,

Yan Xiang,

Shaoqing Li,

Zibin Liu,

Dehui Kong,

Ke Xu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Gou_2023_ICCV, author = {Gou, Weiran and Yi, Ziyao and Xiang, Yan and Li, Shaoqing and Liu, Zibin and Kong, Dehui and Xu, Ke}, title = {SYENet: A Simple Yet Effective Network for Multiple Low-Level Vision Tasks with Real-Time Performance on Mobile Device}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {12182-12195} }
EdaDet: Open-Vocabulary Object Detection Using Early Dense Alignment: Cheng Shi,

Sibei Yang; [pdf] [arXiv]
[bibtex]
@InProceedings{Shi_2023_ICCV, author = {Shi, Cheng and Yang, Sibei}, title = {EdaDet: Open-Vocabulary Object Detection Using Early Dense Alignment}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {15724-15734} }
DOLCE: A Model-Based Probabilistic Diffusion Framework for Limited-Angle CT Reconstruction: Jiaming Liu,

Rushil Anirudh,

Jayaraman J. Thiagarajan,

Stewart He,

K Aditya Mohan,

Ulugbek S. Kamilov,

Hyojin Kim; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Liu_2023_ICCV, author = {Liu, Jiaming and Anirudh, Rushil and Thiagarajan, Jayaraman J. and He, Stewart and Mohan, K Aditya and Kamilov, Ulugbek S. and Kim, Hyojin}, title = {DOLCE: A Model-Based Probabilistic Diffusion Framework for Limited-Angle CT Reconstruction}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {10498-10508} }
Beyond Image Borders: Learning Feature Extrapolation for Unbounded Image Composition: Xiaoyu Liu,

Ming Liu,

Junyi Li,

Shuai Liu,

Xiaotao Wang,

Lei Lei,

Wangmeng Zuo; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Liu_2023_ICCV, author = {Liu, Xiaoyu and Liu, Ming and Li, Junyi and Liu, Shuai and Wang, Xiaotao and Lei, Lei and Zuo, Wangmeng}, title = {Beyond Image Borders: Learning Feature Extrapolation for Unbounded Image Composition}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {13023-13032} }
DeepChange: A Long-Term Person Re-Identification Benchmark with Clothes Change: Peng Xu,

Xiatian Zhu; [pdf] [supp]
[bibtex]
@InProceedings{Xu_2023_ICCV, author = {Xu, Peng and Zhu, Xiatian}, title = {DeepChange: A Long-Term Person Re-Identification Benchmark with Clothes Change}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {11196-11205} }
Discrepant and Multi-Instance Proxies for Unsupervised Person Re-Identification: Chang Zou,

Zeqi Chen,

Zhichao Cui,

Yuehu Liu,

Chi Zhang; [pdf] [supp]
[bibtex]
@InProceedings{Zou_2023_ICCV, author = {Zou, Chang and Chen, Zeqi and Cui, Zhichao and Liu, Yuehu and Zhang, Chi}, title = {Discrepant and Multi-Instance Proxies for Unsupervised Person Re-Identification}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {11058-11068} }
Joint-Relation Transformer for Multi-Person Motion Prediction: Qingyao Xu,

Weibo Mao,

Jingze Gong,

Chenxin Xu,

Siheng Chen,

Weidi Xie,

Ya Zhang,

Yanfeng Wang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Xu_2023_ICCV, author = {Xu, Qingyao and Mao, Weibo and Gong, Jingze and Xu, Chenxin and Chen, Siheng and Xie, Weidi and Zhang, Ya and Wang, Yanfeng}, title = {Joint-Relation Transformer for Multi-Person Motion Prediction}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {9816-9826} }
TMA: Temporal Motion Aggregation for Event-based Optical Flow: Haotian Liu,

Guang Chen,

Sanqing Qu,

Yanping Zhang,

Zhijun Li,

Alois Knoll,

Changjun Jiang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Liu_2023_ICCV, author = {Liu, Haotian and Chen, Guang and Qu, Sanqing and Zhang, Yanping and Li, Zhijun and Knoll, Alois and Jiang, Changjun}, title = {TMA: Temporal Motion Aggregation for Event-based Optical Flow}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {9685-9694} }
Building a Winning Team: Selecting Source Model Ensembles using a Submodular Transferability Estimation Approach: Vimal K B,

Saketh Bachu,

Tanmay Garg,

Niveditha Lakshmi Narasimhan,

Raghavan Konuru,

Vineeth N Balasubramanian; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{B_2023_ICCV, author = {B, Vimal K and Bachu, Saketh and Garg, Tanmay and Narasimhan, Niveditha Lakshmi and Konuru, Raghavan and Balasubramanian, Vineeth N}, title = {Building a Winning Team: Selecting Source Model Ensembles using a Submodular Transferability Estimation Approach}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {11609-11620} }
Plausible Uncertainties for Human Pose Regression: Lennart Bramlage,

Michelle Karg,

Cristóbal Curio; [pdf] [supp]
[bibtex]
@InProceedings{Bramlage_2023_ICCV, author = {Bramlage, Lennart and Karg, Michelle and Curio, Crist\'obal}, title = {Plausible Uncertainties for Human Pose Regression}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {15133-15142} }
DiffIR: Efficient Diffusion Model for Image Restoration: Bin Xia,

Yulun Zhang,

Shiyin Wang,

Yitong Wang,

Xinglong Wu,

Yapeng Tian,

Wenming Yang,

Luc Van Gool; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Xia_2023_ICCV, author = {Xia, Bin and Zhang, Yulun and Wang, Shiyin and Wang, Yitong and Wu, Xinglong and Tian, Yapeng and Yang, Wenming and Van Gool, Luc}, title = {DiffIR: Efficient Diffusion Model for Image Restoration}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {13095-13105} }
Simple Baselines for Interactive Video Retrieval with Questions and Answers: Kaiqu Liang,

Samuel Albanie; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Liang_2023_ICCV, author = {Liang, Kaiqu and Albanie, Samuel}, title = {Simple Baselines for Interactive Video Retrieval with Questions and Answers}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {11091-11101} }
Going Denser with Open-Vocabulary Part Segmentation: Peize Sun,

Shoufa Chen,

Chenchen Zhu,

Fanyi Xiao,

Ping Luo,

Saining Xie,

Zhicheng Yan; [pdf] [arXiv]
[bibtex]
@InProceedings{Sun_2023_ICCV, author = {Sun, Peize and Chen, Shoufa and Zhu, Chenchen and Xiao, Fanyi and Luo, Ping and Xie, Saining and Yan, Zhicheng}, title = {Going Denser with Open-Vocabulary Part Segmentation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {15453-15465} }
OCHID-Fi: Occlusion-Robust Hand Pose Estimation in 3D via RF-Vision: Shujie Zhang,

Tianyue Zheng,

Zhe Chen,

Jingzhi Hu,

Abdelwahed Khamis,

Jiajun Liu,

Jun Luo; [pdf]
[bibtex]
@InProceedings{Zhang_2023_ICCV, author = {Zhang, Shujie and Zheng, Tianyue and Chen, Zhe and Hu, Jingzhi and Khamis, Abdelwahed and Liu, Jiajun and Luo, Jun}, title = {OCHID-Fi: Occlusion-Robust Hand Pose Estimation in 3D via RF-Vision}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {15112-15121} }
Reconstructing Interacting Hands with Interaction Prior from Monocular Images: Binghui Zuo,

Zimeng Zhao,

Wenqian Sun,

Wei Xie,

Zhou Xue,

Yangang Wang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zuo_2023_ICCV, author = {Zuo, Binghui and Zhao, Zimeng and Sun, Wenqian and Xie, Wei and Xue, Zhou and Wang, Yangang}, title = {Reconstructing Interacting Hands with Interaction Prior from Monocular Images}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {9054-9064} }
Towards Realistic Evaluation of Industrial Continual Learning Scenarios with an Emphasis on Energy Consumption and Computational Footprint: Vivek Chavan,

Paul Koch,

Marian Schlüter,

Clemens Briese; [pdf] [supp]
[bibtex]
@InProceedings{Chavan_2023_ICCV, author = {Chavan, Vivek and Koch, Paul and Schl\"uter, Marian and Briese, Clemens}, title = {Towards Realistic Evaluation of Industrial Continual Learning Scenarios with an Emphasis on Energy Consumption and Computational Footprint}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {11506-11518} }
How Much Temporal Long-Term Context is Needed for Action Segmentation?: Emad Bahrami,

Gianpiero Francesca,

Juergen Gall; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Bahrami_2023_ICCV, author = {Bahrami, Emad and Francesca, Gianpiero and Gall, Juergen}, title = {How Much Temporal Long-Term Context is Needed for Action Segmentation?}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {10351-10361} }
3D VR Sketch Guided 3D Shape Prototyping and Exploration: Ling Luo,

Pinaki Nath Chowdhury,

Tao Xiang,

Yi-Zhe Song,

Yulia Gryaditskaya; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Luo_2023_ICCV, author = {Luo, Ling and Chowdhury, Pinaki Nath and Xiang, Tao and Song, Yi-Zhe and Gryaditskaya, Yulia}, title = {3D VR Sketch Guided 3D Shape Prototyping and Exploration}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {9267-9276} }
MDCS: More Diverse Experts with Consistency Self-distillation for Long-tailed Recognition: Qihao Zhao,

Chen Jiang,

Wei Hu,

Fan Zhang,

Jun Liu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhao_2023_ICCV, author = {Zhao, Qihao and Jiang, Chen and Hu, Wei and Zhang, Fan and Liu, Jun}, title = {MDCS: More Diverse Experts with Consistency Self-distillation for Long-tailed Recognition}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {11597-11608} }
Similarity Min-Max: Zero-Shot Day-Night Domain Adaptation: Rundong Luo,

Wenjing Wang,

Wenhan Yang,

Jiaying Liu; [pdf] [supp]
[bibtex]
@InProceedings{Luo_2023_ICCV, author = {Luo, Rundong and Wang, Wenjing and Yang, Wenhan and Liu, Jiaying}, title = {Similarity Min-Max: Zero-Shot Day-Night Domain Adaptation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {8104-8114} }
Dark Side Augmentation: Generating Diverse Night Examples for Metric Learning: Albert Mohwald,

Tomas Jenicek,

Ondřej Chum; [pdf] [supp]
[bibtex]
@InProceedings{Mohwald_2023_ICCV, author = {Mohwald, Albert and Jenicek, Tomas and Chum, Ond\v{r}ej}, title = {Dark Side Augmentation: Generating Diverse Night Examples for Metric Learning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {11153-11163} }
LVOS: A Benchmark for Long-term Video Object Segmentation: Lingyi Hong,

Wenchao Chen,

Zhongying Liu,

Wei Zhang,

Pinxue Guo,

Zhaoyu Chen,

Wenqiang Zhang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Hong_2023_ICCV, author = {Hong, Lingyi and Chen, Wenchao and Liu, Zhongying and Zhang, Wei and Guo, Pinxue and Chen, Zhaoyu and Zhang, Wenqiang}, title = {LVOS: A Benchmark for Long-term Video Object Segmentation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {13480-13492} }
CHAMPAGNE: Learning Real-world Conversation from Large-Scale Web Videos: Seungju Han,

Jack Hessel,

Nouha Dziri,

Yejin Choi,

Youngjae Yu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Han_2023_ICCV, author = {Han, Seungju and Hessel, Jack and Dziri, Nouha and Choi, Yejin and Yu, Youngjae}, title = {CHAMPAGNE: Learning Real-world Conversation from Large-Scale Web Videos}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {15498-15509} }
DeformToon3D: Deformable Neural Radiance Fields for 3D Toonification: Junzhe Zhang,

Yushi Lan,

Shuai Yang,

Fangzhou Hong,

Quan Wang,

Chai Kiat Yeo,

Ziwei Liu,

Chen Change Loy; [pdf] [supp]
[bibtex]
@InProceedings{Zhang_2023_ICCV, author = {Zhang, Junzhe and Lan, Yushi and Yang, Shuai and Hong, Fangzhou and Wang, Quan and Yeo, Chai Kiat and Liu, Ziwei and Loy, Chen Change}, title = {DeformToon3D: Deformable Neural Radiance Fields for 3D Toonification}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {9144-9154} }
Empowering Low-Light Image Enhancer through Customized Learnable Priors: Naishan Zheng,

Man Zhou,

Yanmeng Dong,

Xiangyu Rui,

Jie Huang,

Chongyi Li,

Feng Zhao; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zheng_2023_ICCV, author = {Zheng, Naishan and Zhou, Man and Dong, Yanmeng and Rui, Xiangyu and Huang, Jie and Li, Chongyi and Zhao, Feng}, title = {Empowering Low-Light Image Enhancer through Customized Learnable Priors}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {12559-12569} }
Guiding Image Captioning Models Toward More Specific Captions: Simon Kornblith,

Lala Li,

Zirui Wang,

Thao Nguyen; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kornblith_2023_ICCV, author = {Kornblith, Simon and Li, Lala and Wang, Zirui and Nguyen, Thao}, title = {Guiding Image Captioning Models Toward More Specific Captions}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {15259-15269} }
Towards Effective Instance Discrimination Contrastive Loss for Unsupervised Domain Adaptation: Yixin Zhang,

Zilei Wang,

Junjie Li,

Jiafan Zhuang,

Zihan Lin; [pdf]
[bibtex]
@InProceedings{Zhang_2023_ICCV, author = {Zhang, Yixin and Wang, Zilei and Li, Junjie and Zhuang, Jiafan and Lin, Zihan}, title = {Towards Effective Instance Discrimination Contrastive Loss for Unsupervised Domain Adaptation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {11388-11399} }
FrozenRecon: Pose-free 3D Scene Reconstruction with Frozen Depth Models: Guangkai Xu,

Wei Yin,

Hao Chen,

Chunhua Shen,

Kai Cheng,

Feng Zhao; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Xu_2023_ICCV, author = {Xu, Guangkai and Yin, Wei and Chen, Hao and Shen, Chunhua and Cheng, Kai and Zhao, Feng}, title = {FrozenRecon: Pose-free 3D Scene Reconstruction with Frozen Depth Models}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {9310-9320} }
Affective Image Filter: Reflecting Emotions from Text to Images: Shuchen Weng,

Peixuan Zhang,

Zheng Chang,

Xinlong Wang,

Si Li,

Boxin Shi; [pdf] [supp]
[bibtex]
@InProceedings{Weng_2023_ICCV, author = {Weng, Shuchen and Zhang, Peixuan and Chang, Zheng and Wang, Xinlong and Li, Si and Shi, Boxin}, title = {Affective Image Filter: Reflecting Emotions from Text to Images}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {10810-10819} }
Content-Aware Local GAN for Photo-Realistic Super-Resolution: JoonKyu Park,

Sanghyun Son,

Kyoung Mu Lee; [pdf] [supp]
[bibtex]
@InProceedings{Park_2023_ICCV, author = {Park, JoonKyu and Son, Sanghyun and Lee, Kyoung Mu}, title = {Content-Aware Local GAN for Photo-Realistic Super-Resolution}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {10585-10594} }
Structure-Aware Surface Reconstruction via Primitive Assembly: Jingen Jiang,

Mingyang Zhao,

Shiqing Xin,

Yanchao Yang,

Hanxiao Wang,

Xiaohong Jia,

Dong-Ming Yan; [pdf]
[bibtex]
@InProceedings{Jiang_2023_ICCV, author = {Jiang, Jingen and Zhao, Mingyang and Xin, Shiqing and Yang, Yanchao and Wang, Hanxiao and Jia, Xiaohong and Yan, Dong-Ming}, title = {Structure-Aware Surface Reconstruction via Primitive Assembly}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {14171-14180} }
FineDance: A Fine-grained Choreography Dataset for 3D Full Body Dance Generation: Ronghui Li,

Junfan Zhao,

Yachao Zhang,

Mingyang Su,

Zeping Ren,

Han Zhang,

Yansong Tang,

Xiu Li; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Li_2023_ICCV, author = {Li, Ronghui and Zhao, Junfan and Zhang, Yachao and Su, Mingyang and Ren, Zeping and Zhang, Han and Tang, Yansong and Li, Xiu}, title = {FineDance: A Fine-grained Choreography Dataset for 3D Full Body Dance Generation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {10234-10243} }
Improving Online Lane Graph Extraction by Object-Lane Clustering: Yigit Baran Can,

Alexander Liniger,

Danda Pani Paudel,

Luc Van Gool; [pdf] [arXiv]
[bibtex]
@InProceedings{Can_2023_ICCV, author = {Can, Yigit Baran and Liniger, Alexander and Paudel, Danda Pani and Van Gool, Luc}, title = {Improving Online Lane Graph Extraction by Object-Lane Clustering}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {8591-8601} }
Video Background Music Generation: Dataset, Method and Evaluation: Le Zhuo,

Zhaokai Wang,

Baisen Wang,

Yue Liao,

Chenxi Bao,

Stanley Peng,

Songhao Han,

Aixi Zhang,

Fei Fang,

Si Liu; [pdf] [arXiv]
[bibtex]
@InProceedings{Zhuo_2023_ICCV, author = {Zhuo, Le and Wang, Zhaokai and Wang, Baisen and Liao, Yue and Bao, Chenxi and Peng, Stanley and Han, Songhao and Zhang, Aixi and Fang, Fei and Liu, Si}, title = {Video Background Music Generation: Dataset, Method and Evaluation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {15637-15647} }
Markov Game Video Augmentation for Action Segmentation: Nicolas Aziere,

Sinisa Todorovic; [pdf] [supp]
[bibtex]
@InProceedings{Aziere_2023_ICCV, author = {Aziere, Nicolas and Todorovic, Sinisa}, title = {Markov Game Video Augmentation for Action Segmentation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {13505-13514} }
RegFormer: An Efficient Projection-Aware Transformer Network for Large-Scale Point Cloud Registration: Jiuming Liu,

Guangming Wang,

Zhe Liu,

Chaokang Jiang,

Marc Pollefeys,

Hesheng Wang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Liu_2023_ICCV, author = {Liu, Jiuming and Wang, Guangming and Liu, Zhe and Jiang, Chaokang and Pollefeys, Marc and Wang, Hesheng}, title = {RegFormer: An Efficient Projection-Aware Transformer Network for Large-Scale Point Cloud Registration}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {8451-8460} }
Graphics2RAW: Mapping Computer Graphics Images to Sensor RAW Images: Donghwan Seo,

Abhijith Punnappurath,

Luxi Zhao,

Abdelrahman Abdelhamed,

Sai Kiran Tedla,

Sanguk Park,

Jihwan Choe,

Michael S. Brown; [pdf] [supp]
[bibtex]
@InProceedings{Seo_2023_ICCV, author = {Seo, Donghwan and Punnappurath, Abhijith and Zhao, Luxi and Abdelhamed, Abdelrahman and Tedla, Sai Kiran and Park, Sanguk and Choe, Jihwan and Brown, Michael S.}, title = {Graphics2RAW: Mapping Computer Graphics Images to Sensor RAW Images}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {12622-12631} }
VAD: Vectorized Scene Representation for Efficient Autonomous Driving: Bo Jiang,

Shaoyu Chen,

Qing Xu,

Bencheng Liao,

Jiajie Chen,

Helong Zhou,

Qian Zhang,

Wenyu Liu,

Chang Huang,

Xinggang Wang; [pdf] [arXiv]
[bibtex]
@InProceedings{Jiang_2023_ICCV, author = {Jiang, Bo and Chen, Shaoyu and Xu, Qing and Liao, Bencheng and Chen, Jiajie and Zhou, Helong and Zhang, Qian and Liu, Wenyu and Huang, Chang and Wang, Xinggang}, title = {VAD: Vectorized Scene Representation for Efficient Autonomous Driving}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {8340-8350} }
Batch-based Model Registration for Fast 3D Sherd Reconstruction: Jiepeng Wang,

Congyi Zhang,

Peng Wang,

Xin Li,

Peter J. Cobb,

Christian Theobalt,

Wenping Wang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2023_ICCV, author = {Wang, Jiepeng and Zhang, Congyi and Wang, Peng and Li, Xin and Cobb, Peter J. and Theobalt, Christian and Wang, Wenping}, title = {Batch-based Model Registration for Fast 3D Sherd Reconstruction}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {14519-14529} }
HiFace: High-Fidelity 3D Face Reconstruction by Learning Static and Dynamic Details: Zenghao Chai,

Tianke Zhang,

Tianyu He,

Xu Tan,

Tadas Baltrusaitis,

HsiangTao Wu,

Runnan Li,

Sheng Zhao,

Chun Yuan,

Jiang Bian; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chai_2023_ICCV, author = {Chai, Zenghao and Zhang, Tianke and He, Tianyu and Tan, Xu and Baltrusaitis, Tadas and Wu, HsiangTao and Li, Runnan and Zhao, Sheng and Yuan, Chun and Bian, Jiang}, title = {HiFace: High-Fidelity 3D Face Reconstruction by Learning Static and Dynamic Details}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {9087-9098} }
Fast and Accurate Transferability Measurement by Evaluating Intra-class Feature Variance: Huiwen Xu,

U Kang; [pdf] [arXiv]
[bibtex]
@InProceedings{Xu_2023_ICCV, author = {Xu, Huiwen and Kang, U}, title = {Fast and Accurate Transferability Measurement by Evaluating Intra-class Feature Variance}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {11474-11482} }
Algebraically Rigorous Quaternion Framework for the Neural Network Pose Estimation Problem: Chen Lin,

Andrew J. Hanson,

Sonya M. Hanson; [pdf]
[bibtex]
@InProceedings{Lin_2023_ICCV, author = {Lin, Chen and Hanson, Andrew J. and Hanson, Sonya M.}, title = {Algebraically Rigorous Quaternion Framework for the Neural Network Pose Estimation Problem}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {14097-14106} }
CVSformer: Cross-View Synthesis Transformer for Semantic Scene Completion: Haotian Dong,

Enhui Ma,

Lubo Wang,

Miaohui Wang,

Wuyuan Xie,

Qing Guo,

Ping Li,

Lingyu Liang,

Kairui Yang,

Di Lin; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Dong_2023_ICCV, author = {Dong, Haotian and Ma, Enhui and Wang, Lubo and Wang, Miaohui and Xie, Wuyuan and Guo, Qing and Li, Ping and Liang, Lingyu and Yang, Kairui and Lin, Di}, title = {CVSformer: Cross-View Synthesis Transformer for Semantic Scene Completion}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {8874-8883} }
UrbanGIRAFFE: Representing Urban Scenes as Compositional Generative Neural Feature Fields: Yuanbo Yang,

Yifei Yang,

Hanlei Guo,

Rong Xiong,

Yue Wang,

Yiyi Liao; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yang_2023_ICCV, author = {Yang, Yuanbo and Yang, Yifei and Guo, Hanlei and Xiong, Rong and Wang, Yue and Liao, Yiyi}, title = {UrbanGIRAFFE: Representing Urban Scenes as Compositional Generative Neural Feature Fields}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {9199-9210} }
Active Neural Mapping: Zike Yan,

Haoxiang Yang,

Hongbin Zha; [pdf] [arXiv]
[bibtex]
@InProceedings{Yan_2023_ICCV, author = {Yan, Zike and Yang, Haoxiang and Zha, Hongbin}, title = {Active Neural Mapping}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {10981-10992} }
RecRecNet: Rectangling Rectified Wide-Angle Images by Thin-Plate Spline Model and DoF-based Curriculum Learning: Kang Liao,

Lang Nie,

Chunyu Lin,

Zishuo Zheng,

Yao Zhao; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Liao_2023_ICCV, author = {Liao, Kang and Nie, Lang and Lin, Chunyu and Zheng, Zishuo and Zhao, Yao}, title = {RecRecNet: Rectangling Rectified Wide-Angle Images by Thin-Plate Spline Model and DoF-based Curriculum Learning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {10800-10809} }
Learning Versatile 3D Shape Generation with Improved Auto-regressive Models: Simian Luo,

Xuelin Qian,

Yanwei Fu,

Yinda Zhang,

Ying Tai,

Zhenyu Zhang,

Chengjie Wang,

Xiangyang Xue; [pdf] [supp]
[bibtex]
@InProceedings{Luo_2023_ICCV, author = {Luo, Simian and Qian, Xuelin and Fu, Yanwei and Zhang, Yinda and Tai, Ying and Zhang, Zhenyu and Wang, Chengjie and Xue, Xiangyang}, title = {Learning Versatile 3D Shape Generation with Improved Auto-regressive Models}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {14139-14149} }
DETA: Denoised Task Adaptation for Few-Shot Learning: Ji Zhang,

Lianli Gao,

Xu Luo,

Hengtao Shen,

Jingkuan Song; [pdf] [arXiv]
[bibtex]
@InProceedings{Zhang_2023_ICCV, author = {Zhang, Ji and Gao, Lianli and Luo, Xu and Shen, Hengtao and Song, Jingkuan}, title = {DETA: Denoised Task Adaptation for Few-Shot Learning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {11541-11551} }
Robust Frame-to-Frame Camera Rotation Estimation in Crowded Scenes: Fabien Delattre,

David Dirnfeld,

Phat Nguyen,

Stephen K Scarano,

Michael J Jones,

Pedro Miraldo,

Erik Learned-Miller; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Delattre_2023_ICCV, author = {Delattre, Fabien and Dirnfeld, David and Nguyen, Phat and Scarano, Stephen K and Jones, Michael J and Miraldo, Pedro and Learned-Miller, Erik}, title = {Robust Frame-to-Frame Camera Rotation Estimation in Crowded Scenes}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {9752-9762} }
Bayesian Prompt Learning for Image-Language Model Generalization: Mohammad Mahdi Derakhshani,

Enrique Sanchez,

Adrian Bulat,

Victor G. Turrisi da Costa,

Cees G.M. Snoek,

Georgios Tzimiropoulos,

Brais Martinez; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Derakhshani_2023_ICCV, author = {Derakhshani, Mohammad Mahdi and Sanchez, Enrique and Bulat, Adrian and da Costa, Victor G. Turrisi and Snoek, Cees G.M. and Tzimiropoulos, Georgios and Martinez, Brais}, title = {Bayesian Prompt Learning for Image-Language Model Generalization}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {15237-15246} }
DiLiGenT-Pi: Photometric Stereo for Planar Surfaces with Rich Details - Benchmark Dataset and Beyond: Feishi Wang,

Jieji Ren,

Heng Guo,

Mingjun Ren,

Boxin Shi; [pdf] [supp]
[bibtex]
@InProceedings{Wang_2023_ICCV, author = {Wang, Feishi and Ren, Jieji and Guo, Heng and Ren, Mingjun and Shi, Boxin}, title = {DiLiGenT-Pi: Photometric Stereo for Planar Surfaces with Rich Details - Benchmark Dataset and Beyond}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {9477-9487} }
Accurate and Fast Compressed Video Captioning: Yaojie Shen,

Xin Gu,

Kai Xu,

Heng Fan,

Longyin Wen,

Libo Zhang; [pdf] [arXiv]
[bibtex]
@InProceedings{Shen_2023_ICCV, author = {Shen, Yaojie and Gu, Xin and Xu, Kai and Fan, Heng and Wen, Longyin and Zhang, Libo}, title = {Accurate and Fast Compressed Video Captioning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {15558-15567} }
Visible-Infrared Person Re-Identification via Semantic Alignment and Affinity Inference: Xingye Fang,

Yang Yang,

Ying Fu; [pdf] [supp]
[bibtex]
@InProceedings{Fang_2023_ICCV, author = {Fang, Xingye and Yang, Yang and Fu, Ying}, title = {Visible-Infrared Person Re-Identification via Semantic Alignment and Affinity Inference}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {11270-11279} }
DG3D: Generating High Quality 3D Textured Shapes by Learning to Discriminate Multi-Modal Diffusion-Renderings: Qi Zuo,

Yafei Song,

Jianfang Li,

Lin Liu,

Liefeng Bo; [pdf] [supp]
[bibtex]
@InProceedings{Zuo_2023_ICCV, author = {Zuo, Qi and Song, Yafei and Li, Jianfang and Liu, Lin and Bo, Liefeng}, title = {DG3D: Generating High Quality 3D Textured Shapes by Learning to Discriminate Multi-Modal Diffusion-Renderings}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {14575-14584} }
VLSlice: Interactive Vision-and-Language Slice Discovery: Eric Slyman,

Minsuk Kahng,

Stefan Lee; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Slyman_2023_ICCV, author = {Slyman, Eric and Kahng, Minsuk and Lee, Stefan}, title = {VLSlice: Interactive Vision-and-Language Slice Discovery}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {15291-15301} }
Learning to Ground Instructional Articles in Videos through Narrations: Effrosyni Mavroudi,

Triantafyllos Afouras,

Lorenzo Torresani; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Mavroudi_2023_ICCV, author = {Mavroudi, Effrosyni and Afouras, Triantafyllos and Torresani, Lorenzo}, title = {Learning to Ground Instructional Articles in Videos through Narrations}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {15201-15213} }
MAMo: Leveraging Memory and Attention for Monocular Video Depth Estimation: Rajeev Yasarla,

Hong Cai,

Jisoo Jeong,

Yunxiao Shi,

Risheek Garrepalli,

Fatih Porikli; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yasarla_2023_ICCV, author = {Yasarla, Rajeev and Cai, Hong and Jeong, Jisoo and Shi, Yunxiao and Garrepalli, Risheek and Porikli, Fatih}, title = {MAMo: Leveraging Memory and Attention for Monocular Video Depth Estimation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {8754-8764} }
HDG-ODE: A Hierarchical Continuous-Time Model for Human Pose Forecasting: Yucheng Xing,

Xin Wang; [pdf]
[bibtex]
@InProceedings{Xing_2023_ICCV, author = {Xing, Yucheng and Wang, Xin}, title = {HDG-ODE: A Hierarchical Continuous-Time Model for Human Pose Forecasting}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {14700-14712} }
Self-supervised Monocular Underwater Depth Recovery, Image Restoration, and a Real-sea Video Dataset: Nisha Varghese,

Ashish Kumar,

A. N. Rajagopalan; [pdf] [supp]
[bibtex]
@InProceedings{Varghese_2023_ICCV, author = {Varghese, Nisha and Kumar, Ashish and Rajagopalan, A. N.}, title = {Self-supervised Monocular Underwater Depth Recovery, Image Restoration, and a Real-sea Video Dataset}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {12248-12258} }
Geometrized Transformer for Self-Supervised Homography Estimation: Jiazhen Liu,

Xirong Li; [pdf] [supp]
[bibtex]
@InProceedings{Liu_2023_ICCV, author = {Liu, Jiazhen and Li, Xirong}, title = {Geometrized Transformer for Self-Supervised Homography Estimation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {9556-9565} }
TiDy-PSFs: Computational Imaging with Time-Averaged Dynamic Point-Spread-Functions: Sachin Shah,

Sakshum Kulshrestha,

Christopher A. Metzler; [pdf] [supp]
[bibtex]
@InProceedings{Shah_2023_ICCV, author = {Shah, Sachin and Kulshrestha, Sakshum and Metzler, Christopher A.}, title = {TiDy-PSFs: Computational Imaging with Time-Averaged Dynamic Point-Spread-Functions}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {10657-10667} }
Learning Fine-Grained Features for Pixel-Wise Video Correspondences: Rui Li,

Shenglong Zhou,

Dong Liu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Li_2023_ICCV, author = {Li, Rui and Zhou, Shenglong and Liu, Dong}, title = {Learning Fine-Grained Features for Pixel-Wise Video Correspondences}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {9632-9641} }
FS-DETR: Few-Shot DEtection TRansformer with Prompting and without Re-Training: Adrian Bulat,

Ricardo Guerrero,

Brais Martinez,

Georgios Tzimiropoulos; [pdf] [supp]
[bibtex]
@InProceedings{Bulat_2023_ICCV, author = {Bulat, Adrian and Guerrero, Ricardo and Martinez, Brais and Tzimiropoulos, Georgios}, title = {FS-DETR: Few-Shot DEtection TRansformer with Prompting and without Re-Training}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {11793-11802} }
Learning to Learn: How to Continuously Teach Humans and Machines: Parantak Singh,

You Li,

Ankur Sikarwar,

Stan Weixian Lei,

Difei Gao,

Morgan B. Talbot,

Ying Sun,

Mike Zheng Shou,

Gabriel Kreiman,

Mengmi Zhang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Singh_2023_ICCV, author = {Singh, Parantak and Li, You and Sikarwar, Ankur and Lei, Stan Weixian and Gao, Difei and Talbot, Morgan B. and Sun, Ying and Shou, Mike Zheng and Kreiman, Gabriel and Zhang, Mengmi}, title = {Learning to Learn: How to Continuously Teach Humans and Machines}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {11708-11719} }
A 5-Point Minimal Solver for Event Camera Relative Motion Estimation: Ling Gao,

Hang Su,

Daniel Gehrig,

Marco Cannici,

Davide Scaramuzza,

Laurent Kneip; [pdf]
[bibtex]
@InProceedings{Gao_2023_ICCV, author = {Gao, Ling and Su, Hang and Gehrig, Daniel and Cannici, Marco and Scaramuzza, Davide and Kneip, Laurent}, title = {A 5-Point Minimal Solver for Event Camera Relative Motion Estimation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {8049-8059} }
TM2D: Bimodality Driven 3D Dance Generation via Music-Text Integration: Kehong Gong,

Dongze Lian,

Heng Chang,

Chuan Guo,

Zihang Jiang,

Xinxin Zuo,

Michael Bi Mi,

Xinchao Wang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Gong_2023_ICCV, author = {Gong, Kehong and Lian, Dongze and Chang, Heng and Guo, Chuan and Jiang, Zihang and Zuo, Xinxin and Mi, Michael Bi and Wang, Xinchao}, title = {TM2D: Bimodality Driven 3D Dance Generation via Music-Text Integration}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {9942-9952} }
Bootstrap Motion Forecasting With Self-Consistent Constraints: Maosheng Ye,

Jiamiao Xu,

Xunnong Xu,

Tengfei Wang,

Tongyi Cao,

Qifeng Chen; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ye_2023_ICCV, author = {Ye, Maosheng and Xu, Jiamiao and Xu, Xunnong and Wang, Tengfei and Cao, Tongyi and Chen, Qifeng}, title = {Bootstrap Motion Forecasting With Self-Consistent Constraints}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {8504-8514} }
CDAC: Cross-domain Attention Consistency in Transformer for Domain Adaptive Semantic Segmentation: Kaihong Wang,

Donghyun Kim,

Rogerio Feris,

Margrit Betke; [pdf] [supp]
[bibtex]
@InProceedings{Wang_2023_ICCV, author = {Wang, Kaihong and Kim, Donghyun and Feris, Rogerio and Betke, Margrit}, title = {CDAC: Cross-domain Attention Consistency in Transformer for Domain Adaptive Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {11519-11529} }
Confidence-based Visual Dispersal for Few-shot Unsupervised Domain Adaptation: Yizhe Xiong,

Hui Chen,

Zijia Lin,

Sicheng Zhao,

Guiguang Ding; [pdf] [supp]
[bibtex]
@InProceedings{Xiong_2023_ICCV, author = {Xiong, Yizhe and Chen, Hui and Lin, Zijia and Zhao, Sicheng and Ding, Guiguang}, title = {Confidence-based Visual Dispersal for Few-shot Unsupervised Domain Adaptation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {11621-11631} }
Event-Guided Procedure Planning from Instructional Videos with Text Supervision: An-Lan Wang,

Kun-Yu Lin,

Jia-Run Du,

Jingke Meng,

Wei-Shi Zheng; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2023_ICCV, author = {Wang, An-Lan and Lin, Kun-Yu and Du, Jia-Run and Meng, Jingke and Zheng, Wei-Shi}, title = {Event-Guided Procedure Planning from Instructional Videos with Text Supervision}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {13565-13575} }
Multimodal Motion Conditioned Diffusion Model for Skeleton-based Video Anomaly Detection: Alessandro Flaborea,

Luca Collorone,

Guido Maria D'Amely di Melendugno,

Stefano D'Arrigo,

Bardh Prenkaj,

Fabio Galasso; [pdf] [supp]
[bibtex]
@InProceedings{Flaborea_2023_ICCV, author = {Flaborea, Alessandro and Collorone, Luca and di Melendugno, Guido Maria D'Amely and D'Arrigo, Stefano and Prenkaj, Bardh and Galasso, Fabio}, title = {Multimodal Motion Conditioned Diffusion Model for Skeleton-based Video Anomaly Detection}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {10318-10329} }
CDFSL-V: Cross-Domain Few-Shot Learning for Videos: Sarinda Samarasinghe,

Mamshad Nayeem Rizve,

Navid Kardan,

Mubarak Shah; [pdf] [supp]
[bibtex]
@InProceedings{Samarasinghe_2023_ICCV, author = {Samarasinghe, Sarinda and Rizve, Mamshad Nayeem and Kardan, Navid and Shah, Mubarak}, title = {CDFSL-V: Cross-Domain Few-Shot Learning for Videos}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {11643-11652} }
Towards Viewpoint Robustness in Bird's Eye View Segmentation: Tzofi Klinghoffer,

Jonah Philion,

Wenzheng Chen,

Or Litany,

Zan Gojcic,

Jungseock Joo,

Ramesh Raskar,

Sanja Fidler,

Jose M. Alvarez; [pdf] [supp]
[bibtex]
@InProceedings{Klinghoffer_2023_ICCV, author = {Klinghoffer, Tzofi and Philion, Jonah and Chen, Wenzheng and Litany, Or and Gojcic, Zan and Joo, Jungseock and Raskar, Ramesh and Fidler, Sanja and Alvarez, Jose M.}, title = {Towards Viewpoint Robustness in Bird's Eye View Segmentation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {8515-8524} }
What Can a Cook in Italy Teach a Mechanic in India? Action Recognition Generalisation Over Scenarios and Locations: Chiara Plizzari,

Toby Perrett,

Barbara Caputo,

Dima Damen; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Plizzari_2023_ICCV, author = {Plizzari, Chiara and Perrett, Toby and Caputo, Barbara and Damen, Dima}, title = {What Can a Cook in Italy Teach a Mechanic in India? Action Recognition Generalisation Over Scenarios and Locations}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {13656-13666} }
EMDB: The Electromagnetic Database of Global 3D Human Pose and Shape in the Wild: Manuel Kaufmann,

Jie Song,

Chen Guo,

Kaiyue Shen,

Tianjian Jiang,

Chengcheng Tang,

Juan José Zárate,

Otmar Hilliges; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kaufmann_2023_ICCV, author = {Kaufmann, Manuel and Song, Jie and Guo, Chen and Shen, Kaiyue and Jiang, Tianjian and Tang, Chengcheng and Z\'arate, Juan Jos\'e and Hilliges, Otmar}, title = {EMDB: The Electromagnetic Database of Global 3D Human Pose and Shape in the Wild}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {14632-14643} }
Weakly-Supervised Action Segmentation and Unseen Error Detection in Anomalous Instructional Videos: Reza Ghoddoosian,

Isht Dwivedi,

Nakul Agarwal,

Behzad Dariush; [pdf] [supp]
[bibtex]
@InProceedings{Ghoddoosian_2023_ICCV, author = {Ghoddoosian, Reza and Dwivedi, Isht and Agarwal, Nakul and Dariush, Behzad}, title = {Weakly-Supervised Action Segmentation and Unseen Error Detection in Anomalous Instructional Videos}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {10128-10138} }
Mesh2Tex: Generating Mesh Textures from Image Queries: Alexey Bokhovkin,

Shubham Tulsiani,

Angela Dai; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Bokhovkin_2023_ICCV, author = {Bokhovkin, Alexey and Tulsiani, Shubham and Dai, Angela}, title = {Mesh2Tex: Generating Mesh Textures from Image Queries}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {8918-8928} }
Deep Feature Deblurring Diffusion for Detecting Out-of-Distribution Objects: Aming Wu,

Da Chen,

Cheng Deng; [pdf] [supp]
[bibtex]
@InProceedings{Wu_2023_ICCV, author = {Wu, Aming and Chen, Da and Deng, Cheng}, title = {Deep Feature Deblurring Diffusion for Detecting Out-of-Distribution Objects}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {13381-13391} }
Introducing Language Guidance in Prompt-based Continual Learning: Muhammad Gul Zain Ali Khan,

Muhammad Ferjad Naeem,

Luc Van Gool,

Didier Stricker,

Federico Tombari,

Muhammad Zeshan Afzal; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Khan_2023_ICCV, author = {Khan, Muhammad Gul Zain Ali and Naeem, Muhammad Ferjad and Van Gool, Luc and Stricker, Didier and Tombari, Federico and Afzal, Muhammad Zeshan}, title = {Introducing Language Guidance in Prompt-based Continual Learning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {11463-11473} }
Invariant Training 2D-3D Joint Hard Samples for Few-Shot Point Cloud Recognition: Xuanyu Yi,

Jiajun Deng,

Qianru Sun,

Xian-Sheng Hua,

Joo-Hwee Lim,

Hanwang Zhang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yi_2023_ICCV, author = {Yi, Xuanyu and Deng, Jiajun and Sun, Qianru and Hua, Xian-Sheng and Lim, Joo-Hwee and Zhang, Hanwang}, title = {Invariant Training 2D-3D Joint Hard Samples for Few-Shot Point Cloud Recognition}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {14463-14474} }
EigenPlaces: Training Viewpoint Robust Models for Visual Place Recognition: Gabriele Berton,

Gabriele Trivigno,

Barbara Caputo,

Carlo Masone; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Berton_2023_ICCV, author = {Berton, Gabriele and Trivigno, Gabriele and Caputo, Barbara and Masone, Carlo}, title = {EigenPlaces: Training Viewpoint Robust Models for Visual Place Recognition}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {11080-11090} }
CIRI: Curricular Inactivation for Residue-aware One-shot Video Inpainting: Weiying Zheng,

Cheng Xu,

Xuemiao Xu,

Wenxi Liu,

Shengfeng He; [pdf] [supp]
[bibtex]
@InProceedings{Zheng_2023_ICCV, author = {Zheng, Weiying and Xu, Cheng and Xu, Xuemiao and Liu, Wenxi and He, Shengfeng}, title = {CIRI: Curricular Inactivation for Residue-aware One-shot Video Inpainting}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {13012-13022} }
RSFNet: A White-Box Image Retouching Approach using Region-Specific Color Filters: Wenqi Ouyang,

Yi Dong,

Xiaoyang Kang,

Peiran Ren,

Xin Xu,

Xuansong Xie; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ouyang_2023_ICCV, author = {Ouyang, Wenqi and Dong, Yi and Kang, Xiaoyang and Ren, Peiran and Xu, Xin and Xie, Xuansong}, title = {RSFNet: A White-Box Image Retouching Approach using Region-Specific Color Filters}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {12160-12169} }
Tem-Adapter: Adapting Image-Text Pretraining for Video Question Answer: Guangyi Chen,

Xiao Liu,

Guangrun Wang,

Kun Zhang,

Philip H.S. Torr,

Xiao-Ping Zhang,

Yansong Tang; [pdf] [supp]
[bibtex]
@InProceedings{Chen_2023_ICCV, author = {Chen, Guangyi and Liu, Xiao and Wang, Guangrun and Zhang, Kun and Torr, Philip H.S. and Zhang, Xiao-Ping and Tang, Yansong}, title = {Tem-Adapter: Adapting Image-Text Pretraining for Video Question Answer}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {13945-13955} }
Unleashing the Potential of Spiking Neural Networks with Dynamic Confidence: Chen Li,

Edward G Jones,

Steve Furber; [pdf] [supp]
[bibtex]
@InProceedings{Li_2023_ICCV, author = {Li, Chen and Jones, Edward G and Furber, Steve}, title = {Unleashing the Potential of Spiking Neural Networks with Dynamic Confidence}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {13350-13360} }
TeD-SPAD: Temporal Distinctiveness for Self-Supervised Privacy-Preservation for Video Anomaly Detection: Joseph Fioresi,

Ishan Rajendrakumar Dave,

Mubarak Shah; [pdf] [supp]
[bibtex]
@InProceedings{Fioresi_2023_ICCV, author = {Fioresi, Joseph and Dave, Ishan Rajendrakumar and Shah, Mubarak}, title = {TeD-SPAD: Temporal Distinctiveness for Self-Supervised Privacy-Preservation for Video Anomaly Detection}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {13598-13609} }
HiTeA: Hierarchical Temporal-Aware Video-Language Pre-training: Qinghao Ye,

Guohai Xu,

Ming Yan,

Haiyang Xu,

Qi Qian,

Ji Zhang,

Fei Huang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ye_2023_ICCV, author = {Ye, Qinghao and Xu, Guohai and Yan, Ming and Xu, Haiyang and Qian, Qi and Zhang, Ji and Huang, Fei}, title = {HiTeA: Hierarchical Temporal-Aware Video-Language Pre-training}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {15405-15416} }
VAPCNet: Viewpoint-Aware 3D Point Cloud Completion: Zhiheng Fu,

Longguang Wang,

Lian Xu,

Zhiyong Wang,

Hamid Laga,

Yulan Guo,

Farid Boussaid,

Mohammed Bennamoun; [pdf]
[bibtex]
@InProceedings{Fu_2023_ICCV, author = {Fu, Zhiheng and Wang, Longguang and Xu, Lian and Wang, Zhiyong and Laga, Hamid and Guo, Yulan and Boussaid, Farid and Bennamoun, Mohammed}, title = {VAPCNet: Viewpoint-Aware 3D Point Cloud Completion}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {12108-12118} }
AutoSynth: Learning to Generate 3D Training Data for Object Point Cloud Registration: Zheng Dang,

Mathieu Salzmann; [pdf] [arXiv]
[bibtex]
@InProceedings{Dang_2023_ICCV, author = {Dang, Zheng and Salzmann, Mathieu}, title = {AutoSynth: Learning to Generate 3D Training Data for Object Point Cloud Registration}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {9009-9019} }
Self-supervised Learning of Implicit Shape Representation with Dense Correspondence for Deformable Objects: Baowen Zhang,

Jiahe Li,

Xiaoming Deng,

Yinda Zhang,

Cuixia Ma,

Hongan Wang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhang_2023_ICCV, author = {Zhang, Baowen and Li, Jiahe and Deng, Xiaoming and Zhang, Yinda and Ma, Cuixia and Wang, Hongan}, title = {Self-supervised Learning of Implicit Shape Representation with Dense Correspondence for Deformable Objects}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {14268-14278} }
Scaling Data Generation in Vision-and-Language Navigation: Zun Wang,

Jialu Li,

Yicong Hong,

Yi Wang,

Qi Wu,

Mohit Bansal,

Stephen Gould,

Hao Tan,

Yu Qiao; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2023_ICCV, author = {Wang, Zun and Li, Jialu and Hong, Yicong and Wang, Yi and Wu, Qi and Bansal, Mohit and Gould, Stephen and Tan, Hao and Qiao, Yu}, title = {Scaling Data Generation in Vision-and-Language Navigation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {12009-12020} }
Dual Learning with Dynamic Knowledge Distillation for Partially Relevant Video Retrieval: Jianfeng Dong,

Minsong Zhang,

Zheng Zhang,

Xianke Chen,

Daizong Liu,

Xiaoye Qu,

Xun Wang,

Baolong Liu; [pdf] [supp]
[bibtex]
@InProceedings{Dong_2023_ICCV, author = {Dong, Jianfeng and Zhang, Minsong and Zhang, Zheng and Chen, Xianke and Liu, Daizong and Qu, Xiaoye and Wang, Xun and Liu, Baolong}, title = {Dual Learning with Dynamic Knowledge Distillation for Partially Relevant Video Retrieval}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {11302-11312} }
Disposable Transfer Learning for Selective Source Task Unlearning: Seunghee Koh,

Hyounguk Shon,

Janghyeon Lee,

Hyeong Gwon Hong,

Junmo Kim; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Koh_2023_ICCV, author = {Koh, Seunghee and Shon, Hyounguk and Lee, Janghyeon and Hong, Hyeong Gwon and Kim, Junmo}, title = {Disposable Transfer Learning for Selective Source Task Unlearning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {11752-11760} }
Grounding 3D Object Affordance from 2D Interactions in Images: Yuhang Yang,

Wei Zhai,

Hongchen Luo,

Yang Cao,

Jiebo Luo,

Zheng-Jun Zha; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yang_2023_ICCV, author = {Yang, Yuhang and Zhai, Wei and Luo, Hongchen and Cao, Yang and Luo, Jiebo and Zha, Zheng-Jun}, title = {Grounding 3D Object Affordance from 2D Interactions in Images}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {10905-10915} }
Tube-Link: A Flexible Cross Tube Framework for Universal Video Segmentation: Xiangtai Li,

Haobo Yuan,

Wenwei Zhang,

Guangliang Cheng,

Jiangmiao Pang,

Chen Change Loy; [pdf] [supp]
[bibtex]
@InProceedings{Li_2023_ICCV, author = {Li, Xiangtai and Yuan, Haobo and Zhang, Wenwei and Cheng, Guangliang and Pang, Jiangmiao and Loy, Chen Change}, title = {Tube-Link: A Flexible Cross Tube Framework for Universal Video Segmentation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {13923-13933} }
Hybrid Spectral Denoising Transformer with Guided Attention: Zeqiang Lai,

Chenggang Yan,

Ying Fu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Lai_2023_ICCV, author = {Lai, Zeqiang and Yan, Chenggang and Fu, Ying}, title = {Hybrid Spectral Denoising Transformer with Guided Attention}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {13065-13075} }
HiVLP: Hierarchical Interactive Video-Language Pre-Training: Bin Shao,

Jianzhuang Liu,

Renjing Pei,

Songcen Xu,

Peng Dai,

Juwei Lu,

Weimian Li,

Youliang Yan; [pdf] [supp]
[bibtex]
@InProceedings{Shao_2023_ICCV, author = {Shao, Bin and Liu, Jianzhuang and Pei, Renjing and Xu, Songcen and Dai, Peng and Lu, Juwei and Li, Weimian and Yan, Youliang}, title = {HiVLP: Hierarchical Interactive Video-Language Pre-Training}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {13756-13766} }
Learning Concordant Attention via Target-aware Alignment for Visible-Infrared Person Re-identification: Jianbing Wu,

Hong Liu,

Yuxin Su,

Wei Shi,

Hao Tang; [pdf]
[bibtex]
@InProceedings{Wu_2023_ICCV, author = {Wu, Jianbing and Liu, Hong and Su, Yuxin and Shi, Wei and Tang, Hao}, title = {Learning Concordant Attention via Target-aware Alignment for Visible-Infrared Person Re-identification}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {11122-11131} }
Masked Motion Predictors are Strong 3D Action Representation Learners: Yunyao Mao,

Jiajun Deng,

Wengang Zhou,

Yao Fang,

Wanli Ouyang,

Houqiang Li; [pdf] [arXiv]
[bibtex]
@InProceedings{Mao_2023_ICCV, author = {Mao, Yunyao and Deng, Jiajun and Zhou, Wengang and Fang, Yao and Ouyang, Wanli and Li, Houqiang}, title = {Masked Motion Predictors are Strong 3D Action Representation Learners}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {10181-10191} }
RIGID: Recurrent GAN Inversion and Editing of Real Face Videos: Yangyang Xu,

Shengfeng He,

Kwan-Yee K. Wong,

Ping Luo; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Xu_2023_ICCV, author = {Xu, Yangyang and He, Shengfeng and Wong, Kwan-Yee K. and Luo, Ping}, title = {RIGID: Recurrent GAN Inversion and Editing of Real Face Videos}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {13691-13701} }
CSDA: Learning Category-Scale Joint Feature for Domain Adaptive Object Detection: Changlong Gao,

Chengxu Liu,

Yujie Dun,

Xueming Qian; [pdf] [supp]
[bibtex]
@InProceedings{Gao_2023_ICCV, author = {Gao, Changlong and Liu, Chengxu and Dun, Yujie and Qian, Xueming}, title = {CSDA: Learning Category-Scale Joint Feature for Domain Adaptive Object Detection}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {11421-11430} }
Single Image Defocus Deblurring via Implicit Neural Inverse Kernels: Yuhui Quan,

Xin Yao,

Hui Ji; [pdf] [supp]
[bibtex]
@InProceedings{Quan_2023_ICCV, author = {Quan, Yuhui and Yao, Xin and Ji, Hui}, title = {Single Image Defocus Deblurring via Implicit Neural Inverse Kernels}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {12600-12610} }
AvatarCraft: Transforming Text into Neural Human Avatars with Parameterized Shape and Pose Control: Ruixiang Jiang,

Can Wang,

Jingbo Zhang,

Menglei Chai,

Mingming He,

Dongdong Chen,

Jing Liao; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Jiang_2023_ICCV, author = {Jiang, Ruixiang and Wang, Can and Zhang, Jingbo and Chai, Menglei and He, Mingming and Chen, Dongdong and Liao, Jing}, title = {AvatarCraft: Transforming Text into Neural Human Avatars with Parameterized Shape and Pose Control}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {14371-14382} }
Why Is Prompt Tuning for Vision-Language Models Robust to Noisy Labels?: Cheng-En Wu,

Yu Tian,

Haichao Yu,

Heng Wang,

Pedro Morgado,

Yu Hen Hu,

Linjie Yang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wu_2023_ICCV, author = {Wu, Cheng-En and Tian, Yu and Yu, Haichao and Wang, Heng and Morgado, Pedro and Hu, Yu Hen and Yang, Linjie}, title = {Why Is Prompt Tuning for Vision-Language Models Robust to Noisy Labels?}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {15488-15497} }
Unified Pre-Training with Pseudo Texts for Text-To-Image Person Re-Identification: Zhiyin Shao,

Xinyu Zhang,

Changxing Ding,

Jian Wang,

Jingdong Wang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Shao_2023_ICCV, author = {Shao, Zhiyin and Zhang, Xinyu and Ding, Changxing and Wang, Jian and Wang, Jingdong}, title = {Unified Pre-Training with Pseudo Texts for Text-To-Image Person Re-Identification}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {11174-11184} }
Traj-MAE: Masked Autoencoders for Trajectory Prediction: Hao Chen,

Jiaze Wang,

Kun Shao,

Furui Liu,

Jianye Hao,

Chenyong Guan,

Guangyong Chen,

Pheng-Ann Heng; [pdf] [supp]
[bibtex]
@InProceedings{Chen_2023_ICCV, author = {Chen, Hao and Wang, Jiaze and Shao, Kun and Liu, Furui and Hao, Jianye and Guan, Chenyong and Chen, Guangyong and Heng, Pheng-Ann}, title = {Traj-MAE: Masked Autoencoders for Trajectory Prediction}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {8351-8362} }
UniFusion: Unified Multi-View Fusion Transformer for Spatial-Temporal Representation in Bird's-Eye-View: Zequn Qin,

Jingyu Chen,

Chao Chen,

Xiaozhi Chen,

Xi Li; [pdf] [supp]
[bibtex]
@InProceedings{Qin_2023_ICCV, author = {Qin, Zequn and Chen, Jingyu and Chen, Chao and Chen, Xiaozhi and Li, Xi}, title = {UniFusion: Unified Multi-View Fusion Transformer for Spatial-Temporal Representation in Bird's-Eye-View}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {8690-8699} }
Sample-adaptive Augmentation for Point Cloud Recognition Against Real-world Corruptions: Jie Wang,

Lihe Ding,

Tingfa Xu,

Shaocong Dong,

Xinli Xu,

Long Bai,

Jianan Li; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2023_ICCV, author = {Wang, Jie and Ding, Lihe and Xu, Tingfa and Dong, Shaocong and Xu, Xinli and Bai, Long and Li, Jianan}, title = {Sample-adaptive Augmentation for Point Cloud Recognition Against Real-world Corruptions}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {14330-14339} }
Modality Unifying Network for Visible-Infrared Person Re-Identification: Hao Yu,

Xu Cheng,

Wei Peng,

Weihao Liu,

Guoying Zhao; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yu_2023_ICCV, author = {Yu, Hao and Cheng, Xu and Peng, Wei and Liu, Weihao and Zhao, Guoying}, title = {Modality Unifying Network for Visible-Infrared Person Re-Identification}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {11185-11195} }
Taming Contrast Maximization for Learning Sequential, Low-latency, Event-based Optical Flow: Federico Paredes-Vallés,

Kirk Y. W. Scheper,

Christophe De Wagter,

Guido C. H. E. de Croon; [pdf] [supp]
[bibtex]
@InProceedings{Paredes-Valles_2023_ICCV, author = {Paredes-Vall\'es, Federico and Scheper, Kirk Y. W. and De Wagter, Christophe and de Croon, Guido C. H. E.}, title = {Taming Contrast Maximization for Learning Sequential, Low-latency, Event-based Optical Flow}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {9695-9705} }
CASSPR: Cross Attention Single Scan Place Recognition: Yan Xia,

Mariia Gladkova,

Rui Wang,

Qianyun Li,

Uwe Stilla,

João F Henriques,

Daniel Cremers; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Xia_2023_ICCV, author = {Xia, Yan and Gladkova, Mariia and Wang, Rui and Li, Qianyun and Stilla, Uwe and Henriques, Jo\~ao F and Cremers, Daniel}, title = {CASSPR: Cross Attention Single Scan Place Recognition}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {8461-8472} }
DDFM: Denoising Diffusion Model for Multi-Modality Image Fusion: Zixiang Zhao,

Haowen Bai,

Yuanzhi Zhu,

Jiangshe Zhang,

Shuang Xu,

Yulun Zhang,

Kai Zhang,

Deyu Meng,

Radu Timofte,

Luc Van Gool; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhao_2023_ICCV, author = {Zhao, Zixiang and Bai, Haowen and Zhu, Yuanzhi and Zhang, Jiangshe and Xu, Shuang and Zhang, Yulun and Zhang, Kai and Meng, Deyu and Timofte, Radu and Van Gool, Luc}, title = {DDFM: Denoising Diffusion Model for Multi-Modality Image Fusion}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {8082-8093} }
A Unified Continual Learning Framework with General Parameter-Efficient Tuning: Qiankun Gao,

Chen Zhao,

Yifan Sun,

Teng Xi,

Gang Zhang,

Bernard Ghanem,

Jian Zhang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Gao_2023_ICCV, author = {Gao, Qiankun and Zhao, Chen and Sun, Yifan and Xi, Teng and Zhang, Gang and Ghanem, Bernard and Zhang, Jian}, title = {A Unified Continual Learning Framework with General Parameter-Efficient Tuning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {11483-11493} }
Hierarchical Generation of Human-Object Interactions with Diffusion Probabilistic Models: Huaijin Pi,

Sida Peng,

Minghui Yang,

Xiaowei Zhou,

Hujun Bao; [pdf]
[bibtex]
@InProceedings{Pi_2023_ICCV, author = {Pi, Huaijin and Peng, Sida and Yang, Minghui and Zhou, Xiaowei and Bao, Hujun}, title = {Hierarchical Generation of Human-Object Interactions with Diffusion Probabilistic Models}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {15061-15073} }
Learning Data-Driven Vector-Quantized Degradation Model for Animation Video Super-Resolution: Zixi Tuo,

Huan Yang,

Jianlong Fu,

Yujie Dun,

Xueming Qian; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Tuo_2023_ICCV, author = {Tuo, Zixi and Yang, Huan and Fu, Jianlong and Dun, Yujie and Qian, Xueming}, title = {Learning Data-Driven Vector-Quantized Degradation Model for Animation Video Super-Resolution}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {13179-13189} }
Calibrating Panoramic Depth Estimation for Practical Localization and Mapping: Junho Kim,

Eun Sun Lee,

Young Min Kim; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kim_2023_ICCV, author = {Kim, Junho and Lee, Eun Sun and Kim, Young Min}, title = {Calibrating Panoramic Depth Estimation for Practical Localization and Mapping}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {8830-8840} }
DiffDis: Empowering Generative Diffusion Model with Cross-Modal Discrimination Capability: Runhui Huang,

Jianhua Han,

Guansong Lu,

Xiaodan Liang,

Yihan Zeng,

Wei Zhang,

Hang Xu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Huang_2023_ICCV, author = {Huang, Runhui and Han, Jianhua and Lu, Guansong and Liang, Xiaodan and Zeng, Yihan and Zhang, Wei and Xu, Hang}, title = {DiffDis: Empowering Generative Diffusion Model with Cross-Modal Discrimination Capability}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {15713-15723} }
View Consistent Purification for Accurate Cross-View Localization: Shan Wang,

Yanhao Zhang,

Akhil Perincherry,

Ankit Vora,

Hongdong Li; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2023_ICCV, author = {Wang, Shan and Zhang, Yanhao and Perincherry, Akhil and Vora, Ankit and Li, Hongdong}, title = {View Consistent Purification for Accurate Cross-View Localization}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {8197-8206} }
Efficient Video Action Detection with Token Dropout and Context Refinement: Lei Chen,

Zhan Tong,

Yibing Song,

Gangshan Wu,

Limin Wang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chen_2023_ICCV, author = {Chen, Lei and Tong, Zhan and Song, Yibing and Wu, Gangshan and Wang, Limin}, title = {Efficient Video Action Detection with Token Dropout and Context Refinement}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {10388-10399} }
Explicit Motion Disentangling for Efficient Optical Flow Estimation: Changxing Deng,

Ao Luo,

Haibin Huang,

Shaodan Ma,

Jiangyu Liu,

Shuaicheng Liu; [pdf]
[bibtex]
@InProceedings{Deng_2023_ICCV, author = {Deng, Changxing and Luo, Ao and Huang, Haibin and Ma, Shaodan and Liu, Jiangyu and Liu, Shuaicheng}, title = {Explicit Motion Disentangling for Efficient Optical Flow Estimation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {9521-9530} }
From Chaos Comes Order: Ordering Event Representations for Object Recognition and Detection: Nikola Zubić,

Daniel Gehrig,

Mathias Gehrig,

Davide Scaramuzza; [pdf] [supp]
[bibtex]
@InProceedings{Zubic_2023_ICCV, author = {Zubi\'c, Nikola and Gehrig, Daniel and Gehrig, Mathias and Scaramuzza, Davide}, title = {From Chaos Comes Order: Ordering Event Representations for Object Recognition and Detection}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {12846-12856} }
Identity-Consistent Aggregation for Video Object Detection: Chaorui Deng,

Da Chen,

Qi Wu; [pdf] [arXiv]
[bibtex]
@InProceedings{Deng_2023_ICCV, author = {Deng, Chaorui and Chen, Da and Wu, Qi}, title = {Identity-Consistent Aggregation for Video Object Detection}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {13434-13444} }
Relightify: Relightable 3D Faces from a Single Image via Diffusion Models: Foivos Paraperas Papantoniou,

Alexandros Lattas,

Stylianos Moschoglou,

Stefanos Zafeiriou; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Papantoniou_2023_ICCV, author = {Papantoniou, Foivos Paraperas and Lattas, Alexandros and Moschoglou, Stylianos and Zafeiriou, Stefanos}, title = {Relightify: Relightable 3D Faces from a Single Image via Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {8806-8817} }
Leveraging Spatio-Temporal Dependency for Skeleton-Based Action Recognition: Jungho Lee,

Minhyeok Lee,

Suhwan Cho,

Sungmin Woo,

Sungjun Jang,

Sangyoun Lee; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Lee_2023_ICCV, author = {Lee, Jungho and Lee, Minhyeok and Cho, Suhwan and Woo, Sungmin and Jang, Sungjun and Lee, Sangyoun}, title = {Leveraging Spatio-Temporal Dependency for Skeleton-Based Action Recognition}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {10255-10264} }
Camera-Driven Representation Learning for Unsupervised Domain Adaptive Person Re-identification: Geon Lee,

Sanghoon Lee,

Dohyung Kim,

Younghoon Shin,

Yongsang Yoon,

Bumsub Ham; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Lee_2023_ICCV, author = {Lee, Geon and Lee, Sanghoon and Kim, Dohyung and Shin, Younghoon and Yoon, Yongsang and Ham, Bumsub}, title = {Camera-Driven Representation Learning for Unsupervised Domain Adaptive Person Re-identification}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {11453-11462} }
Name Your Colour For the Task: Artificially Discover Colour Naming via Colour Quantisation Transformer: Shenghan Su,

Lin Gu,

Yue Yang,

Zenghui Zhang,

Tatsuya Harada; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Su_2023_ICCV, author = {Su, Shenghan and Gu, Lin and Yang, Yue and Zhang, Zenghui and Harada, Tatsuya}, title = {Name Your Colour For the Task: Artificially Discover Colour Naming via Colour Quantisation Transformer}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {12021-12031} }
FSAR: Federated Skeleton-based Action Recognition with Adaptive Topology Structure and Knowledge Distillation: Jingwen Guo,

Hong Liu,

Shitong Sun,

Tianyu Guo,

Min Zhang,

Chenyang Si; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Guo_2023_ICCV, author = {Guo, Jingwen and Liu, Hong and Sun, Shitong and Guo, Tianyu and Zhang, Min and Si, Chenyang}, title = {FSAR: Federated Skeleton-based Action Recognition with Adaptive Topology Structure and Knowledge Distillation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {10400-10410} }
Video Adverse-Weather-Component Suppression Network via Weather Messenger and Adversarial Backpropagation: Yijun Yang,

Angelica I. Aviles-Rivero,

Huazhu Fu,

Ye Liu,

Weiming Wang,

Lei Zhu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yang_2023_ICCV, author = {Yang, Yijun and Aviles-Rivero, Angelica I. and Fu, Huazhu and Liu, Ye and Wang, Weiming and Zhu, Lei}, title = {Video Adverse-Weather-Component Suppression Network via Weather Messenger and Adversarial Backpropagation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {13200-13210} }
Part-Aware Transformer for Generalizable Person Re-identification: Hao Ni,

Yuke Li,

Lianli Gao,

Heng Tao Shen,

Jingkuan Song; [pdf] [arXiv]
[bibtex]
@InProceedings{Ni_2023_ICCV, author = {Ni, Hao and Li, Yuke and Gao, Lianli and Shen, Heng Tao and Song, Jingkuan}, title = {Part-Aware Transformer for Generalizable Person Re-identification}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {11280-11289} }
Blending-NeRF: Text-Driven Localized Editing in Neural Radiance Fields: Hyeonseop Song,

Seokhun Choi,

Hoseok Do,

Chul Lee,

Taehyeong Kim; [pdf] [supp]
[bibtex]
@InProceedings{Song_2023_ICCV, author = {Song, Hyeonseop and Choi, Seokhun and Do, Hoseok and Lee, Chul and Kim, Taehyeong}, title = {Blending-NeRF: Text-Driven Localized Editing in Neural Radiance Fields}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {14383-14393} }
Panoramas from Photons: Sacha Jungerman,

Atul Ingle,

Mohit Gupta; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Jungerman_2023_ICCV, author = {Jungerman, Sacha and Ingle, Atul and Gupta, Mohit}, title = {Panoramas from Photons}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {10626-10636} }
Global Adaptation Meets Local Generalization: Unsupervised Domain Adaptation for 3D Human Pose Estimation: Wenhao Chai,

Zhongyu Jiang,

Jenq-Neng Hwang,

Gaoang Wang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chai_2023_ICCV, author = {Chai, Wenhao and Jiang, Zhongyu and Hwang, Jenq-Neng and Wang, Gaoang}, title = {Global Adaptation Meets Local Generalization: Unsupervised Domain Adaptation for 3D Human Pose Estimation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {14655-14665} }
DeFormer: Integrating Transformers with Deformable Models for 3D Shape Abstraction from a Single Image: Di Liu,

Xiang Yu,

Meng Ye,

Qilong Zhangli,

Zhuowei Li,

Zhixing Zhang,

Dimitris N. Metaxas; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Liu_2023_ICCV, author = {Liu, Di and Yu, Xiang and Ye, Meng and Zhangli, Qilong and Li, Zhuowei and Zhang, Zhixing and Metaxas, Dimitris N.}, title = {DeFormer: Integrating Transformers with Deformable Models for 3D Shape Abstraction from a Single Image}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {14236-14246} }
Cross-view Semantic Alignment for Livestreaming Product Recognition: Wenjie Yang,

Yiyi Chen,

Yan Li,

Yanhua Cheng,

Xudong Liu,

Quan Chen,

Han Li; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yang_2023_ICCV, author = {Yang, Wenjie and Chen, Yiyi and Li, Yan and Cheng, Yanhua and Liu, Xudong and Chen, Quan and Li, Han}, title = {Cross-view Semantic Alignment for Livestreaming Product Recognition}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {13404-13413} }
Continuously Masked Transformer for Image Inpainting: Keunsoo Ko,

Chang-Su Kim; [pdf] [supp]
[bibtex]
@InProceedings{Ko_2023_ICCV, author = {Ko, Keunsoo and Kim, Chang-Su}, title = {Continuously Masked Transformer for Image Inpainting}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {13169-13178} }
Vanishing Point Estimation in Uncalibrated Images with Prior Gravity Direction: Rémi Pautrat,

Shaohui Liu,

Petr Hruby,

Marc Pollefeys,

Daniel Barath; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Pautrat_2023_ICCV, author = {Pautrat, R\'emi and Liu, Shaohui and Hruby, Petr and Pollefeys, Marc and Barath, Daniel}, title = {Vanishing Point Estimation in Uncalibrated Images with Prior Gravity Direction}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {14118-14127} }
Learn TAROT with MENTOR: A Meta-Learned Self-Supervised Approach for Trajectory Prediction: Mozhgan Pourkeshavarz,

Changhe Chen,

Amir Rasouli; [pdf] [supp]
[bibtex]
@InProceedings{Pourkeshavarz_2023_ICCV, author = {Pourkeshavarz, Mozhgan and Chen, Changhe and Rasouli, Amir}, title = {Learn TAROT with MENTOR: A Meta-Learned Self-Supervised Approach for Trajectory Prediction}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {8384-8393} }
MatrixVT: Efficient Multi-Camera to BEV Transformation for 3D Perception: Hongyu Zhou,

Zheng Ge,

Zeming Li,

Xiangyu Zhang; [pdf] [arXiv]
[bibtex]
@InProceedings{Zhou_2023_ICCV, author = {Zhou, Hongyu and Ge, Zheng and Li, Zeming and Zhang, Xiangyu}, title = {MatrixVT: Efficient Multi-Camera to BEV Transformation for 3D Perception}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {8548-8557} }
Local and Global Logit Adjustments for Long-Tailed Learning: Yingfan Tao,

Jingna Sun,

Hao Yang,

Li Chen,

Xu Wang,

Wenming Yang,

Daniel Du,

Min Zheng; [pdf]
[bibtex]
@InProceedings{Tao_2023_ICCV, author = {Tao, Yingfan and Sun, Jingna and Yang, Hao and Chen, Li and Wang, Xu and Yang, Wenming and Du, Daniel and Zheng, Min}, title = {Local and Global Logit Adjustments for Long-Tailed Learning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {11783-11792} }
Sensitivity-Aware Visual Parameter-Efficient Fine-Tuning: Haoyu He,

Jianfei Cai,

Jing Zhang,

Dacheng Tao,

Bohan Zhuang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{He_2023_ICCV, author = {He, Haoyu and Cai, Jianfei and Zhang, Jing and Tao, Dacheng and Zhuang, Bohan}, title = {Sensitivity-Aware Visual Parameter-Efficient Fine-Tuning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {11825-11835} }
Weakly-supervised 3D Pose Transfer with Keypoints: Jinnan Chen,

Chen Li,

Gim Hee Lee; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chen_2023_ICCV, author = {Chen, Jinnan and Li, Chen and Lee, Gim Hee}, title = {Weakly-supervised 3D Pose Transfer with Keypoints}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {15156-15165} }
On the Effectiveness of Spectral Discriminators for Perceptual Quality Improvement: Xin Luo,

Yunan Zhu,

Shunxin Xu,

Dong Liu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Luo_2023_ICCV, author = {Luo, Xin and Zhu, Yunan and Xu, Shunxin and Liu, Dong}, title = {On the Effectiveness of Spectral Discriminators for Perceptual Quality Improvement}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {13243-13253} }
Diffusion-Based 3D Human Pose Estimation with Multi-Hypothesis Aggregation: Wenkang Shan,

Zhenhua Liu,

Xinfeng Zhang,

Zhao Wang,

Kai Han,

Shanshe Wang,

Siwei Ma,

Wen Gao; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Shan_2023_ICCV, author = {Shan, Wenkang and Liu, Zhenhua and Zhang, Xinfeng and Wang, Zhao and Han, Kai and Wang, Shanshe and Ma, Siwei and Gao, Wen}, title = {Diffusion-Based 3D Human Pose Estimation with Multi-Hypothesis Aggregation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {14761-14771} }
RPEFlow: Multimodal Fusion of RGB-PointCloud-Event for Joint Optical Flow and Scene Flow Estimation: Zhexiong Wan,

Yuxin Mao,

Jing Zhang,

Yuchao Dai; [pdf] [supp]
[bibtex]
@InProceedings{Wan_2023_ICCV, author = {Wan, Zhexiong and Mao, Yuxin and Zhang, Jing and Dai, Yuchao}, title = {RPEFlow: Multimodal Fusion of RGB-PointCloud-Event for Joint Optical Flow and Scene Flow Estimation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {10030-10040} }
DyGait: Exploiting Dynamic Representations for High-performance Gait Recognition: Ming Wang,

Xianda Guo,

Beibei Lin,

Tian Yang,

Zheng Zhu,

Lincheng Li,

Shunli Zhang,

Xin Yu; [pdf] [arXiv]
[bibtex]
@InProceedings{Wang_2023_ICCV, author = {Wang, Ming and Guo, Xianda and Lin, Beibei and Yang, Tian and Zhu, Zheng and Li, Lincheng and Zhang, Shunli and Yu, Xin}, title = {DyGait: Exploiting Dynamic Representations for High-performance Gait Recognition}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {13424-13433} }
Helping Hands: An Object-Aware Ego-Centric Video Recognition Model: Chuhan Zhang,

Ankush Gupta,

Andrew Zisserman; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhang_2023_ICCV, author = {Zhang, Chuhan and Gupta, Ankush and Zisserman, Andrew}, title = {Helping Hands: An Object-Aware Ego-Centric Video Recognition Model}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {13901-13912} }
SpinCam: High-Speed Imaging via a Rotating Point-Spread Function: Dorian Chan,

Mark Sheinin,

Matthew O'Toole; [pdf] [supp]
[bibtex]
@InProceedings{Chan_2023_ICCV, author = {Chan, Dorian and Sheinin, Mark and O'Toole, Matthew}, title = {SpinCam: High-Speed Imaging via a Rotating Point-Spread Function}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {10789-10799} }
GlueStick: Robust Image Matching by Sticking Points and Lines Together: Rémi Pautrat,

Iago Suárez,

Yifan Yu,

Marc Pollefeys,

Viktor Larsson; [pdf] [supp]
[bibtex]
@InProceedings{Pautrat_2023_ICCV, author = {Pautrat, R\'emi and Su\'arez, Iago and Yu, Yifan and Pollefeys, Marc and Larsson, Viktor}, title = {GlueStick: Robust Image Matching by Sticking Points and Lines Together}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {9706-9716} }
Computational 3D Imaging with Position Sensors: Jeremy Klotz,

Mohit Gupta,

Aswin C. Sankaranarayanan; [pdf] [supp]
[bibtex]
@InProceedings{Klotz_2023_ICCV, author = {Klotz, Jeremy and Gupta, Mohit and Sankaranarayanan, Aswin C.}, title = {Computational 3D Imaging with Position Sensors}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {8125-8134} }
Towards Multi-Layered 3D Garments Animation: Yidi Shao,

Chen Change Loy,

Bo Dai; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Shao_2023_ICCV, author = {Shao, Yidi and Loy, Chen Change and Dai, Bo}, title = {Towards Multi-Layered 3D Garments Animation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {14361-14370} }
Learning Image Harmonization in the Linear Color Space: Ke Xu,

Gerhard Petrus Hancke,

Rynson W.H. Lau; [pdf]
[bibtex]
@InProceedings{Xu_2023_ICCV, author = {Xu, Ke and Hancke, Gerhard Petrus and Lau, Rynson W.H.}, title = {Learning Image Harmonization in the Linear Color Space}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {12570-12579} }
Chasing Clouds: Differentiable Volumetric Rasterisation of Point Clouds as a Highly Efficient and Accurate Loss for Large-Scale Deformable 3D Registration: Mattias P. Heinrich,

Alexander Bigalke,

Christoph Großbröhmer,

Lasse Hansen; [pdf] [supp]
[bibtex]
@InProceedings{Heinrich_2023_ICCV, author = {Heinrich, Mattias P. and Bigalke, Alexander and Gro{\ss}br\"ohmer, Christoph and Hansen, Lasse}, title = {Chasing Clouds: Differentiable Volumetric Rasterisation of Point Clouds as a Highly Efficient and Accurate Loss for Large-Scale Deformable 3D Registration}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {8026-8036} }
The Devil is in the Upsampling: Architectural Decisions Made Simpler for Denoising with Deep Image Prior: Yilin Liu,

Jiang Li,

Yunkui Pang,

Dong Nie,

Pew-Thian Yap; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Liu_2023_ICCV, author = {Liu, Yilin and Li, Jiang and Pang, Yunkui and Nie, Dong and Yap, Pew-Thian}, title = {The Devil is in the Upsampling: Architectural Decisions Made Simpler for Denoising with Deep Image Prior}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {12408-12417} }
Video Object Segmentation-aware Video Frame Interpolation: Jun-Sang Yoo,

Hongjae Lee,

Seung-Won Jung; [pdf] [supp]
[bibtex]
@InProceedings{Yoo_2023_ICCV, author = {Yoo, Jun-Sang and Lee, Hongjae and Jung, Seung-Won}, title = {Video Object Segmentation-aware Video Frame Interpolation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {12322-12333} }
Coherent Event Guided Low-Light Video Enhancement: Jinxiu Liang,

Yixin Yang,

Boyu Li,

Peiqi Duan,

Yong Xu,

Boxin Shi; [pdf] [supp]
[bibtex]
@InProceedings{Liang_2023_ICCV, author = {Liang, Jinxiu and Yang, Yixin and Li, Boyu and Duan, Peiqi and Xu, Yong and Shi, Boxin}, title = {Coherent Event Guided Low-Light Video Enhancement}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {10615-10625} }
FCCNs: Fully Complex-valued Convolutional Networks using Complex-valued Color Model and Loss Function: Saurabh Yadav,

Koteswar Rao Jerripothula; [pdf] [supp]
[bibtex]
@InProceedings{Yadav_2023_ICCV, author = {Yadav, Saurabh and Jerripothula, Koteswar Rao}, title = {FCCNs: Fully Complex-valued Convolutional Networks using Complex-valued Color Model and Loss Function}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {10689-10698} }
S-TREK: Sequential Translation and Rotation Equivariant Keypoints for Local Feature Extraction: Emanuele Santellani,

Christian Sormann,

Mattia Rossi,

Andreas Kuhn,

Friedrich Fraundorfer; [pdf] [supp]
[bibtex]
@InProceedings{Santellani_2023_ICCV, author = {Santellani, Emanuele and Sormann, Christian and Rossi, Mattia and Kuhn, Andreas and Fraundorfer, Friedrich}, title = {S-TREK: Sequential Translation and Rotation Equivariant Keypoints for Local Feature Extraction}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {9728-9737} }
E2NeRF: Event Enhanced Neural Radiance Fields from Blurry Images: Yunshan Qi,

Lin Zhu,

Yu Zhang,

Jia Li; [pdf] [supp]
[bibtex]
@InProceedings{Qi_2023_ICCV, author = {Qi, Yunshan and Zhu, Lin and Zhang, Yu and Li, Jia}, title = {E2NeRF: Event Enhanced Neural Radiance Fields from Blurry Images}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {13254-13264} }
EgoTV: Egocentric Task Verification from Natural Language Task Descriptions: Rishi Hazra,

Brian Chen,

Akshara Rai,

Nitin Kamra,

Ruta Desai; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Hazra_2023_ICCV, author = {Hazra, Rishi and Chen, Brian and Rai, Akshara and Kamra, Nitin and Desai, Ruta}, title = {EgoTV: Egocentric Task Verification from Natural Language Task Descriptions}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {15417-15429} }
LMR: A Large-Scale Multi-Reference Dataset for Reference-Based Super-Resolution: Lin Zhang,

Xin Li,

Dongliang He,

Fu Li,

Errui Ding,

Zhaoxiang Zhang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhang_2023_ICCV, author = {Zhang, Lin and Li, Xin and He, Dongliang and Li, Fu and Ding, Errui and Zhang, Zhaoxiang}, title = {LMR: A Large-Scale Multi-Reference Dataset for Reference-Based Super-Resolution}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {13118-13127} }
Neural Implicit Surface Evolution: Tiago Novello,

Vinicius da Silva,

Guilherme Schardong,

Luiz Schirmer,

Helio Lopes,

Luiz Velho; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Novello_2023_ICCV, author = {Novello, Tiago and da Silva, Vinicius and Schardong, Guilherme and Schirmer, Luiz and Lopes, Helio and Velho, Luiz}, title = {Neural Implicit Surface Evolution}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {14279-14289} }
Distribution-Aligned Diffusion for Human Mesh Recovery: Lin Geng Foo,

Jia Gong,

Hossein Rahmani,

Jun Liu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Foo_2023_ICCV, author = {Foo, Lin Geng and Gong, Jia and Rahmani, Hossein and Liu, Jun}, title = {Distribution-Aligned Diffusion for Human Mesh Recovery}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {9221-9232} }
Diffuse3D: Wide-Angle 3D Photography via Bilateral Diffusion: Yutao Jiang,

Yang Zhou,

Yuan Liang,

Wenxi Liu,

Jianbo Jiao,

Yuhui Quan,

Shengfeng He; [pdf] [supp]
[bibtex]
@InProceedings{Jiang_2023_ICCV, author = {Jiang, Yutao and Zhou, Yang and Liang, Yuan and Liu, Wenxi and Jiao, Jianbo and Quan, Yuhui and He, Shengfeng}, title = {Diffuse3D: Wide-Angle 3D Photography via Bilateral Diffusion}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {8998-9008} }
Tubelet-Contrastive Self-Supervision for Video-Efficient Generalization: Fida Mohammad Thoker,

Hazel Doughty,

Cees G. M. Snoek; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Thoker_2023_ICCV, author = {Thoker, Fida Mohammad and Doughty, Hazel and Snoek, Cees G. M.}, title = {Tubelet-Contrastive Self-Supervision for Video-Efficient Generalization}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {13812-13823} }
Generalizing Event-Based Motion Deblurring in Real-World Scenarios: Xiang Zhang,

Lei Yu,

Wen Yang,

Jianzhuang Liu,

Gui-Song Xia; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhang_2023_ICCV, author = {Zhang, Xiang and Yu, Lei and Yang, Wen and Liu, Jianzhuang and Xia, Gui-Song}, title = {Generalizing Event-Based Motion Deblurring in Real-World Scenarios}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {10734-10744} }
RCA-NOC: Relative Contrastive Alignment for Novel Object Captioning: Jiashuo Fan,

Yaoyuan Liang,

Leyao Liu,

Shaolun Huang,

Lei Zhang; [pdf]
[bibtex]
@InProceedings{Fan_2023_ICCV, author = {Fan, Jiashuo and Liang, Yaoyuan and Liu, Leyao and Huang, Shaolun and Zhang, Lei}, title = {RCA-NOC: Relative Contrastive Alignment for Novel Object Captioning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {15510-15520} }
What Can Simple Arithmetic Operations Do for Temporal Modeling?: Wenhao Wu,

Yuxin Song,

Zhun Sun,

Jingdong Wang,

Chang Xu,

Wanli Ouyang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wu_2023_ICCV, author = {Wu, Wenhao and Song, Yuxin and Sun, Zhun and Wang, Jingdong and Xu, Chang and Ouyang, Wanli}, title = {What Can Simple Arithmetic Operations Do for Temporal Modeling?}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {13712-13722} }
Pixel Adaptive Deep Unfolding Transformer for Hyperspectral Image Reconstruction: Miaoyu Li,

Ying Fu,

Ji Liu,

Yulun Zhang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Li_2023_ICCV, author = {Li, Miaoyu and Fu, Ying and Liu, Ji and Zhang, Yulun}, title = {Pixel Adaptive Deep Unfolding Transformer for Hyperspectral Image Reconstruction}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {12959-12968} }
Dynamic PlenOctree for Adaptive Sampling Refinement in Explicit NeRF: Haotian Bai,

Yiqi Lin,

Yize Chen,

Lin Wang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Bai_2023_ICCV, author = {Bai, Haotian and Lin, Yiqi and Chen, Yize and Wang, Lin}, title = {Dynamic PlenOctree for Adaptive Sampling Refinement in Explicit NeRF}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {8785-8795} }
Scene Matters: Model-based Deep Video Compression: Lv Tang,

Xinfeng Zhang,

Gai Zhang,

Xiaoqi Ma; [pdf] [arXiv]
[bibtex]
@InProceedings{Tang_2023_ICCV, author = {Tang, Lv and Zhang, Xinfeng and Zhang, Gai and Ma, Xiaoqi}, title = {Scene Matters: Model-based Deep Video Compression}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {12481-12491} }
A Good Student is Cooperative and Reliable: CNN-Transformer Collaborative Learning for Semantic Segmentation: Jinjing Zhu,

Yunhao Luo,

Xu Zheng,

Hao Wang,

Lin Wang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhu_2023_ICCV, author = {Zhu, Jinjing and Luo, Yunhao and Zheng, Xu and Wang, Hao and Wang, Lin}, title = {A Good Student is Cooperative and Reliable: CNN-Transformer Collaborative Learning for Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {11720-11730} }
Fan-Beam Binarization Difference Projection (FB-BDP): A Novel Local Object Descriptor for Fine-Grained Leaf Image Retrieval: Xin Chen,

Bin Wang,

Yongsheng Gao; [pdf]
[bibtex]
@InProceedings{Chen_2023_ICCV, author = {Chen, Xin and Wang, Bin and Gao, Yongsheng}, title = {Fan-Beam Binarization Difference Projection (FB-BDP): A Novel Local Object Descriptor for Fine-Grained Leaf Image Retrieval}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {11102-11111} }
InterDiff: Generating 3D Human-Object Interactions with Physics-Informed Diffusion: Sirui Xu,

Zhengyuan Li,

Yu-Xiong Wang,

Liang-Yan Gui; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Xu_2023_ICCV, author = {Xu, Sirui and Li, Zhengyuan and Wang, Yu-Xiong and Gui, Liang-Yan}, title = {InterDiff: Generating 3D Human-Object Interactions with Physics-Informed Diffusion}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {14928-14940} }
IST-Net: Prior-Free Category-Level Pose Estimation with Implicit Space Transformation: Jianhui Liu,

Yukang Chen,

Xiaoqing Ye,

Xiaojuan Qi; [pdf] [supp]
[bibtex]
@InProceedings{Liu_2023_ICCV, author = {Liu, Jianhui and Chen, Yukang and Ye, Xiaoqing and Qi, Xiaojuan}, title = {IST-Net: Prior-Free Category-Level Pose Estimation with Implicit Space Transformation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {13978-13988} }
Curvature-Aware Training for Coordinate Networks: Hemanth Saratchandran,

Shin-Fang Chng,

Sameera Ramasinghe,

Lachlan MacDonald,

Simon Lucey; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Saratchandran_2023_ICCV, author = {Saratchandran, Hemanth and Chng, Shin-Fang and Ramasinghe, Sameera and MacDonald, Lachlan and Lucey, Simon}, title = {Curvature-Aware Training for Coordinate Networks}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {13328-13338} }
Learning Rain Location Prior for Nighttime Deraining: Fan Zhang,

Shaodi You,

Yu Li,

Ying Fu; [pdf] [supp]
[bibtex]
@InProceedings{Zhang_2023_ICCV, author = {Zhang, Fan and You, Shaodi and Li, Yu and Fu, Ying}, title = {Learning Rain Location Prior for Nighttime Deraining}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {13148-13157} }
FBLNet: FeedBack Loop Network for Driver Attention Prediction: Yilong Chen,

Zhixiong Nan,

Tao Xiang; [pdf] [arXiv]
[bibtex]
@InProceedings{Chen_2023_ICCV, author = {Chen, Yilong and Nan, Zhixiong and Xiang, Tao}, title = {FBLNet: FeedBack Loop Network for Driver Attention Prediction}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {13371-13380} }
Video Anomaly Detection via Sequentially Learning Multiple Pretext Tasks: Chenrui Shi,

Che Sun,

Yuwei Wu,

Yunde Jia; [pdf] [supp]
[bibtex]
@InProceedings{Shi_2023_ICCV, author = {Shi, Chenrui and Sun, Che and Wu, Yuwei and Jia, Yunde}, title = {Video Anomaly Detection via Sequentially Learning Multiple Pretext Tasks}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {10330-10340} }
SlaBins: Fisheye Depth Estimation using Slanted Bins on Road Environments: Jongsung Lee,

Gyeongsu Cho,

Jeongin Park,

Kyongjun Kim,

Seongoh Lee,

Jung-Hee Kim,

Seong-Gyun Jeong,

Kyungdon Joo; [pdf] [supp]
[bibtex]
@InProceedings{Lee_2023_ICCV, author = {Lee, Jongsung and Cho, Gyeongsu and Park, Jeongin and Kim, Kyongjun and Lee, Seongoh and Kim, Jung-Hee and Jeong, Seong-Gyun and Joo, Kyungdon}, title = {SlaBins: Fisheye Depth Estimation using Slanted Bins on Road Environments}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {8765-8774} }
March in Chat: Interactive Prompting for Remote Embodied Referring Expression: Yanyuan Qiao,

Yuankai Qi,

Zheng Yu,

Jing Liu,

Qi Wu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Qiao_2023_ICCV, author = {Qiao, Yanyuan and Qi, Yuankai and Yu, Zheng and Liu, Jing and Wu, Qi}, title = {March in Chat: Interactive Prompting for Remote Embodied Referring Expression}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {15758-15767} }
Efficient Unified Demosaicing for Bayer and Non-Bayer Patterned Image Sensors: Haechang Lee,

Dongwon Park,

Wongi Jeong,

Kijeong Kim,

Hyunwoo Je,

Dongil Ryu,

Se Young Chun; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Lee_2023_ICCV, author = {Lee, Haechang and Park, Dongwon and Jeong, Wongi and Kim, Kijeong and Je, Hyunwoo and Ryu, Dongil and Chun, Se Young}, title = {Efficient Unified Demosaicing for Bayer and Non-Bayer Patterned Image Sensors}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {12750-12759} }
Spatially-Adaptive Feature Modulation for Efficient Image Super-Resolution: Long Sun,

Jiangxin Dong,

Jinhui Tang,

Jinshan Pan; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Sun_2023_ICCV, author = {Sun, Long and Dong, Jiangxin and Tang, Jinhui and Pan, Jinshan}, title = {Spatially-Adaptive Feature Modulation for Efficient Image Super-Resolution}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {13190-13199} }
Unsupervised Image Denoising in Real-World Scenarios via Self-Collaboration Parallel Generative Adversarial Branches: Xin Lin,

Chao Ren,

Xiao Liu,

Jie Huang,

Yinjie Lei; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Lin_2023_ICCV, author = {Lin, Xin and Ren, Chao and Liu, Xiao and Huang, Jie and Lei, Yinjie}, title = {Unsupervised Image Denoising in Real-World Scenarios via Self-Collaboration Parallel Generative Adversarial Branches}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {12642-12652} }
Self-supervised Image Denoising with Downsampled Invariance Loss and Conditional Blind-Spot Network: Yeong Il Jang,

Keuntek Lee,

Gu Yong Park,

Seyun Kim,

Nam Ik Cho; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Jang_2023_ICCV, author = {Jang, Yeong Il and Lee, Keuntek and Park, Gu Yong and Kim, Seyun and Cho, Nam Ik}, title = {Self-supervised Image Denoising with Downsampled Invariance Loss and Conditional Blind-Spot Network}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {12196-12205} }
Generative Action Description Prompts for Skeleton-based Action Recognition: Wangmeng Xiang,

Chao Li,

Yuxuan Zhou,

Biao Wang,

Lei Zhang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Xiang_2023_ICCV, author = {Xiang, Wangmeng and Li, Chao and Zhou, Yuxuan and Wang, Biao and Zhang, Lei}, title = {Generative Action Description Prompts for Skeleton-based Action Recognition}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {10276-10285} }
Transparent Shape from a Single View Polarization Image: Mingqi Shao,

Chongkun Xia,

Zhendong Yang,

Junnan Huang,

Xueqian Wang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Shao_2023_ICCV, author = {Shao, Mingqi and Xia, Chongkun and Yang, Zhendong and Huang, Junnan and Wang, Xueqian}, title = {Transparent Shape from a Single View Polarization Image}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {9277-9286} }
DriveAdapter: Breaking the Coupling Barrier of Perception and Planning in End-to-End Autonomous Driving: Xiaosong Jia,

Yulu Gao,

Li Chen,

Junchi Yan,

Patrick Langechuan Liu,

Hongyang Li; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Jia_2023_ICCV, author = {Jia, Xiaosong and Gao, Yulu and Chen, Li and Yan, Junchi and Liu, Patrick Langechuan and Li, Hongyang}, title = {DriveAdapter: Breaking the Coupling Barrier of Perception and Planning in End-to-End Autonomous Driving}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {7953-7963} }
General Planar Motion from a Pair of 3D Correspondences: Juan Carlos Dibene,

Zhixiang Min,

Enrique Dunn; [pdf] [supp]
[bibtex]
@InProceedings{Dibene_2023_ICCV, author = {Dibene, Juan Carlos and Min, Zhixiang and Dunn, Enrique}, title = {General Planar Motion from a Pair of 3D Correspondences}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {8060-8070} }
Single Depth-image 3D Reflection Symmetry and Shape Prediction: Zhaoxuan Zhang,

Bo Dong,

Tong Li,

Felix Heide,

Pieter Peers,

Baocai Yin,

Xin Yang; [pdf] [supp]
[bibtex]
@InProceedings{Zhang_2023_ICCV, author = {Zhang, Zhaoxuan and Dong, Bo and Li, Tong and Heide, Felix and Peers, Pieter and Yin, Baocai and Yang, Xin}, title = {Single Depth-image 3D Reflection Symmetry and Shape Prediction}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {8896-8906} }
Downscaled Representation Matters: Improving Image Rescaling with Collaborative Downscaled Images: Bingna Xu,

Yong Guo,

Luoqian Jiang,

Mianjie Yu,

Jian Chen; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Xu_2023_ICCV, author = {Xu, Bingna and Guo, Yong and Jiang, Luoqian and Yu, Mianjie and Chen, Jian}, title = {Downscaled Representation Matters: Improving Image Rescaling with Collaborative Downscaled Images}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {12237-12247} }
Attention Discriminant Sampling for Point Clouds: Cheng-Yao Hong,

Yu-Ying Chou,

Tyng-Luh Liu; [pdf] [supp]
[bibtex]
@InProceedings{Hong_2023_ICCV, author = {Hong, Cheng-Yao and Chou, Yu-Ying and Liu, Tyng-Luh}, title = {Attention Discriminant Sampling for Point Clouds}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {14429-14440} }
IHNet: Iterative Hierarchical Network Guided by High-Resolution Estimated Information for Scene Flow Estimation: Yun Wang,

Cheng Chi,

Min Lin,

Xin Yang; [pdf]
[bibtex]
@InProceedings{Wang_2023_ICCV, author = {Wang, Yun and Chi, Cheng and Lin, Min and Yang, Xin}, title = {IHNet: Iterative Hierarchical Network Guided by High-Resolution Estimated Information for Scene Flow Estimation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {10073-10082} }
SimNP: Learning Self-Similarity Priors Between Neural Points: Christopher Wewer,

Eddy Ilg,

Bernt Schiele,

Jan Eric Lenssen; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wewer_2023_ICCV, author = {Wewer, Christopher and Ilg, Eddy and Schiele, Bernt and Lenssen, Jan Eric}, title = {SimNP: Learning Self-Similarity Priors Between Neural Points}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {8841-8852} }
Beyond the Limitation of Monocular 3D Detector via Knowledge Distillation: Yiran Yang,

Dongshuo Yin,

Xuee Rong,

Xian Sun,

Wenhui Diao,

Xinming Li; [pdf]
[bibtex]
@InProceedings{Yang_2023_ICCV, author = {Yang, Yiran and Yin, Dongshuo and Rong, Xuee and Sun, Xian and Diao, Wenhui and Li, Xinming}, title = {Beyond the Limitation of Monocular 3D Detector via Knowledge Distillation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {9077-9086} }
Temporal-Coded Spiking Neural Networks with Dynamic Firing Threshold: Learning with Event-Driven Backpropagation: Wenjie Wei,

Malu Zhang,

Hong Qu,

Ammar Belatreche,

Jian Zhang,

Hong Chen; [pdf]
[bibtex]
@InProceedings{Wei_2023_ICCV, author = {Wei, Wenjie and Zhang, Malu and Qu, Hong and Belatreche, Ammar and Zhang, Jian and Chen, Hong}, title = {Temporal-Coded Spiking Neural Networks with Dynamic Firing Threshold: Learning with Event-Driven Backpropagation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {10552-10562} }
NeO 360: Neural Fields for Sparse View Synthesis of Outdoor Scenes: Muhammad Zubair Irshad,

Sergey Zakharov,

Katherine Liu,

Vitor Guizilini,

Thomas Kollar,

Adrien Gaidon,

Zsolt Kira,

Rares Ambrus; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Irshad_2023_ICCV, author = {Irshad, Muhammad Zubair and Zakharov, Sergey and Liu, Katherine and Guizilini, Vitor and Kollar, Thomas and Gaidon, Adrien and Kira, Zsolt and Ambrus, Rares}, title = {NeO 360: Neural Fields for Sparse View Synthesis of Outdoor Scenes}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {9187-9198} }
UnLoc: A Unified Framework for Video Localization Tasks: Shen Yan,

Xuehan Xiong,

Arsha Nagrani,

Anurag Arnab,

Zhonghao Wang,

Weina Ge,

David Ross,

Cordelia Schmid; [pdf] [arXiv]
[bibtex]
@InProceedings{Yan_2023_ICCV, author = {Yan, Shen and Xiong, Xuehan and Nagrani, Arsha and Arnab, Anurag and Wang, Zhonghao and Ge, Weina and Ross, David and Schmid, Cordelia}, title = {UnLoc: A Unified Framework for Video Localization Tasks}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {13623-13633} }
Fast Inference and Update of Probabilistic Density Estimation on Trajectory Prediction: Takahiro Maeda,

Norimichi Ukita; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Maeda_2023_ICCV, author = {Maeda, Takahiro and Ukita, Norimichi}, title = {Fast Inference and Update of Probabilistic Density Estimation on Trajectory Prediction}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {9795-9805} }
Adaptive Spiral Layers for Efficient 3D Representation Learning on Meshes: Francesca Babiloni,

Matteo Maggioni,

Thomas Tanay,

Jiankang Deng,

Ales Leonardis,

Stefanos Zafeiriou; [pdf] [supp]
[bibtex]
@InProceedings{Babiloni_2023_ICCV, author = {Babiloni, Francesca and Maggioni, Matteo and Tanay, Thomas and Deng, Jiankang and Leonardis, Ales and Zafeiriou, Stefanos}, title = {Adaptive Spiral Layers for Efficient 3D Representation Learning on Meshes}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {14620-14631} }
Convex Decomposition of Indoor Scenes: Vaibhav Vavilala,

David Forsyth; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Vavilala_2023_ICCV, author = {Vavilala, Vaibhav and Forsyth, David}, title = {Convex Decomposition of Indoor Scenes}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {9176-9186} }
Toward Unsupervised Realistic Visual Question Answering: Yuwei Zhang,

Chih-Hui Ho,

Nuno Vasconcelos; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhang_2023_ICCV, author = {Zhang, Yuwei and Ho, Chih-Hui and Vasconcelos, Nuno}, title = {Toward Unsupervised Realistic Visual Question Answering}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {15613-15624} }
Video OWL-ViT: Temporally-consistent Open-world Localization in Video: Georg Heigold,

Matthias Minderer,

Alexey Gritsenko,

Alex Bewley,

Daniel Keysers,

Mario Lučić,

Fisher Yu,

Thomas Kipf; [pdf] [supp]
[bibtex]
@InProceedings{Heigold_2023_ICCV, author = {Heigold, Georg and Minderer, Matthias and Gritsenko, Alexey and Bewley, Alex and Keysers, Daniel and Lu\v{c}i\'c, Mario and Yu, Fisher and Kipf, Thomas}, title = {Video OWL-ViT: Temporally-consistent Open-world Localization in Video}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {13802-13811} }
Physics-Driven Turbulence Image Restoration with Stochastic Refinement: Ajay Jaiswal,

Xingguang Zhang,

Stanley H. Chan,

Zhangyang Wang; [pdf] [arXiv]
[bibtex]
@InProceedings{Jaiswal_2023_ICCV, author = {Jaiswal, Ajay and Zhang, Xingguang and Chan, Stanley H. and Wang, Zhangyang}, title = {Physics-Driven Turbulence Image Restoration with Stochastic Refinement}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {12170-12181} }
Enhancing Non-line-of-sight Imaging via Learnable Inverse Kernel and Attention Mechanisms: Yanhua Yu,

Siyuan Shen,

Zi Wang,

Binbin Huang,

Yuehan Wang,

Xingyue Peng,

Suan Xia,

Ping Liu,

Ruiqian Li,

Shiying Li; [pdf]
[bibtex]
@InProceedings{Yu_2023_ICCV, author = {Yu, Yanhua and Shen, Siyuan and Wang, Zi and Huang, Binbin and Wang, Yuehan and Peng, Xingyue and Xia, Suan and Liu, Ping and Li, Ruiqian and Li, Shiying}, title = {Enhancing Non-line-of-sight Imaging via Learnable Inverse Kernel and Attention Mechanisms}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {10563-10573} }
DECO: Dense Estimation of 3D Human-Scene Contact In The Wild: Shashank Tripathi,

Agniv Chatterjee,

Jean-Claude Passy,

Hongwei Yi,

Dimitrios Tzionas,

Michael J. Black; [pdf] [supp]
[bibtex]
@InProceedings{Tripathi_2023_ICCV, author = {Tripathi, Shashank and Chatterjee, Agniv and Passy, Jean-Claude and Yi, Hongwei and Tzionas, Dimitrios and Black, Michael J.}, title = {DECO: Dense Estimation of 3D Human-Scene Contact In The Wild}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {8001-8013} }
PlaneRecTR: Unified Query Learning for 3D Plane Recovery from a Single View: Jingjia Shi,

Shuaifeng Zhi,

Kai Xu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Shi_2023_ICCV, author = {Shi, Jingjia and Zhi, Shuaifeng and Xu, Kai}, title = {PlaneRecTR: Unified Query Learning for 3D Plane Recovery from a Single View}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {9377-9386} }
EigenTrajectory: Low-Rank Descriptors for Multi-Modal Trajectory Forecasting: Inhwan Bae,

Jean Oh,

Hae-Gon Jeon; [pdf] [arXiv]
[bibtex]
@InProceedings{Bae_2023_ICCV, author = {Bae, Inhwan and Oh, Jean and Jeon, Hae-Gon}, title = {EigenTrajectory: Low-Rank Descriptors for Multi-Modal Trajectory Forecasting}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {10017-10029} }
Video-FocalNets: Spatio-Temporal Focal Modulation for Video Action Recognition: Syed Talal Wasim,

Muhammad Uzair Khattak,

Muzammal Naseer,

Salman Khan,

Mubarak Shah,

Fahad Shahbaz Khan; [pdf]
[bibtex]
@InProceedings{Wasim_2023_ICCV, author = {Wasim, Syed Talal and Khattak, Muhammad Uzair and Naseer, Muzammal and Khan, Salman and Shah, Mubarak and Khan, Fahad Shahbaz}, title = {Video-FocalNets: Spatio-Temporal Focal Modulation for Video Action Recognition}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {13778-13789} }
Hidden Biases of End-to-End Driving Models: Bernhard Jaeger,

Kashyap Chitta,

Andreas Geiger; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Jaeger_2023_ICCV, author = {Jaeger, Bernhard and Chitta, Kashyap and Geiger, Andreas}, title = {Hidden Biases of End-to-End Driving Models}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {8240-8249} }
PIDRo: Parallel Isomeric Attention with Dynamic Routing for Text-Video Retrieval: Peiyan Guan,

Renjing Pei,

Bin Shao,

Jianzhuang Liu,

Weimian Li,

Jiaxi Gu,

Hang Xu,

Songcen Xu,

Youliang Yan,

Edmund Y. Lam; [pdf] [supp]
[bibtex]
@InProceedings{Guan_2023_ICCV, author = {Guan, Peiyan and Pei, Renjing and Shao, Bin and Liu, Jianzhuang and Li, Weimian and Gu, Jiaxi and Xu, Hang and Xu, Songcen and Yan, Youliang and Lam, Edmund Y.}, title = {PIDRo: Parallel Isomeric Attention with Dynamic Routing for Text-Video Retrieval}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {11164-11173} }
RFD-ECNet: Extreme Underwater Image Compression with Reference to Feature Dictionary: Mengyao Li,

Liquan Shen,

Peng Ye,

Guorui Feng,

Zheyin Wang; [pdf] [supp]
[bibtex]
@InProceedings{Li_2023_ICCV, author = {Li, Mengyao and Shen, Liquan and Ye, Peng and Feng, Guorui and Wang, Zheyin}, title = {RFD-ECNet: Extreme Underwater Image Compression with Reference to Feature Dictionary}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {12980-12989} }
High-Resolution Document Shadow Removal via A Large-Scale Real-World Dataset and A Frequency-Aware Shadow Erasing Net: Zinuo Li,

Xuhang Chen,

Chi-Man Pun,

Xiaodong Cun; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Li_2023_ICCV, author = {Li, Zinuo and Chen, Xuhang and Pun, Chi-Man and Cun, Xiaodong}, title = {High-Resolution Document Shadow Removal via A Large-Scale Real-World Dataset and A Frequency-Aware Shadow Erasing Net}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {12449-12458} }
SILT: Shadow-Aware Iterative Label Tuning for Learning to Detect Shadows from Noisy Labels: Han Yang,

Tianyu Wang,

Xiaowei Hu,

Chi-Wing Fu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yang_2023_ICCV, author = {Yang, Han and Wang, Tianyu and Hu, Xiaowei and Fu, Chi-Wing}, title = {SILT: Shadow-Aware Iterative Label Tuning for Learning to Detect Shadows from Noisy Labels}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {12687-12698} }
Implicit Autoencoder for Point-Cloud Self-Supervised Representation Learning: Siming Yan,

Zhenpei Yang,

Haoxiang Li,

Chen Song,

Li Guan,

Hao Kang,

Gang Hua,

Qixing Huang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yan_2023_ICCV, author = {Yan, Siming and Yang, Zhenpei and Li, Haoxiang and Song, Chen and Guan, Li and Kang, Hao and Hua, Gang and Huang, Qixing}, title = {Implicit Autoencoder for Point-Cloud Self-Supervised Representation Learning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {14530-14542} }
Speech4Mesh: Speech-Assisted Monocular 3D Facial Reconstruction for Speech-Driven 3D Facial Animation: Shan He,

Haonan He,

Shuo Yang,

Xiaoyan Wu,

Pengcheng Xia,

Bing Yin,

Cong Liu,

Lirong Dai,

Chang Xu; [pdf] [supp]
[bibtex]
@InProceedings{He_2023_ICCV, author = {He, Shan and He, Haonan and Yang, Shuo and Wu, Xiaoyan and Xia, Pengcheng and Yin, Bing and Liu, Cong and Dai, Lirong and Xu, Chang}, title = {Speech4Mesh: Speech-Assisted Monocular 3D Facial Reconstruction for Speech-Driven 3D Facial Animation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {14192-14202} }
Generalizing Neural Human Fitting to Unseen Poses With Articulated SE(3) Equivariance: Haiwen Feng,

Peter Kulits,

Shichen Liu,

Michael J. Black,

Victoria Fernandez Abrevaya; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Feng_2023_ICCV, author = {Feng, Haiwen and Kulits, Peter and Liu, Shichen and Black, Michael J. and Abrevaya, Victoria Fernandez}, title = {Generalizing Neural Human Fitting to Unseen Poses With Articulated SE(3) Equivariance}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {7977-7988} }
Learning from Noisy Pseudo Labels for Semi-Supervised Temporal Action Localization: Kun Xia,

Le Wang,

Sanping Zhou,

Gang Hua,

Wei Tang; [pdf] [supp]
[bibtex]
@InProceedings{Xia_2023_ICCV, author = {Xia, Kun and Wang, Le and Zhou, Sanping and Hua, Gang and Tang, Wei}, title = {Learning from Noisy Pseudo Labels for Semi-Supervised Temporal Action Localization}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {10160-10169} }
Activate and Reject: Towards Safe Domain Generalization under Category Shift: Chaoqi Chen,

Luyao Tang,

Leitian Tao,

Hong-Yu Zhou,

Yue Huang,

Xiaoguang Han,

Yizhou Yu; [pdf]
[bibtex]
@InProceedings{Chen_2023_ICCV, author = {Chen, Chaoqi and Tang, Luyao and Tao, Leitian and Zhou, Hong-Yu and Huang, Yue and Han, Xiaoguang and Yu, Yizhou}, title = {Activate and Reject: Towards Safe Domain Generalization under Category Shift}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {11552-11563} }
Dynamic Mesh Recovery from Partial Point Cloud Sequence: Hojun Jang,

Minkwan Kim,

Jinseok Bae,

Young Min Kim; [pdf] [supp]
[bibtex]
@InProceedings{Jang_2023_ICCV, author = {Jang, Hojun and Kim, Minkwan and Bae, Jinseok and Kim, Young Min}, title = {Dynamic Mesh Recovery from Partial Point Cloud Sequence}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {15074-15084} }
Neural Deformable Models for 3D Bi-Ventricular Heart Shape Reconstruction and Modeling from 2D Sparse Cardiac Magnetic Resonance Imaging: Meng Ye,

Dong Yang,

Mikael Kanski,

Leon Axel,

Dimitris Metaxas; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ye_2023_ICCV, author = {Ye, Meng and Yang, Dong and Kanski, Mikael and Axel, Leon and Metaxas, Dimitris}, title = {Neural Deformable Models for 3D Bi-Ventricular Heart Shape Reconstruction and Modeling from 2D Sparse Cardiac Magnetic Resonance Imaging}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {14247-14256} }
Nonrigid Object Contact Estimation With Regional Unwrapping Transformer: Wei Xie,

Zimeng Zhao,

Shiying Li,

Binghui Zuo,

Yangang Wang; [pdf] [arXiv]
[bibtex]
@InProceedings{Xie_2023_ICCV, author = {Xie, Wei and Zhao, Zimeng and Li, Shiying and Zuo, Binghui and Wang, Yangang}, title = {Nonrigid Object Contact Estimation With Regional Unwrapping Transformer}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {9342-9351} }
Semi-supervised Semantics-guided Adversarial Training for Robust Trajectory Prediction: Ruochen Jiao,

Xiangguo Liu,

Takami Sato,

Qi Alfred Chen,

Qi Zhu; [pdf] [supp]
[bibtex]
@InProceedings{Jiao_2023_ICCV, author = {Jiao, Ruochen and Liu, Xiangguo and Sato, Takami and Chen, Qi Alfred and Zhu, Qi}, title = {Semi-supervised Semantics-guided Adversarial Training for Robust Trajectory Prediction}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {8207-8217} }
Linear-Covariance Loss for End-to-End Learning of 6D Pose Estimation: Fulin Liu,

Yinlin Hu,

Mathieu Salzmann; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Liu_2023_ICCV, author = {Liu, Fulin and Hu, Yinlin and Salzmann, Mathieu}, title = {Linear-Covariance Loss for End-to-End Learning of 6D Pose Estimation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {14107-14117} }
RLSAC: Reinforcement Learning Enhanced Sample Consensus for End-to-End Robust Estimation: Chang Nie,

Guangming Wang,

Zhe Liu,

Luca Cavalli,

Marc Pollefeys,

Hesheng Wang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Nie_2023_ICCV, author = {Nie, Chang and Wang, Guangming and Liu, Zhe and Cavalli, Luca and Pollefeys, Marc and Wang, Hesheng}, title = {RLSAC: Reinforcement Learning Enhanced Sample Consensus for End-to-End Robust Estimation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {9891-9900} }
Multi-Frequency Representation Enhancement with Privilege Information for Video Super-Resolution: Fei Li,

Linfeng Zhang,

Zikun Liu,

Juan Lei,

Zhenbo Li; [pdf] [supp]
[bibtex]
@InProceedings{Li_2023_ICCV, author = {Li, Fei and Zhang, Linfeng and Liu, Zikun and Lei, Juan and Li, Zhenbo}, title = {Multi-Frequency Representation Enhancement with Privilege Information for Video Super-Resolution}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {12814-12825} }
Self-supervised Pre-training for Mirror Detection: Jiaying Lin,

Rynson W.H. Lau; [pdf]
[bibtex]
@InProceedings{Lin_2023_ICCV, author = {Lin, Jiaying and Lau, Rynson W.H.}, title = {Self-supervised Pre-training for Mirror Detection}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {12227-12236} }
GlowGAN: Unsupervised Learning of HDR Images from LDR Images in the Wild: Chao Wang,

Ana Serrano,

Xingang Pan,

Bin Chen,

Karol Myszkowski,

Hans-Peter Seidel,

Christian Theobalt,

Thomas Leimkühler; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2023_ICCV, author = {Wang, Chao and Serrano, Ana and Pan, Xingang and Chen, Bin and Myszkowski, Karol and Seidel, Hans-Peter and Theobalt, Christian and Leimk\"uhler, Thomas}, title = {GlowGAN: Unsupervised Learning of HDR Images from LDR Images in the Wild}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {10509-10519} }
Dual Pseudo-Labels Interactive Self-Training for Semi-Supervised Visible-Infrared Person Re-Identification: Jiangming Shi,

Yachao Zhang,

Xiangbo Yin,

Yuan Xie,

Zhizhong Zhang,

Jianping Fan,

Zhongchao Shi,

Yanyun Qu; [pdf] [supp]
[bibtex]
@InProceedings{Shi_2023_ICCV, author = {Shi, Jiangming and Zhang, Yachao and Yin, Xiangbo and Xie, Yuan and Zhang, Zhizhong and Fan, Jianping and Shi, Zhongchao and Qu, Yanyun}, title = {Dual Pseudo-Labels Interactive Self-Training for Semi-Supervised Visible-Infrared Person Re-Identification}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {11218-11228} }
Learned Compressive Representations for Single-Photon 3D Imaging: Felipe Gutierrez-Barragan,

Fangzhou Mu,

Andrei Ardelean,

Atul Ingle,

Claudio Bruschini,

Edoardo Charbon,

Yin Li,

Mohit Gupta,

Andreas Velten; [pdf] [supp]
[bibtex]
@InProceedings{Gutierrez-Barragan_2023_ICCV, author = {Gutierrez-Barragan, Felipe and Mu, Fangzhou and Ardelean, Andrei and Ingle, Atul and Bruschini, Claudio and Charbon, Edoardo and Li, Yin and Gupta, Mohit and Velten, Andreas}, title = {Learned Compressive Representations for Single-Photon 3D Imaging}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {10756-10766} }
Alignment-free HDR Deghosting with Semantics Consistent Transformer: Steven Tel,

Zongwei Wu,

Yulun Zhang,

Barthélémy Heyrman,

Cédric Demonceaux,

Radu Timofte,

Dominique Ginhac; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Tel_2023_ICCV, author = {Tel, Steven and Wu, Zongwei and Zhang, Yulun and Heyrman, Barth\'el\'emy and Demonceaux, C\'edric and Timofte, Radu and Ginhac, Dominique}, title = {Alignment-free HDR Deghosting with Semantics Consistent Transformer}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {12836-12845} }
Multi3DRefer: Grounding Text Description to Multiple 3D Objects: Yiming Zhang,

ZeMing Gong,

Angel X. Chang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhang_2023_ICCV, author = {Zhang, Yiming and Gong, ZeMing and Chang, Angel X.}, title = {Multi3DRefer: Grounding Text Description to Multiple 3D Objects}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {15225-15236} }
Examining Autoexposure for Challenging Scenes: SaiKiran Tedla,

Beixuan Yang,

Michael S. Brown; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Tedla_2023_ICCV, author = {Tedla, SaiKiran and Yang, Beixuan and Brown, Michael S.}, title = {Examining Autoexposure for Challenging Scenes}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {13076-13085} }
Improved Visual Fine-tuning with Natural Language Supervision: Junyang Wang,

Yuanhong Xu,

Juhua Hu,

Ming Yan,

Jitao Sang,

Qi Qian; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2023_ICCV, author = {Wang, Junyang and Xu, Yuanhong and Hu, Juhua and Yan, Ming and Sang, Jitao and Qian, Qi}, title = {Improved Visual Fine-tuning with Natural Language Supervision}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {11899-11909} }
Person Re-Identification without Identification via Event anonymization: Shafiq Ahmad,

Pietro Morerio,

Alessio Del Bue; [pdf] [arXiv]
[bibtex]
@InProceedings{Ahmad_2023_ICCV, author = {Ahmad, Shafiq and Morerio, Pietro and Del Bue, Alessio}, title = {Person Re-Identification without Identification via Event anonymization}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {11132-11141} }
Self-Feedback DETR for Temporal Action Detection: Jihwan Kim,

Miso Lee,

Jae-Pil Heo; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kim_2023_ICCV, author = {Kim, Jihwan and Lee, Miso and Heo, Jae-Pil}, title = {Self-Feedback DETR for Temporal Action Detection}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {10286-10296} }
UMC: A Unified Bandwidth-efficient and Multi-resolution based Collaborative Perception Framework: Tianhang Wang,

Guang Chen,

Kai Chen,

Zhengfa Liu,

Bo Zhang,

Alois Knoll,

Changjun Jiang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2023_ICCV, author = {Wang, Tianhang and Chen, Guang and Chen, Kai and Liu, Zhengfa and Zhang, Bo and Knoll, Alois and Jiang, Changjun}, title = {UMC: A Unified Bandwidth-efficient and Multi-resolution based Collaborative Perception Framework}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {8187-8196} }
Viewing Graph Solvability in Practice: Federica Arrigoni,

Tomas Pajdla,

Andrea Fusiello; [pdf]
[bibtex]
@InProceedings{Arrigoni_2023_ICCV, author = {Arrigoni, Federica and Pajdla, Tomas and Fusiello, Andrea}, title = {Viewing Graph Solvability in Practice}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {8147-8155} }
SATR: Zero-Shot Semantic Segmentation of 3D Shapes: Ahmed Abdelreheem,

Ivan Skorokhodov,

Maks Ovsjanikov,

Peter Wonka; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Abdelreheem_2023_ICCV, author = {Abdelreheem, Ahmed and Skorokhodov, Ivan and Ovsjanikov, Maks and Wonka, Peter}, title = {SATR: Zero-Shot Semantic Segmentation of 3D Shapes}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {15166-15179} }
Pseudo Flow Consistency for Self-Supervised 6D Object Pose Estimation: Yang Hai,

Rui Song,

Jiaojiao Li,

David Ferstl,

Yinlin Hu; [pdf] [arXiv]
[bibtex]
@InProceedings{Hai_2023_ICCV, author = {Hai, Yang and Song, Rui and Li, Jiaojiao and Ferstl, David and Hu, Yinlin}, title = {Pseudo Flow Consistency for Self-Supervised 6D Object Pose Estimation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {14075-14085} }
Probabilistic Human Mesh Recovery in 3D Scenes from Egocentric Views: Siwei Zhang,

Qianli Ma,

Yan Zhang,

Sadegh Aliakbarian,

Darren Cosker,

Siyu Tang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhang_2023_ICCV, author = {Zhang, Siwei and Ma, Qianli and Zhang, Yan and Aliakbarian, Sadegh and Cosker, Darren and Tang, Siyu}, title = {Probabilistic Human Mesh Recovery in 3D Scenes from Egocentric Views}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {7989-8000} }
SceneRF: Self-Supervised Monocular 3D Scene Reconstruction with Radiance Fields: Anh-Quan Cao,

Raoul de Charette; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Cao_2023_ICCV, author = {Cao, Anh-Quan and de Charette, Raoul}, title = {SceneRF: Self-Supervised Monocular 3D Scene Reconstruction with Radiance Fields}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {9387-9398} }
INT2: Interactive Trajectory Prediction at Intersections: Zhijie Yan,

Pengfei Li,

Zheng Fu,

Shaocong Xu,

Yongliang Shi,

Xiaoxue Chen,

Yuhang Zheng,

Yang Li,

Tianyu Liu,

Chuxuan Li,

Nairui Luo,

Xu Gao,

Yilun Chen,

Zuoxu Wang,

Yifeng Shi,

Pengfei Huang,

Zhengxiao Han,

Jirui Yuan,

Jiangtao Gong,

Guyue Zhou,

Hang Zhao,

Hao Zhao; [pdf]
[bibtex]
@InProceedings{Yan_2023_ICCV, author = {Yan, Zhijie and Li, Pengfei and Fu, Zheng and Xu, Shaocong and Shi, Yongliang and Chen, Xiaoxue and Zheng, Yuhang and Li, Yang and Liu, Tianyu and Li, Chuxuan and Luo, Nairui and Gao, Xu and Chen, Yilun and Wang, Zuoxu and Shi, Yifeng and Huang, Pengfei and Han, Zhengxiao and Yuan, Jirui and Gong, Jiangtao and Zhou, Guyue and Zhao, Hang and Zhao, Hao}, title = {INT2: Interactive Trajectory Prediction at Intersections}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {8536-8547} }
MapPrior: Bird's-Eye View Map Layout Estimation with Generative Models: Xiyue Zhu,

Vlas Zyrianov,

Zhijian Liu,

Shenlong Wang; [pdf] [supp]
[bibtex]
@InProceedings{Zhu_2023_ICCV, author = {Zhu, Xiyue and Zyrianov, Vlas and Liu, Zhijian and Wang, Shenlong}, title = {MapPrior: Bird's-Eye View Map Layout Estimation with Generative Models}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {8228-8239} }
Conditional Cross Attention Network for Multi-Space Embedding without Entanglement in Only a SINGLE Network: Chull Hwan Song,

Taebaek Hwang,

Jooyoung Yoon,

Shunghyun Choi,

Yeong Hyeon Gu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Song_2023_ICCV, author = {Song, Chull Hwan and Hwang, Taebaek and Yoon, Jooyoung and Choi, Shunghyun and Gu, Yeong Hyeon}, title = {Conditional Cross Attention Network for Multi-Space Embedding without Entanglement in Only a SINGLE Network}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {11112-11121} }
MB-TaylorFormer: Multi-Branch Efficient Transformer Expanded by Taylor Formula for Image Dehazing: Yuwei Qiu,

Kaihao Zhang,

Chenxi Wang,

Wenhan Luo,

Hongdong Li,

Zhi Jin; [pdf] [supp]
[bibtex]
@InProceedings{Qiu_2023_ICCV, author = {Qiu, Yuwei and Zhang, Kaihao and Wang, Chenxi and Luo, Wenhan and Li, Hongdong and Jin, Zhi}, title = {MB-TaylorFormer: Multi-Branch Efficient Transformer Expanded by Taylor Formula for Image Dehazing}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {12802-12813} }
FocalFormer3D: Focusing on Hard Instance for 3D Object Detection: Yilun Chen,

Zhiding Yu,

Yukang Chen,

Shiyi Lan,

Anima Anandkumar,

Jiaya Jia,

Jose M. Alvarez; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chen_2023_ICCV, author = {Chen, Yilun and Yu, Zhiding and Chen, Yukang and Lan, Shiyi and Anandkumar, Anima and Jia, Jiaya and Alvarez, Jose M.}, title = {FocalFormer3D: Focusing on Hard Instance for 3D Object Detection}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {8394-8405} }
TEMPO: Efficient Multi-View Pose Estimation, Tracking, and Forecasting: Rohan Choudhury,

Kris M. Kitani,

László A. Jeni; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Choudhury_2023_ICCV, author = {Choudhury, Rohan and Kitani, Kris M. and Jeni, L\'aszl\'o A.}, title = {TEMPO: Efficient Multi-View Pose Estimation, Tracking, and Forecasting}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {14750-14760} }
DiffPose: SpatioTemporal Diffusion Model for Video-Based Human Pose Estimation: Runyang Feng,

Yixing Gao,

Tze Ho Elden Tse,

Xueqing Ma,

Hyung Jin Chang; [pdf] [arXiv]
[bibtex]
@InProceedings{Feng_2023_ICCV, author = {Feng, Runyang and Gao, Yixing and Tse, Tze Ho Elden and Ma, Xueqing and Chang, Hyung Jin}, title = {DiffPose: SpatioTemporal Diffusion Model for Video-Based Human Pose Estimation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {14861-14872} }
IntentQA: Context-aware Video Intent Reasoning: Jiapeng Li,

Ping Wei,

Wenjuan Han,

Lifeng Fan; [pdf] [supp]
[bibtex]
@InProceedings{Li_2023_ICCV, author = {Li, Jiapeng and Wei, Ping and Han, Wenjuan and Fan, Lifeng}, title = {IntentQA: Context-aware Video Intent Reasoning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {11963-11974} }
Robust Monocular Depth Estimation under Challenging Conditions: Stefano Gasperini,

Nils Morbitzer,

HyunJun Jung,

Nassir Navab,

Federico Tombari; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Gasperini_2023_ICCV, author = {Gasperini, Stefano and Morbitzer, Nils and Jung, HyunJun and Navab, Nassir and Tombari, Federico}, title = {Robust Monocular Depth Estimation under Challenging Conditions}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {8177-8186} }
Parametric Depth Based Feature Representation Learning for Object Detection and Segmentation in Bird's-Eye View: Jiayu Yang,

Enze Xie,

Miaomiao Liu,

Jose M. Alvarez; [pdf]
[bibtex]
@InProceedings{Yang_2023_ICCV, author = {Yang, Jiayu and Xie, Enze and Liu, Miaomiao and Alvarez, Jose M.}, title = {Parametric Depth Based Feature Representation Learning for Object Detection and Segmentation in Bird's-Eye View}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {8483-8492} }
Global Features are All You Need for Image Retrieval and Reranking: Shihao Shao,

Kaifeng Chen,

Arjun Karpur,

Qinghua Cui,

André Araujo,

Bingyi Cao; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Shao_2023_ICCV, author = {Shao, Shihao and Chen, Kaifeng and Karpur, Arjun and Cui, Qinghua and Araujo, Andr\'e and Cao, Bingyi}, title = {Global Features are All You Need for Image Retrieval and Reranking}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {11036-11046} }
DPF-Net: Combining Explicit Shape Priors in Deformable Primitive Field for Unsupervised Structural Reconstruction of 3D Objects: Qingyao Shuai,

Chi Zhang,

Kaizhi Yang,

Xuejin Chen; [pdf] [supp]
[bibtex]
@InProceedings{Shuai_2023_ICCV, author = {Shuai, Qingyao and Zhang, Chi and Yang, Kaizhi and Chen, Xuejin}, title = {DPF-Net: Combining Explicit Shape Priors in Deformable Primitive Field for Unsupervised Structural Reconstruction of 3D Objects}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {14321-14329} }
CORE: Co-planarity Regularized Monocular Geometry Estimation with Weak Supervision: Yuguang Li,

Kai Wang,

Hui Li,

Seon-Min Rhee,

Seungju Han,

Jihye Kim,

Min Yang,

Ran Yang,

Feng Zhu; [pdf] [supp]
[bibtex]
@InProceedings{Li_2023_ICCV, author = {Li, Yuguang and Wang, Kai and Li, Hui and Rhee, Seon-Min and Han, Seungju and Kim, Jihye and Yang, Min and Yang, Ran and Zhu, Feng}, title = {CORE: Co-planarity Regularized Monocular Geometry Estimation with Weak Supervision}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {8796-8805} }
A Sentence Speaks a Thousand Images: Domain Generalization through Distilling CLIP with Language Guidance: Zeyi Huang,

Andy Zhou,

Zijian Ling,

Mu Cai,

Haohan Wang,

Yong Jae Lee; [pdf]
[bibtex]
@InProceedings{Huang_2023_ICCV, author = {Huang, Zeyi and Zhou, Andy and Ling, Zijian and Cai, Mu and Wang, Haohan and Lee, Yong Jae}, title = {A Sentence Speaks a Thousand Images: Domain Generalization through Distilling CLIP with Language Guidance}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {11685-11695} }
Yes, we CANN: Constrained Approximate Nearest Neighbors for Local Feature-Based Visual Localization: Dror Aiger,

Andre Araujo,

Simon Lynen; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Aiger_2023_ICCV, author = {Aiger, Dror and Araujo, Andre and Lynen, Simon}, title = {Yes, we CANN: Constrained Approximate Nearest Neighbors for Local Feature-Based Visual Localization}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {13339-13349} }
Multi-Object Navigation with Dynamically Learned Neural Implicit Representations: Pierre Marza,

Laetitia Matignon,

Olivier Simonin,

Christian Wolf; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Marza_2023_ICCV, author = {Marza, Pierre and Matignon, Laetitia and Simonin, Olivier and Wolf, Christian}, title = {Multi-Object Navigation with Dynamically Learned Neural Implicit Representations}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {11004-11015} }
NPC: Neural Point Characters from Video: Shih-Yang Su,

Timur Bagautdinov,

Helge Rhodin; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Su_2023_ICCV, author = {Su, Shih-Yang and Bagautdinov, Timur and Rhodin, Helge}, title = {NPC: Neural Point Characters from Video}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {14795-14805} }
CrossLoc3D: Aerial-Ground Cross-Source 3D Place Recognition: Tianrui Guan,

Aswath Muthuselvam,

Montana Hoover,

Xijun Wang,

Jing Liang,

Adarsh Jagan Sathyamoorthy,

Damon Conover,

Dinesh Manocha; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Guan_2023_ICCV, author = {Guan, Tianrui and Muthuselvam, Aswath and Hoover, Montana and Wang, Xijun and Liang, Jing and Sathyamoorthy, Adarsh Jagan and Conover, Damon and Manocha, Dinesh}, title = {CrossLoc3D: Aerial-Ground Cross-Source 3D Place Recognition}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {11335-11344} }
Recursive Video Lane Detection: Dongkwon Jin,

Dahyun Kim,

Chang-Su Kim; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Jin_2023_ICCV, author = {Jin, Dongkwon and Kim, Dahyun and Kim, Chang-Su}, title = {Recursive Video Lane Detection}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {8473-8482} }
Unsupervised Self-Driving Attention Prediction via Uncertainty Mining and Knowledge Embedding: Pengfei Zhu,

Mengshi Qi,

Xia Li,

Weijian Li,

Huadong Ma; [pdf] [arXiv]
[bibtex]
@InProceedings{Zhu_2023_ICCV, author = {Zhu, Pengfei and Qi, Mengshi and Li, Xia and Li, Weijian and Ma, Huadong}, title = {Unsupervised Self-Driving Attention Prediction via Uncertainty Mining and Knowledge Embedding}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {8558-8568} }
DLGSANet: Lightweight Dynamic Local and Global Self-Attention Networks for Image Super-Resolution: Xiang Li,

Jiangxin Dong,

Jinhui Tang,

Jinshan Pan; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Li_2023_ICCV, author = {Li, Xiang and Dong, Jiangxin and Tang, Jinhui and Pan, Jinshan}, title = {DLGSANet: Lightweight Dynamic Local and Global Self-Attention Networks for Image Super-Resolution}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {12792-12801} }
Black-Box Unsupervised Domain Adaptation with Bi-Directional Atkinson-Shiffrin Memory: Jingyi Zhang,

Jiaxing Huang,

Xueying Jiang,

Shijian Lu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhang_2023_ICCV, author = {Zhang, Jingyi and Huang, Jiaxing and Jiang, Xueying and Lu, Shijian}, title = {Black-Box Unsupervised Domain Adaptation with Bi-Directional Atkinson-Shiffrin Memory}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {11771-11782} }
Disentangling Spatial and Temporal Learning for Efficient Image-to-Video Transfer Learning: Zhiwu Qing,

Shiwei Zhang,

Ziyuan Huang,

Yingya Zhang,

Changxin Gao,

Deli Zhao,

Nong Sang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Qing_2023_ICCV, author = {Qing, Zhiwu and Zhang, Shiwei and Huang, Ziyuan and Zhang, Yingya and Gao, Changxin and Zhao, Deli and Sang, Nong}, title = {Disentangling Spatial and Temporal Learning for Efficient Image-to-Video Transfer Learning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {13934-13944} }
Coarse-to-Fine: Learning Compact Discriminative Representation for Single-Stage Image Retrieval: Yunquan Zhu,

Xinkai Gao,

Bo Ke,

Ruizhi Qiao,

Xing Sun; [pdf]
[bibtex]
@InProceedings{Zhu_2023_ICCV, author = {Zhu, Yunquan and Gao, Xinkai and Ke, Bo and Qiao, Ruizhi and Sun, Xing}, title = {Coarse-to-Fine: Learning Compact Discriminative Representation for Single-Stage Image Retrieval}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {11260-11269} }
Deep Fusion Transformer Network with Weighted Vector-Wise Keypoints Voting for Robust 6D Object Pose Estimation: Jun Zhou,

Kai Chen,

Linlin Xu,

Qi Dou,

Jing Qin; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhou_2023_ICCV, author = {Zhou, Jun and Chen, Kai and Xu, Linlin and Dou, Qi and Qin, Jing}, title = {Deep Fusion Transformer Network with Weighted Vector-Wise Keypoints Voting for Robust 6D Object Pose Estimation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {13967-13977} }
BT^2: Backward-compatible Training with Basis Transformation: Yifei Zhou,

Zilu Li,

Abhinav Shrivastava,

Hengshuang Zhao,

Antonio Torralba,

Taipeng Tian,

Ser-Nam Lim; [pdf] [supp]
[bibtex]
@InProceedings{Zhou_2023_ICCV, author = {Zhou, Yifei and Li, Zilu and Shrivastava, Abhinav and Zhao, Hengshuang and Torralba, Antonio and Tian, Taipeng and Lim, Ser-Nam}, title = {BT{\textasciicircum}2: Backward-compatible Training with Basis Transformation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {11229-11238} }
ViperGPT: Visual Inference via Python Execution for Reasoning: Dídac Surís,

Sachit Menon,

Carl Vondrick; [pdf] [supp]
[bibtex]
@InProceedings{Suris_2023_ICCV, author = {Sur{\'\i}s, D{\'\i}dac and Menon, Sachit and Vondrick, Carl}, title = {ViperGPT: Visual Inference via Python Execution for Reasoning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {11888-11898} }
Fine-grained Visible Watermark Removal: Li Niu,

Xing Zhao,

Bo Zhang,

Liqing Zhang; [pdf]
[bibtex]
@InProceedings{Niu_2023_ICCV, author = {Niu, Li and Zhao, Xing and Zhang, Bo and Zhang, Liqing}, title = {Fine-grained Visible Watermark Removal}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {12770-12779} }
GridMM: Grid Memory Map for Vision-and-Language Navigation: Zihan Wang,

Xiangyang Li,

Jiahao Yang,

Yeqi Liu,

Shuqiang Jiang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2023_ICCV, author = {Wang, Zihan and Li, Xiangyang and Yang, Jiahao and Liu, Yeqi and Jiang, Shuqiang}, title = {GridMM: Grid Memory Map for Vision-and-Language Navigation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {15625-15636} }
LAC - Latent Action Composition for Skeleton-based Action Segmentation: Di Yang,

Yaohui Wang,

Antitza Dantcheva,

Quan Kong,

Lorenzo Garattoni,

Gianpiero Francesca,

Francois Bremond; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yang_2023_ICCV, author = {Yang, Di and Wang, Yaohui and Dantcheva, Antitza and Kong, Quan and Garattoni, Lorenzo and Francesca, Gianpiero and Bremond, Francois}, title = {LAC - Latent Action Composition for Skeleton-based Action Segmentation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {13679-13690} }
Learning Vision-and-Language Navigation from YouTube Videos: Kunyang Lin,

Peihao Chen,

Diwei Huang,

Thomas H. Li,

Mingkui Tan,

Chuang Gan; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Lin_2023_ICCV, author = {Lin, Kunyang and Chen, Peihao and Huang, Diwei and Li, Thomas H. and Tan, Mingkui and Gan, Chuang}, title = {Learning Vision-and-Language Navigation from YouTube Videos}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {8317-8326} }
Uncertainty-aware State Space Transformer for Egocentric 3D Hand Trajectory Forecasting: Wentao Bao,

Lele Chen,

Libing Zeng,

Zhong Li,

Yi Xu,

Junsong Yuan,

Yu Kong; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Bao_2023_ICCV, author = {Bao, Wentao and Chen, Lele and Zeng, Libing and Li, Zhong and Xu, Yi and Yuan, Junsong and Kong, Yu}, title = {Uncertainty-aware State Space Transformer for Egocentric 3D Hand Trajectory Forecasting}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {13702-13711} }
Pretrained Language Models as Visual Planners for Human Assistance: Dhruvesh Patel,

Hamid Eghbalzadeh,

Nitin Kamra,

Michael Louis Iuzzolino,

Unnat Jain,

Ruta Desai; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Patel_2023_ICCV, author = {Patel, Dhruvesh and Eghbalzadeh, Hamid and Kamra, Nitin and Iuzzolino, Michael Louis and Jain, Unnat and Desai, Ruta}, title = {Pretrained Language Models as Visual Planners for Human Assistance}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {15302-15314} }
Dynamic Point Fields: Sergey Prokudin,

Qianli Ma,

Maxime Raafat,

Julien Valentin,

Siyu Tang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Prokudin_2023_ICCV, author = {Prokudin, Sergey and Ma, Qianli and Raafat, Maxime and Valentin, Julien and Tang, Siyu}, title = {Dynamic Point Fields}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {7964-7976} }
Lip2Vec: Efficient and Robust Visual Speech Recognition via Latent-to-Latent Visual to Audio Representation Mapping: Yasser Abdelaziz Dahou Djilali,

Sanath Narayan,

Haithem Boussaid,

Ebtessam Almazrouei,

Merouane Debbah; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Djilali_2023_ICCV, author = {Djilali, Yasser Abdelaziz Dahou and Narayan, Sanath and Boussaid, Haithem and Almazrouei, Ebtessam and Debbah, Merouane}, title = {Lip2Vec: Efficient and Robust Visual Speech Recognition via Latent-to-Latent Visual to Audio Representation Mapping}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {13790-13801} }
Spectral Graphormer: Spectral Graph-Based Transformer for Egocentric Two-Hand Reconstruction using Multi-View Color Images: Tze Ho Elden Tse,

Franziska Mueller,

Zhengyang Shen,

Danhang Tang,

Thabo Beeler,

Mingsong Dou,

Yinda Zhang,

Sasa Petrovic,

Hyung Jin Chang,

Jonathan Taylor,

Bardia Doosti; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Tse_2023_ICCV, author = {Tse, Tze Ho Elden and Mueller, Franziska and Shen, Zhengyang and Tang, Danhang and Beeler, Thabo and Dou, Mingsong and Zhang, Yinda and Petrovic, Sasa and Chang, Hyung Jin and Taylor, Jonathan and Doosti, Bardia}, title = {Spectral Graphormer: Spectral Graph-Based Transformer for Egocentric Two-Hand Reconstruction using Multi-View Color Images}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {14666-14677} }
Recovering a Molecule's 3D Dynamics from Liquid-phase Electron Microscopy Movies: Enze Ye,

Yuhang Wang,

Hong Zhang,

Yiqin Gao,

Huan Wang,

He Sun; [pdf] [supp]
[bibtex]
@InProceedings{Ye_2023_ICCV, author = {Ye, Enze and Wang, Yuhang and Zhang, Hong and Gao, Yiqin and Wang, Huan and Sun, He}, title = {Recovering a Molecule's 3D Dynamics from Liquid-phase Electron Microscopy Movies}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {10767-10777} }
SOCS: Semantically-Aware Object Coordinate Space for Category-Level 6D Object Pose Estimation under Large Shape Variations: Boyan Wan,

Yifei Shi,

Kai Xu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wan_2023_ICCV, author = {Wan, Boyan and Shi, Yifei and Xu, Kai}, title = {SOCS: Semantically-Aware Object Coordinate Space for Category-Level 6D Object Pose Estimation under Large Shape Variations}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {14065-14074} }
NeRF-LOAM: Neural Implicit Representation for Large-Scale Incremental LiDAR Odometry and Mapping: Junyuan Deng,

Qi Wu,

Xieyuanli Chen,

Songpengcheng Xia,

Zhen Sun,

Guoqing Liu,

Wenxian Yu,

Ling Pei; [pdf] [supp]
[bibtex]
@InProceedings{Deng_2023_ICCV, author = {Deng, Junyuan and Wu, Qi and Chen, Xieyuanli and Xia, Songpengcheng and Sun, Zhen and Liu, Guoqing and Yu, Wenxian and Pei, Ling}, title = {NeRF-LOAM: Neural Implicit Representation for Large-Scale Incremental LiDAR Odometry and Mapping}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {8218-8227} }
OmniLabel: A Challenging Benchmark for Language-Based Object Detection: Samuel Schulter,

Vijay Kumar B G,

Yumin Suh,

Konstantinos M. Dafnis,

Zhixing Zhang,

Shiyu Zhao,

Dimitris Metaxas; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Schulter_2023_ICCV, author = {Schulter, Samuel and G, Vijay Kumar B and Suh, Yumin and Dafnis, Konstantinos M. and Zhang, Zhixing and Zhao, Shiyu and Metaxas, Dimitris}, title = {OmniLabel: A Challenging Benchmark for Language-Based Object Detection}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {11953-11962} }
Divide&Classify: Fine-Grained Classification for City-Wide Visual Geo-Localization: Gabriele Trivigno,

Gabriele Berton,

Juan Aragon,

Barbara Caputo,

Carlo Masone; [pdf] [supp]
[bibtex]
@InProceedings{Trivigno_2023_ICCV, author = {Trivigno, Gabriele and Berton, Gabriele and Aragon, Juan and Caputo, Barbara and Masone, Carlo}, title = {Divide\&Classify: Fine-Grained Classification for City-Wide Visual Geo-Localization}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {11142-11152} }
3D Semantic Subspace Traverser: Empowering 3D Generative Model with Shape Editing Capability: Ruowei Wang,

Yu Liu,

Pei Su,

Jianwei Zhang,

Qijun Zhao; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2023_ICCV, author = {Wang, Ruowei and Liu, Yu and Su, Pei and Zhang, Jianwei and Zhao, Qijun}, title = {3D Semantic Subspace Traverser: Empowering 3D Generative Model with Shape Editing Capability}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {14406-14417} }
Text2Room: Extracting Textured 3D Meshes from 2D Text-to-Image Models: Lukas Höllein,

Ang Cao,

Andrew Owens,

Justin Johnson,

Matthias Nießner; [pdf] [supp]
[bibtex]
@InProceedings{Hollein_2023_ICCV, author = {H\"ollein, Lukas and Cao, Ang and Owens, Andrew and Johnson, Justin and Nie{\ss}ner, Matthias}, title = {Text2Room: Extracting Textured 3D Meshes from 2D Text-to-Image Models}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {7909-7920} }
On the Robustness of Normalizing Flows for Inverse Problems in Imaging: Seongmin Hong,

Inbum Park,

Se Young Chun; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Hong_2023_ICCV, author = {Hong, Seongmin and Park, Inbum and Chun, Se Young}, title = {On the Robustness of Normalizing Flows for Inverse Problems in Imaging}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {10745-10755} }
DistillBEV: Boosting Multi-Camera 3D Object Detection with Cross-Modal Knowledge Distillation: Zeyu Wang,

Dingwen Li,

Chenxu Luo,

Cihang Xie,

Xiaodong Yang; [pdf] [supp]
[bibtex]
@InProceedings{Wang_2023_ICCV, author = {Wang, Zeyu and Li, Dingwen and Luo, Chenxu and Xie, Cihang and Yang, Xiaodong}, title = {DistillBEV: Boosting Multi-Camera 3D Object Detection with Cross-Modal Knowledge Distillation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {8637-8646} }
PoseFix: Correcting 3D Human Poses with Natural Language: Ginger Delmas,

Philippe Weinzaepfel,

Francesc Moreno-Noguer,

Grégory Rogez; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Delmas_2023_ICCV, author = {Delmas, Ginger and Weinzaepfel, Philippe and Moreno-Noguer, Francesc and Rogez, Gr\'egory}, title = {PoseFix: Correcting 3D Human Poses with Natural Language}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {15018-15028} }
TAPIR: Tracking Any Point with Per-Frame Initialization and Temporal Refinement: Carl Doersch,

Yi Yang,

Mel Vecerik,

Dilara Gokay,

Ankush Gupta,

Yusuf Aytar,

Joao Carreira,

Andrew Zisserman; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Doersch_2023_ICCV, author = {Doersch, Carl and Yang, Yi and Vecerik, Mel and Gokay, Dilara and Gupta, Ankush and Aytar, Yusuf and Carreira, Joao and Zisserman, Andrew}, title = {TAPIR: Tracking Any Point with Per-Frame Initialization and Temporal Refinement}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {10061-10072} }
SwinLSTM: Improving Spatiotemporal Prediction Accuracy using Swin Transformer and LSTM: Song Tang,

Chuang Li,

Pu Zhang,

RongNian Tang; [pdf] [arXiv]
[bibtex]
@InProceedings{Tang_2023_ICCV, author = {Tang, Song and Li, Chuang and Zhang, Pu and Tang, RongNian}, title = {SwinLSTM: Improving Spatiotemporal Prediction Accuracy using Swin Transformer and LSTM}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {13470-13479} }
DEDRIFT: Robust Similarity Search under Content Drift: Dmitry Baranchuk,

Matthijs Douze,

Yash Upadhyay,

I. Zeki Yalniz; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Baranchuk_2023_ICCV, author = {Baranchuk, Dmitry and Douze, Matthijs and Upadhyay, Yash and Yalniz, I. Zeki}, title = {DEDRIFT: Robust Similarity Search under Content Drift}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {11026-11035} }
Audio-Enhanced Text-to-Video Retrieval using Text-Conditioned Feature Alignment: Sarah Ibrahimi,

Xiaohang Sun,

Pichao Wang,

Amanmeet Garg,

Ashutosh Sanan,

Mohamed Omar; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ibrahimi_2023_ICCV, author = {Ibrahimi, Sarah and Sun, Xiaohang and Wang, Pichao and Garg, Amanmeet and Sanan, Ashutosh and Omar, Mohamed}, title = {Audio-Enhanced Text-to-Video Retrieval using Text-Conditioned Feature Alignment}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {12054-12064} }
Prior-guided Source-free Domain Adaptation for Human Pose Estimation: Dripta S. Raychaudhuri,

Calvin-Khang Ta,

Arindam Dutta,

Rohit Lal,

Amit K. Roy-Chowdhury; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Raychaudhuri_2023_ICCV, author = {Raychaudhuri, Dripta S. and Ta, Calvin-Khang and Dutta, Arindam and Lal, Rohit and Roy-Chowdhury, Amit K.}, title = {Prior-guided Source-free Domain Adaptation for Human Pose Estimation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {14996-15006} }
Auxiliary Tasks Benefit 3D Skeleton-based Human Motion Prediction: Chenxin Xu,

Robby T. Tan,

Yuhong Tan,

Siheng Chen,

Xinchao Wang,

Yanfeng Wang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Xu_2023_ICCV, author = {Xu, Chenxin and Tan, Robby T. and Tan, Yuhong and Chen, Siheng and Wang, Xinchao and Wang, Yanfeng}, title = {Auxiliary Tasks Benefit 3D Skeleton-based Human Motion Prediction}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {9509-9520} }
Measuring Asymmetric Gradient Discrepancy in Parallel Continual Learning: Fan Lyu,

Qing Sun,

Fanhua Shang,

Liang Wan,

Wei Feng; [pdf] [supp]
[bibtex]
@InProceedings{Lyu_2023_ICCV, author = {Lyu, Fan and Sun, Qing and Shang, Fanhua and Wan, Liang and Feng, Wei}, title = {Measuring Asymmetric Gradient Discrepancy in Parallel Continual Learning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {11411-11420} }
HyperDiffusion: Generating Implicit Neural Fields with Weight-Space Diffusion: Ziya Erkoç,

Fangchang Ma,

Qi Shan,

Matthias Nießner,

Angela Dai; [pdf] [supp]
[bibtex]
@InProceedings{Erkoc_2023_ICCV, author = {Erko\c{c}, Ziya and Ma, Fangchang and Shan, Qi and Nie{\ss}ner, Matthias and Dai, Angela}, title = {HyperDiffusion: Generating Implicit Neural Fields with Weight-Space Diffusion}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {14300-14310} }
Retinexformer: One-stage Retinex-based Transformer for Low-light Image Enhancement: Yuanhao Cai,

Hao Bian,

Jing Lin,

Haoqian Wang,

Radu Timofte,

Yulun Zhang; [pdf] [arXiv]
[bibtex]
@InProceedings{Cai_2023_ICCV, author = {Cai, Yuanhao and Bian, Hao and Lin, Jing and Wang, Haoqian and Timofte, Radu and Zhang, Yulun}, title = {Retinexformer: One-stage Retinex-based Transformer for Low-light Image Enhancement}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {12504-12513} }
Linear Spaces of Meanings: Compositional Structures in Vision-Language Models: Matthew Trager,

Pramuditha Perera,

Luca Zancato,

Alessandro Achille,

Parminder Bhatia,

Stefano Soatto; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Trager_2023_ICCV, author = {Trager, Matthew and Perera, Pramuditha and Zancato, Luca and Achille, Alessandro and Bhatia, Parminder and Soatto, Stefano}, title = {Linear Spaces of Meanings: Compositional Structures in Vision-Language Models}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {15395-15404} }
Tracking by Natural Language Specification with Long Short-term Context Decoupling: Ding Ma,

Xiangqian Wu; [pdf]
[bibtex]
@InProceedings{Ma_2023_ICCV, author = {Ma, Ding and Wu, Xiangqian}, title = {Tracking by Natural Language Specification with Long Short-term Context Decoupling}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {14012-14021} }
Pyramid Dual Domain Injection Network for Pan-sharpening: Xuanhua He,

Keyu Yan,

Rui Li,

Chengjun Xie,

Jie Zhang,

Man Zhou; [pdf]
[bibtex]
@InProceedings{He_2023_ICCV, author = {He, Xuanhua and Yan, Keyu and Li, Rui and Xie, Chengjun and Zhang, Jie and Zhou, Man}, title = {Pyramid Dual Domain Injection Network for Pan-sharpening}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {12908-12917} }
NeSS-ST: Detecting Good and Stable Keypoints with a Neural Stability Score and the Shi-Tomasi detector: Konstantin Pakulev,

Alexander Vakhitov,

Gonzalo Ferrer; [pdf] [supp]
[bibtex]
@InProceedings{Pakulev_2023_ICCV, author = {Pakulev, Konstantin and Vakhitov, Alexander and Ferrer, Gonzalo}, title = {NeSS-ST: Detecting Good and Stable Keypoints with a Neural Stability Score and the Shi-Tomasi detector}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {9578-9588} }
Video Action Segmentation via Contextually Refined Temporal Keypoints: Borui Jiang,

Yang Jin,

Zhentao Tan,

Yadong Mu; [pdf] [supp]
[bibtex]
@InProceedings{Jiang_2023_ICCV, author = {Jiang, Borui and Jin, Yang and Tan, Zhentao and Mu, Yadong}, title = {Video Action Segmentation via Contextually Refined Temporal Keypoints}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {13836-13845} }
Shatter and Gather: Learning Referring Image Segmentation with Text Supervision: Dongwon Kim,

Namyup Kim,

Cuiling Lan,

Suha Kwak; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kim_2023_ICCV, author = {Kim, Dongwon and Kim, Namyup and Lan, Cuiling and Kwak, Suha}, title = {Shatter and Gather: Learning Referring Image Segmentation with Text Supervision}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {15547-15557} }
Two-in-One Depth: Bridging the Gap Between Monocular and Binocular Self-Supervised Depth Estimation: Zhengming Zhou,

Qiulei Dong; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhou_2023_ICCV, author = {Zhou, Zhengming and Dong, Qiulei}, title = {Two-in-One Depth: Bridging the Gap Between Monocular and Binocular Self-Supervised Depth Estimation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {9411-9421} }
Rethinking Pose Estimation in Crowds: Overcoming the Detection Information Bottleneck and Ambiguity: Mu Zhou,

Lucas Stoffl,

Mackenzie Weygandt Mathis,

Alexander Mathis; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhou_2023_ICCV, author = {Zhou, Mu and Stoffl, Lucas and Mathis, Mackenzie Weygandt and Mathis, Alexander}, title = {Rethinking Pose Estimation in Crowds: Overcoming the Detection Information Bottleneck and Ambiguity}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {14689-14699} }
Social Diffusion: Long-term Multiple Human Motion Anticipation: Julian Tanke,

Linguang Zhang,

Amy Zhao,

Chengcheng Tang,

Yujun Cai,

Lezi Wang,

Po-Chen Wu,

Juergen Gall,

Cem Keskin; [pdf] [supp]
[bibtex]
@InProceedings{Tanke_2023_ICCV, author = {Tanke, Julian and Zhang, Linguang and Zhao, Amy and Tang, Chengcheng and Cai, Yujun and Wang, Lezi and Wu, Po-Chen and Gall, Juergen and Keskin, Cem}, title = {Social Diffusion: Long-term Multiple Human Motion Anticipation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {9601-9611} }
Synchronize Feature Extracting and Matching: A Single Branch Framework for 3D Object Tracking: Teli Ma,

Mengmeng Wang,

Jimin Xiao,

Huifeng Wu,

Yong Liu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ma_2023_ICCV, author = {Ma, Teli and Wang, Mengmeng and Xiao, Jimin and Wu, Huifeng and Liu, Yong}, title = {Synchronize Feature Extracting and Matching: A Single Branch Framework for 3D Object Tracking}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {9953-9963} }
Leveraging Intrinsic Properties for Non-Rigid Garment Alignment: Siyou Lin,

Boyao Zhou,

Zerong Zheng,

Hongwen Zhang,

Yebin Liu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Lin_2023_ICCV, author = {Lin, Siyou and Zhou, Boyao and Zheng, Zerong and Zhang, Hongwen and Liu, Yebin}, title = {Leveraging Intrinsic Properties for Non-Rigid Garment Alignment}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {14485-14496} }
P2C: Self-Supervised Point Cloud Completion from Single Partial Clouds: Ruikai Cui,

Shi Qiu,

Saeed Anwar,

Jiawei Liu,

Chaoyue Xing,

Jing Zhang,

Nick Barnes; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Cui_2023_ICCV, author = {Cui, Ruikai and Qiu, Shi and Anwar, Saeed and Liu, Jiawei and Xing, Chaoyue and Zhang, Jing and Barnes, Nick}, title = {P2C: Self-Supervised Point Cloud Completion from Single Partial Clouds}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {14351-14360} }
A Game of Bundle Adjustment - Learning Efficient Convergence: Amir Belder,

Refael Vivanti,

Ayellet Tal; [pdf]
[bibtex]
@InProceedings{Belder_2023_ICCV, author = {Belder, Amir and Vivanti, Refael and Tal, Ayellet}, title = {A Game of Bundle Adjustment - Learning Efficient Convergence}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {8428-8437} }
Learning Correction Filter via Degradation-Adaptive Regression for Blind Single Image Super-Resolution: Hongyang Zhou,

Xiaobin Zhu,

Jianqing Zhu,

Zheng Han,

Shi-Xue Zhang,

Jingyan Qin,

Xu-Cheng Yin; [pdf] [supp]
[bibtex]
@InProceedings{Zhou_2023_ICCV, author = {Zhou, Hongyang and Zhu, Xiaobin and Zhu, Jianqing and Han, Zheng and Zhang, Shi-Xue and Qin, Jingyan and Yin, Xu-Cheng}, title = {Learning Correction Filter via Degradation-Adaptive Regression for Blind Single Image Super-Resolution}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {12365-12375} }
SINC: Spatial Composition of 3D Human Motions for Simultaneous Action Generation: Nikos Athanasiou,

Mathis Petrovich,

Michael J. Black,

Gül Varol; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Athanasiou_2023_ICCV, author = {Athanasiou, Nikos and Petrovich, Mathis and Black, Michael J. and Varol, G\"ul}, title = {SINC: Spatial Composition of 3D Human Motions for Simultaneous Action Generation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {9984-9995} }
MV-DeepSDF: Implicit Modeling with Multi-Sweep Point Clouds for 3D Vehicle Reconstruction in Autonomous Driving: Yibo Liu,

Kelly Zhu,

Guile Wu,

Yuan Ren,

Bingbing Liu,

Yang Liu,

Jinjun Shan; [pdf] [supp]
[bibtex]
@InProceedings{Liu_2023_ICCV, author = {Liu, Yibo and Zhu, Kelly and Wu, Guile and Ren, Yuan and Liu, Bingbing and Liu, Yang and Shan, Jinjun}, title = {MV-DeepSDF: Implicit Modeling with Multi-Sweep Point Clouds for 3D Vehicle Reconstruction in Autonomous Driving}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {8306-8316} }
CHORD: Category-level Hand-held Object Reconstruction via Shape Deformation: Kailin Li,

Lixin Yang,

Haoyu Zhen,

Zenan Lin,

Xinyu Zhan,

Licheng Zhong,

Jian Xu,

Kejian Wu,

Cewu Lu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Li_2023_ICCV, author = {Li, Kailin and Yang, Lixin and Zhen, Haoyu and Lin, Zenan and Zhan, Xinyu and Zhong, Licheng and Xu, Jian and Wu, Kejian and Lu, Cewu}, title = {CHORD: Category-level Hand-held Object Reconstruction via Shape Deformation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {9444-9454} }
Towards Universal LiDAR-Based 3D Object Detection by Multi-Domain Knowledge Transfer: Guile Wu,

Tongtong Cao,

Bingbing Liu,

Xingxin Chen,

Yuan Ren; [pdf]
[bibtex]
@InProceedings{Wu_2023_ICCV, author = {Wu, Guile and Cao, Tongtong and Liu, Bingbing and Chen, Xingxin and Ren, Yuan}, title = {Towards Universal LiDAR-Based 3D Object Detection by Multi-Domain Knowledge Transfer}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {8669-8678} }
Towards High-Fidelity Text-Guided 3D Face Generation and Manipulation Using only Images: Cuican Yu,

Guansong Lu,

Yihan Zeng,

Jian Sun,

Xiaodan Liang,

Huibin Li,

Zongben Xu,

Songcen Xu,

Wei Zhang,

Hang Xu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yu_2023_ICCV, author = {Yu, Cuican and Lu, Guansong and Zeng, Yihan and Sun, Jian and Liang, Xiaodan and Li, Huibin and Xu, Zongben and Xu, Songcen and Zhang, Wei and Xu, Hang}, title = {Towards High-Fidelity Text-Guided 3D Face Generation and Manipulation Using only Images}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {15326-15337} }
ENTL: Embodied Navigation Trajectory Learner: Klemen Kotar,

Aaron Walsman,

Roozbeh Mottaghi; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kotar_2023_ICCV, author = {Kotar, Klemen and Walsman, Aaron and Mottaghi, Roozbeh}, title = {ENTL: Embodied Navigation Trajectory Learner}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {10863-10872} }
AGG-Net: Attention Guided Gated-Convolutional Network for Depth Image Completion: Dongyue Chen,

Tingxuan Huang,

Zhimin Song,

Shizhuo Deng,

Tong Jia; [pdf] [supp]
[bibtex]
@InProceedings{Chen_2023_ICCV, author = {Chen, Dongyue and Huang, Tingxuan and Song, Zhimin and Deng, Shizhuo and Jia, Tong}, title = {AGG-Net: Attention Guided Gated-Convolutional Network for Depth Image Completion}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {8853-8862} }
Real-Time Neural Rasterization for Large Scenes: Jeffrey Yunfan Liu,

Yun Chen,

Ze Yang,

Jingkang Wang,

Sivabalan Manivasagam,

Raquel Urtasun; [pdf] [supp]
[bibtex]
@InProceedings{Liu_2023_ICCV, author = {Liu, Jeffrey Yunfan and Chen, Yun and Yang, Ze and Wang, Jingkang and Manivasagam, Sivabalan and Urtasun, Raquel}, title = {Real-Time Neural Rasterization for Large Scenes}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {8416-8427} }
MixSpeech: Cross-Modality Self-Learning with Audio-Visual Stream Mixup for Visual Speech Translation and Recognition: Xize Cheng,

Tao Jin,

Rongjie Huang,

Linjun Li,

Wang Lin,

Zehan Wang,

Ye Wang,

Huadai Liu,

Aoxiong Yin,

Zhou Zhao; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Cheng_2023_ICCV, author = {Cheng, Xize and Jin, Tao and Huang, Rongjie and Li, Linjun and Lin, Wang and Wang, Zehan and Wang, Ye and Liu, Huadai and Yin, Aoxiong and Zhao, Zhou}, title = {MixSpeech: Cross-Modality Self-Learning with Audio-Visual Stream Mixup for Visual Speech Translation and Recognition}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {15735-15745} }
Innovating Real Fisheye Image Correction with Dual Diffusion Architecture: Shangrong Yang,

Chunyu Lin,

Kang Liao,

Yao Zhao; [pdf] [supp]
[bibtex]
@InProceedings{Yang_2023_ICCV, author = {Yang, Shangrong and Lin, Chunyu and Liao, Kang and Zhao, Yao}, title = {Innovating Real Fisheye Image Correction with Dual Diffusion Architecture}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {12699-12708} }
Global Perception Based Autoregressive Neural Processes: Jinyang Tai; [pdf]
[bibtex]
@InProceedings{Tai_2023_ICCV, author = {Tai, Jinyang}, title = {Global Perception Based Autoregressive Neural Processes}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {10487-10497} }
VQA Therapy: Exploring Answer Differences by Visually Grounding Answers: Chongyan Chen,

Samreen Anjum,

Danna Gurari; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chen_2023_ICCV, author = {Chen, Chongyan and Anjum, Samreen and Gurari, Danna}, title = {VQA Therapy: Exploring Answer Differences by Visually Grounding Answers}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {15315-15325} }
Energy-based Self-Training and Normalization for Unsupervised Domain Adaptation: Samitha Herath,

Basura Fernando,

Ehsan Abbasnejad,

Munawar Hayat,

Shahram Khadivi,

Mehrtash Harandi,

Hamid Rezatofighi,

Gholamreza Haffari; [pdf] [supp]
[bibtex]
@InProceedings{Herath_2023_ICCV, author = {Herath, Samitha and Fernando, Basura and Abbasnejad, Ehsan and Hayat, Munawar and Khadivi, Shahram and Harandi, Mehrtash and Rezatofighi, Hamid and Haffari, Gholamreza}, title = {Energy-based Self-Training and Normalization for Unsupervised Domain Adaptation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {11653-11662} }
Collaborative Tracking Learning for Frame-Rate-Insensitive Multi-Object Tracking: Yiheng Liu,

Junta Wu,

Yi Fu; [pdf] [arXiv]
[bibtex]
@InProceedings{Liu_2023_ICCV, author = {Liu, Yiheng and Wu, Junta and Fu, Yi}, title = {Collaborative Tracking Learning for Frame-Rate-Insensitive Multi-Object Tracking}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {9964-9973} }
Prompt-aligned Gradient for Prompt Tuning: Beier Zhu,

Yulei Niu,

Yucheng Han,

Yue Wu,

Hanwang Zhang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhu_2023_ICCV, author = {Zhu, Beier and Niu, Yulei and Han, Yucheng and Wu, Yue and Zhang, Hanwang}, title = {Prompt-aligned Gradient for Prompt Tuning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {15659-15669} }
Aperture Diffraction for Compact Snapshot Spectral Imaging: Tao Lv,

Hao Ye,

Quan Yuan,

Zhan Shi,

Yibo Wang,

Shuming Wang,

Xun Cao; [pdf] [supp]
[bibtex]
@InProceedings{Lv_2023_ICCV, author = {Lv, Tao and Ye, Hao and Yuan, Quan and Shi, Zhan and Wang, Yibo and Wang, Shuming and Cao, Xun}, title = {Aperture Diffraction for Compact Snapshot Spectral Imaging}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {10574-10584} }
Diffusion Action Segmentation: Daochang Liu,

Qiyue Li,

Anh-Dung Dinh,

Tingting Jiang,

Mubarak Shah,

Chang Xu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Liu_2023_ICCV, author = {Liu, Daochang and Li, Qiyue and Dinh, Anh-Dung and Jiang, Tingting and Shah, Mubarak and Xu, Chang}, title = {Diffusion Action Segmentation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {10139-10149} }
Scalable Video Object Segmentation with Simplified Framework: Qiangqiang Wu,

Tianyu Yang,

Wei Wu,

Antoni B. Chan; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wu_2023_ICCV, author = {Wu, Qiangqiang and Yang, Tianyu and Wu, Wei and Chan, Antoni B.}, title = {Scalable Video Object Segmentation with Simplified Framework}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {13879-13889} }
Rehearsal-Free Domain Continual Face Anti-Spoofing: Generalize More and Forget Less: Rizhao Cai,

Yawen Cui,

Zhi Li,

Zitong Yu,

Haoliang Li,

Yongjian Hu,

Alex Kot; [pdf] [supp]
[bibtex]
@InProceedings{Cai_2023_ICCV, author = {Cai, Rizhao and Cui, Yawen and Li, Zhi and Yu, Zitong and Li, Haoliang and Hu, Yongjian and Kot, Alex}, title = {Rehearsal-Free Domain Continual Face Anti-Spoofing: Generalize More and Forget Less}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {8037-8048} }
Towards General Low-Light Raw Noise Synthesis and Modeling: Feng Zhang,

Bin Xu,

Zhiqiang Li,

Xinran Liu,

Qingbo Lu,

Changxin Gao,

Nong Sang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhang_2023_ICCV, author = {Zhang, Feng and Xu, Bin and Li, Zhiqiang and Liu, Xinran and Lu, Qingbo and Gao, Changxin and Sang, Nong}, title = {Towards General Low-Light Raw Noise Synthesis and Modeling}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {10820-10830} }
Beyond the Pixel: a Photometrically Calibrated HDR Dataset for Luminance and Color Prediction: Christophe Bolduc,

Justine Giroux,

Marc Hébert,

Claude Demers,

Jean-François Lalonde; [pdf] [supp]
[bibtex]
@InProceedings{Bolduc_2023_ICCV, author = {Bolduc, Christophe and Giroux, Justine and H\'ebert, Marc and Demers, Claude and Lalonde, Jean-Fran\c{c}ois}, title = {Beyond the Pixel: a Photometrically Calibrated HDR Dataset for Luminance and Color Prediction}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {8071-8081} }
Prototypical Mixing and Retrieval-Based Refinement for Label Noise-Resistant Image Retrieval: Xinlong Yang,

Haixin Wang,

Jinan Sun,

Shikun Zhang,

Chong Chen,

Xian-Sheng Hua,

Xiao Luo; [pdf] [supp]
[bibtex]
@InProceedings{Yang_2023_ICCV, author = {Yang, Xinlong and Wang, Haixin and Sun, Jinan and Zhang, Shikun and Chen, Chong and Hua, Xian-Sheng and Luo, Xiao}, title = {Prototypical Mixing and Retrieval-Based Refinement for Label Noise-Resistant Image Retrieval}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {11239-11249} }
AccFlow: Backward Accumulation for Long-Range Optical Flow: Guangyang Wu,

Xiaohong Liu,

Kunming Luo,

Xi Liu,

Qingqing Zheng,

Shuaicheng Liu,

Xinyang Jiang,

Guangtao Zhai,

Wenyi Wang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wu_2023_ICCV, author = {Wu, Guangyang and Liu, Xiaohong and Luo, Kunming and Liu, Xi and Zheng, Qingqing and Liu, Shuaicheng and Jiang, Xinyang and Zhai, Guangtao and Wang, Wenyi}, title = {AccFlow: Backward Accumulation for Long-Range Optical Flow}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {12119-12128} }
Contrastive Model Adaptation for Cross-Condition Robustness in Semantic Segmentation: David Brüggemann,

Christos Sakaridis,

Tim Broedermann,

Luc Van Gool; [pdf] [supp]
[bibtex]
@InProceedings{Bruggemann_2023_ICCV, author = {Br\"uggemann, David and Sakaridis, Christos and Broedermann, Tim and Van Gool, Luc}, title = {Contrastive Model Adaptation for Cross-Condition Robustness in Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {11378-11387} }
Creative Birds: Self-Supervised Single-View 3D Style Transfer: Renke Wang,

Guimin Que,

Shuo Chen,

Xiang Li,

Jun Li,

Jian Yang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2023_ICCV, author = {Wang, Renke and Que, Guimin and Chen, Shuo and Li, Xiang and Li, Jun and Yang, Jian}, title = {Creative Birds: Self-Supervised Single-View 3D Style Transfer}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {8775-8784} }
Boosting Novel Category Discovery Over Domains with Soft Contrastive Learning and All in One Classifier: Zelin Zang,

Lei Shang,

Senqiao Yang,

Fei Wang,

Baigui Sun,

Xuansong Xie,

Stan Z. Li; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zang_2023_ICCV, author = {Zang, Zelin and Shang, Lei and Yang, Senqiao and Wang, Fei and Sun, Baigui and Xie, Xuansong and Li, Stan Z.}, title = {Boosting Novel Category Discovery Over Domains with Soft Contrastive Learning and All in One Classifier}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {11858-11867} }
Search for or Navigate to? Dual Adaptive Thinking for Object Navigation: Ronghao Dang,

Liuyi Wang,

Zongtao He,

Shuai Su,

Jiagui Tang,

Chengju Liu,

Qijun Chen; [pdf] [arXiv]
[bibtex]
@InProceedings{Dang_2023_ICCV, author = {Dang, Ronghao and Wang, Liuyi and He, Zongtao and Su, Shuai and Tang, Jiagui and Liu, Chengju and Chen, Qijun}, title = {Search for or Navigate to? Dual Adaptive Thinking for Object Navigation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {8250-8259} }
OmniZoomer: Learning to Move and Zoom in on Sphere at High-Resolution: Zidong Cao,

Hao Ai,

Yan-Pei Cao,

Ying Shan,

Xiaohu Qie,

Lin Wang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Cao_2023_ICCV, author = {Cao, Zidong and Ai, Hao and Cao, Yan-Pei and Shan, Ying and Qie, Xiaohu and Wang, Lin}, title = {OmniZoomer: Learning to Move and Zoom in on Sphere at High-Resolution}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {12897-12907} }
Knowing Where to Focus: Event-aware Transformer for Video Grounding: Jinhyun Jang,

Jungin Park,

Jin Kim,

Hyeongjun Kwon,

Kwanghoon Sohn; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Jang_2023_ICCV, author = {Jang, Jinhyun and Park, Jungin and Kim, Jin and Kwon, Hyeongjun and Sohn, Kwanghoon}, title = {Knowing Where to Focus: Event-aware Transformer for Video Grounding}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {13846-13856} }
Movement Enhancement toward Multi-Scale Video Feature Representation for Temporal Action Detection: Zixuan Zhao,

Dongqi Wang,

Xu Zhao; [pdf]
[bibtex]
@InProceedings{Zhao_2023_ICCV, author = {Zhao, Zixuan and Wang, Dongqi and Zhao, Xu}, title = {Movement Enhancement toward Multi-Scale Video Feature Representation for Temporal Action Detection}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {13555-13564} }
Single Image Deblurring with Row-dependent Blur Magnitude: Xiang Ji,

Zhixiang Wang,

Shin'ichi Satoh,

Yinqiang Zheng; [pdf] [supp]
[bibtex]
@InProceedings{Ji_2023_ICCV, author = {Ji, Xiang and Wang, Zhixiang and Satoh, Shin'ichi and Zheng, Yinqiang}, title = {Single Image Deblurring with Row-dependent Blur Magnitude}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {12269-12280} }
Deep Active Contours for Real-time 6-DoF Object Tracking: Long Wang,

Shen Yan,

Jianan Zhen,

Yu Liu,

Maojun Zhang,

Guofeng Zhang,

Xiaowei Zhou; [pdf]
[bibtex]
@InProceedings{Wang_2023_ICCV, author = {Wang, Long and Yan, Shen and Zhen, Jianan and Liu, Yu and Zhang, Maojun and Zhang, Guofeng and Zhou, Xiaowei}, title = {Deep Active Contours for Real-time 6-DoF Object Tracking}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {14034-14044} }
Improving 3D Imaging with Pre-Trained Perpendicular 2D Diffusion Models: Suhyeon Lee,

Hyungjin Chung,

Minyoung Park,

Jonghyuk Park,

Wi-Sun Ryu,

Jong Chul Ye; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Lee_2023_ICCV, author = {Lee, Suhyeon and Chung, Hyungjin and Park, Minyoung and Park, Jonghyuk and Ryu, Wi-Sun and Ye, Jong Chul}, title = {Improving 3D Imaging with Pre-Trained Perpendicular 2D Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {10710-10720} }
Online Class Incremental Learning on Stochastic Blurry Task Boundary via Mask and Visual Prompt Tuning: Jun-Yeong Moon,

Keon-Hee Park,

Jung Uk Kim,

Gyeong-Moon Park; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Moon_2023_ICCV, author = {Moon, Jun-Yeong and Park, Keon-Hee and Kim, Jung Uk and Park, Gyeong-Moon}, title = {Online Class Incremental Learning on Stochastic Blurry Task Boundary via Mask and Visual Prompt Tuning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {11731-11741} }
SCANet: Scene Complexity Aware Network for Weakly-Supervised Video Moment Retrieval: Sunjae Yoon,

Gwanhyeong Koo,

Dahyun Kim,

Chang D. Yoo; [pdf] [supp]
[bibtex]
@InProceedings{Yoon_2023_ICCV, author = {Yoon, Sunjae and Koo, Gwanhyeong and Kim, Dahyun and Yoo, Chang D.}, title = {SCANet: Scene Complexity Aware Network for Weakly-Supervised Video Moment Retrieval}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {13576-13586} }
Neural Interactive Keypoint Detection: Jie Yang,

Ailing Zeng,

Feng Li,

Shilong Liu,

Ruimao Zhang,

Lei Zhang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yang_2023_ICCV, author = {Yang, Jie and Zeng, Ailing and Li, Feng and Liu, Shilong and Zhang, Ruimao and Zhang, Lei}, title = {Neural Interactive Keypoint Detection}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {15122-15132} }
Knowledge-Aware Prompt Tuning for Generalizable Vision-Language Models: Baoshuo Kan,

Teng Wang,

Wenpeng Lu,

Xiantong Zhen,

Weili Guan,

Feng Zheng; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kan_2023_ICCV, author = {Kan, Baoshuo and Wang, Teng and Lu, Wenpeng and Zhen, Xiantong and Guan, Weili and Zheng, Feng}, title = {Knowledge-Aware Prompt Tuning for Generalizable Vision-Language Models}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {15670-15680} }
Leveraging Inpainting for Single-Image Shadow Removal: Xiaoguang Li,

Qing Guo,

Rabab Abdelfattah,

Di Lin,

Wei Feng,

Ivor Tsang,

Song Wang; [pdf] [arXiv]
[bibtex]
@InProceedings{Li_2023_ICCV, author = {Li, Xiaoguang and Guo, Qing and Abdelfattah, Rabab and Lin, Di and Feng, Wei and Tsang, Ivor and Wang, Song}, title = {Leveraging Inpainting for Single-Image Shadow Removal}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {13055-13064} }
Accurate 3D Face Reconstruction with Facial Component Tokens: Tianke Zhang,

Xuangeng Chu,

Yunfei Liu,

Lijian Lin,

Zhendong Yang,

Zhengzhuo Xu,

Chengkun Cao,

Fei Yu,

Changyin Zhou,

Chun Yuan,

Yu Li; [pdf] [supp]
[bibtex]
@InProceedings{Zhang_2023_ICCV, author = {Zhang, Tianke and Chu, Xuangeng and Liu, Yunfei and Lin, Lijian and Yang, Zhendong and Xu, Zhengzhuo and Cao, Chengkun and Yu, Fei and Zhou, Changyin and Yuan, Chun and Li, Yu}, title = {Accurate 3D Face Reconstruction with Facial Component Tokens}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {9033-9042} }
Implicit Neural Representation for Cooperative Low-light Image Enhancement: Shuzhou Yang,

Moxuan Ding,

Yanmin Wu,

Zihan Li,

Jian Zhang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yang_2023_ICCV, author = {Yang, Shuzhou and Ding, Moxuan and Wu, Yanmin and Li, Zihan and Zhang, Jian}, title = {Implicit Neural Representation for Cooperative Low-light Image Enhancement}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {12918-12927} }
ReLeaPS : Reinforcement Learning-based Illumination Planning for Generalized Photometric Stereo: Jun Hoong Chan,

Bohan Yu,

Heng Guo,

Jieji Ren,

Zongqing Lu,

Boxin Shi; [pdf] [supp]
[bibtex]
@InProceedings{Chan_2023_ICCV, author = {Chan, Jun Hoong and Yu, Bohan and Guo, Heng and Ren, Jieji and Lu, Zongqing and Shi, Boxin}, title = {ReLeaPS : Reinforcement Learning-based Illumination Planning for Generalized Photometric Stereo}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {9167-9175} }
Learning Foresightful Dense Visual Affordance for Deformable Object Manipulation: Ruihai Wu,

Chuanruo Ning,

Hao Dong; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wu_2023_ICCV, author = {Wu, Ruihai and Ning, Chuanruo and Dong, Hao}, title = {Learning Foresightful Dense Visual Affordance for Deformable Object Manipulation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {10947-10956} }
CiteTracker: Correlating Image and Text for Visual Tracking: Xin Li,

Yuqing Huang,

Zhenyu He,

Yaowei Wang,

Huchuan Lu,

Ming-Hsuan Yang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Li_2023_ICCV, author = {Li, Xin and Huang, Yuqing and He, Zhenyu and Wang, Yaowei and Lu, Huchuan and Yang, Ming-Hsuan}, title = {CiteTracker: Correlating Image and Text for Visual Tracking}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {9974-9983} }
PHRIT: Parametric Hand Representation with Implicit Template: Zhisheng Huang,

Yujin Chen,

Di Kang,

Jinlu Zhang,

Zhigang Tu; [pdf] [supp]
[bibtex]
@InProceedings{Huang_2023_ICCV, author = {Huang, Zhisheng and Chen, Yujin and Kang, Di and Zhang, Jinlu and Tu, Zhigang}, title = {PHRIT: Parametric Hand Representation with Implicit Template}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {14974-14984} }
BEVPlace: Learning LiDAR-based Place Recognition using Bird's Eye View Images: Lun Luo,

Shuhang Zheng,

Yixuan Li,

Yongzhi Fan,

Beinan Yu,

Si-Yuan Cao,

Junwei Li,

Hui-Liang Shen; [pdf] [supp]
[bibtex]
@InProceedings{Luo_2023_ICCV, author = {Luo, Lun and Zheng, Shuhang and Li, Yixuan and Fan, Yongzhi and Yu, Beinan and Cao, Si-Yuan and Li, Junwei and Shen, Hui-Liang}, title = {BEVPlace: Learning LiDAR-based Place Recognition using Bird's Eye View Images}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {8700-8709} }
TrajPAC: Towards Robustness Verification of Pedestrian Trajectory Prediction Models: Liang Zhang,

Nathaniel Xu,

Pengfei Yang,

Gaojie Jin,

Cheng-Chao Huang,

Lijun Zhang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhang_2023_ICCV, author = {Zhang, Liang and Xu, Nathaniel and Yang, Pengfei and Jin, Gaojie and Huang, Cheng-Chao and Zhang, Lijun}, title = {TrajPAC: Towards Robustness Verification of Pedestrian Trajectory Prediction Models}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {8327-8339} }
Learning Point Cloud Completion without Complete Point Clouds: A Pose-Aware Approach: Jihun Kim,

Hyeokjun Kweon,

Yunseo Yang,

Kuk-Jin Yoon; [pdf] [supp]
[bibtex]
@InProceedings{Kim_2023_ICCV, author = {Kim, Jihun and Kweon, Hyeokjun and Yang, Yunseo and Yoon, Kuk-Jin}, title = {Learning Point Cloud Completion without Complete Point Clouds: A Pose-Aware Approach}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {14203-14213} }
Frequency Guidance Matters in Few-Shot Learning: Hao Cheng,

Siyuan Yang,

Joey Tianyi Zhou,

Lanqing Guo,

Bihan Wen; [pdf] [supp]
[bibtex]
@InProceedings{Cheng_2023_ICCV, author = {Cheng, Hao and Yang, Siyuan and Zhou, Joey Tianyi and Guo, Lanqing and Wen, Bihan}, title = {Frequency Guidance Matters in Few-Shot Learning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {11814-11824} }
Spherical Space Feature Decomposition for Guided Depth Map Super-Resolution: Zixiang Zhao,

Jiangshe Zhang,

Xiang Gu,

Chengli Tan,

Shuang Xu,

Yulun Zhang,

Radu Timofte,

Luc Van Gool; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhao_2023_ICCV, author = {Zhao, Zixiang and Zhang, Jiangshe and Gu, Xiang and Tan, Chengli and Xu, Shuang and Zhang, Yulun and Timofte, Radu and Van Gool, Luc}, title = {Spherical Space Feature Decomposition for Guided Depth Map Super-Resolution}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {12547-12558} }
Tiled Multiplane Images for Practical 3D Photography: Numair Khan,

Lei Xiao,

Douglas Lanman; [pdf] [arXiv]
[bibtex]
@InProceedings{Khan_2023_ICCV, author = {Khan, Numair and Xiao, Lei and Lanman, Douglas}, title = {Tiled Multiplane Images for Practical 3D Photography}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {10454-10464} }
HTML: Hybrid Temporal-scale Multimodal Learning Framework for Referring Video Object Segmentation: Mingfei Han,

Yali Wang,

Zhihui Li,

Lina Yao,

Xiaojun Chang,

Yu Qiao; [pdf] [supp]
[bibtex]
@InProceedings{Han_2023_ICCV, author = {Han, Mingfei and Wang, Yali and Li, Zhihui and Yao, Lina and Chang, Xiaojun and Qiao, Yu}, title = {HTML: Hybrid Temporal-scale Multimodal Learning Framework for Referring Video Object Segmentation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {13414-13423} }
PointDC: Unsupervised Semantic Segmentation of 3D Point Clouds via Cross-Modal Distillation and Super-Voxel Clustering: Zisheng Chen,

Hongbin Xu,

Weitao Chen,

Zhipeng Zhou,

Haihong Xiao,

Baigui Sun,

Xuansong Xie,

Wenxiong kang; [pdf] [supp]
[bibtex]
@InProceedings{Chen_2023_ICCV, author = {Chen, Zisheng and Xu, Hongbin and Chen, Weitao and Zhou, Zhipeng and Xiao, Haihong and Sun, Baigui and Xie, Xuansong and kang, Wenxiong}, title = {PointDC: Unsupervised Semantic Segmentation of 3D Point Clouds via Cross-Modal Distillation and Super-Voxel Clustering}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {14290-14299} }
MV-Map: Offboard HD-Map Generation with Multi-view Consistency: Ziyang Xie,

Ziqi Pang,

Yu-Xiong Wang; [pdf] [supp]
[bibtex]
@InProceedings{Xie_2023_ICCV, author = {Xie, Ziyang and Pang, Ziqi and Wang, Yu-Xiong}, title = {MV-Map: Offboard HD-Map Generation with Multi-view Consistency}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {8658-8668} }
Multi-view Self-supervised Disentanglement for General Image Denoising: Hao Chen,

Chenyuan Qu,

Yu Zhang,

Chen Chen,

Jianbo Jiao; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chen_2023_ICCV, author = {Chen, Hao and Qu, Chenyuan and Zhang, Yu and Chen, Chen and Jiao, Jianbo}, title = {Multi-view Self-supervised Disentanglement for General Image Denoising}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {12281-12291} }
SHERF: Generalizable Human NeRF from a Single Image: Shoukang Hu,

Fangzhou Hong,

Liang Pan,

Haiyi Mei,

Lei Yang,

Ziwei Liu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Hu_2023_ICCV, author = {Hu, Shoukang and Hong, Fangzhou and Pan, Liang and Mei, Haiyi and Yang, Lei and Liu, Ziwei}, title = {SHERF: Generalizable Human NeRF from a Single Image}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {9352-9364} }
MVPSNet: Fast Generalizable Multi-view Photometric Stereo: Dongxu Zhao,

Daniel Lichy,

Pierre-Nicolas Perrin,

Jan-Michael Frahm,

Soumyadip Sengupta; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhao_2023_ICCV, author = {Zhao, Dongxu and Lichy, Daniel and Perrin, Pierre-Nicolas and Frahm, Jan-Michael and Sengupta, Soumyadip}, title = {MVPSNet: Fast Generalizable Multi-view Photometric Stereo}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {12525-12536} }
Human from Blur: Human Pose Tracking from Blurry Images: Yiming Zhao,

Denys Rozumnyi,

Jie Song,

Otmar Hilliges,

Marc Pollefeys,

Martin R. Oswald; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhao_2023_ICCV, author = {Zhao, Yiming and Rozumnyi, Denys and Song, Jie and Hilliges, Otmar and Pollefeys, Marc and Oswald, Martin R.}, title = {Human from Blur: Human Pose Tracking from Blurry Images}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {14905-14915} }
Uni-3D: A Universal Model for Panoptic 3D Scene Reconstruction: Xiang Zhang,

Zeyuan Chen,

Fangyin Wei,

Zhuowen Tu; [pdf]
[bibtex]
@InProceedings{Zhang_2023_ICCV, author = {Zhang, Xiang and Chen, Zeyuan and Wei, Fangyin and Tu, Zhuowen}, title = {Uni-3D: A Universal Model for Panoptic 3D Scene Reconstruction}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {9256-9266} }
Full-Body Articulated Human-Object Interaction: Nan Jiang,

Tengyu Liu,

Zhexuan Cao,

Jieming Cui,

Zhiyuan Zhang,

Yixin Chen,

He Wang,

Yixin Zhu,

Siyuan Huang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Jiang_2023_ICCV, author = {Jiang, Nan and Liu, Tengyu and Cao, Zhexuan and Cui, Jieming and Zhang, Zhiyuan and Chen, Yixin and Wang, He and Zhu, Yixin and Huang, Siyuan}, title = {Full-Body Articulated Human-Object Interaction}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {9365-9376} }
FeatureNeRF: Learning Generalizable NeRFs by Distilling Foundation Models: Jianglong Ye,

Naiyan Wang,

Xiaolong Wang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ye_2023_ICCV, author = {Ye, Jianglong and Wang, Naiyan and Wang, Xiaolong}, title = {FeatureNeRF: Learning Generalizable NeRFs by Distilling Foundation Models}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {8962-8973} }
SRFormer: Permuted Self-Attention for Single Image Super-Resolution: Yupeng Zhou,

Zhen Li,

Chun-Le Guo,

Song Bai,

Ming-Ming Cheng,

Qibin Hou; [pdf] [arXiv]
[bibtex]
@InProceedings{Zhou_2023_ICCV, author = {Zhou, Yupeng and Li, Zhen and Guo, Chun-Le and Bai, Song and Cheng, Ming-Ming and Hou, Qibin}, title = {SRFormer: Permuted Self-Attention for Single Image Super-Resolution}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {12780-12791} }
Deep Homography Mixture for Single Image Rolling Shutter Correction: Weilong Yan,

Robby T. Tan,

Bing Zeng,

Shuaicheng Liu; [pdf]
[bibtex]
@InProceedings{Yan_2023_ICCV, author = {Yan, Weilong and Tan, Robby T. and Zeng, Bing and Liu, Shuaicheng}, title = {Deep Homography Mixture for Single Image Rolling Shutter Correction}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {9868-9877} }
Audio-Visual Glance Network for Efficient Video Recognition: Muhammad Adi Nugroho,

Sangmin Woo,

Sumin Lee,

Changick Kim; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Nugroho_2023_ICCV, author = {Nugroho, Muhammad Adi and Woo, Sangmin and Lee, Sumin and Kim, Changick}, title = {Audio-Visual Glance Network for Efficient Video Recognition}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {10150-10159} }
STEPs: Self-Supervised Key Step Extraction and Localization from Unlabeled Procedural Videos: Anshul Shah,

Benjamin Lundell,

Harpreet Sawhney,

Rama Chellappa; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Shah_2023_ICCV, author = {Shah, Anshul and Lundell, Benjamin and Sawhney, Harpreet and Chellappa, Rama}, title = {STEPs: Self-Supervised Key Step Extraction and Localization from Unlabeled Procedural Videos}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {10375-10387} }
Towards Robust and Smooth 3D Multi-Person Pose Estimation from Monocular Videos in the Wild: Sungchan Park,

Eunyi You,

Inhoe Lee,

Joonseok Lee; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Park_2023_ICCV, author = {Park, Sungchan and You, Eunyi and Lee, Inhoe and Lee, Joonseok}, title = {Towards Robust and Smooth 3D Multi-Person Pose Estimation from Monocular Videos in the Wild}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {14772-14782} }
Clustering based Point Cloud Representation Learning for 3D Analysis: Tuo Feng,

Wenguan Wang,

Xiaohan Wang,

Yi Yang,

Qinghua Zheng; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Feng_2023_ICCV, author = {Feng, Tuo and Wang, Wenguan and Wang, Xiaohan and Yang, Yi and Zheng, Qinghua}, title = {Clustering based Point Cloud Representation Learning for 3D Analysis}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {8283-8294} }
Forecast-MAE: Self-supervised Pre-training for Motion Forecasting with Masked Autoencoders: Jie Cheng,

Xiaodong Mei,

Ming Liu; [pdf] [supp]
[bibtex]
@InProceedings{Cheng_2023_ICCV, author = {Cheng, Jie and Mei, Xiaodong and Liu, Ming}, title = {Forecast-MAE: Self-supervised Pre-training for Motion Forecasting with Masked Autoencoders}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {8679-8689} }
Efficient Transformer-based 3D Object Detection with Dynamic Token Halting: Mao Ye,

Gregory P. Meyer,

Yuning Chai,

Qiang Liu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ye_2023_ICCV, author = {Ye, Mao and Meyer, Gregory P. and Chai, Yuning and Liu, Qiang}, title = {Efficient Transformer-based 3D Object Detection with Dynamic Token Halting}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {8438-8450} }
Video Task Decathlon: Unifying Image and Video Tasks in Autonomous Driving: Thomas E. Huang,

Yifan Liu,

Luc Van Gool,

Fisher Yu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Huang_2023_ICCV, author = {Huang, Thomas E. and Liu, Yifan and Van Gool, Luc and Yu, Fisher}, title = {Video Task Decathlon: Unifying Image and Video Tasks in Autonomous Driving}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {8647-8657} }
PreSTU: Pre-Training for Scene-Text Understanding: Jihyung Kil,

Soravit Changpinyo,

Xi Chen,

Hexiang Hu,

Sebastian Goodman,

Wei-Lun Chao,

Radu Soricut; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kil_2023_ICCV, author = {Kil, Jihyung and Changpinyo, Soravit and Chen, Xi and Hu, Hexiang and Goodman, Sebastian and Chao, Wei-Lun and Soricut, Radu}, title = {PreSTU: Pre-Training for Scene-Text Understanding}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {15270-15280} }; Back