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,