Papers
- Back
Towards Attack-tolerant Federated Learning via Critical Parameter Analysis-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Han_2023_ICCV, author = {Han, Sungwon and Park, Sungwon and Wu, Fangzhao and Kim, Sundong and Zhu, Bin and Xie, Xing and Cha, Meeyoung}, title = {Towards Attack-tolerant Federated Learning via Critical Parameter Analysis}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {4999-5008} }
Stochastic Segmentation with Conditional Categorical Diffusion Models-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Zbinden_2023_ICCV, author = {Zbinden, Lukas and Doorenbos, Lars and Pissas, Theodoros and Huber, Adrian Thomas and Sznitman, Raphael and M\'arquez-Neila, Pablo}, title = {Stochastic Segmentation with Conditional Categorical Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {1119-1129} }
A Dynamic Dual-Processing Object Detection Framework Inspired by the Brain's Recognition Mechanism-
[pdf]
[bibtex]@InProceedings{Zhang_2023_ICCV, author = {Zhang, Minying and Bu, Tianpeng and Hu, Lulu}, title = {A Dynamic Dual-Processing Object Detection Framework Inspired by the Brain's Recognition Mechanism}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {6264-6274} }
Hard No-Box Adversarial Attack on Skeleton-Based Human Action Recognition with Skeleton-Motion-Informed Gradient-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Lu_2023_ICCV, author = {Lu, Zhengzhi and Wang, He and Chang, Ziyi and Yang, Guoan and Shum, Hubert P. H.}, title = {Hard No-Box Adversarial Attack on Skeleton-Based Human Action Recognition with Skeleton-Motion-Informed Gradient}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {4597-4606} }
GameFormer: Game-theoretic Modeling and Learning of Transformer-based Interactive Prediction and Planning for Autonomous Driving-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Huang_2023_ICCV, author = {Huang, Zhiyu and Liu, Haochen and Lv, Chen}, title = {GameFormer: Game-theoretic Modeling and Learning of Transformer-based Interactive Prediction and Planning for Autonomous Driving}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {3903-3913} }
Learning in Imperfect Environment: Multi-Label Classification with Long-Tailed Distribution and Partial Labels-
[pdf]
[arXiv]
[bibtex]@InProceedings{Zhang_2023_ICCV, author = {Zhang, Wenqiao and Liu, Changshuo and Zeng, Lingze and Ooi, Bengchin and Tang, Siliang and Zhuang, Yueting}, title = {Learning in Imperfect Environment: Multi-Label Classification with Long-Tailed Distribution and Partial Labels}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {1423-1432} }
Flexible Visual Recognition by Evidential Modeling of Confusion and Ignorance-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Fan_2023_ICCV, author = {Fan, Lei and Liu, Bo and Li, Haoxiang and Wu, Ying and Hua, Gang}, title = {Flexible Visual Recognition by Evidential Modeling of Confusion and Ignorance}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {1338-1347} }
Texture Generation on 3D Meshes with Point-UV Diffusion-
[pdf]
[arXiv]
[bibtex]@InProceedings{Yu_2023_ICCV, author = {Yu, Xin and Dai, Peng and Li, Wenbo and Ma, Lan and Liu, Zhengzhe and Qi, Xiaojuan}, title = {Texture Generation on 3D Meshes with Point-UV Diffusion}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {4206-4216} }
Enhanced Soft Label for Semi-Supervised Semantic Segmentation-
[pdf]
[supp]
[bibtex]@InProceedings{Ma_2023_ICCV, author = {Ma, Jie and Wang, Chuan and Liu, Yang and Lin, Liang and Li, Guanbin}, title = {Enhanced Soft Label for Semi-Supervised Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {1185-1195} }
HM-ViT: Hetero-Modal Vehicle-to-Vehicle Cooperative Perception with Vision Transformer-
[pdf]
[supp]
[bibtex]@InProceedings{Xiang_2023_ICCV, author = {Xiang, Hao and Xu, Runsheng and Ma, Jiaqi}, title = {HM-ViT: Hetero-Modal Vehicle-to-Vehicle Cooperative Perception with Vision Transformer}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {284-295} }
HyperReenact: One-Shot Reenactment via Jointly Learning to Refine and Retarget Faces-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Bounareli_2023_ICCV, author = {Bounareli, Stella and Tzelepis, Christos and Argyriou, Vasileios and Patras, Ioannis and Tzimiropoulos, Georgios}, title = {HyperReenact: One-Shot Reenactment via Jointly Learning to Refine and Retarget Faces}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {7149-7159} }
Unified Visual Relationship Detection with Vision and Language Models-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Zhao_2023_ICCV, author = {Zhao, Long and Yuan, Liangzhe and Gong, Boqing and Cui, Yin and Schroff, Florian and Yang, Ming-Hsuan and Adam, Hartwig and Liu, Ting}, title = {Unified Visual Relationship Detection with Vision and Language Models}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {6962-6973} }
Rickrolling the Artist: Injecting Backdoors into Text Encoders for Text-to-Image Synthesis-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Struppek_2023_ICCV, author = {Struppek, Lukas and Hintersdorf, Dominik and Kersting, Kristian}, title = {Rickrolling the Artist: Injecting Backdoors into Text Encoders for Text-to-Image Synthesis}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {4584-4596} }
LD-ZNet: A Latent Diffusion Approach for Text-Based Image Segmentation-
[pdf]
[supp]
[bibtex]@InProceedings{PNVR_2023_ICCV, author = {PNVR, Koutilya and Singh, Bharat and Ghosh, Pallabi and Siddiquie, Behjat and Jacobs, David}, title = {LD-ZNet: A Latent Diffusion Approach for Text-Based Image Segmentation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {4157-4168} }
Downstream-agnostic Adversarial Examples-
[pdf]
[arXiv]
[bibtex]@InProceedings{Zhou_2023_ICCV, author = {Zhou, Ziqi and Hu, Shengshan and Zhao, Ruizhi and Wang, Qian and Zhang, Leo Yu and Hou, Junhui and Jin, Hai}, title = {Downstream-agnostic Adversarial Examples}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {4345-4355} }
Studying How to Efficiently and Effectively Guide Models with Explanations-
[pdf]
[supp]
[bibtex]@InProceedings{Rao_2023_ICCV, author = {Rao, Sukrut and B\"ohle, Moritz and Parchami-Araghi, Amin and Schiele, Bernt}, title = {Studying How to Efficiently and Effectively Guide Models with Explanations}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {1922-1933} }
SkeletonMAE: Graph-based Masked Autoencoder for Skeleton Sequence Pre-training-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Yan_2023_ICCV, author = {Yan, Hong and Liu, Yang and Wei, Yushen and Li, Zhen and Li, Guanbin and Lin, Liang}, title = {SkeletonMAE: Graph-based Masked Autoencoder for Skeleton Sequence Pre-training}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {5606-5618} }
Pose-Free Neural Radiance Fields via Implicit Pose Regularization-
[pdf]
[arXiv]
[bibtex]@InProceedings{Zhang_2023_ICCV, author = {Zhang, Jiahui and Zhan, Fangneng and Yu, Yingchen and Liu, Kunhao and Wu, Rongliang and Zhang, Xiaoqin and Shao, Ling and Lu, Shijian}, title = {Pose-Free Neural Radiance Fields via Implicit Pose Regularization}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {3534-3543} }
Encyclopedic VQA: Visual Questions About Detailed Properties of Fine-Grained Categories-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Mensink_2023_ICCV, author = {Mensink, Thomas and Uijlings, Jasper and Castrejon, Lluis and Goel, Arushi and Cadar, Felipe and Zhou, Howard and Sha, Fei and Araujo, Andr\'e and Ferrari, Vittorio}, title = {Encyclopedic VQA: Visual Questions About Detailed Properties of Fine-Grained Categories}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {3113-3124} }
Towards Understanding the Generalization of Deepfake Detectors from a Game-Theoretical View-
[pdf]
[supp]
[bibtex]@InProceedings{Yao_2023_ICCV, author = {Yao, Kelu and Wang, Jin and Diao, Boyu and Li, Chao}, title = {Towards Understanding the Generalization of Deepfake Detectors from a Game-Theoretical View}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {2031-2041} }
3DPPE: 3D Point Positional Encoding for Transformer-based Multi-Camera 3D Object Detection-
[pdf]
[supp]
[bibtex]@InProceedings{Shu_2023_ICCV, author = {Shu, Changyong and Deng, Jiajun and Yu, Fisher and Liu, Yifan}, title = {3DPPE: 3D Point Positional Encoding for Transformer-based Multi-Camera 3D Object Detection}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {3580-3589} }
VertexSerum: Poisoning Graph Neural Networks for Link Inference-
[pdf]
[arXiv]
[bibtex]@InProceedings{Ding_2023_ICCV, author = {Ding, Ruyi and Duan, Shijin and Xu, Xiaolin and Fei, Yunsi}, title = {VertexSerum: Poisoning Graph Neural Networks for Link Inference}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {4532-4541} }
Deep Geometrized Cartoon Line Inbetweening-
[pdf]
[supp]
[bibtex]@InProceedings{Siyao_2023_ICCV, author = {Siyao, Li and Gu, Tianpei and Xiao, Weiye and Ding, Henghui and Liu, Ziwei and Loy, Chen Change}, title = {Deep Geometrized Cartoon Line Inbetweening}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {7291-7300} }
MatrixCity: A Large-scale City Dataset for City-scale Neural Rendering and Beyond-
[pdf]
[supp]
[bibtex]@InProceedings{Li_2023_ICCV, author = {Li, Yixuan and Jiang, Lihan and Xu, Linning and Xiangli, Yuanbo and Wang, Zhenzhi and Lin, Dahua and Dai, Bo}, title = {MatrixCity: A Large-scale City Dataset for City-scale Neural Rendering and Beyond}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {3205-3215} }
LinkGAN: Linking GAN Latents to Pixels for Controllable Image Synthesis-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Zhu_2023_ICCV, author = {Zhu, Jiapeng and Yang, Ceyuan and Shen, Yujun and Shi, Zifan and Dai, Bo and Zhao, Deli and Chen, Qifeng}, title = {LinkGAN: Linking GAN Latents to Pixels for Controllable Image Synthesis}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {7656-7666} }
SVDiff: Compact Parameter Space for Diffusion Fine-Tuning-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Han_2023_ICCV, author = {Han, Ligong and Li, Yinxiao and Zhang, Han and Milanfar, Peyman and Metaxas, Dimitris and Yang, Feng}, title = {SVDiff: Compact Parameter Space for Diffusion Fine-Tuning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {7323-7334} }
Distilling Large Vision-Language Model with Out-of-Distribution Generalizability-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Li_2023_ICCV, author = {Li, Xuanlin and Fang, Yunhao and Liu, Minghua and Ling, Zhan and Tu, Zhuowen and Su, Hao}, title = {Distilling Large Vision-Language Model with Out-of-Distribution Generalizability}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {2492-2503} }
What do neural networks learn in image classification? A frequency shortcut perspective-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Wang_2023_ICCV, author = {Wang, Shunxin and Veldhuis, Raymond and Brune, Christoph and Strisciuglio, Nicola}, title = {What do neural networks learn in image classification? A frequency shortcut perspective}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {1433-1442} }
PromptCap: Prompt-Guided Image Captioning for VQA with GPT-3-
[pdf]
[supp]
[bibtex]@InProceedings{Hu_2023_ICCV, author = {Hu, Yushi and Hua, Hang and Yang, Zhengyuan and Shi, Weijia and Smith, Noah A. and Luo, Jiebo}, title = {PromptCap: Prompt-Guided Image Captioning for VQA with GPT-3}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {2963-2975} }
Periodically Exchange Teacher-Student for Source-Free Object Detection-
[pdf]
[bibtex]@InProceedings{Liu_2023_ICCV, author = {Liu, Qipeng and Lin, Luojun and Shen, Zhifeng and Yang, Zhifeng}, title = {Periodically Exchange Teacher-Student for Source-Free Object Detection}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {6414-6424} }
Learning to Transform for Generalizable Instance-wise Invariance-
[pdf]
[bibtex]@InProceedings{Singhal_2023_ICCV, author = {Singhal, Utkarsh and Esteves, Carlos and Makadia, Ameesh and Yu, Stella X.}, title = {Learning to Transform for Generalizable Instance-wise Invariance}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {6211-6221} }
Multiple Instance Learning Framework with Masked Hard Instance Mining for Whole Slide Image Classification-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Tang_2023_ICCV, author = {Tang, Wenhao and Huang, Sheng and Zhang, Xiaoxian and Zhou, Fengtao and Zhang, Yi and Liu, Bo}, title = {Multiple Instance Learning Framework with Masked Hard Instance Mining for Whole Slide Image Classification}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {4078-4087} }
Unsupervised Compositional Concepts Discovery with Text-to-Image Generative Models-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Liu_2023_ICCV, author = {Liu, Nan and Du, Yilun and Li, Shuang and Tenenbaum, Joshua B. and Torralba, Antonio}, title = {Unsupervised Compositional Concepts Discovery with Text-to-Image Generative Models}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {2085-2095} }
Partition-And-Debias: Agnostic Biases Mitigation via a Mixture of Biases-Specific Experts-
[pdf]
[supp]
[bibtex]@InProceedings{Li_2023_ICCV, author = {Li, Jiaxuan and Vo, Duc Minh and Nakayama, Hideki}, title = {Partition-And-Debias: Agnostic Biases Mitigation via a Mixture of Biases-Specific Experts}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {4924-4934} }
Spatial Self-Distillation for Object Detection with Inaccurate Bounding Boxes-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Wu_2023_ICCV, author = {Wu, Di and Chen, Pengfei and Yu, Xuehui and Li, Guorong and Han, Zhenjun and Jiao, Jianbin}, title = {Spatial Self-Distillation for Object Detection with Inaccurate Bounding Boxes}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {6855-6865} }
CC3D: Layout-Conditioned Generation of Compositional 3D Scenes-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Bahmani_2023_ICCV, author = {Bahmani, Sherwin and Park, Jeong Joon and Paschalidou, Despoina and Yan, Xingguang and Wetzstein, Gordon and Guibas, Leonidas and Tagliasacchi, Andrea}, title = {CC3D: Layout-Conditioned Generation of Compositional 3D Scenes}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {7171-7181} }
TextPSG: Panoptic Scene Graph Generation from Textual Descriptions-
[pdf]
[supp]
[bibtex]@InProceedings{Zhao_2023_ICCV, author = {Zhao, Chengyang and Shen, Yikang and Chen, Zhenfang and Ding, Mingyu and Gan, Chuang}, title = {TextPSG: Panoptic Scene Graph Generation from Textual Descriptions}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {2839-2850} }
Cross-modal Latent Space Alignment for Image to Avatar Translation-
[pdf]
[supp]
[bibtex]@InProceedings{de_Guevara_2023_ICCV, author = {de Guevara, Manuel Ladron and Echevarria, Jose and Li, Yijun and Hold-Geoffroy, Yannick and Smith, Cameron and Ito, Daichi}, title = {Cross-modal Latent Space Alignment for Image to Avatar Translation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {520-529} }
Inspecting the Geographical Representativeness of Images from Text-to-Image Models-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Basu_2023_ICCV, author = {Basu, Abhipsa and Babu, R. Venkatesh and Pruthi, Danish}, title = {Inspecting the Geographical Representativeness of Images from Text-to-Image Models}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {5136-5147} }
HSR-Diff: Hyperspectral Image Super-Resolution via Conditional Diffusion Models-
[pdf]
[supp]
[bibtex]@InProceedings{Wu_2023_ICCV, author = {Wu, Chanyue and Wang, Dong and Bai, Yunpeng and Mao, Hanyu and Li, Ying and Shen, Qiang}, title = {HSR-Diff: Hyperspectral Image Super-Resolution via Conditional Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {7083-7093} }
Advancing Example Exploitation Can Alleviate Critical Challenges in Adversarial Training-
[pdf]
[supp]
[bibtex]@InProceedings{Ge_2023_ICCV, author = {Ge, Yao and Li, Yun and Han, Keji and Zhu, Junyi and Long, Xianzhong}, title = {Advancing Example Exploitation Can Alleviate Critical Challenges in Adversarial Training}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {145-154} }
ShiftNAS: Improving One-shot NAS via Probability Shift-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Zhang_2023_ICCV, author = {Zhang, Mingyang and Yu, Xinyi and Zhao, Haodong and Ou, Linlin}, title = {ShiftNAS: Improving One-shot NAS via Probability Shift}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {5919-5928} }
Adaptive Testing of Computer Vision Models-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Gao_2023_ICCV, author = {Gao, Irena and Ilharco, Gabriel and Lundberg, Scott and Ribeiro, Marco Tulio}, title = {Adaptive Testing of Computer Vision Models}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {4003-4014} }
Feature Proliferation -- the "Cancer" in StyleGAN and its Treatments-
[pdf]
[supp]
[bibtex]@InProceedings{Song_2023_ICCV, author = {Song, Shuang and Liang, Yuanbang and Wu, Jing and Lai, Yu-Kun and Qin, Yipeng}, title = {Feature Proliferation -- the ''Cancer'' in StyleGAN and its Treatments}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {2360-2370} }
Multi-Label Self-Supervised Learning with Scene Images-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Zhu_2023_ICCV, author = {Zhu, Ke and Fu, Minghao and Wu, Jianxin}, title = {Multi-Label Self-Supervised Learning with Scene Images}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {6694-6703} }
Enhancing Fine-Tuning Based Backdoor Defense with Sharpness-Aware Minimization-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Zhu_2023_ICCV, author = {Zhu, Mingli and Wei, Shaokui and Shen, Li and Fan, Yanbo and Wu, Baoyuan}, title = {Enhancing Fine-Tuning Based Backdoor Defense with Sharpness-Aware Minimization}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {4466-4477} }
Deep Geometry-Aware Camera Self-Calibration from Video-
[pdf]
[supp]
[bibtex]@InProceedings{Hagemann_2023_ICCV, author = {Hagemann, Annika and Knorr, Moritz and Stiller, Christoph}, title = {Deep Geometry-Aware Camera Self-Calibration from Video}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {3438-3448} }
Exploring Object-Centric Temporal Modeling for Efficient Multi-View 3D Object Detection-
[pdf]
[arXiv]
[bibtex]@InProceedings{Wang_2023_ICCV, author = {Wang, Shihao and Liu, Yingfei and Wang, Tiancai and Li, Ying and Zhang, Xiangyu}, title = {Exploring Object-Centric Temporal Modeling for Efficient Multi-View 3D Object Detection}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {3621-3631} }
ScanNet++: A High-Fidelity Dataset of 3D Indoor Scenes-
[pdf]
[supp]
[bibtex]@InProceedings{Yeshwanth_2023_ICCV, author = {Yeshwanth, Chandan and Liu, Yueh-Cheng and Nie{\ss}ner, Matthias and Dai, Angela}, title = {ScanNet++: A High-Fidelity Dataset of 3D Indoor Scenes}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {12-22} }
Improving Diversity in Zero-Shot GAN Adaptation with Semantic Variations-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Jeon_2023_ICCV, author = {Jeon, Seogkyu and Liu, Bei and Lee, Pilhyeon and Hong, Kibeom and Fu, Jianlong and Byun, Hyeran}, title = {Improving Diversity in Zero-Shot GAN Adaptation with Semantic Variations}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {7258-7267} }
Vox-E: Text-Guided Voxel Editing of 3D Objects-
[pdf]
[supp]
[bibtex]@InProceedings{Sella_2023_ICCV, author = {Sella, Etai and Fiebelman, Gal and Hedman, Peter and Averbuch-Elor, Hadar}, title = {Vox-E: Text-Guided Voxel Editing of 3D Objects}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {430-440} }
Unilaterally Aggregated Contrastive Learning with Hierarchical Augmentation for Anomaly Detection-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Wang_2023_ICCV, author = {Wang, Guodong and Wang, Yunhong and Qin, Jie and Zhang, Dongming and Bao, Xiuguo and Huang, Di}, title = {Unilaterally Aggregated Contrastive Learning with Hierarchical Augmentation for Anomaly Detection}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {6888-6897} }
Learning Image-Adaptive Codebooks for Class-Agnostic Image Restoration-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Liu_2023_ICCV, author = {Liu, Kechun and Jiang, Yitong and Choi, Inchang and Gu, Jinwei}, title = {Learning Image-Adaptive Codebooks for Class-Agnostic Image Restoration}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {5373-5383} }
3D Segmentation of Humans in Point Clouds with Synthetic Data-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Takmaz_2023_ICCV, author = {Takmaz, Ay\c{c}a and Schult, Jonas and Kaftan, Irem and Ak\c{c}ay, Mertcan and Leibe, Bastian and Sumner, Robert and Engelmann, Francis and Tang, Siyu}, title = {3D Segmentation of Humans in Point Clouds with Synthetic Data}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {1292-1304} }
Mastering Spatial Graph Prediction of Road Networks-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Sotiris_2023_ICCV, author = {Sotiris, Anagnostidis and Lucchi, Aurelien and Hofmann, Thomas}, title = {Mastering Spatial Graph Prediction of Road Networks}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {5408-5418} }
Domain Generalization via Rationale Invariance-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Chen_2023_ICCV, author = {Chen, Liang and Zhang, Yong and Song, Yibing and van den Hengel, Anton and Liu, Lingqiao}, title = {Domain Generalization via Rationale Invariance}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {1751-1760} }
ProbVLM: Probabilistic Adapter for Frozen Vison-Language Models-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Upadhyay_2023_ICCV, author = {Upadhyay, Uddeshya and Karthik, Shyamgopal and Mancini, Massimiliano and Akata, Zeynep}, title = {ProbVLM: Probabilistic Adapter for Frozen Vison-Language Models}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {1899-1910} }
Latent-OFER: Detect, Mask, and Reconstruct with Latent Vectors for Occluded Facial Expression Recognition-
[pdf]
[supp]
[bibtex]@InProceedings{Lee_2023_ICCV, author = {Lee, Isack and Lee, Eungi and Yoo, Seok Bong}, title = {Latent-OFER: Detect, Mask, and Reconstruct with Latent Vectors for Occluded Facial Expression Recognition}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {1536-1546} }
Self-supervised Cross-view Representation Reconstruction for Change Captioning-
[pdf]
[supp]
[bibtex]@InProceedings{Tu_2023_ICCV, author = {Tu, Yunbin and Li, Liang and Su, Li and Zha, Zheng-Jun and Yan, Chenggang and Huang, Qingming}, title = {Self-supervised Cross-view Representation Reconstruction for Change Captioning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {2805-2815} }
Unify, Align and Refine: Multi-Level Semantic Alignment for Radiology Report Generation-
[pdf]
[arXiv]
[bibtex]@InProceedings{Li_2023_ICCV, author = {Li, Yaowei and Yang, Bang and Cheng, Xuxin and Zhu, Zhihong and Li, Hongxiang and Zou, Yuexian}, title = {Unify, Align and Refine: Multi-Level Semantic Alignment for Radiology Report Generation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {2863-2874} }
Scene-Aware Feature Matching-
[pdf]
[arXiv]
[bibtex]@InProceedings{Lu_2023_ICCV, author = {Lu, Xiaoyong and Yan, Yaping and Wei, Tong and Du, Songlin}, title = {Scene-Aware Feature Matching}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {3704-3713} }
FDViT: Improve the Hierarchical Architecture of Vision Transformer-
[pdf]
[bibtex]@InProceedings{Xu_2023_ICCV, author = {Xu, Yixing and Li, Chao and Li, Dong and Sheng, Xiao and Jiang, Fan and Tian, Lu and Sirasao, Ashish}, title = {FDViT: Improve the Hierarchical Architecture of Vision Transformer}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {5950-5960} }
Towards Robust Model Watermark via Reducing Parametric Vulnerability-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Gan_2023_ICCV, author = {Gan, Guanhao and Li, Yiming and Wu, Dongxian and Xia, Shu-Tao}, title = {Towards Robust Model Watermark via Reducing Parametric Vulnerability}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {4751-4761} }
LEA2: A Lightweight Ensemble Adversarial Attack via Non-overlapping Vulnerable Frequency Regions-
[pdf]
[supp]
[bibtex]@InProceedings{Qian_2023_ICCV, author = {Qian, Yaguan and He, Shuke and Zhao, Chenyu and Sha, Jiaqiang and Wang, Wei and Wang, Bin}, title = {LEA2: A Lightweight Ensemble Adversarial Attack via Non-overlapping Vulnerable Frequency Regions}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {4510-4521} }
Unsupervised Domain Adaptive Detection with Network Stability Analysis-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Zhou_2023_ICCV, author = {Zhou, Wenzhang and Fan, Heng and Luo, Tiejian and Zhang, Libo}, title = {Unsupervised Domain Adaptive Detection with Network Stability Analysis}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {6986-6995} }
MeViS: A Large-scale Benchmark for Video Segmentation with Motion Expressions-
[pdf]
[arXiv]
[bibtex]@InProceedings{Ding_2023_ICCV, author = {Ding, Henghui and Liu, Chang and He, Shuting and Jiang, Xudong and Loy, Chen Change}, title = {MeViS: A Large-scale Benchmark for Video Segmentation with Motion Expressions}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {2694-2703} }
OPERA: Omni-Supervised Representation Learning with Hierarchical Supervisions-
[pdf]
[arXiv]
[bibtex]@InProceedings{Wang_2023_ICCV, author = {Wang, Chengkun and Zheng, Wenzhao and Zhu, Zheng and Zhou, Jie and Lu, Jiwen}, title = {OPERA: Omni-Supervised Representation Learning with Hierarchical Supervisions}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {5559-5570} }
GPFL: Simultaneously Learning Global and Personalized Feature Information for Personalized Federated Learning-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Zhang_2023_ICCV, author = {Zhang, Jianqing and Hua, Yang and Wang, Hao and Song, Tao and Xue, Zhengui and Ma, Ruhui and Cao, Jian and Guan, Haibing}, title = {GPFL: Simultaneously Learning Global and Personalized Feature Information for Personalized Federated Learning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {5041-5051} }
Efficient Region-Aware Neural Radiance Fields for High-Fidelity Talking Portrait Synthesis-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Li_2023_ICCV, author = {Li, Jiahe and Zhang, Jiawei and Bai, Xiao and Zhou, Jun and Gu, Lin}, title = {Efficient Region-Aware Neural Radiance Fields for High-Fidelity Talking Portrait Synthesis}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {7568-7578} }
End2End Multi-View Feature Matching with Differentiable Pose Optimization-
[pdf]
[supp]
[bibtex]@InProceedings{Roessle_2023_ICCV, author = {Roessle, Barbara and Nie{\ss}ner, Matthias}, title = {End2End Multi-View Feature Matching with Differentiable Pose Optimization}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {477-487} }
Exploring the Benefits of Visual Prompting in Differential Privacy-
[pdf]
[arXiv]
[bibtex]@InProceedings{Li_2023_ICCV, author = {Li, Yizhe and Tsai, Yu-Lin and Yu, Chia-Mu and Chen, Pin-Yu and Ren, Xuebin}, title = {Exploring the Benefits of Visual Prompting in Differential Privacy}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {5158-5167} }
Mining bias-target Alignment from Voronoi Cells-
[pdf]
[arXiv]
[bibtex]@InProceedings{Nahon_2023_ICCV, author = {Nahon, R\'emi and Nguyen, Van-Tam and Tartaglione, Enzo}, title = {Mining bias-target Alignment from Voronoi Cells}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {4946-4955} }
The Victim and The Beneficiary: Exploiting a Poisoned Model to Train a Clean Model on Poisoned Data-
[pdf]
[supp]
[bibtex]@InProceedings{Zhu_2023_ICCV, author = {Zhu, Zixuan and Wang, Rui and Zou, Cong and Jing, Lihua}, title = {The Victim and The Beneficiary: Exploiting a Poisoned Model to Train a Clean Model on Poisoned Data}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {155-164} }
DIFFGUARD: Semantic Mismatch-Guided Out-of-Distribution Detection Using Pre-Trained Diffusion Models-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Gao_2023_ICCV, author = {Gao, Ruiyuan and Zhao, Chenchen and Hong, Lanqing and Xu, Qiang}, title = {DIFFGUARD: Semantic Mismatch-Guided Out-of-Distribution Detection Using Pre-Trained Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {1579-1589} }
Tracking Anything with Decoupled Video Segmentation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Cheng_2023_ICCV, author = {Cheng, Ho Kei and Oh, Seoung Wug and Price, Brian and Schwing, Alexander and Lee, Joon-Young}, title = {Tracking Anything with Decoupled Video Segmentation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {1316-1326} }
Generative Gradient Inversion via Over-Parameterized Networks in Federated Learning-
[pdf]
[supp]
[bibtex]@InProceedings{Zhang_2023_ICCV, author = {Zhang, Chi and Xiaoman, Zhang and Sotthiwat, Ekanut and Xu, Yanyu and Liu, Ping and Zhen, Liangli and Liu, Yong}, title = {Generative Gradient Inversion via Over-Parameterized Networks in Federated Learning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {5126-5135} }
EQ-Net: Elastic Quantization Neural Networks-
[pdf]
[supp]
[bibtex]@InProceedings{Xu_2023_ICCV, author = {Xu, Ke and Han, Lei and Tian, Ye and Yang, Shangshang and Zhang, Xingyi}, title = {EQ-Net: Elastic Quantization Neural Networks}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {1505-1514} }
Exploring Open-Vocabulary Semantic Segmentation from CLIP Vision Encoder Distillation Only-
[pdf]
[supp]
[bibtex]@InProceedings{Chen_2023_ICCV, author = {Chen, Jun and Zhu, Deyao and Qian, Guocheng and Ghanem, Bernard and Yan, Zhicheng and Zhu, Chenchen and Xiao, Fanyi and Culatana, Sean Chang and Elhoseiny, Mohamed}, title = {Exploring Open-Vocabulary Semantic Segmentation from CLIP Vision Encoder Distillation Only}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {699-710} }
Parallax-Tolerant Unsupervised Deep Image Stitching-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Nie_2023_ICCV, author = {Nie, Lang and Lin, Chunyu and Liao, Kang and Liu, Shuaicheng and Zhao, Yao}, title = {Parallax-Tolerant Unsupervised Deep Image Stitching}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {7399-7408} }
M2T: Masking Transformers Twice for Faster Decoding-
[pdf]
[supp]
[bibtex]@InProceedings{Mentzer_2023_ICCV, author = {Mentzer, Fabian and Agustson, Eirikur and Tschannen, Michael}, title = {M2T: Masking Transformers Twice for Faster Decoding}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {5340-5349} }
CoIn: Contrastive Instance Feature Mining for Outdoor 3D Object Detection with Very Limited Annotations-
[pdf]
[supp]
[bibtex]@InProceedings{Xia_2023_ICCV, author = {Xia, Qiming and Deng, Jinhao and Wen, Chenglu and Wu, Hai and Shi, Shaoshuai and Li, Xin and Wang, Cheng}, title = {CoIn: Contrastive Instance Feature Mining for Outdoor 3D Object Detection with Very Limited Annotations}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {6254-6263} }
Computation and Data Efficient Backdoor Attacks-
[pdf]
[bibtex]@InProceedings{Wu_2023_ICCV, author = {Wu, Yutong and Han, Xingshuo and Qiu, Han and Zhang, Tianwei}, title = {Computation and Data Efficient Backdoor Attacks}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {4805-4814} }
Decouple Before Interact: Multi-Modal Prompt Learning for Continual Visual Question Answering-
[pdf]
[supp]
[bibtex]@InProceedings{Qian_2023_ICCV, author = {Qian, Zi and Wang, Xin and Duan, Xuguang and Qin, Pengda and Li, Yuhong and Zhu, Wenwu}, title = {Decouple Before Interact: Multi-Modal Prompt Learning for Continual Visual Question Answering}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {2953-2962} }
Unsupervised Manifold Linearizing and Clustering-
[pdf]
[arXiv]
[bibtex]@InProceedings{Ding_2023_ICCV, author = {Ding, Tianjiao and Tong, Shengbang and Chan, Kwan Ho Ryan and Dai, Xili and Ma, Yi and Haeffele, Benjamin D.}, title = {Unsupervised Manifold Linearizing and Clustering}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {5450-5461} }
MMVP: Motion-Matrix-Based Video Prediction-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Zhong_2023_ICCV, author = {Zhong, Yiqi and Liang, Luming and Zharkov, Ilya and Neumann, Ulrich}, title = {MMVP: Motion-Matrix-Based Video Prediction}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {4273-4283} }
Human Preference Score: Better Aligning Text-to-Image Models with Human Preference-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Wu_2023_ICCV, author = {Wu, Xiaoshi and Sun, Keqiang and Zhu, Feng and Zhao, Rui and Li, Hongsheng}, title = {Human Preference Score: Better Aligning Text-to-Image Models with Human Preference}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {2096-2105} }
Guided Motion Diffusion for Controllable Human Motion Synthesis-
[pdf]
[supp]
[bibtex]@InProceedings{Karunratanakul_2023_ICCV, author = {Karunratanakul, Korrawe and Preechakul, Konpat and Suwajanakorn, Supasorn and Tang, Siyu}, title = {Guided Motion Diffusion for Controllable Human Motion Synthesis}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {2151-2162} }
DiffuMask: Synthesizing Images with Pixel-level Annotations for Semantic Segmentation Using Diffusion Models-
[pdf]
[arXiv]
[bibtex]@InProceedings{Wu_2023_ICCV, author = {Wu, Weijia and Zhao, Yuzhong and Shou, Mike Zheng and Zhou, Hong and Shen, Chunhua}, title = {DiffuMask: Synthesizing Images with Pixel-level Annotations for Semantic Segmentation Using Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {1206-1217} }
StyleDomain: Efficient and Lightweight Parameterizations of StyleGAN for One-shot and Few-shot Domain Adaptation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Alanov_2023_ICCV, author = {Alanov, Aibek and Titov, Vadim and Nakhodnov, Maksim and Vetrov, Dmitry}, title = {StyleDomain: Efficient and Lightweight Parameterizations of StyleGAN for One-shot and Few-shot Domain Adaptation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {2184-2194} }
RankMixup: Ranking-Based Mixup Training for Network Calibration-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Noh_2023_ICCV, author = {Noh, Jongyoun and Park, Hyekang and Lee, Junghyup and Ham, Bumsub}, title = {RankMixup: Ranking-Based Mixup Training for Network Calibration}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {1358-1368} }
Learning to Generate Semantic Layouts for Higher Text-Image Correspondence in Text-to-Image Synthesis-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Park_2023_ICCV, author = {Park, Minho and Yun, Jooyeol and Choi, Seunghwan and Choo, Jaegul}, title = {Learning to Generate Semantic Layouts for Higher Text-Image Correspondence in Text-to-Image Synthesis}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {7591-7600} }
Erasing Concepts from Diffusion Models-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Gandikota_2023_ICCV, author = {Gandikota, Rohit and Materzynska, Joanna and Fiotto-Kaufman, Jaden and Bau, David}, title = {Erasing Concepts from Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {2426-2436} }
Fully Attentional Networks with Self-emerging Token Labeling-
[pdf]
[bibtex]@InProceedings{Zhao_2023_ICCV, author = {Zhao, Bingyin and Yu, Zhiding and Lan, Shiyi and Cheng, Yutao and Anandkumar, Anima and Lao, Yingjie and Alvarez, Jose M.}, title = {Fully Attentional Networks with Self-emerging Token Labeling}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {5585-5595} }
ACTIVE: Towards Highly Transferable 3D Physical Camouflage for Universal and Robust Vehicle Evasion-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Suryanto_2023_ICCV, author = {Suryanto, Naufal and Kim, Yongsu and Larasati, Harashta Tatimma and Kang, Hyoeun and Le, Thi-Thu-Huong and Hong, Yoonyoung and Yang, Hunmin and Oh, Se-Yoon and Kim, Howon}, title = {ACTIVE: Towards Highly Transferable 3D Physical Camouflage for Universal and Robust Vehicle Evasion}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {4305-4314} }
Too Large; Data Reduction for Vision-Language Pre-Training-
[pdf]
[arXiv]
[bibtex]@InProceedings{Wang_2023_ICCV, author = {Wang, Alex Jinpeng and Lin, Kevin Qinghong and Zhang, David Junhao and Lei, Stan Weixian and Shou, Mike Zheng}, title = {Too Large; Data Reduction for Vision-Language Pre-Training}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {3147-3157} }
Towards Deeply Unified Depth-aware Panoptic Segmentation with Bi-directional Guidance Learning-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{He_2023_ICCV, author = {He, Junwen and Wang, Yifan and Wang, Lijun and Lu, Huchuan and Luo, Bin and He, Jun-Yan and Lan, Jin-Peng and Geng, Yifeng and Xie, Xuansong}, title = {Towards Deeply Unified Depth-aware Panoptic Segmentation with Bi-directional Guidance Learning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {4111-4121} }
Point-Query Quadtree for Crowd Counting, Localization, and More-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Liu_2023_ICCV, author = {Liu, Chengxin and Lu, Hao and Cao, Zhiguo and Liu, Tongliang}, title = {Point-Query Quadtree for Crowd Counting, Localization, and More}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {1676-1685} }
Zero-Shot Spatial Layout Conditioning for Text-to-Image Diffusion Models-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Couairon_2023_ICCV, author = {Couairon, Guillaume and Careil, Marl\`ene and Cord, Matthieu and Lathuili\`ere, St\'ephane and Verbeek, Jakob}, title = {Zero-Shot Spatial Layout Conditioning for Text-to-Image Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {2174-2183} }
SegGPT: Towards Segmenting Everything in Context-
[pdf]
[supp]
[bibtex]@InProceedings{Wang_2023_ICCV, author = {Wang, Xinlong and Zhang, Xiaosong and Cao, Yue and Wang, Wen and Shen, Chunhua and Huang, Tiejun}, title = {SegGPT: Towards Segmenting Everything in Context}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {1130-1140} }
DDColor: Towards Photo-Realistic Image Colorization via Dual Decoders-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Kang_2023_ICCV, author = {Kang, Xiaoyang and Yang, Tao and Ouyang, Wenqi and Ren, Peiran and Li, Lingzhi and Xie, Xuansong}, title = {DDColor: Towards Photo-Realistic Image Colorization via Dual Decoders}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {328-338} }
Visual Explanations via Iterated Integrated Attributions-
[pdf]
[supp]
[bibtex]@InProceedings{Barkan_2023_ICCV, author = {Barkan, Oren and Elisha, Yehonatan and Asher, Yuval and Eshel, Amit and Koenigstein, Noam}, title = {Visual Explanations via Iterated Integrated Attributions}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {2073-2084} }
Pairwise Similarity Learning is SimPLE-
[pdf]
[supp]
[bibtex]@InProceedings{Wen_2023_ICCV, author = {Wen, Yandong and Liu, Weiyang and Feng, Yao and Raj, Bhiksha and Singh, Rita and Weller, Adrian and Black, Michael J. and Sch\"olkopf, Bernhard}, title = {Pairwise Similarity Learning is SimPLE}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {5308-5318} }
GO-SLAM: Global Optimization for Consistent 3D Instant Reconstruction-
[pdf]
[supp]
[bibtex]@InProceedings{Zhang_2023_ICCV, author = {Zhang, Youmin and Tosi, Fabio and Mattoccia, Stefano and Poggi, Matteo}, title = {GO-SLAM: Global Optimization for Consistent 3D Instant Reconstruction}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {3727-3737} }
FACTS: First Amplify Correlations and Then Slice to Discover Bias-
[pdf]
[supp]
[bibtex]@InProceedings{Yenamandra_2023_ICCV, author = {Yenamandra, Sriram and Ramesh, Pratik and Prabhu, Viraj and Hoffman, Judy}, title = {FACTS: First Amplify Correlations and Then Slice to Discover Bias}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {4794-4804} }
Mask-Attention-Free Transformer for 3D Instance Segmentation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Lai_2023_ICCV, author = {Lai, Xin and Yuan, Yuhui and Chu, Ruihang and Chen, Yukang and Hu, Han and Jia, Jiaya}, title = {Mask-Attention-Free Transformer for 3D Instance Segmentation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {3693-3703} }
EgoLoc: Revisiting 3D Object Localization from Egocentric Videos with Visual Queries-
[pdf]
[arXiv]
[bibtex]@InProceedings{Mai_2023_ICCV, author = {Mai, Jinjie and Hamdi, Abdullah and Giancola, Silvio and Zhao, Chen and Ghanem, Bernard}, title = {EgoLoc: Revisiting 3D Object Localization from Egocentric Videos with Visual Queries}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {45-57} }
FLatten Transformer: Vision Transformer using Focused Linear Attention-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Han_2023_ICCV, author = {Han, Dongchen and Pan, Xuran and Han, Yizeng and Song, Shiji and Huang, Gao}, title = {FLatten Transformer: Vision Transformer using Focused Linear Attention}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {5961-5971} }
ADNet: Lane Shape Prediction via Anchor Decomposition-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Xiao_2023_ICCV, author = {Xiao, Lingyu and Li, Xiang and Yang, Sen and Yang, Wankou}, title = {ADNet: Lane Shape Prediction via Anchor Decomposition}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {6404-6413} }
HollowNeRF: Pruning Hashgrid-Based NeRFs with Trainable Collision Mitigation-
[pdf]
[arXiv]
[bibtex]@InProceedings{Xie_2023_ICCV, author = {Xie, Xiufeng and Gherardi, Riccardo and Pan, Zhihong and Huang, Stephen}, title = {HollowNeRF: Pruning Hashgrid-Based NeRFs with Trainable Collision Mitigation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {3480-3490} }
A Complete Recipe for Diffusion Generative Models-
[pdf]
[supp]
[bibtex]@InProceedings{Pandey_2023_ICCV, author = {Pandey, Kushagra and Mandt, Stephan}, title = {A Complete Recipe for Diffusion Generative Models}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {4261-4272} }
The Devil is in the Crack Orientation: A New Perspective for Crack Detection-
[pdf]
[bibtex]@InProceedings{Chen_2023_ICCV, author = {Chen, Zhuangzhuang and Zhang, Jin and Lai, Zhuonan and Zhu, Guanming and Liu, Zun and Chen, Jie and Li, Jianqiang}, title = {The Devil is in the Crack Orientation: A New Perspective for Crack Detection}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {6653-6663} }
FedPD: Federated Open Set Recognition with Parameter Disentanglement-
[pdf]
[bibtex]@InProceedings{Yang_2023_ICCV, author = {Yang, Chen and Zhu, Meilu and Liu, Yifan and Yuan, Yixuan}, title = {FedPD: Federated Open Set Recognition with Parameter Disentanglement}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {4882-4891} }
WaterMask: Instance Segmentation for Underwater Imagery-
[pdf]
[bibtex]@InProceedings{Lian_2023_ICCV, author = {Lian, Shijie and Li, Hua and Cong, Runmin and Li, Suqi and Zhang, Wei and Kwong, Sam}, title = {WaterMask: Instance Segmentation for Underwater Imagery}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {1305-1315} }
MosaiQ: Quantum Generative Adversarial Networks for Image Generation on NISQ Computers-
[pdf]
[arXiv]
[bibtex]@InProceedings{Silver_2023_ICCV, author = {Silver, Daniel and Patel, Tirthak and Cutler, William and Ranjan, Aditya and Gandhi, Harshitta and Tiwari, Devesh}, title = {MosaiQ: Quantum Generative Adversarial Networks for Image Generation on NISQ Computers}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {7030-7039} }
DVIS: Decoupled Video Instance Segmentation Framework-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Zhang_2023_ICCV, author = {Zhang, Tao and Tian, Xingye and Wu, Yu and Ji, Shunping and Wang, Xuebo and Zhang, Yuan and Wan, Pengfei}, title = {DVIS: Decoupled Video Instance Segmentation Framework}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {1282-1291} }
Rethinking Amodal Video Segmentation from Learning Supervised Signals with Object-centric Representation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Fan_2023_ICCV, author = {Fan, Ke and Lei, Jingshi and Qian, Xuelin and Yu, Miaopeng and Xiao, Tianjun and He, Tong and Zhang, Zheng and Fu, Yanwei}, title = {Rethinking Amodal Video Segmentation from Learning Supervised Signals with Object-centric Representation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {1272-1281} }
Distilled Reverse Attention Network for Open-world Compositional Zero-Shot Learning-
[pdf]
[arXiv]
[bibtex]@InProceedings{Li_2023_ICCV, author = {Li, Yun and Liu, Zhe and Jha, Saurav and Yao, Lina}, title = {Distilled Reverse Attention Network for Open-world Compositional Zero-Shot Learning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {1782-1791} }
TexFusion: Synthesizing 3D Textures with Text-Guided Image Diffusion Models-
[pdf]
[supp]
[bibtex]@InProceedings{Cao_2023_ICCV, author = {Cao, Tianshi and Kreis, Karsten and Fidler, Sanja and Sharp, Nicholas and Yin, Kangxue}, title = {TexFusion: Synthesizing 3D Textures with Text-Guided Image Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {4169-4181} }
Shift from Texture-bias to Shape-bias: Edge Deformation-based Augmentation for Robust Object Recognition-
[pdf]
[supp]
[bibtex]@InProceedings{He_2023_ICCV, author = {He, Xilin and Lin, Qinliang and Luo, Cheng and Xie, Weicheng and Song, Siyang and Liu, Feng and Shen, Linlin}, title = {Shift from Texture-bias to Shape-bias: Edge Deformation-based Augmentation for Robust Object Recognition}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {1526-1535} }
Data-free Knowledge Distillation for Fine-grained Visual Categorization-
[pdf]
[supp]
[bibtex]@InProceedings{Shao_2023_ICCV, author = {Shao, Renrong and Zhang, Wei and Yin, Jianhua and Wang, Jun}, title = {Data-free Knowledge Distillation for Fine-grained Visual Categorization}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {1515-1525} }
EgoPCA: A New Framework for Egocentric Hand-Object Interaction Understanding-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Xu_2023_ICCV, author = {Xu, Yue and Li, Yong-Lu and Huang, Zhemin and Liu, Michael Xu and Lu, Cewu and Tai, Yu-Wing and Tang, Chi-Keung}, title = {EgoPCA: A New Framework for Egocentric Hand-Object Interaction Understanding}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {5273-5284} }
I Can't Believe There's No Images! Learning Visual Tasks Using only Language Supervision-
[pdf]
[supp]
[bibtex]@InProceedings{Gu_2023_ICCV, author = {Gu, Sophia and Clark, Christopher and Kembhavi, Aniruddha}, title = {I Can't Believe There's No Images! Learning Visual Tasks Using only Language Supervision}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {2672-2683} }
Feature Prediction Diffusion Model for Video Anomaly Detection-
[pdf]
[bibtex]@InProceedings{Yan_2023_ICCV, author = {Yan, Cheng and Zhang, Shiyu and Liu, Yang and Pang, Guansong and Wang, Wenjun}, title = {Feature Prediction Diffusion Model for Video Anomaly Detection}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {5527-5537} }
MasQCLIP for Open-Vocabulary Universal Image Segmentation-
[pdf]
[bibtex]@InProceedings{Xu_2023_ICCV, author = {Xu, Xin and Xiong, Tianyi and Ding, Zheng and Tu, Zhuowen}, title = {MasQCLIP for Open-Vocabulary Universal Image Segmentation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {887-898} }
Self-similarity Driven Scale-invariant Learning for Weakly Supervised Person Search-
[pdf]
[arXiv]
[bibtex]@InProceedings{Wang_2023_ICCV, author = {Wang, Benzhi and Yang, Yang and Wu, Jinlin and Qi, Guo-jun and Lei, Zhen}, title = {Self-similarity Driven Scale-invariant Learning for Weakly Supervised Person Search}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {1813-1822} }
Ord2Seq: Regarding Ordinal Regression as Label Sequence Prediction-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Wang_2023_ICCV, author = {Wang, Jinhong and Cheng, Yi and Chen, Jintai and Chen, TingTing and Chen, Danny and Wu, Jian}, title = {Ord2Seq: Regarding Ordinal Regression as Label Sequence Prediction}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {5865-5875} }
Controllable Visual-Tactile Synthesis-
[pdf]
[arXiv]
[bibtex]@InProceedings{Gao_2023_ICCV, author = {Gao, Ruihan and Yuan, Wenzhen and Zhu, Jun-Yan}, title = {Controllable Visual-Tactile Synthesis}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {7040-7052} }
Keep It SimPool: Who Said Supervised Transformers Suffer from Attention Deficit?-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Psomas_2023_ICCV, author = {Psomas, Bill and Kakogeorgiou, Ioannis and Karantzalos, Konstantinos and Avrithis, Yannis}, title = {Keep It SimPool: Who Said Supervised Transformers Suffer from Attention Deficit?}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {5350-5360} }
LoGoPrompt: Synthetic Text Images Can Be Good Visual Prompts for Vision-Language Models-
[pdf]
[arXiv]
[bibtex]@InProceedings{Shi_2023_ICCV, author = {Shi, Cheng and Yang, Sibei}, title = {LoGoPrompt: Synthetic Text Images Can Be Good Visual Prompts for Vision-Language Models}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {2932-2941} }
FeatEnHancer: Enhancing Hierarchical Features for Object Detection and Beyond Under Low-Light Vision-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Hashmi_2023_ICCV, author = {Hashmi, Khurram Azeem and Kallempudi, Goutham and Stricker, Didier and Afzal, Muhammad Zeshan}, title = {FeatEnHancer: Enhancing Hierarchical Features for Object Detection and Beyond Under Low-Light Vision}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {6725-6735} }
Saliency Regularization for Self-Training with Partial Annotations-
[pdf]
[supp]
[bibtex]@InProceedings{Wang_2023_ICCV, author = {Wang, Shouwen and Wan, Qian and Xiang, Xiang and Zeng, Zhigang}, title = {Saliency Regularization for Self-Training with Partial Annotations}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {1611-1620} }
Stabilizing Visual Reinforcement Learning via Asymmetric Interactive Cooperation-
[pdf]
[bibtex]@InProceedings{Zhai_2023_ICCV, author = {Zhai, Yunpeng and Peng, Peixi and Zhao, Yifan and Huang, Yangru and Tian, Yonghong}, title = {Stabilizing Visual Reinforcement Learning via Asymmetric Interactive Cooperation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {207-216} }
Learning Hierarchical Features with Joint Latent Space Energy-Based Prior-
[pdf]
[supp]
[bibtex]@InProceedings{Cui_2023_ICCV, author = {Cui, Jiali and Wu, Ying Nian and Han, Tian}, title = {Learning Hierarchical Features with Joint Latent Space Energy-Based Prior}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {2218-2227} }
UniFormerV2: Unlocking the Potential of Image ViTs for Video Understanding-
[pdf]
[supp]
[bibtex]@InProceedings{Li_2023_ICCV, author = {Li, Kunchang and Wang, Yali and He, Yinan and Li, Yizhuo and Wang, Yi and Wang, Limin and Qiao, Yu}, title = {UniFormerV2: Unlocking the Potential of Image ViTs for Video Understanding}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {1632-1643} }
TARGET: Federated Class-Continual Learning via Exemplar-Free Distillation-
[pdf]
[arXiv]
[bibtex]@InProceedings{Zhang_2023_ICCV, author = {Zhang, Jie and Chen, Chen and Zhuang, Weiming and Lyu, Lingjuan}, title = {TARGET: Federated Class-Continual Learning via Exemplar-Free Distillation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {4782-4793} }
DiffV2S: Diffusion-Based Video-to-Speech Synthesis with Vision-Guided Speaker Embedding-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Choi_2023_ICCV, author = {Choi, Jeongsoo and Hong, Joanna and Ro, Yong Man}, title = {DiffV2S: Diffusion-Based Video-to-Speech Synthesis with Vision-Guided Speaker Embedding}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {7812-7821} }
The Effectiveness of MAE Pre-Pretraining for Billion-Scale Pretraining-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Singh_2023_ICCV, author = {Singh, Mannat and Duval, Quentin and Alwala, Kalyan Vasudev and Fan, Haoqi and Aggarwal, Vaibhav and Adcock, Aaron and Joulin, Armand and Dollar, Piotr and Feichtenhofer, Christoph and Girshick, Ross and Girdhar, Rohit and Misra, Ishan}, title = {The Effectiveness of MAE Pre-Pretraining for Billion-Scale Pretraining}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {5484-5494} }
GPA-3D: Geometry-aware Prototype Alignment for Unsupervised Domain Adaptive 3D Object Detection from Point Clouds-
[pdf]
[supp]
[bibtex]@InProceedings{Li_2023_ICCV, author = {Li, Ziyu and Guo, Jingming and Cao, Tongtong and Bingbing, Liu and Yang, Wankou}, title = {GPA-3D: Geometry-aware Prototype Alignment for Unsupervised Domain Adaptive 3D Object Detection from Point Clouds}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {6394-6403} }
TransHuman: A Transformer-based Human Representation for Generalizable Neural Human Rendering-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Pan_2023_ICCV, author = {Pan, Xiao and Yang, Zongxin and Ma, Jianxin and Zhou, Chang and Yang, Yi}, title = {TransHuman: A Transformer-based Human Representation for Generalizable Neural Human Rendering}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {3544-3555} }
Unsupervised Surface Anomaly Detection with Diffusion Probabilistic Model-
[pdf]
[supp]
[bibtex]@InProceedings{Zhang_2023_ICCV, author = {Zhang, Xinyi and Li, Naiqi and Li, Jiawei and Dai, Tao and Jiang, Yong and Xia, Shu-Tao}, title = {Unsupervised Surface Anomaly Detection with Diffusion Probabilistic Model}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {6782-6791} }
Simoun: Synergizing Interactive Motion-appearance Understanding for Vision-based Reinforcement Learning-
[pdf]
[supp]
[bibtex]@InProceedings{Huang_2023_ICCV, author = {Huang, Yangru and Peng, Peixi and Zhao, Yifan and Zhai, Yunpeng and Xu, Haoran and Tian, Yonghong}, title = {Simoun: Synergizing Interactive Motion-appearance Understanding for Vision-based Reinforcement Learning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {176-185} }
Representation Disparity-aware Distillation for 3D Object Detection-
[pdf]
[arXiv]
[bibtex]@InProceedings{Li_2023_ICCV, author = {Li, Yanjing and Xu, Sheng and Lin, Mingbao and Yin, Jihao and Zhang, Baochang and Cao, Xianbin}, title = {Representation Disparity-aware Distillation for 3D Object Detection}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {6715-6724} }
Breaking The Limits of Text-conditioned 3D Motion Synthesis with Elaborative Descriptions-
[pdf]
[bibtex]@InProceedings{Qian_2023_ICCV, author = {Qian, Yijun and Urbanek, Jack and Hauptmann, Alexander G. and Won, Jungdam}, title = {Breaking The Limits of Text-conditioned 3D Motion Synthesis with Elaborative Descriptions}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {2306-2316} }
VL-PET: Vision-and-Language Parameter-Efficient Tuning via Granularity Control-
[pdf]
[supp]
[bibtex]@InProceedings{Hu_2023_ICCV, author = {Hu, Zi-Yuan and Li, Yanyang and Lyu, Michael R. and Wang, Liwei}, title = {VL-PET: Vision-and-Language Parameter-Efficient Tuning via Granularity Control}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {3010-3020} }
ROME: Robustifying Memory-Efficient NAS via Topology Disentanglement and Gradient Accumulation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Wang_2023_ICCV, author = {Wang, Xiaoxing and Chu, Xiangxiang and Fan, Yuda and Zhang, Zhexi and Zhang, Bo and Yang, Xiaokang and Yan, Junchi}, title = {ROME: Robustifying Memory-Efficient NAS via Topology Disentanglement and Gradient Accumulation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {5939-5949} }
Toward Multi-Granularity Decision-Making: Explicit Visual Reasoning with Hierarchical Knowledge-
[pdf]
[supp]
[bibtex]@InProceedings{Zhang_2023_ICCV, author = {Zhang, Yifeng and Chen, Shi and Zhao, Qi}, title = {Toward Multi-Granularity Decision-Making: Explicit Visual Reasoning with Hierarchical Knowledge}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {2573-2583} }
3D-aware Image Generation using 2D Diffusion Models-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Xiang_2023_ICCV, author = {Xiang, Jianfeng and Yang, Jiaolong and Huang, Binbin and Tong, Xin}, title = {3D-aware Image Generation using 2D Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {2383-2393} }
ICE-NeRF: Interactive Color Editing of NeRFs via Decomposition-Aware Weight Optimization-
[pdf]
[bibtex]@InProceedings{Lee_2023_ICCV, author = {Lee, Jae-Hyeok and Kim, Dae-Shik}, title = {ICE-NeRF: Interactive Color Editing of NeRFs via Decomposition-Aware Weight Optimization}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {3491-3501} }
SPANet: Frequency-balancing Token Mixer using Spectral Pooling Aggregation Modulation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Yun_2023_ICCV, author = {Yun, Guhnoo and Yoo, Juhan and Kim, Kijung and Lee, Jeongho and Kim, Dong Hwan}, title = {SPANet: Frequency-balancing Token Mixer using Spectral Pooling Aggregation Modulation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {6113-6124} }
ASAG: Building Strong One-Decoder-Layer Sparse Detectors via Adaptive Sparse Anchor Generation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Fu_2023_ICCV, author = {Fu, Shenghao and Yan, Junkai and Gao, Yipeng and Xie, Xiaohua and Zheng, Wei-Shi}, title = {ASAG: Building Strong One-Decoder-Layer Sparse Detectors via Adaptive Sparse Anchor Generation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {6328-6338} }
The Perils of Learning From Unlabeled Data: Backdoor Attacks on Semi-supervised Learning-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Shejwalkar_2023_ICCV, author = {Shejwalkar, Virat and Lyu, Lingjuan and Houmansadr, Amir}, title = {The Perils of Learning From Unlabeled Data: Backdoor Attacks on Semi-supervised Learning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {4730-4740} }
StyleDiffusion: Controllable Disentangled Style Transfer via Diffusion Models-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Wang_2023_ICCV, author = {Wang, Zhizhong and Zhao, Lei and Xing, Wei}, title = {StyleDiffusion: Controllable Disentangled Style Transfer via Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {7677-7689} }
AdvDiffuser: Natural Adversarial Example Synthesis with Diffusion Models-
[pdf]
[bibtex]@InProceedings{Chen_2023_ICCV, author = {Chen, Xinquan and Gao, Xitong and Zhao, Juanjuan and Ye, Kejiang and Xu, Cheng-Zhong}, title = {AdvDiffuser: Natural Adversarial Example Synthesis with Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {4562-4572} }
DarSwin: Distortion Aware Radial Swin Transformer-
[pdf]
[bibtex]@InProceedings{Athwale_2023_ICCV, author = {Athwale, Akshaya and Afrasiyabi, Arman and Lag\"ue, Justin and Shili, Ichrak and Ahmad, Ola and Lalonde, Jean-Fran\c{c}ois}, title = {DarSwin: Distortion Aware Radial Swin Transformer}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {5929-5938} }
Take-A-Photo: 3D-to-2D Generative Pre-training of Point Cloud Models-
[pdf]
[supp]
[bibtex]@InProceedings{Wang_2023_ICCV, author = {Wang, Ziyi and Yu, Xumin and Rao, Yongming and Zhou, Jie and Lu, Jiwen}, title = {Take-A-Photo: 3D-to-2D Generative Pre-training of Point Cloud Models}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {5640-5650} }
Open-vocabulary Panoptic Segmentation with Embedding Modulation-
[pdf]
[arXiv]
[bibtex]@InProceedings{Chen_2023_ICCV, author = {Chen, Xi and Li, Shuang and Lim, Ser-Nam and Torralba, Antonio and Zhao, Hengshuang}, title = {Open-vocabulary Panoptic Segmentation with Embedding Modulation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {1141-1150} }
Beyond Single Path Integrated Gradients for Reliable Input Attribution via Randomized Path Sampling-
[pdf]
[supp]
[bibtex]@InProceedings{Jeon_2023_ICCV, author = {Jeon, Giyoung and Jeong, Haedong and Choi, Jaesik}, title = {Beyond Single Path Integrated Gradients for Reliable Input Attribution via Randomized Path Sampling}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {2052-2061} }
Foreground-Background Separation through Concept Distillation from Generative Image Foundation Models-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Dombrowski_2023_ICCV, author = {Dombrowski, Mischa and Reynaud, Hadrien and Baugh, Matthew and Kainz, Bernhard}, title = {Foreground-Background Separation through Concept Distillation from Generative Image Foundation Models}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {988-998} }
ENVIDR: Implicit Differentiable Renderer with Neural Environment Lighting-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Liang_2023_ICCV, author = {Liang, Ruofan and Chen, Huiting and Li, Chunlin and Chen, Fan and Panneer, Selvakumar and Vijaykumar, Nandita}, title = {ENVIDR: Implicit Differentiable Renderer with Neural Environment Lighting}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {79-89} }
Not All Steps are Created Equal: Selective Diffusion Distillation for Image Manipulation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Wang_2023_ICCV, author = {Wang, Luozhou and Yang, Shuai and Liu, Shu and Chen, Ying-cong}, title = {Not All Steps are Created Equal: Selective Diffusion Distillation for Image Manipulation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {7472-7481} }
ALIP: Adaptive Language-Image Pre-Training with Synthetic Caption-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Yang_2023_ICCV, author = {Yang, Kaicheng and Deng, Jiankang and An, Xiang and Li, Jiawei and Feng, Ziyong and Guo, Jia and Yang, Jing and Liu, Tongliang}, title = {ALIP: Adaptive Language-Image Pre-Training with Synthetic Caption}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {2922-2931} }
LaPE: Layer-adaptive Position Embedding for Vision Transformers with Independent Layer Normalization-
[pdf]
[supp]
[bibtex]@InProceedings{Yu_2023_ICCV, author = {Yu, Runyi and Wang, Zhennan and Wang, Yinhuai and Li, Kehan and Liu, Chang and Duan, Haoyi and Ji, Xiangyang and Chen, Jie}, title = {LaPE: Layer-adaptive Position Embedding for Vision Transformers with Independent Layer Normalization}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {5886-5896} }
SA-BEV: Generating Semantic-Aware Bird's-Eye-View Feature for Multi-view 3D Object Detection-
[pdf]
[supp]
[bibtex]@InProceedings{Zhang_2023_ICCV, author = {Zhang, Jinqing and Zhang, Yanan and Liu, Qingjie and Wang, Yunhong}, title = {SA-BEV: Generating Semantic-Aware Bird's-Eye-View Feature for Multi-view 3D Object Detection}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {3348-3357} }
Global Knowledge Calibration for Fast Open-Vocabulary Segmentation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Han_2023_ICCV, author = {Han, Kunyang and Liu, Yong and Liew, Jun Hao and Ding, Henghui and Liu, Jiajun and Wang, Yitong and Tang, Yansong and Yang, Yujiu and Feng, Jiashi and Zhao, Yao and Wei, Yunchao}, title = {Global Knowledge Calibration for Fast Open-Vocabulary Segmentation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {797-807} }
Compatibility of Fundamental Matrices for Complete Viewing Graphs-
[pdf]
[supp]
[bibtex]@InProceedings{Bratelund_2023_ICCV, author = {Br\r{a}telund, Martin and Rydell, Felix}, title = {Compatibility of Fundamental Matrices for Complete Viewing Graphs}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {3328-3336} }
MAtch, eXpand and Improve: Unsupervised Finetuning for Zero-Shot Action Recognition with Language Knowledge-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Lin_2023_ICCV, author = {Lin, Wei and Karlinsky, Leonid and Shvetsova, Nina and Possegger, Horst and Kozinski, Mateusz and Panda, Rameswar and Feris, Rogerio and Kuehne, Hilde and Bischof, Horst}, title = {MAtch, eXpand and Improve: Unsupervised Finetuning for Zero-Shot Action Recognition with Language Knowledge}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {2851-2862} }
Space Engage: Collaborative Space Supervision for Contrastive-Based Semi-Supervised Semantic Segmentation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Wang_2023_ICCV, author = {Wang, Changqi and Xie, Haoyu and Yuan, Yuhui and Fu, Chong and Yue, Xiangyu}, title = {Space Engage: Collaborative Space Supervision for Contrastive-Based Semi-Supervised Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {931-942} }
Delving into Motion-Aware Matching for Monocular 3D Object Tracking-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Huang_2023_ICCV, author = {Huang, Kuan-Chih and Yang, Ming-Hsuan and Tsai, Yi-Hsuan}, title = {Delving into Motion-Aware Matching for Monocular 3D Object Tracking}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {6909-6918} }
Fast Adversarial Training with Smooth Convergence-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Zhao_2023_ICCV, author = {Zhao, Mengnan and Zhang, Lihe and Kong, Yuqiu and Yin, Baocai}, title = {Fast Adversarial Training with Smooth Convergence}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {4720-4729} }
A-STAR: Test-time Attention Segregation and Retention for Text-to-image Synthesis-
[pdf]
[supp]
[bibtex]@InProceedings{Agarwal_2023_ICCV, author = {Agarwal, Aishwarya and Karanam, Srikrishna and Joseph, K J and Saxena, Apoorv and Goswami, Koustava and Srinivasan, Balaji Vasan}, title = {A-STAR: Test-time Attention Segregation and Retention for Text-to-image Synthesis}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {2283-2293} }
FaceCLIPNeRF: Text-driven 3D Face Manipulation using Deformable Neural Radiance Fields-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Hwang_2023_ICCV, author = {Hwang, Sungwon and Hyung, Junha and Kim, Daejin and Kim, Min-Jung and Choo, Jaegul}, title = {FaceCLIPNeRF: Text-driven 3D Face Manipulation using Deformable Neural Radiance Fields}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {3469-3479} }
Learning Shape Primitives via Implicit Convexity Regularization-
[pdf]
[supp]
[bibtex]@InProceedings{Huang_2023_ICCV, author = {Huang, Xiaoyang and Zhang, Yi and Chen, Kai and Li, Teng and Zhang, Wenjun and Ni, Bingbing}, title = {Learning Shape Primitives via Implicit Convexity Regularization}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {3642-3651} }
ITI-GEN: Inclusive Text-to-Image Generation-
[pdf]
[supp]
[bibtex]@InProceedings{Zhang_2023_ICCV, author = {Zhang, Cheng and Chen, Xuanbai and Chai, Siqi and Wu, Chen Henry and Lagun, Dmitry and Beeler, Thabo and De la Torre, Fernando}, title = {ITI-GEN: Inclusive Text-to-Image Generation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {3969-3980} }
Learning Neural Eigenfunctions for Unsupervised Semantic Segmentation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Deng_2023_ICCV, author = {Deng, Zhijie and Luo, Yucen}, title = {Learning Neural Eigenfunctions for Unsupervised Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {551-561} }
Shape Analysis of Euclidean Curves under Frenet-Serret Framework-
[pdf]
[supp]
[bibtex]@InProceedings{Chassat_2023_ICCV, author = {Chassat, Perrine and Park, Juhyun and Brunel, Nicolas}, title = {Shape Analysis of Euclidean Curves under Frenet-Serret Framework}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {4027-4036} }
Efficient Diffusion Training via Min-SNR Weighting Strategy-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Hang_2023_ICCV, author = {Hang, Tiankai and Gu, Shuyang and Li, Chen and Bao, Jianmin and Chen, Dong and Hu, Han and Geng, Xin and Guo, Baining}, title = {Efficient Diffusion Training via Min-SNR Weighting Strategy}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {7441-7451} }
Perceptual Grouping in Contrastive Vision-Language Models-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Ranasinghe_2023_ICCV, author = {Ranasinghe, Kanchana and McKinzie, Brandon and Ravi, Sachin and Yang, Yinfei and Toshev, Alexander and Shlens, Jonathon}, title = {Perceptual Grouping in Contrastive Vision-Language Models}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {5571-5584} }
Dynamic Perceiver for Efficient Visual Recognition-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Han_2023_ICCV, author = {Han, Yizeng and Han, Dongchen and Liu, Zeyu and Wang, Yulin and Pan, Xuran and Pu, Yifan and Deng, Chao and Feng, Junlan and Song, Shiji and Huang, Gao}, title = {Dynamic Perceiver for Efficient Visual Recognition}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {5992-6002} }
Phasic Content Fusing Diffusion Model with Directional Distribution Consistency for Few-Shot Model Adaption-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Hu_2023_ICCV, author = {Hu, Teng and Zhang, Jiangning and Liu, Liang and Yi, Ran and Kou, Siqi and Zhu, Haokun and Chen, Xu and Wang, Yabiao and Wang, Chengjie and Ma, Lizhuang}, title = {Phasic Content Fusing Diffusion Model with Directional Distribution Consistency for Few-Shot Model Adaption}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {2406-2415} }
HAL3D: Hierarchical Active Learning for Fine-Grained 3D Part Labeling-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Yu_2023_ICCV, author = {Yu, Fenggen and Qian, Yiming and Gil-Ureta, Francisca and Jackson, Brian and Bennett, Eric and Zhang, Hao}, title = {HAL3D: Hierarchical Active Learning for Fine-Grained 3D Part Labeling}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {865-875} }
FedPerfix: Towards Partial Model Personalization of Vision Transformers in Federated Learning-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Sun_2023_ICCV, author = {Sun, Guangyu and Mendieta, Matias and Luo, Jun and Wu, Shandong and Chen, Chen}, title = {FedPerfix: Towards Partial Model Personalization of Vision Transformers in Federated Learning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {4988-4998} }
Conditional 360-degree Image Synthesis for Immersive Indoor Scene Decoration-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Shum_2023_ICCV, author = {Shum, Ka Chun and Pang, Hong-Wing and Hua, Binh-Son and Nguyen, Duc Thanh and Yeung, Sai-Kit}, title = {Conditional 360-degree Image Synthesis for Immersive Indoor Scene Decoration}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {4478-4488} }
SIDGAN: High-Resolution Dubbed Video Generation via Shift-Invariant Learning-
[pdf]
[supp]
[bibtex]@InProceedings{Muaz_2023_ICCV, author = {Muaz, Urwa and Jang, Wondong and Tripathi, Rohun and Mani, Santhosh and Ouyang, Wenbin and Gadde, Ravi Teja and Gecer, Baris and Elizondo, Sergio and Madad, Reza and Nair, Naveen}, title = {SIDGAN: High-Resolution Dubbed Video Generation via Shift-Invariant Learning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {7833-7842} }
Meta-ZSDETR: Zero-shot DETR with Meta-learning-
[pdf]
[supp]
[bibtex]@InProceedings{Zhang_2023_ICCV, author = {Zhang, Lu and Zhang, Chenbo and Zhao, Jiajia and Guan, Jihong and Zhou, Shuigeng}, title = {Meta-ZSDETR: Zero-shot DETR with Meta-learning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {6845-6854} }
STPrivacy: Spatio-Temporal Privacy-Preserving Action Recognition-
[pdf]
[arXiv]
[bibtex]@InProceedings{Li_2023_ICCV, author = {Li, Ming and Xu, Xiangyu and Fan, Hehe and Zhou, Pan and Liu, Jun and Liu, Jia-Wei and Li, Jiahe and Keppo, Jussi and Shou, Mike Zheng and Yan, Shuicheng}, title = {STPrivacy: Spatio-Temporal Privacy-Preserving Action Recognition}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {5106-5115} }
Computationally-Efficient Neural Image Compression with Shallow Decoders-
[pdf]
[supp]
[bibtex]@InProceedings{Yang_2023_ICCV, author = {Yang, Yibo and Mandt, Stephan}, title = {Computationally-Efficient Neural Image Compression with Shallow Decoders}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {530-540} }
Tracing the Origin of Adversarial Attack for Forensic Investigation and Deterrence-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Fang_2023_ICCV, author = {Fang, Han and Zhang, Jiyi and Qiu, Yupeng and Liu, Jiayang and Xu, Ke and Fang, Chengfang and Chang, Ee-Chien}, title = {Tracing the Origin of Adversarial Attack for Forensic Investigation and Deterrence}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {4335-4344} }
Scenimefy: Learning to Craft Anime Scene via Semi-Supervised Image-to-Image Translation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Jiang_2023_ICCV, author = {Jiang, Yuxin and Jiang, Liming and Yang, Shuai and Loy, Chen Change}, title = {Scenimefy: Learning to Craft Anime Scene via Semi-Supervised Image-to-Image Translation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {7357-7367} }
DR-Tune: Improving Fine-tuning of Pretrained Visual Models by Distribution Regularization with Semantic Calibration-
[pdf]
[supp]
[bibtex]@InProceedings{Zhou_2023_ICCV, author = {Zhou, Nan and Chen, Jiaxin and Huang, Di}, title = {DR-Tune: Improving Fine-tuning of Pretrained Visual Models by Distribution Regularization with Semantic Calibration}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {1547-1556} }
Dense 2D-3D Indoor Prediction with Sound via Aligned Cross-Modal Distillation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Yun_2023_ICCV, author = {Yun, Heeseung and Na, Joonil and Kim, Gunhee}, title = {Dense 2D-3D Indoor Prediction with Sound via Aligned Cross-Modal Distillation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {7863-7872} }
EverLight: Indoor-Outdoor Editable HDR Lighting Estimation-
[pdf]
[arXiv]
[bibtex]@InProceedings{Dastjerdi_2023_ICCV, author = {Dastjerdi, Mohammad Reza Karimi and Eisenmann, Jonathan and Hold-Geoffroy, Yannick and Lalonde, Jean-Fran\c{c}ois}, title = {EverLight: Indoor-Outdoor Editable HDR Lighting Estimation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {7420-7429} }
MARS: Model-agnostic Biased Object Removal without Additional Supervision for Weakly-Supervised Semantic Segmentation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Jo_2023_ICCV, author = {Jo, Sanghyun and Yu, In-Jae and Kim, Kyungsu}, title = {MARS: Model-agnostic Biased Object Removal without Additional Supervision for Weakly-Supervised Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {614-623} }
Few-Shot Physically-Aware Articulated Mesh Generation via Hierarchical Deformation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Liu_2023_ICCV, author = {Liu, Xueyi and Wang, Bin and Wang, He and Yi, Li}, title = {Few-Shot Physically-Aware Articulated Mesh Generation via Hierarchical Deformation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {854-864} }
Single-Stage Diffusion NeRF: A Unified Approach to 3D Generation and Reconstruction-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Chen_2023_ICCV, author = {Chen, Hansheng and Gu, Jiatao and Chen, Anpei and Tian, Wei and Tu, Zhuowen and Liu, Lingjie and Su, Hao}, title = {Single-Stage Diffusion NeRF: A Unified Approach to 3D Generation and Reconstruction}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {2416-2425} }
One-Shot Generative Domain Adaptation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Yang_2023_ICCV, author = {Yang, Ceyuan and Shen, Yujun and Zhang, Zhiyi and Xu, Yinghao and Zhu, Jiapeng and Wu, Zhirong and Zhou, Bolei}, title = {One-Shot Generative Domain Adaptation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {7733-7742} }
HybridAugment++: Unified Frequency Spectra Perturbations for Model Robustness-
[pdf]
[supp]
[bibtex]@InProceedings{Yucel_2023_ICCV, author = {Yucel, Mehmet Kerim and Cinbis, Ramazan Gokberk and Duygulu, Pinar}, title = {HybridAugment++: Unified Frequency Spectra Perturbations for Model Robustness}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {5718-5728} }
Doppelgangers: Learning to Disambiguate Images of Similar Structures-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Cai_2023_ICCV, author = {Cai, Ruojin and Tung, Joseph and Wang, Qianqian and Averbuch-Elor, Hadar and Hariharan, Bharath and Snavely, Noah}, title = {Doppelgangers: Learning to Disambiguate Images of Similar Structures}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {34-44} }
Improving Generalization of Adversarial Training via Robust Critical Fine-Tuning-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Zhu_2023_ICCV, author = {Zhu, Kaijie and Hu, Xixu and Wang, Jindong and Xie, Xing and Yang, Ge}, title = {Improving Generalization of Adversarial Training via Robust Critical Fine-Tuning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {4424-4434} }
Understanding the Feature Norm for Out-of-Distribution Detection-
[pdf]
[supp]
[bibtex]@InProceedings{Park_2023_ICCV, author = {Park, Jaewoo and Chai, Jacky Chen Long and Yoon, Jaeho and Teoh, Andrew Beng Jin}, title = {Understanding the Feature Norm for Out-of-Distribution Detection}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {1557-1567} }
Knowledge Proxy Intervention for Deconfounded Video Question Answering-
[pdf]
[supp]
[bibtex]@InProceedings{Li_2023_ICCV, author = {Li, Jiangtong and Niu, Li and Zhang, Liqing}, title = {Knowledge Proxy Intervention for Deconfounded Video Question Answering}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {2782-2793} }
DetZero: Rethinking Offboard 3D Object Detection with Long-term Sequential Point Clouds-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Ma_2023_ICCV, author = {Ma, Tao and Yang, Xuemeng and Zhou, Hongbin and Li, Xin and Shi, Botian and Liu, Junjie and Yang, Yuchen and Liu, Zhizheng and He, Liang and Qiao, Yu and Li, Yikang and Li, Hongsheng}, title = {DetZero: Rethinking Offboard 3D Object Detection with Long-term Sequential Point Clouds}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {6736-6747} }
Learning from Noisy Data for Semi-Supervised 3D Object Detection-
[pdf]
[bibtex]@InProceedings{Chen_2023_ICCV, author = {Chen, Zehui and Li, Zhenyu and Wang, Shuo and Fu, Dengpan and Zhao, Feng}, title = {Learning from Noisy Data for Semi-Supervised 3D Object Detection}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {6929-6939} }
Towards Authentic Face Restoration with Iterative Diffusion Models and Beyond-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Zhao_2023_ICCV, author = {Zhao, Yang and Hou, Tingbo and Su, Yu-Chuan and Jia, Xuhui and Li, Yandong and Grundmann, Matthias}, title = {Towards Authentic Face Restoration with Iterative Diffusion Models and Beyond}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {7312-7322} }
Group DETR: Fast DETR Training with Group-Wise One-to-Many Assignment-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Chen_2023_ICCV, author = {Chen, Qiang and Chen, Xiaokang and Wang, Jian and Zhang, Shan and Yao, Kun and Feng, Haocheng and Han, Junyu and Ding, Errui and Zeng, Gang and Wang, Jingdong}, title = {Group DETR: Fast DETR Training with Group-Wise One-to-Many Assignment}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {6633-6642} }
DETRs with Collaborative Hybrid Assignments Training-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Zong_2023_ICCV, author = {Zong, Zhuofan and Song, Guanglu and Liu, Yu}, title = {DETRs with Collaborative Hybrid Assignments Training}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {6748-6758} }
Multi-Modal Neural Radiance Field for Monocular Dense SLAM with a Light-Weight ToF Sensor-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Liu_2023_ICCV, author = {Liu, Xinyang and Li, Yijin and Teng, Yanbin and Bao, Hujun and Zhang, Guofeng and Zhang, Yinda and Cui, Zhaopeng}, title = {Multi-Modal Neural Radiance Field for Monocular Dense SLAM with a Light-Weight ToF Sensor}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {1-11} }
MonoNeRD: NeRF-like Representations for Monocular 3D Object Detection-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Xu_2023_ICCV, author = {Xu, Junkai and Peng, Liang and Cheng, Haoran and Li, Hao and Qian, Wei and Li, Ke and Wang, Wenxiao and Cai, Deng}, title = {MonoNeRD: NeRF-like Representations for Monocular 3D Object Detection}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {6814-6824} }
Monocular 3D Object Detection with Bounding Box Denoising in 3D by Perceiver-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Liu_2023_ICCV, author = {Liu, Xianpeng and Zheng, Ce and Cheng, Kelvin B and Xue, Nan and Qi, Guo-Jun and Wu, Tianfu}, title = {Monocular 3D Object Detection with Bounding Box Denoising in 3D by Perceiver}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {6436-6446} }
WaveIPT: Joint Attention and Flow Alignment in the Wavelet domain for Pose Transfer-
[pdf]
[supp]
[bibtex]@InProceedings{Ma_2023_ICCV, author = {Ma, Liyuan and Gao, Tingwei and Jiang, Haitian and Shen, Haibin and Huang, Kejie}, title = {WaveIPT: Joint Attention and Flow Alignment in the Wavelet domain for Pose Transfer}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {7215-7225} }
PARTNER: Level up the Polar Representation for LiDAR 3D Object Detection-
[pdf]
[arXiv]
[bibtex]@InProceedings{Nie_2023_ICCV, author = {Nie, Ming and Xue, Yujing and Wang, Chunwei and Ye, Chaoqiang and Xu, Hang and Zhu, Xinge and Huang, Qingqiu and Mi, Michael Bi and Wang, Xinchao and Zhang, Li}, title = {PARTNER: Level up the Polar Representation for LiDAR 3D Object Detection}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {3801-3813} }
Corrupting Neuron Explanations of Deep Visual Features-
[pdf]
[supp]
[bibtex]@InProceedings{Srivastava_2023_ICCV, author = {Srivastava, Divyansh and Oikarinen, Tuomas and Weng, Tsui-Wei}, title = {Corrupting Neuron Explanations of Deep Visual Features}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {1877-1886} }
PNI : Industrial Anomaly Detection using Position and Neighborhood Information-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Bae_2023_ICCV, author = {Bae, Jaehyeok and Lee, Jae-Han and Kim, Seyun}, title = {PNI : Industrial Anomaly Detection using Position and Neighborhood Information}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {6373-6383} }
Bidirectionally Deformable Motion Modulation For Video-based Human Pose Transfer-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Yu_2023_ICCV, author = {Yu, Wing-Yin and Po, Lai-Man and Cheung, Ray C.C. and Zhao, Yuzhi and Xue, Yu and Li, Kun}, title = {Bidirectionally Deformable Motion Modulation For Video-based Human Pose Transfer}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {7502-7512} }
Objects Do Not Disappear: Video Object Detection by Single-Frame Object Location Anticipation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Liu_2023_ICCV, author = {Liu, Xin and Nejadasl, Fatemeh Karimi and van Gemert, Jan C. and Booij, Olaf and Pintea, Silvia L.}, title = {Objects Do Not Disappear: Video Object Detection by Single-Frame Object Location Anticipation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {6950-6961} }
Learning from Semantic Alignment between Unpaired Multiviews for Egocentric Video Recognition-
[pdf]
[arXiv]
[bibtex]@InProceedings{Wang_2023_ICCV, author = {Wang, Qitong and Zhao, Long and Yuan, Liangzhe and Liu, Ting and Peng, Xi}, title = {Learning from Semantic Alignment between Unpaired Multiviews for Egocentric Video Recognition}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {3307-3317} }
Source-free Depth for Object Pop-out-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{WU_2023_ICCV, author = {WU, Zongwei and Paudel, Danda Pani and Fan, Deng-Ping and Wang, Jingjing and Wang, Shuo and Demonceaux, C\'edric and Timofte, Radu and Van Gool, Luc}, title = {Source-free Depth for Object Pop-out}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {1032-1042} }
Token-Label Alignment for Vision Transformers-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Xiao_2023_ICCV, author = {Xiao, Han and Zheng, Wenzhao and Zhu, Zheng and Zhou, Jie and Lu, Jiwen}, title = {Token-Label Alignment for Vision Transformers}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {5495-5504} }
Learning Gabor Texture Features for Fine-Grained Recognition-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Zhu_2023_ICCV, author = {Zhu, Lanyun and Chen, Tianrun and Yin, Jianxiong and See, Simon and Liu, Jun}, title = {Learning Gabor Texture Features for Fine-Grained Recognition}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {1621-1631} }
An Embarrassingly Simple Backdoor Attack on Self-supervised Learning-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Li_2023_ICCV, author = {Li, Changjiang and Pang, Ren and Xi, Zhaohan and Du, Tianyu and Ji, Shouling and Yao, Yuan and Wang, Ting}, title = {An Embarrassingly Simple Backdoor Attack on Self-supervised Learning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {4367-4378} }
Partition Speeds Up Learning Implicit Neural Representations Based on Exponential-Increase Hypothesis-
[pdf]
[supp]
[bibtex]@InProceedings{Liu_2023_ICCV, author = {Liu, Ke and Liu, Feng and Wang, Haishuai and Ma, Ning and Bu, Jiajun and Han, Bo}, title = {Partition Speeds Up Learning Implicit Neural Representations Based on Exponential-Increase Hypothesis}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {5474-5483} }
Uncertainty Guided Adaptive Warping for Robust and Efficient Stereo Matching-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Jing_2023_ICCV, author = {Jing, Junpeng and Li, Jiankun and Xiong, Pengfei and Liu, Jiangyu and Liu, Shuaicheng and Guo, Yichen and Deng, Xin and Xu, Mai and Jiang, Lai and Sigal, Leonid}, title = {Uncertainty Guided Adaptive Warping for Robust and Efficient Stereo Matching}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {3318-3327} }
CGBA: Curvature-aware Geometric Black-box Attack-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Reza_2023_ICCV, author = {Reza, Md Farhamdur and Rahmati, Ali and Wu, Tianfu and Dai, Huaiyu}, title = {CGBA: Curvature-aware Geometric Black-box Attack}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {124-133} }
Unsupervised Facial Performance Editing via Vector-Quantized StyleGAN Representations-
[pdf]
[supp]
[bibtex]@InProceedings{Kicanaoglu_2023_ICCV, author = {Kicanaoglu, Berkay and Garrido, Pablo and Bharaj, Gaurav}, title = {Unsupervised Facial Performance Editing via Vector-Quantized StyleGAN Representations}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {2371-2382} }
A Multidimensional Analysis of Social Biases in Vision Transformers-
[pdf]
[arXiv]
[bibtex]@InProceedings{Brinkmann_2023_ICCV, author = {Brinkmann, Jannik and Swoboda, Paul and Bartelt, Christian}, title = {A Multidimensional Analysis of Social Biases in Vision Transformers}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {4914-4923} }
PGFed: Personalize Each Client's Global Objective for Federated Learning-
[pdf]
[supp]
[bibtex]@InProceedings{Luo_2023_ICCV, author = {Luo, Jun and Mendieta, Matias and Chen, Chen and Wu, Shandong}, title = {PGFed: Personalize Each Client's Global Objective for Federated Learning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {3946-3956} }
Instance and Category Supervision are Alternate Learners for Continual Learning-
[pdf]
[supp]
[bibtex]@InProceedings{Tian_2023_ICCV, author = {Tian, Xudong and Zhang, Zhizhong and Tan, Xin and Liu, Jun and Wang, Chengjie and Qu, Yanyun and Jiang, Guannan and Xie, Yuan}, title = {Instance and Category Supervision are Alternate Learners for Continual Learning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {5596-5605} }
Diverse Data Augmentation with Diffusions for Effective Test-time Prompt Tuning-
[pdf]
[arXiv]
[bibtex]@InProceedings{Feng_2023_ICCV, author = {Feng, Chun-Mei and Yu, Kai and Liu, Yong and Khan, Salman and Zuo, Wangmeng}, title = {Diverse Data Augmentation with Diffusions for Effective Test-time Prompt Tuning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {2704-2714} }
GePSAn: Generative Procedure Step Anticipation in Cooking Videos-
[pdf]
[supp]
[bibtex]@InProceedings{Abdelsalam_2023_ICCV, author = {Abdelsalam, Mohamed A. and Rangrej, Samrudhdhi B. and Hadji, Isma and Dvornik, Nikita and Derpanis, Konstantinos G. and Fazly, Afsaneh}, title = {GePSAn: Generative Procedure Step Anticipation in Cooking Videos}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {2988-2997} }
AutoDiffusion: Training-Free Optimization of Time Steps and Architectures for Automated Diffusion Model Acceleration-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Li_2023_ICCV, author = {Li, Lijiang and Li, Huixia and Zheng, Xiawu and Wu, Jie and Xiao, Xuefeng and Wang, Rui and Zheng, Min and Pan, Xin and Chao, Fei and Ji, Rongrong}, title = {AutoDiffusion: Training-Free Optimization of Time Steps and Architectures for Automated Diffusion Model Acceleration}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {7105-7114} }
DPS-Net: Deep Polarimetric Stereo Depth Estimation-
[pdf]
[supp]
[bibtex]@InProceedings{Tian_2023_ICCV, author = {Tian, Chaoran and Pan, Weihong and Wang, Zimo and Mao, Mao and Zhang, Guofeng and Bao, Hujun and Tan, Ping and Cui, Zhaopeng}, title = {DPS-Net: Deep Polarimetric Stereo Depth Estimation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {3569-3579} }
SpaceEvo: Hardware-Friendly Search Space Design for Efficient INT8 Inference-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Wang_2023_ICCV, author = {Wang, Xudong and Zhang, Li Lyna and Xu, Jiahang and Zhang, Quanlu and Wang, Yujing and Yang, Yuqing and Zheng, Ningxin and Cao, Ting and Yang, Mao}, title = {SpaceEvo: Hardware-Friendly Search Space Design for Efficient INT8 Inference}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {5819-5828} }
How Far Pre-trained Models Are from Neural Collapse on the Target Dataset Informs their Transferability-
[pdf]
[supp]
[bibtex]@InProceedings{Wang_2023_ICCV, author = {Wang, Zijian and Luo, Yadan and Zheng, Liang and Huang, Zi and Baktashmotlagh, Mahsa}, title = {How Far Pre-trained Models Are from Neural Collapse on the Target Dataset Informs their Transferability}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {5549-5558} }
Convolutional Networks with Oriented 1D Kernels-
[pdf]
[supp]
[bibtex]@InProceedings{Kirchmeyer_2023_ICCV, author = {Kirchmeyer, Alexandre and Deng, Jia}, title = {Convolutional Networks with Oriented 1D Kernels}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {6222-6232} }
Improving Pixel-based MIM by Reducing Wasted Modeling Capability-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Liu_2023_ICCV, author = {Liu, Yuan and Zhang, Songyang and Chen, Jiacheng and Yu, Zhaohui and Chen, Kai and Lin, Dahua}, title = {Improving Pixel-based MIM by Reducing Wasted Modeling Capability}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {5361-5372} }
Towards Memory- and Time-Efficient Backpropagation for Training Spiking Neural Networks-
[pdf]
[supp]
[bibtex]@InProceedings{Meng_2023_ICCV, author = {Meng, Qingyan and Xiao, Mingqing and Yan, Shen and Wang, Yisen and Lin, Zhouchen and Luo, Zhi-Quan}, title = {Towards Memory- and Time-Efficient Backpropagation for Training Spiking Neural Networks}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {6166-6176} }
When to Learn What: Model-Adaptive Data Augmentation Curriculum-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Hou_2023_ICCV, author = {Hou, Chengkai and Zhang, Jieyu and Zhou, Tianyi}, title = {When to Learn What: Model-Adaptive Data Augmentation Curriculum}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {1717-1728} }
COPILOT: Human-Environment Collision Prediction and Localization from Egocentric Videos-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Pan_2023_ICCV, author = {Pan, Boxiao and Shen, Bokui and Rempe, Davis and Paschalidou, Despoina and Mo, Kaichun and Yang, Yanchao and Guibas, Leonidas J.}, title = {COPILOT: Human-Environment Collision Prediction and Localization from Egocentric Videos}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {5262-5272} }
EGformer: Equirectangular Geometry-biased Transformer for 360 Depth Estimation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Yun_2023_ICCV, author = {Yun, Ilwi and Shin, Chanyong and Lee, Hyunku and Lee, Hyuk-Jae and Rhee, Chae Eun}, title = {EGformer: Equirectangular Geometry-biased Transformer for 360 Depth Estimation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {6101-6112} }
Size Does Matter: Size-aware Virtual Try-on via Clothing-oriented Transformation Try-on Network-
[pdf]
[supp]
[bibtex]@InProceedings{Chen_2023_ICCV, author = {Chen, Chieh-Yun and Chen, Yi-Chung and Shuai, Hong-Han and Cheng, Wen-Huang}, title = {Size Does Matter: Size-aware Virtual Try-on via Clothing-oriented Transformation Try-on Network}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {7513-7522} }
Generating Realistic Images from In-the-wild Sounds-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Lee_2023_ICCV, author = {Lee, Taegyeong and Kang, Jeonghun and Kim, Hyeonyu and Kim, Taehwan}, title = {Generating Realistic Images from In-the-wild Sounds}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {7160-7170} }
Candidate-aware Selective Disambiguation Based On Normalized Entropy for Instance-dependent Partial-label Learning-
[pdf]
[bibtex]@InProceedings{He_2023_ICCV, author = {He, Shuo and Yang, Guowu and Feng, Lei}, title = {Candidate-aware Selective Disambiguation Based On Normalized Entropy for Instance-dependent Partial-label Learning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {1792-1801} }
Open-vocabulary Video Question Answering: A New Benchmark for Evaluating the Generalizability of Video Question Answering Models-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Ko_2023_ICCV, author = {Ko, Dohwan and Lee, Ji Soo and Choi, Miso and Chu, Jaewon and Park, Jihwan and Kim, Hyunwoo J.}, title = {Open-vocabulary Video Question Answering: A New Benchmark for Evaluating the Generalizability of Video Question Answering Models}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {3101-3112} }
Using a Waffle Iron for Automotive Point Cloud Semantic Segmentation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Puy_2023_ICCV, author = {Puy, Gilles and Boulch, Alexandre and Marlet, Renaud}, title = {Using a Waffle Iron for Automotive Point Cloud Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {3379-3389} }
AutoReP: Automatic ReLU Replacement for Fast Private Network Inference-
[pdf]
[arXiv]
[bibtex]@InProceedings{Peng_2023_ICCV, author = {Peng, Hongwu and Huang, Shaoyi and Zhou, Tong and Luo, Yukui and Wang, Chenghong and Wang, Zigeng and Zhao, Jiahui and Xie, Xi and Li, Ang and Geng, Tony and Mahmood, Kaleel and Wen, Wujie and Xu, Xiaolin and Ding, Caiwen}, title = {AutoReP: Automatic ReLU Replacement for Fast Private Network Inference}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {5178-5188} }
Center-Based Decoupled Point-cloud Registration for 6D Object Pose Estimation-
[pdf]
[bibtex]@InProceedings{Jiang_2023_ICCV, author = {Jiang, Haobo and Dang, Zheng and Gu, Shuo and Xie, Jin and Salzmann, Mathieu and Yang, Jian}, title = {Center-Based Decoupled Point-cloud Registration for 6D Object Pose Estimation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {3427-3437} }
GAIT: Generating Aesthetic Indoor Tours with Deep Reinforcement Learning-
[pdf]
[supp]
[bibtex]@InProceedings{Xie_2023_ICCV, author = {Xie, Desai and Hu, Ping and Sun, Xin and Pirk, Soren and Zhang, Jianming and Mech, Radomir and Kaufman, Arie E.}, title = {GAIT: Generating Aesthetic Indoor Tours with Deep Reinforcement Learning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {7409-7419} }
Rethinking Mobile Block for Efficient Attention-based Models-
[pdf]
[arXiv]
[bibtex]@InProceedings{Zhang_2023_ICCV, author = {Zhang, Jiangning and Li, Xiangtai and Li, Jian and Liu, Liang and Xue, Zhucun and Zhang, Boshen and Jiang, Zhengkai and Huang, Tianxin and Wang, Yabiao and Wang, Chengjie}, title = {Rethinking Mobile Block for Efficient Attention-based Models}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {1389-1400} }
REAP: A Large-Scale Realistic Adversarial Patch Benchmark-
[pdf]
[arXiv]
[bibtex]@InProceedings{Hingun_2023_ICCV, author = {Hingun, Nabeel and Sitawarin, Chawin and Li, Jerry and Wagner, David}, title = {REAP: A Large-Scale Realistic Adversarial Patch Benchmark}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {4640-4651} }
StegaNeRF: Embedding Invisible Information within Neural Radiance Fields-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Li_2023_ICCV, author = {Li, Chenxin and Feng, Brandon Y. and Fan, Zhiwen and Pan, Panwang and Wang, Zhangyang}, title = {StegaNeRF: Embedding Invisible Information within Neural Radiance Fields}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {441-453} }
Robust Evaluation of Diffusion-Based Adversarial Purification-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Lee_2023_ICCV, author = {Lee, Minjong and Kim, Dongwoo}, title = {Robust Evaluation of Diffusion-Based Adversarial Purification}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {134-144} }
Hyperbolic Audio-visual Zero-shot Learning-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Hong_2023_ICCV, author = {Hong, Jie and Hayder, Zeeshan and Han, Junlin and Fang, Pengfei and Harandi, Mehrtash and Petersson, Lars}, title = {Hyperbolic Audio-visual Zero-shot Learning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {7873-7883} }
ModelGiF: Gradient Fields for Model Functional Distance-
[pdf]
[arXiv]
[bibtex]@InProceedings{Song_2023_ICCV, author = {Song, Jie and Xu, Zhengqi and Wu, Sai and Chen, Gang and Song, Mingli}, title = {ModelGiF: Gradient Fields for Model Functional Distance}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {6125-6135} }
SIGMA: Scale-Invariant Global Sparse Shape Matching-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Gao_2023_ICCV, author = {Gao, Maolin and Roetzer, Paul and Eisenberger, Marvin and L\"ahner, Zorah and Moeller, Michael and Cremers, Daniel and Bernard, Florian}, title = {SIGMA: Scale-Invariant Global Sparse Shape Matching}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {645-654} }
VidStyleODE: Disentangled Video Editing via StyleGAN and NeuralODEs-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Ali_2023_ICCV, author = {Ali, Moayed Haji and Bond, Andrew and Birdal, Tolga and Ceylan, Duygu and Karacan, Levent and Erdem, Erkut and Erdem, Aykut}, title = {VidStyleODE: Disentangled Video Editing via StyleGAN and NeuralODEs}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {7523-7534} }
LeaF: Learning Frames for 4D Point Cloud Sequence Understanding-
[pdf]
[bibtex]@InProceedings{Liu_2023_ICCV, author = {Liu, Yunze and Chen, Junyu and Zhang, Zekai and Huang, Jingwei and Yi, Li}, title = {LeaF: Learning Frames for 4D Point Cloud Sequence Understanding}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {604-613} }
Towards Improved Input Masking for Convolutional Neural Networks-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Balasubramanian_2023_ICCV, author = {Balasubramanian, Sriram and Feizi, Soheil}, title = {Towards Improved Input Masking for Convolutional Neural Networks}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {1855-1865} }
Gramian Attention Heads are Strong yet Efficient Vision Learners-
[pdf]
[supp]
[bibtex]@InProceedings{Ryu_2023_ICCV, author = {Ryu, Jongbin and Han, Dongyoon and Lim, Jongwoo}, title = {Gramian Attention Heads are Strong yet Efficient Vision Learners}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {5841-5851} }
MI-GAN: A Simple Baseline for Image Inpainting on Mobile Devices-
[pdf]
[supp]
[bibtex]@InProceedings{Sargsyan_2023_ICCV, author = {Sargsyan, Andranik and Navasardyan, Shant and Xu, Xingqian and Shi, Humphrey}, title = {MI-GAN: A Simple Baseline for Image Inpainting on Mobile Devices}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {7335-7345} }
A Large-Scale Outdoor Multi-Modal Dataset and Benchmark for Novel View Synthesis and Implicit Scene Reconstruction-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Lu_2023_ICCV, author = {Lu, Chongshan and Yin, Fukun and Chen, Xin and Liu, Wen and Chen, Tao and Yu, Gang and Fan, Jiayuan}, title = {A Large-Scale Outdoor Multi-Modal Dataset and Benchmark for Novel View Synthesis and Implicit Scene Reconstruction}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {7557-7567} }
Unleashing Vanilla Vision Transformer with Masked Image Modeling for Object Detection-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Fang_2023_ICCV, author = {Fang, Yuxin and Yang, Shusheng and Wang, Shijie and Ge, Yixiao and Shan, Ying and Wang, Xinggang}, title = {Unleashing Vanilla Vision Transformer with Masked Image Modeling for Object Detection}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {6244-6253} }
Spatio-Temporal Crop Aggregation for Video Representation Learning-
[pdf]
[arXiv]
[bibtex]@InProceedings{Sameni_2023_ICCV, author = {Sameni, Sepehr and Jenni, Simon and Favaro, Paolo}, title = {Spatio-Temporal Crop Aggregation for Video Representation Learning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {5664-5674} }
Zero-guidance Segmentation Using Zero Segment Labels-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Rewatbowornwong_2023_ICCV, author = {Rewatbowornwong, Pitchaporn and Chatthee, Nattanat and Chuangsuwanich, Ekapol and Suwajanakorn, Supasorn}, title = {Zero-guidance Segmentation Using Zero Segment Labels}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {1162-1172} }
Communication-efficient Federated Learning with Single-Step Synthetic Features Compressor for Faster Convergence-
[pdf]
[arXiv]
[bibtex]@InProceedings{Zhou_2023_ICCV, author = {Zhou, Yuhao and Shi, Mingjia and Li, Yuanxi and Sun, Yanan and Ye, Qing and Lv, Jiancheng}, title = {Communication-efficient Federated Learning with Single-Step Synthetic Features Compressor for Faster Convergence}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {5031-5040} }
CTVIS: Consistent Training for Online Video Instance Segmentation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Ying_2023_ICCV, author = {Ying, Kaining and Zhong, Qing and Mao, Weian and Wang, Zhenhua and Chen, Hao and Wu, Lin Yuanbo and Liu, Yifan and Fan, Chengxiang and Zhuge, Yunzhi and Shen, Chunhua}, title = {CTVIS: Consistent Training for Online Video Instance Segmentation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {899-908} }
Unsupervised Video Object Segmentation with Online Adversarial Self-Tuning-
[pdf]
[bibtex]@InProceedings{Su_2023_ICCV, author = {Su, Tiankang and Song, Huihui and Liu, Dong and Liu, Bo and Liu, Qingshan}, title = {Unsupervised Video Object Segmentation with Online Adversarial Self-Tuning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {688-698} }
GlobalMapper: Arbitrary-Shaped Urban Layout Generation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{He_2023_ICCV, author = {He, Liu and Aliaga, Daniel}, title = {GlobalMapper: Arbitrary-Shaped Urban Layout Generation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {454-464} }
Unified Coarse-to-Fine Alignment for Video-Text Retrieval-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Wang_2023_ICCV, author = {Wang, Ziyang and Sung, Yi-Lin and Cheng, Feng and Bertasius, Gedas and Bansal, Mohit}, title = {Unified Coarse-to-Fine Alignment for Video-Text Retrieval}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {2816-2827} }
Gradient-Regulated Meta-Prompt Learning for Generalizable Vision-Language Models-
[pdf]
[arXiv]
[bibtex]@InProceedings{Li_2023_ICCV, author = {Li, Juncheng and Gao, Minghe and Wei, Longhui and Tang, Siliang and Zhang, Wenqiao and Li, Mengze and Ji, Wei and Tian, Qi and Chua, Tat-Seng and Zhuang, Yueting}, title = {Gradient-Regulated Meta-Prompt Learning for Generalizable Vision-Language Models}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {2551-2562} }
MUter: Machine Unlearning on Adversarially Trained Models-
[pdf]
[supp]
[bibtex]@InProceedings{Liu_2023_ICCV, author = {Liu, Junxu and Xue, Mingsheng and Lou, Jian and Zhang, Xiaoyu and Xiong, Li and Qin, Zhan}, title = {MUter: Machine Unlearning on Adversarially Trained Models}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {4892-4902} }
ParCNetV2: Oversized Kernel with Enhanced Attention-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Xu_2023_ICCV, author = {Xu, Ruihan and Zhang, Haokui and Hu, Wenze and Zhang, Shiliang and Wang, Xiaoyu}, title = {ParCNetV2: Oversized Kernel with Enhanced Attention}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {5752-5762} }
RealGraph: A Multiview Dataset for 4D Real-world Context Graph Generation-
[pdf]
[supp]
[bibtex]@InProceedings{Lin_2023_ICCV, author = {Lin, Haozhe and Chen, Zequn and Zhang, Jinzhi and Bai, Bing and Wang, Yu and Huang, Ruqi and Fang, Lu}, title = {RealGraph: A Multiview Dataset for 4D Real-world Context Graph Generation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {3758-3768} }
PivotNet: Vectorized Pivot Learning for End-to-end HD Map Construction-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Ding_2023_ICCV, author = {Ding, Wenjie and Qiao, Limeng and Qiu, Xi and Zhang, Chi}, title = {PivotNet: Vectorized Pivot Learning for End-to-end HD Map Construction}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {3672-3682} }
Universal Domain Adaptation via Compressive Attention Matching-
[pdf]
[arXiv]
[bibtex]@InProceedings{Zhu_2023_ICCV, author = {Zhu, Didi and Li, Yinchuan and Yuan, Junkun and Li, Zexi and Kuang, Kun and Wu, Chao}, title = {Universal Domain Adaptation via Compressive Attention Matching}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {6974-6985} }
Point2Mask: Point-supervised Panoptic Segmentation via Optimal Transport-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Li_2023_ICCV, author = {Li, Wentong and Yuan, Yuqian and Wang, Song and Zhu, Jianke and Li, Jianshu and Liu, Jian and Zhang, Lei}, title = {Point2Mask: Point-supervised Panoptic Segmentation via Optimal Transport}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {572-581} }
RFLA: A Stealthy Reflected Light Adversarial Attack in the Physical World-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Wang_2023_ICCV, author = {Wang, Donghua and Yao, Wen and Jiang, Tingsong and Li, Chao and Chen, Xiaoqian}, title = {RFLA: A Stealthy Reflected Light Adversarial Attack in the Physical World}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {4455-4465} }
Nearest Neighbor Guidance for Out-of-Distribution Detection-
[pdf]
[supp]
[bibtex]@InProceedings{Park_2023_ICCV, author = {Park, Jaewoo and Jung, Yoon Gyo and Teoh, Andrew Beng Jin}, title = {Nearest Neighbor Guidance for Out-of-Distribution Detection}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {1686-1695} }
Diffusion-SDF: Conditional Generative Modeling of Signed Distance Functions-
[pdf]
[bibtex]@InProceedings{Chou_2023_ICCV, author = {Chou, Gene and Bahat, Yuval and Heide, Felix}, title = {Diffusion-SDF: Conditional Generative Modeling of Signed Distance Functions}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {2262-2272} }
Open-Vocabulary Object Detection With an Open Corpus-
[pdf]
[supp]
[bibtex]@InProceedings{Wang_2023_ICCV, author = {Wang, Jiong and Zhang, Huiming and Hong, Haiwen and Jin, Xuan and He, Yuan and Xue, Hui and Zhao, Zhou}, title = {Open-Vocabulary Object Detection With an Open Corpus}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {6759-6769} }
Spectrum-guided Multi-granularity Referring Video Object Segmentation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Miao_2023_ICCV, author = {Miao, Bo and Bennamoun, Mohammed and Gao, Yongsheng and Mian, Ajmal}, title = {Spectrum-guided Multi-granularity Referring Video Object Segmentation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {920-930} }
Sound Source Localization is All about Cross-Modal Alignment-
[pdf]
[arXiv]
[bibtex]@InProceedings{Senocak_2023_ICCV, author = {Senocak, Arda and Ryu, Hyeonggon and Kim, Junsik and Oh, Tae-Hyun and Pfister, Hanspeter and Chung, Joon Son}, title = {Sound Source Localization is All about Cross-Modal Alignment}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {7777-7787} }
BlendFace: Re-designing Identity Encoders for Face-Swapping-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Shiohara_2023_ICCV, author = {Shiohara, Kaede and Yang, Xingchao and Taketomi, Takafumi}, title = {BlendFace: Re-designing Identity Encoders for Face-Swapping}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {7634-7644} }
Test-time Personalizable Forecasting of 3D Human Poses-
[pdf]
[supp]
[bibtex]@InProceedings{Cui_2023_ICCV, author = {Cui, Qiongjie and Sun, Huaijiang and Lu, Jianfeng and Li, Weiqing and Li, Bin and Yi, Hongwei and Wang, Haofan}, title = {Test-time Personalizable Forecasting of 3D Human Poses}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {274-283} }
DreamBooth3D: Subject-Driven Text-to-3D Generation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Raj_2023_ICCV, author = {Raj, Amit and Kaza, Srinivas and Poole, Ben and Niemeyer, Michael and Ruiz, Nataniel and Mildenhall, Ben and Zada, Shiran and Aberman, Kfir and Rubinstein, Michael and Barron, Jonathan and Li, Yuanzhen and Jampani, Varun}, title = {DreamBooth3D: Subject-Driven Text-to-3D Generation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {2349-2359} }
Dynamic Snake Convolution Based on Topological Geometric Constraints for Tubular Structure Segmentation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Qi_2023_ICCV, author = {Qi, Yaolei and He, Yuting and Qi, Xiaoming and Zhang, Yuan and Yang, Guanyu}, title = {Dynamic Snake Convolution Based on Topological Geometric Constraints for Tubular Structure Segmentation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {6070-6079} }
Learning to Upsample by Learning to Sample-
[pdf]
[arXiv]
[bibtex]@InProceedings{Liu_2023_ICCV, author = {Liu, Wenze and Lu, Hao and Fu, Hongtao and Cao, Zhiguo}, title = {Learning to Upsample by Learning to Sample}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {6027-6037} }
LayoutDiffusion: Improving Graphic Layout Generation by Discrete Diffusion Probabilistic Models-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Zhang_2023_ICCV, author = {Zhang, Junyi and Guo, Jiaqi and Sun, Shizhao and Lou, Jian-Guang and Zhang, Dongmei}, title = {LayoutDiffusion: Improving Graphic Layout Generation by Discrete Diffusion Probabilistic Models}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {7226-7236} }
Efficiently Robustify Pre-Trained Models-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Jain_2023_ICCV, author = {Jain, Nishant and Behl, Harkirat and Rawat, Yogesh Singh and Vineet, Vibhav}, title = {Efficiently Robustify Pre-Trained Models}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {5505-5515} }
XMem++: Production-level Video Segmentation From Few Annotated Frames-
[pdf]
[supp]
[bibtex]@InProceedings{Bekuzarov_2023_ICCV, author = {Bekuzarov, Maksym and Bermudez, Ariana and Lee, Joon-Young and Li, Hao}, title = {XMem++: Production-level Video Segmentation From Few Annotated Frames}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {635-644} }
End-to-End Diffusion Latent Optimization Improves Classifier Guidance-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Wallace_2023_ICCV, author = {Wallace, Bram and Gokul, Akash and Ermon, Stefano and Naik, Nikhil}, title = {End-to-End Diffusion Latent Optimization Improves Classifier Guidance}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {7280-7290} }
TRM-UAP: Enhancing the Transferability of Data-Free Universal Adversarial Perturbation via Truncated Ratio Maximization-
[pdf]
[supp]
[bibtex]@InProceedings{Liu_2023_ICCV, author = {Liu, Yiran and Feng, Xin and Wang, Yunlong and Yang, Wu and Ming, Di}, title = {TRM-UAP: Enhancing the Transferability of Data-Free Universal Adversarial Perturbation via Truncated Ratio Maximization}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {4762-4771} }
Scratching Visual Transformer's Back with Uniform Attention-
[pdf]
[supp]
[bibtex]@InProceedings{Hyeon-Woo_2023_ICCV, author = {Hyeon-Woo, Nam and Yu-Ji, Kim and Heo, Byeongho and Han, Dongyoon and Oh, Seong Joon and Oh, Tae-Hyun}, title = {Scratching Visual Transformer's Back with Uniform Attention}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {5807-5818} }
Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video Generation-
[pdf]
[supp]
[bibtex]@InProceedings{Wu_2023_ICCV, author = {Wu, Jay Zhangjie and Ge, Yixiao and Wang, Xintao and Lei, Stan Weixian and Gu, Yuchao and Shi, Yufei and Hsu, Wynne and Shan, Ying and Qie, Xiaohu and Shou, Mike Zheng}, title = {Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video Generation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {7623-7633} }
Anchor-Intermediate Detector: Decoupling and Coupling Bounding Boxes for Accurate Object Detection-
[pdf]
[bibtex]@InProceedings{Lv_2023_ICCV, author = {Lv, Yilong and Li, Min and He, Yujie and Li, Shaopeng and He, Zhuzhen and Yang, Aitao}, title = {Anchor-Intermediate Detector: Decoupling and Coupling Bounding Boxes for Accurate Object Detection}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {6275-6284} }
Extensible and Efficient Proxy for Neural Architecture Search-
[pdf]
[supp]
[bibtex]@InProceedings{Li_2023_ICCV, author = {Li, Yuhong and Li, Jiajie and Hao, Cong and Li, Pan and Xiong, Jinjun and Chen, Deming}, title = {Extensible and Efficient Proxy for Neural Architecture Search}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {6199-6210} }
MAAL: Multimodality-Aware Autoencoder-Based Affordance Learning for 3D Articulated Objects-
[pdf]
[supp]
[bibtex]@InProceedings{Liang_2023_ICCV, author = {Liang, Yuanzhi and Wang, Xiaohan and Zhu, Linchao and Yang, Yi}, title = {MAAL: Multimodality-Aware Autoencoder-Based Affordance Learning for 3D Articulated Objects}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {217-227} }
Benchmarking and Analyzing Robust Point Cloud Recognition: Bag of Tricks for Defending Adversarial Examples-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Ji_2023_ICCV, author = {Ji, Qiufan and Wang, Lin and Shi, Cong and Hu, Shengshan and Chen, Yingying and Sun, Lichao}, title = {Benchmarking and Analyzing Robust Point Cloud Recognition: Bag of Tricks for Defending Adversarial Examples}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {4295-4304} }
Poincare ResNet-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{van_Spengler_2023_ICCV, author = {van Spengler, Max and Berkhout, Erwin and Mettes, Pascal}, title = {Poincare ResNet}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {5419-5428} }
Subclass-balancing Contrastive Learning for Long-tailed Recognition-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Hou_2023_ICCV, author = {Hou, Chengkai and Zhang, Jieyu and Wang, Haonan and Zhou, Tianyi}, title = {Subclass-balancing Contrastive Learning for Long-tailed Recognition}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {5395-5407} }
Dynamic Mesh-Aware Radiance Fields-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Qiao_2023_ICCV, author = {Qiao, Yi-Ling and Gao, Alexander and Xu, Yiran and Feng, Yue and Huang, Jia-Bin and Lin, Ming C.}, title = {Dynamic Mesh-Aware Radiance Fields}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {385-396} }
Learning Support and Trivial Prototypes for Interpretable Image Classification-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Wang_2023_ICCV, author = {Wang, Chong and Liu, Yuyuan and Chen, Yuanhong and Liu, Fengbei and Tian, Yu and McCarthy, Davis and Frazer, Helen and Carneiro, Gustavo}, title = {Learning Support and Trivial Prototypes for Interpretable Image Classification}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {2062-2072} }
Decoupled DETR: Spatially Disentangling Localization and Classification for Improved End-to-End Object Detection-
[pdf]
[bibtex]@InProceedings{Zhang_2023_ICCV, author = {Zhang, Manyuan and Song, Guanglu and Liu, Yu and Li, Hongsheng}, title = {Decoupled DETR: Spatially Disentangling Localization and Classification for Improved End-to-End Object Detection}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {6601-6610} }
GIFD: A Generative Gradient Inversion Method with Feature Domain Optimization-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Fang_2023_ICCV, author = {Fang, Hao and Chen, Bin and Wang, Xuan and Wang, Zhi and Xia, Shu-Tao}, title = {GIFD: A Generative Gradient Inversion Method with Feature Domain Optimization}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {4967-4976} }
Generalized Sum Pooling for Metric Learning-
[pdf]
[supp]
[bibtex]@InProceedings{Gurbuz_2023_ICCV, author = {G\"urb\"uz, Yeti Z. and Sener, Ozan and Alatan, A. Aydin}, title = {Generalized Sum Pooling for Metric Learning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {5462-5473} }
AlignDet: Aligning Pre-training and Fine-tuning in Object Detection-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Li_2023_ICCV, author = {Li, Ming and Wu, Jie and Wang, Xionghui and Chen, Chen and Qin, Jie and Xiao, Xuefeng and Wang, Rui and Zheng, Min and Pan, Xin}, title = {AlignDet: Aligning Pre-training and Fine-tuning in Object Detection}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {6866-6876} }
Dense Text-to-Image Generation with Attention Modulation-
[pdf]
[arXiv]
[bibtex]@InProceedings{Kim_2023_ICCV, author = {Kim, Yunji and Lee, Jiyoung and Kim, Jin-Hwa and Ha, Jung-Woo and Zhu, Jun-Yan}, title = {Dense Text-to-Image Generation with Attention Modulation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {7701-7711} }
Sentence Attention Blocks for Answer Grounding-
[pdf]
[arXiv]
[bibtex]@InProceedings{Khoshsirat_2023_ICCV, author = {Khoshsirat, Seyedalireza and Kambhamettu, Chandra}, title = {Sentence Attention Blocks for Answer Grounding}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {6080-6090} }
Towards Fairness-aware Adversarial Network Pruning-
[pdf]
[bibtex]@InProceedings{Zhang_2023_ICCV, author = {Zhang, Lei and Wang, Zhibo and Dong, Xiaowei and Feng, Yunhe and Pang, Xiaoyi and Zhang, Zhifei and Ren, Kui}, title = {Towards Fairness-aware Adversarial Network Pruning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {5168-5177} }
Breaking Temporal Consistency: Generating Video Universal Adversarial Perturbations Using Image Models-
[pdf]
[supp]
[bibtex]@InProceedings{Kim_2023_ICCV, author = {Kim, Hee-Seon and Son, Minji and Kim, Minbeom and Kwon, Myung-Joon and Kim, Changick}, title = {Breaking Temporal Consistency: Generating Video Universal Adversarial Perturbations Using Image Models}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {4325-4334} }
Smoothness Similarity Regularization for Few-Shot GAN Adaptation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Sushko_2023_ICCV, author = {Sushko, Vadim and Wang, Ruyu and Gall, Juergen}, title = {Smoothness Similarity Regularization for Few-Shot GAN Adaptation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {7073-7082} }
Distilling Coarse-to-Fine Semantic Matching Knowledge for Weakly Supervised 3D Visual Grounding-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Wang_2023_ICCV, author = {Wang, Zehan and Huang, Haifeng and Zhao, Yang and Li, Linjun and Cheng, Xize and Zhu, Yichen and Yin, Aoxiong and Zhao, Zhou}, title = {Distilling Coarse-to-Fine Semantic Matching Knowledge for Weakly Supervised 3D Visual Grounding}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {2662-2671} }
zPROBE: Zero Peek Robustness Checks for Federated Learning-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Ghodsi_2023_ICCV, author = {Ghodsi, Zahra and Javaheripi, Mojan and Sheybani, Nojan and Zhang, Xinqiao and Huang, Ke and Koushanfar, Farinaz}, title = {zPROBE: Zero Peek Robustness Checks for Federated Learning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {4860-4870} }
Generative Prompt Model for Weakly Supervised Object Localization-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Zhao_2023_ICCV, author = {Zhao, Yuzhong and Ye, Qixiang and Wu, Weijia and Shen, Chunhua and Wan, Fang}, title = {Generative Prompt Model for Weakly Supervised Object Localization}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {6351-6361} }
ActFormer: A GAN-based Transformer towards General Action-Conditioned 3D Human Motion Generation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Xu_2023_ICCV, author = {Xu, Liang and Song, Ziyang and Wang, Dongliang and Su, Jing and Fang, Zhicheng and Ding, Chenjing and Gan, Weihao and Yan, Yichao and Jin, Xin and Yang, Xiaokang and Zeng, Wenjun and Wu, Wei}, title = {ActFormer: A GAN-based Transformer towards General Action-Conditioned 3D Human Motion Generation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {2228-2238} }
Hiding Visual Information via Obfuscating Adversarial Perturbations-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Su_2023_ICCV, author = {Su, Zhigang and Zhou, Dawei and Wang, Nannan and Liu, Decheng and Wang, Zhen and Gao, Xinbo}, title = {Hiding Visual Information via Obfuscating Adversarial Perturbations}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {4356-4366} }
Category-aware Allocation Transformer for Weakly Supervised Object Localization-
[pdf]
[supp]
[bibtex]@InProceedings{Chen_2023_ICCV, author = {Chen, Zhiwei and Ding, Jinren and Cao, Liujuan and Shen, Yunhang and Zhang, Shengchuan and Jiang, Guannan and Ji, Rongrong}, title = {Category-aware Allocation Transformer for Weakly Supervised Object Localization}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {6643-6652} }
Domain Specified Optimization for Deployment Authorization-
[pdf]
[supp]
[bibtex]@InProceedings{Wang_2023_ICCV, author = {Wang, Haotian and Chi, Haoang and Yang, Wenjing and Lin, Zhipeng and Geng, Mingyang and Lan, Long and Zhang, Jing and Tao, Dacheng}, title = {Domain Specified Optimization for Deployment Authorization}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {5095-5105} }
Locally Stylized Neural Radiance Fields-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Pang_2023_ICCV, author = {Pang, Hong-Wing and Hua, Binh-Son and Yeung, Sai-Kit}, title = {Locally Stylized Neural Radiance Fields}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {307-316} }
Confidence-aware Pseudo-label Learning for Weakly Supervised Visual Grounding-
[pdf]
[bibtex]@InProceedings{Liu_2023_ICCV, author = {Liu, Yang and Zhang, Jiahua and Chen, Qingchao and Peng, Yuxin}, title = {Confidence-aware Pseudo-label Learning for Weakly Supervised Visual Grounding}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {2828-2838} }
Luminance-aware Color Transform for Multiple Exposure Correction-
[pdf]
[supp]
[bibtex]@InProceedings{Baek_2023_ICCV, author = {Baek, Jong-Hyeon and Kim, DaeHyun and Choi, Su-Min and Lee, Hyo-jun and Kim, Hanul and Koh, Yeong Jun}, title = {Luminance-aware Color Transform for Multiple Exposure Correction}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {6156-6165} }
A Simple Framework for Open-Vocabulary Segmentation and Detection-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Zhang_2023_ICCV, author = {Zhang, Hao and Li, Feng and Zou, Xueyan and Liu, Shilong and Li, Chunyuan and Yang, Jianwei and Zhang, Lei}, title = {A Simple Framework for Open-Vocabulary Segmentation and Detection}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {1020-1031} }
Alignment Before Aggregation: Trajectory Memory Retrieval Network for Video Object Segmentation-
[pdf]
[supp]
[bibtex]@InProceedings{Sun_2023_ICCV, author = {Sun, Rui and Wang, Yuan and Mai, Huayu and Zhang, Tianzhu and Wu, Feng}, title = {Alignment Before Aggregation: Trajectory Memory Retrieval Network for Video Object Segmentation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {1218-1228} }
Deep Directly-Trained Spiking Neural Networks for Object Detection-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Su_2023_ICCV, author = {Su, Qiaoyi and Chou, Yuhong and Hu, Yifan and Li, Jianing and Mei, Shijie and Zhang, Ziyang and Li, Guoqi}, title = {Deep Directly-Trained Spiking Neural Networks for Object Detection}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {6555-6565} }
Masked Autoencoders Are Stronger Knowledge Distillers-
[pdf]
[supp]
[bibtex]@InProceedings{Lao_2023_ICCV, author = {Lao, Shanshan and Song, Guanglu and Liu, Boxiao and Liu, Yu and Yang, Yujiu}, title = {Masked Autoencoders Are Stronger Knowledge Distillers}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {6384-6393} }
ASIC: Aligning Sparse in-the-wild Image Collections-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Gupta_2023_ICCV, author = {Gupta, Kamal and Jampani, Varun and Esteves, Carlos and Shrivastava, Abhinav and Makadia, Ameesh and Snavely, Noah and Kar, Abhishek}, title = {ASIC: Aligning Sparse in-the-wild Image Collections}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {4134-4145} }
Residual Pattern Learning for Pixel-Wise Out-of-Distribution Detection in Semantic Segmentation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Liu_2023_ICCV, author = {Liu, Yuyuan and Ding, Choubo and Tian, Yu and Pang, Guansong and Belagiannis, Vasileios and Reid, Ian and Carneiro, Gustavo}, title = {Residual Pattern Learning for Pixel-Wise Out-of-Distribution Detection in Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {1151-1161} }
Hierarchical Visual Primitive Experts for Compositional Zero-Shot Learning-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Kim_2023_ICCV, author = {Kim, Hanjae and Lee, Jiyoung and Park, Seongheon and Sohn, Kwanghoon}, title = {Hierarchical Visual Primitive Experts for Compositional Zero-Shot Learning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {5675-5685} }
Segment Every Reference Object in Spatial and Temporal Spaces-
[pdf]
[supp]
[bibtex]@InProceedings{Wu_2023_ICCV, author = {Wu, Jiannan and Jiang, Yi and Yan, Bin and Lu, Huchuan and Yuan, Zehuan and Luo, Ping}, title = {Segment Every Reference Object in Spatial and Temporal Spaces}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {2538-2550} }
Unified Out-Of-Distribution Detection: A Model-Specific Perspective-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Averly_2023_ICCV, author = {Averly, Reza and Chao, Wei-Lun}, title = {Unified Out-Of-Distribution Detection: A Model-Specific Perspective}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {1453-1463} }
RankMatch: Fostering Confidence and Consistency in Learning with Noisy Labels-
[pdf]
[supp]
[bibtex]@InProceedings{Zhang_2023_ICCV, author = {Zhang, Ziyi and Chen, Weikai and Fang, Chaowei and Li, Zhen and Chen, Lechao and Lin, Liang and Li, Guanbin}, title = {RankMatch: Fostering Confidence and Consistency in Learning with Noisy Labels}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {1644-1654} }
MixReorg: Cross-Modal Mixed Patch Reorganization is a Good Mask Learner for Open-World Semantic Segmentation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Cai_2023_ICCV, author = {Cai, Kaixin and Ren, Pengzhen and Zhu, Yi and Xu, Hang and Liu, Jianzhuang and Li, Changlin and Wang, Guangrun and Liang, Xiaodan}, title = {MixReorg: Cross-Modal Mixed Patch Reorganization is a Good Mask Learner for Open-World Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {1196-1205} }
Preface: A Data-driven Volumetric Prior for Few-shot Ultra High-resolution Face Synthesis-
[pdf]
[supp]
[bibtex]@InProceedings{Buhler_2023_ICCV, author = {B\"uhler, Marcel C. and Sarkar, Kripasindhu and Shah, Tanmay and Li, Gengyan and Wang, Daoye and Helminger, Leonhard and Orts-Escolano, Sergio and Lagun, Dmitry and Hilliges, Otmar and Beeler, Thabo and Meka, Abhimitra}, title = {Preface: A Data-driven Volumetric Prior for Few-shot Ultra High-resolution Face Synthesis}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {3402-3413} }
ICICLE: Interpretable Class Incremental Continual Learning-
[pdf]
[supp]
[bibtex]@InProceedings{Rymarczyk_2023_ICCV, author = {Rymarczyk, Dawid and van de Weijer, Joost and Zieli\'nski, Bartosz and Twardowski, Bartlomiej}, title = {ICICLE: Interpretable Class Incremental Continual Learning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {1887-1898} }
PointCLIP V2: Prompting CLIP and GPT for Powerful 3D Open-world Learning-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Zhu_2023_ICCV, author = {Zhu, Xiangyang and Zhang, Renrui and He, Bowei and Guo, Ziyu and Zeng, Ziyao and Qin, Zipeng and Zhang, Shanghang and Gao, Peng}, title = {PointCLIP V2: Prompting CLIP and GPT for Powerful 3D Open-world Learning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {2639-2650} }
Identification of Systematic Errors of Image Classifiers on Rare Subgroups-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Metzen_2023_ICCV, author = {Metzen, Jan Hendrik and Hutmacher, Robin and Hua, N. Grace and Boreiko, Valentyn and Zhang, Dan}, title = {Identification of Systematic Errors of Image Classifiers on Rare Subgroups}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {5064-5073} }
Clusterformer: Cluster-based Transformer for 3D Object Detection in Point Clouds-
[pdf]
[bibtex]@InProceedings{Pei_2023_ICCV, author = {Pei, Yu and Zhao, Xian and Li, Hao and Ma, Jingyuan and Zhang, Jingwei and Pu, Shiliang}, title = {Clusterformer: Cluster-based Transformer for 3D Object Detection in Point Clouds}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {6664-6673} }
CDUL: CLIP-Driven Unsupervised Learning for Multi-Label Image Classification-
[pdf]
[arXiv]
[bibtex]@InProceedings{Abdelfattah_2023_ICCV, author = {Abdelfattah, Rabab and Guo, Qing and Li, Xiaoguang and Wang, Xiaofeng and Wang, Song}, title = {CDUL: CLIP-Driven Unsupervised Learning for Multi-Label Image Classification}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {1348-1357} }
Your Diffusion Model is Secretly a Zero-Shot Classifier-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Li_2023_ICCV, author = {Li, Alexander C. and Prabhudesai, Mihir and Duggal, Shivam and Brown, Ellis and Pathak, Deepak}, title = {Your Diffusion Model is Secretly a Zero-Shot Classifier}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {2206-2217} }
Backpropagation Path Search On Adversarial Transferability-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Xu_2023_ICCV, author = {Xu, Zhuoer and Gu, Zhangxuan and Zhang, Jianping and Cui, Shiwen and Meng, Changhua and Wang, Weiqiang}, title = {Backpropagation Path Search On Adversarial Transferability}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {4663-4673} }
Boosting Adversarial Transferability via Gradient Relevance Attack-
[pdf]
[bibtex]@InProceedings{Zhu_2023_ICCV, author = {Zhu, Hegui and Ren, Yuchen and Sui, Xiaoyan and Yang, Lianping and Jiang, Wuming}, title = {Boosting Adversarial Transferability via Gradient Relevance Attack}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {4741-4750} }
CLIPN for Zero-Shot OOD Detection: Teaching CLIP to Say No-
[pdf]
[arXiv]
[bibtex]@InProceedings{Wang_2023_ICCV, author = {Wang, Hualiang and Li, Yi and Yao, Huifeng and Li, Xiaomeng}, title = {CLIPN for Zero-Shot OOD Detection: Teaching CLIP to Say No}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {1802-1812} }
CO-Net: Learning Multiple Point Cloud Tasks at Once with A Cohesive Network-
[pdf]
[supp]
[bibtex]@InProceedings{Xie_2023_ICCV, author = {Xie, Tao and Wang, Ke and Lu, Siyi and Zhang, Yukun and Dai, Kun and Li, Xiaoyu and Xu, Jie and Wang, Li and Zhao, Lijun and Zhang, Xinyu and Li, Ruifeng}, title = {CO-Net: Learning Multiple Point Cloud Tasks at Once with A Cohesive Network}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {3523-3533} }
Quality Diversity for Visual Pre-Training-
[pdf]
[supp]
[bibtex]@InProceedings{Chavhan_2023_ICCV, author = {Chavhan, Ruchika and Gouk, Henry and Li, Da and Hospedales, Timothy}, title = {Quality Diversity for Visual Pre-Training}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {5384-5394} }
UniDexGrasp++: Improving Dexterous Grasping Policy Learning via Geometry-Aware Curriculum and Iterative Generalist-Specialist Learning-
[pdf]
[supp]
[bibtex]@InProceedings{Wan_2023_ICCV, author = {Wan, Weikang and Geng, Haoran and Liu, Yun and Shan, Zikang and Yang, Yaodong and Yi, Li and Wang, He}, title = {UniDexGrasp++: Improving Dexterous Grasping Policy Learning via Geometry-Aware Curriculum and Iterative Generalist-Specialist Learning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {3891-3902} }
FerKD: Surgical Label Adaptation for Efficient Distillation-
[pdf]
[supp]
[bibtex]@InProceedings{Shen_2023_ICCV, author = {Shen, Zhiqiang}, title = {FerKD: Surgical Label Adaptation for Efficient Distillation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {1666-1675} }
Neural Fields for Structured Lighting-
[pdf]
[supp]
[bibtex]@InProceedings{Shandilya_2023_ICCV, author = {Shandilya, Aarrushi and Attal, Benjamin and Richardt, Christian and Tompkin, James and O'toole, Matthew}, title = {Neural Fields for Structured Lighting}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {3512-3522} }
ClothPose: A Real-world Benchmark for Visual Analysis of Garment Pose via An Indirect Recording Solution-
[pdf]
[bibtex]@InProceedings{Xu_2023_ICCV, author = {Xu, Wenqiang and Du, Wenxin and Xue, Han and Li, Yutong and Ye, Ruolin and Wang, Yan-Feng and Lu, Cewu}, title = {ClothPose: A Real-world Benchmark for Visual Analysis of Garment Pose via An Indirect Recording Solution}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {58-68} }
Unsupervised Object Localization with Representer Point Selection-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Song_2023_ICCV, author = {Song, Yeonghwan and Jang, Seokwoo and Katabi, Dina and Son, Jeany}, title = {Unsupervised Object Localization with Representer Point Selection}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {6534-6544} }
SEMPART: Self-supervised Multi-resolution Partitioning of Image Semantics-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Ravindran_2023_ICCV, author = {Ravindran, Sriram and Basu, Debraj}, title = {SEMPART: Self-supervised Multi-resolution Partitioning of Image Semantics}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {723-733} }
Flatness-Aware Minimization for Domain Generalization-
[pdf]
[arXiv]
[bibtex]@InProceedings{Zhang_2023_ICCV, author = {Zhang, Xingxuan and Xu, Renzhe and Yu, Han and Dong, Yancheng and Tian, Pengfei and Cui, Peng}, title = {Flatness-Aware Minimization for Domain Generalization}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {5189-5202} }
ProtoFL: Unsupervised Federated Learning via Prototypical Distillation-
[pdf]
[arXiv]
[bibtex]@InProceedings{Kim_2023_ICCV, author = {Kim, Hansol and Kwak, Youngjun and Jung, Minyoung and Shin, Jinho and Kim, Youngsung and Kim, Changick}, title = {ProtoFL: Unsupervised Federated Learning via Prototypical Distillation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {6470-6479} }
Multi-label Affordance Mapping from Egocentric Vision-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Mur-Labadia_2023_ICCV, author = {Mur-Labadia, Lorenzo and Guerrero, Jose J. and Martinez-Cantin, Ruben}, title = {Multi-label Affordance Mapping from Egocentric Vision}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {5238-5249} }
Unified Adversarial Patch for Cross-Modal Attacks in the Physical World-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Wei_2023_ICCV, author = {Wei, Xingxing and Huang, Yao and Sun, Yitong and Yu, Jie}, title = {Unified Adversarial Patch for Cross-Modal Attacks in the Physical World}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {4445-4454} }
Misalign, Contrast then Distill: Rethinking Misalignments in Language-Image Pre-training-
[pdf]
[bibtex]@InProceedings{Kim_2023_ICCV, author = {Kim, Bumsoo and Jo, Yeonsik and Kim, Jinhyung and Kim, Seunghwan}, title = {Misalign, Contrast then Distill: Rethinking Misalignments in Language-Image Pre-training}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {2563-2572} }
MixPath: A Unified Approach for One-shot Neural Architecture Search-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Chu_2023_ICCV, author = {Chu, Xiangxiang and Lu, Shun and Li, Xudong and Zhang, Bo}, title = {MixPath: A Unified Approach for One-shot Neural Architecture Search}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {5972-5981} }
Enhancing NeRF akin to Enhancing LLMs: Generalizable NeRF Transformer with Mixture-of-View-Experts-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Cong_2023_ICCV, author = {Cong, Wenyan and Liang, Hanxue and Wang, Peihao and Fan, Zhiwen and Chen, Tianlong and Varma, Mukund and Wang, Yi and Wang, Zhangyang}, title = {Enhancing NeRF akin to Enhancing LLMs: Generalizable NeRF Transformer with Mixture-of-View-Experts}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {3193-3204} }
Task-aware Adaptive Learning for Cross-domain Few-shot Learning-
[pdf]
[bibtex]@InProceedings{Guo_2023_ICCV, author = {Guo, Yurong and Du, Ruoyi and Dong, Yuan and Hospedales, Timothy and Song, Yi-Zhe and Ma, Zhanyu}, title = {Task-aware Adaptive Learning for Cross-domain Few-shot Learning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {1590-1599} }
Revisiting Domain-Adaptive 3D Object Detection by Reliable, Diverse and Class-balanced Pseudo-Labeling-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Chen_2023_ICCV, author = {Chen, Zhuoxiao and Luo, Yadan and Wang, Zheng and Baktashmotlagh, Mahsa and Huang, Zi}, title = {Revisiting Domain-Adaptive 3D Object Detection by Reliable, Diverse and Class-balanced Pseudo-Labeling}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {3714-3726} }
Efficient Adaptive Human-Object Interaction Detection with Concept-guided Memory-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Lei_2023_ICCV, author = {Lei, Ting and Caba, Fabian and Chen, Qingchao and Jin, Hailin and Peng, Yuxin and Liu, Yang}, title = {Efficient Adaptive Human-Object Interaction Detection with Concept-guided Memory}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {6480-6490} }
Attentive Mask CLIP-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Yang_2023_ICCV, author = {Yang, Yifan and Huang, Weiquan and Wei, Yixuan and Peng, Houwen and Jiang, Xinyang and Jiang, Huiqiang and Wei, Fangyun and Wang, Yin and Hu, Han and Qiu, Lili and Yang, Yuqing}, title = {Attentive Mask CLIP}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {2771-2781} }
Motion-Guided Masking for Spatiotemporal Representation Learning-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Fan_2023_ICCV, author = {Fan, David and Wang, Jue and Liao, Shuai and Zhu, Yi and Bhat, Vimal and Santos-Villalobos, Hector and MV, Rohith and Li, Xinyu}, title = {Motion-Guided Masking for Spatiotemporal Representation Learning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {5619-5629} }
Urban Radiance Field Representation with Deformable Neural Mesh Primitives-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Lu_2023_ICCV, author = {Lu, Fan and Xu, Yan and Chen, Guang and Li, Hongsheng and Lin, Kwan-Yee and Jiang, Changjun}, title = {Urban Radiance Field Representation with Deformable Neural Mesh Primitives}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {465-476} }
Adaptive Frequency Filters As Efficient Global Token Mixers-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Huang_2023_ICCV, author = {Huang, Zhipeng and Zhang, Zhizheng and Lan, Cuiling and Zha, Zheng-Jun and Lu, Yan and Guo, Baining}, title = {Adaptive Frequency Filters As Efficient Global Token Mixers}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {6049-6059} }
Zolly: Zoom Focal Length Correctly for Perspective-Distorted Human Mesh Reconstruction-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Wang_2023_ICCV, author = {Wang, Wenjia and Ge, Yongtao and Mei, Haiyi and Cai, Zhongang and Sun, Qingping and Wang, Yanjun and Shen, Chunhua and Yang, Lei and Komura, Taku}, title = {Zolly: Zoom Focal Length Correctly for Perspective-Distorted Human Mesh Reconstruction}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {3925-3935} }
Beyond One-to-One: Rethinking the Referring Image Segmentation-
[pdf]
[supp]
[bibtex]@InProceedings{Hu_2023_ICCV, author = {Hu, Yutao and Wang, Qixiong and Shao, Wenqi and Xie, Enze and Li, Zhenguo and Han, Jungong and Luo, Ping}, title = {Beyond One-to-One: Rethinking the Referring Image Segmentation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {4067-4077} }
MoreauGrad: Sparse and Robust Interpretation of Neural Networks via Moreau Envelope-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Zhang_2023_ICCV, author = {Zhang, Jingwei and Farnia, Farzan}, title = {MoreauGrad: Sparse and Robust Interpretation of Neural Networks via Moreau Envelope}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {2021-2030} }
Class-Incremental Grouping Network for Continual Audio-Visual Learning-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Mo_2023_ICCV, author = {Mo, Shentong and Pian, Weiguo and Tian, Yapeng}, title = {Class-Incremental Grouping Network for Continual Audio-Visual Learning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {7788-7798} }
Improving Sample Quality of Diffusion Models Using Self-Attention Guidance-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Hong_2023_ICCV, author = {Hong, Susung and Lee, Gyuseong and Jang, Wooseok and Kim, Seungryong}, title = {Improving Sample Quality of Diffusion Models Using Self-Attention Guidance}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {7462-7471} }
Evaluating Data Attribution for Text-to-Image Models-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Wang_2023_ICCV, author = {Wang, Sheng-Yu and Efros, Alexei A. and Zhu, Jun-Yan and Zhang, Richard}, title = {Evaluating Data Attribution for Text-to-Image Models}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {7192-7203} }
Delta Denoising Score-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Hertz_2023_ICCV, author = {Hertz, Amir and Aberman, Kfir and Cohen-Or, Daniel}, title = {Delta Denoising Score}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {2328-2337} }
Hierarchical Prior Mining for Non-local Multi-View Stereo-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Ren_2023_ICCV, author = {Ren, Chunlin and Xu, Qingshan and Zhang, Shikun and Yang, Jiaqi}, title = {Hierarchical Prior Mining for Non-local Multi-View Stereo}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {3611-3620} }
Generative Multiplane Neural Radiance for 3D-Aware Image Generation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Kumar_2023_ICCV, author = {Kumar, Amandeep and Bhunia, Ankan Kumar and Narayan, Sanath and Cholakkal, Hisham and Anwer, Rao Muhammad and Khan, Salman and Yang, Ming-Hsuan and Khan, Fahad Shahbaz}, title = {Generative Multiplane Neural Radiance for 3D-Aware Image Generation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {7388-7398} }
Boosting Semantic Segmentation from the Perspective of Explicit Class Embeddings-
[pdf]
[arXiv]
[bibtex]@InProceedings{Liu_2023_ICCV, author = {Liu, Yuhe and Liu, Chuanjian and Han, Kai and Tang, Quan and Qin, Zengchang}, title = {Boosting Semantic Segmentation from the Perspective of Explicit Class Embeddings}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {821-831} }
Learning to Identify Critical States for Reinforcement Learning from Videos-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Liu_2023_ICCV, author = {Liu, Haozhe and Zhuge, Mingchen and Li, Bing and Wang, Yuhui and Faccio, Francesco and Ghanem, Bernard and Schmidhuber, J\"urgen}, title = {Learning to Identify Critical States for Reinforcement Learning from Videos}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {1955-1965} }
Editing Implicit Assumptions in Text-to-Image Diffusion Models-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Orgad_2023_ICCV, author = {Orgad, Hadas and Kawar, Bahjat and Belinkov, Yonatan}, title = {Editing Implicit Assumptions in Text-to-Image Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {7053-7061} }
Conceptual and Hierarchical Latent Space Decomposition for Face Editing-
[pdf]
[supp]
[bibtex]@InProceedings{Ozkan_2023_ICCV, author = {Ozkan, Savas and Ozay, Mete and Robinson, Tom}, title = {Conceptual and Hierarchical Latent Space Decomposition for Face Editing}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {7248-7257} }
VL-Match: Enhancing Vision-Language Pretraining with Token-Level and Instance-Level Matching-
[pdf]
[bibtex]@InProceedings{Bi_2023_ICCV, author = {Bi, Junyu and Cheng, Daixuan and Yao, Ping and Pang, Bochen and Zhan, Yuefeng and Yang, Chuanguang and Wang, Yujing and Sun, Hao and Deng, Weiwei and Zhang, Qi}, title = {VL-Match: Enhancing Vision-Language Pretraining with Token-Level and Instance-Level Matching}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {2584-2593} }
Translating Images to Road Network: A Non-Autoregressive Sequence-to-Sequence Approach-
[pdf]
[supp]
[bibtex]@InProceedings{Lu_2023_ICCV, author = {Lu, Jiachen and Peng, Renyuan and Cai, Xinyue and Xu, Hang and Li, Hongyang and Wen, Feng and Zhang, Wei and Zhang, Li}, title = {Translating Images to Road Network: A Non-Autoregressive Sequence-to-Sequence Approach}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {23-33} }
Generative Novel View Synthesis with 3D-Aware Diffusion Models-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Chan_2023_ICCV, author = {Chan, Eric R. and Nagano, Koki and Chan, Matthew A. and Bergman, Alexander W. and Park, Jeong Joon and Levy, Axel and Aittala, Miika and De Mello, Shalini and Karras, Tero and Wetzstein, Gordon}, title = {Generative Novel View Synthesis with 3D-Aware Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {4217-4229} }
ALWOD: Active Learning for Weakly-Supervised Object Detection-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Wang_2023_ICCV, author = {Wang, Yuting and Ilic, Velibor and Li, Jiatong and Kisa\v{c}anin, Branislav and Pavlovic, Vladimir}, title = {ALWOD: Active Learning for Weakly-Supervised Object Detection}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {6459-6469} }
S-VolSDF: Sparse Multi-View Stereo Regularization of Neural Implicit Surfaces-
[pdf]
[supp]
[bibtex]@InProceedings{Wu_2023_ICCV, author = {Wu, Haoyu and Graikos, Alexandros and Samaras, Dimitris}, title = {S-VolSDF: Sparse Multi-View Stereo Regularization of Neural Implicit Surfaces}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {3556-3568} }
TextManiA: Enriching Visual Feature by Text-driven Manifold Augmentation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Ye-Bin_2023_ICCV, author = {Ye-Bin, Moon and Kim, Jisoo and Kim, Hongyeob and Son, Kilho and Oh, Tae-Hyun}, title = {TextManiA: Enriching Visual Feature by Text-driven Manifold Augmentation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {2526-2537} }
Breaking Common Sense: WHOOPS! A Vision-and-Language Benchmark of Synthetic and Compositional Images-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Bitton-Guetta_2023_ICCV, author = {Bitton-Guetta, Nitzan and Bitton, Yonatan and Hessel, Jack and Schmidt, Ludwig and Elovici, Yuval and Stanovsky, Gabriel and Schwartz, Roy}, title = {Breaking Common Sense: WHOOPS! A Vision-and-Language Benchmark of Synthetic and Compositional Images}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {2616-2627} }
Consistent Depth Prediction for Transparent Object Reconstruction from RGB-D Camera-
[pdf]
[supp]
[bibtex]@InProceedings{Cai_2023_ICCV, author = {Cai, Yuxiang and Zhu, Yifan and Zhang, Haiwei and Ren, Bo}, title = {Consistent Depth Prediction for Transparent Object Reconstruction from RGB-D Camera}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {3459-3468} }
DETR Does Not Need Multi-Scale or Locality Design-
[pdf]
[supp]
[bibtex]@InProceedings{Lin_2023_ICCV, author = {Lin, Yutong and Yuan, Yuhui and Zhang, Zheng and Li, Chen and Zheng, Nanning and Hu, Han}, title = {DETR Does Not Need Multi-Scale or Locality Design}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {6545-6554} }
ClusT3: Information Invariant Test-Time Training-
[pdf]
[supp]
[bibtex]@InProceedings{Hakim_2023_ICCV, author = {Hakim, Gustavo A. Vargas and Osowiechi, David and Noori, Mehrdad and Cheraghalikhani, Milad and Bahri, Ali and Ben Ayed, Ismail and Desrosiers, Christian}, title = {ClusT3: Information Invariant Test-Time Training}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {6136-6145} }
AssetField: Assets Mining and Reconfiguration in Ground Feature Plane Representation-
[pdf]
[arXiv]
[bibtex]@InProceedings{Xiangli_2023_ICCV, author = {Xiangli, Yuanbo and Xu, Linning and Pan, Xingang and Zhao, Nanxuan and Dai, Bo and Lin, Dahua}, title = {AssetField: Assets Mining and Reconfiguration in Ground Feature Plane Representation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {3251-3261} }
SAGA: Spectral Adversarial Geometric Attack on 3D Meshes-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Stolik_2023_ICCV, author = {Stolik, Tomer and Lang, Itai and Avidan, Shai}, title = {SAGA: Spectral Adversarial Geometric Attack on 3D Meshes}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {4284-4294} }
Learning Navigational Visual Representations with Semantic Map Supervision-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Hong_2023_ICCV, author = {Hong, Yicong and Zhou, Yang and Zhang, Ruiyi and Dernoncourt, Franck and Bui, Trung and Gould, Stephen and Tan, Hao}, title = {Learning Navigational Visual Representations with Semantic Map Supervision}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {3055-3067} }
Shortcut-V2V: Compression Framework for Video-to-Video Translation Based on Temporal Redundancy Reduction-
[pdf]
[supp]
[bibtex]@InProceedings{Chung_2023_ICCV, author = {Chung, Chaeyeon and Park, Yeojeong and Choi, Seunghwan and Ganbat, Munkhsoyol and Choo, Jaegul}, title = {Shortcut-V2V: Compression Framework for Video-to-Video Translation Based on Temporal Redundancy Reduction}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {7612-7622} }
SG-Former: Self-guided Transformer with Evolving Token Reallocation-
[pdf]
[bibtex]@InProceedings{Ren_2023_ICCV, author = {Ren, Sucheng and Yang, Xingyi and Liu, Songhua and Wang, Xinchao}, title = {SG-Former: Self-guided Transformer with Evolving Token Reallocation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {6003-6014} }
ProtoTransfer: Cross-Modal Prototype Transfer for Point Cloud Segmentation-
[pdf]
[supp]
[bibtex]@InProceedings{Tang_2023_ICCV, author = {Tang, Pin and Xu, Hai-Ming and Ma, Chao}, title = {ProtoTransfer: Cross-Modal Prototype Transfer for Point Cloud Segmentation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {3337-3347} }
Deep Image Harmonization with Globally Guided Feature Transformation and Relation Distillation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Niu_2023_ICCV, author = {Niu, Li and Tan, Linfeng and Tao, Xinhao and Cao, Junyan and Guo, Fengjun and Long, Teng and Zhang, Liqing}, title = {Deep Image Harmonization with Globally Guided Feature Transformation and Relation Distillation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {7723-7732} }
VQ3D: Learning a 3D-Aware Generative Model on ImageNet-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Sargent_2023_ICCV, author = {Sargent, Kyle and Koh, Jing Yu and Zhang, Han and Chang, Huiwen and Herrmann, Charles and Srinivasan, Pratul and Wu, Jiajun and Sun, Deqing}, title = {VQ3D: Learning a 3D-Aware Generative Model on ImageNet}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {4240-4250} }
2D-3D Interlaced Transformer for Point Cloud Segmentation with Scene-Level Supervision-
[pdf]
[supp]
[bibtex]@InProceedings{Yang_2023_ICCV, author = {Yang, Cheng-Kun and Chen, Min-Hung and Chuang, Yung-Yu and Lin, Yen-Yu}, title = {2D-3D Interlaced Transformer for Point Cloud Segmentation with Scene-Level Supervision}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {977-987} }
Collecting The Puzzle Pieces: Disentangled Self-Driven Human Pose Transfer by Permuting Textures-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Li_2023_ICCV, author = {Li, Nannan and Shih, Kevin J and Plummer, Bryan A.}, title = {Collecting The Puzzle Pieces: Disentangled Self-Driven Human Pose Transfer by Permuting Textures}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {7126-7137} }
Sound Localization from Motion: Jointly Learning Sound Direction and Camera Rotation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Chen_2023_ICCV, author = {Chen, Ziyang and Qian, Shengyi and Owens, Andrew}, title = {Sound Localization from Motion: Jointly Learning Sound Direction and Camera Rotation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {7897-7908} }
Prompt Tuning Inversion for Text-driven Image Editing Using Diffusion Models-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Dong_2023_ICCV, author = {Dong, Wenkai and Xue, Song and Duan, Xiaoyue and Han, Shumin}, title = {Prompt Tuning Inversion for Text-driven Image Editing Using Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {7430-7440} }
UnitedHuman: Harnessing Multi-Source Data for High-Resolution Human Generation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Fu_2023_ICCV, author = {Fu, Jianglin and Li, Shikai and Jiang, Yuming and Lin, Kwan-Yee and Wu, Wayne and Liu, Ziwei}, title = {UnitedHuman: Harnessing Multi-Source Data for High-Resolution Human Generation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {7301-7311} }
Neural Microfacet Fields for Inverse Rendering-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Mai_2023_ICCV, author = {Mai, Alexander and Verbin, Dor and Kuester, Falko and Fridovich-Keil, Sara}, title = {Neural Microfacet Fields for Inverse Rendering}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {408-418} }
Understanding Self-attention Mechanism via Dynamical System Perspective-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Huang_2023_ICCV, author = {Huang, Zhongzhan and Liang, Mingfu and Qin, Jinghui and Zhong, Shanshan and Lin, Liang}, title = {Understanding Self-attention Mechanism via Dynamical System Perspective}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {1412-1422} }
DDG-Net: Discriminability-Driven Graph Network for Weakly-supervised Temporal Action Localization-
[pdf]
[supp]
[bibtex]@InProceedings{Tang_2023_ICCV, author = {Tang, Xiaojun and Fan, Junsong and Luo, Chuanchen and Zhang, Zhaoxiang and Zhang, Man and Yang, Zongyuan}, title = {DDG-Net: Discriminability-Driven Graph Network for Weakly-supervised Temporal Action Localization}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {6622-6632} }
Rethinking Data Distillation: Do Not Overlook Calibration-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Zhu_2023_ICCV, author = {Zhu, Dongyao and Lei, Bowen and Zhang, Jie and Fang, Yanbo and Xie, Yiqun and Zhang, Ruqi and Xu, Dongkuan}, title = {Rethinking Data Distillation: Do Not Overlook Calibration}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {4935-4945} }
Building Vision Transformers with Hierarchy Aware Feature Aggregation-
[pdf]
[supp]
[bibtex]@InProceedings{Chen_2023_ICCV, author = {Chen, Yongjie and Liu, Hongmin and Yin, Haoran and Fan, Bin}, title = {Building Vision Transformers with Hierarchy Aware Feature Aggregation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {5908-5918} }
SAL-ViT: Towards Latency Efficient Private Inference on ViT using Selective Attention Search with a Learnable Softmax Approximation-
[pdf]
[bibtex]@InProceedings{Zhang_2023_ICCV, author = {Zhang, Yuke and Chen, Dake and Kundu, Souvik and Li, Chenghao and Beerel, Peter A.}, title = {SAL-ViT: Towards Latency Efficient Private Inference on ViT using Selective Attention Search with a Learnable Softmax Approximation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {5116-5125} }
TIJO: Trigger Inversion with Joint Optimization for Defending Multimodal Backdoored Models-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Sur_2023_ICCV, author = {Sur, Indranil and Sikka, Karan and Walmer, Matthew and Koneripalli, Kaushik and Roy, Anirban and Lin, Xiao and Divakaran, Ajay and Jha, Susmit}, title = {TIJO: Trigger Inversion with Joint Optimization for Defending Multimodal Backdoored Models}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {165-175} }
Improving Adversarial Robustness of Masked Autoencoders via Test-time Frequency-domain Prompting-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Huang_2023_ICCV, author = {Huang, Qidong and Dong, Xiaoyi and Chen, Dongdong and Chen, Yinpeng and Yuan, Lu and Hua, Gang and Zhang, Weiming and Yu, Nenghai}, title = {Improving Adversarial Robustness of Masked Autoencoders via Test-time Frequency-domain Prompting}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {1600-1610} }
The Making and Breaking of Camouflage-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Lamdouar_2023_ICCV, author = {Lamdouar, Hala and Xie, Weidi and Zisserman, Andrew}, title = {The Making and Breaking of Camouflage}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {832-842} }
Object as Query: Lifting Any 2D Object Detector to 3D Detection-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Wang_2023_ICCV, author = {Wang, Zitian and Huang, Zehao and Fu, Jiahui and Wang, Naiyan and Liu, Si}, title = {Object as Query: Lifting Any 2D Object Detector to 3D Detection}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {3791-3800} }
Versatile Diffusion: Text, Images and Variations All in One Diffusion Model-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Xu_2023_ICCV, author = {Xu, Xingqian and Wang, Zhangyang and Zhang, Gong and Wang, Kai and Shi, Humphrey}, title = {Versatile Diffusion: Text, Images and Variations All in One Diffusion Model}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {7754-7765} }
Sat2Density: Faithful Density Learning from Satellite-Ground Image Pairs-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Qian_2023_ICCV, author = {Qian, Ming and Xiong, Jincheng and Xia, Gui-Song and Xue, Nan}, title = {Sat2Density: Faithful Density Learning from Satellite-Ground Image Pairs}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {3683-3692} }
Expressive Text-to-Image Generation with Rich Text-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Ge_2023_ICCV, author = {Ge, Songwei and Park, Taesung and Zhu, Jun-Yan and Huang, Jia-Bin}, title = {Expressive Text-to-Image Generation with Rich Text}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {7545-7556} }
Text-Driven Generative Domain Adaptation with Spectral Consistency Regularization-
[pdf]
[bibtex]@InProceedings{Liu_2023_ICCV, author = {Liu, Zhenhuan and Li, Liang and Xiao, Jiayu and Zha, Zheng-Jun and Huang, Qingming}, title = {Text-Driven Generative Domain Adaptation with Spectral Consistency Regularization}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {7019-7029} }
Neural Reconstruction of Relightable Human Model from Monocular Video-
[pdf]
[supp]
[bibtex]@InProceedings{Sun_2023_ICCV, author = {Sun, Wenzhang and Che, Yunlong and Huang, Han and Guo, Yandong}, title = {Neural Reconstruction of Relightable Human Model from Monocular Video}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {397-407} }
FB-BEV: BEV Representation from Forward-Backward View Transformations-
[pdf]
[supp]
[bibtex]@InProceedings{Li_2023_ICCV, author = {Li, Zhiqi and Yu, Zhiding and Wang, Wenhai and Anandkumar, Anima and Lu, Tong and Alvarez, Jose M.}, title = {FB-BEV: BEV Representation from Forward-Backward View Transformations}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {6919-6928} }
BoxSnake: Polygonal Instance Segmentation with Box Supervision-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Yang_2023_ICCV, author = {Yang, Rui and Song, Lin and Ge, Yixiao and Li, Xiu}, title = {BoxSnake: Polygonal Instance Segmentation with Box Supervision}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {766-776} }
ClimateNeRF: Extreme Weather Synthesis in Neural Radiance Field-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Li_2023_ICCV, author = {Li, Yuan and Lin, Zhi-Hao and Forsyth, David and Huang, Jia-Bin and Wang, Shenlong}, title = {ClimateNeRF: Extreme Weather Synthesis in Neural Radiance Field}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {3227-3238} }
Monte Carlo Linear Clustering with Single-Point Supervision is Enough for Infrared Small Target Detection-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Li_2023_ICCV, author = {Li, Boyang and Wang, Yingqian and Wang, Longguang and Zhang, Fei and Liu, Ting and Lin, Zaiping and An, Wei and Guo, Yulan}, title = {Monte Carlo Linear Clustering with Single-Point Supervision is Enough for Infrared Small Target Detection}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {1009-1019} }
Practical Membership Inference Attacks Against Large-Scale Multi-Modal Models: A Pilot Study-
[pdf]
[supp]
[bibtex]@InProceedings{Ko_2023_ICCV, author = {Ko, Myeongseob and Jin, Ming and Wang, Chenguang and Jia, Ruoxi}, title = {Practical Membership Inference Attacks Against Large-Scale Multi-Modal Models: A Pilot Study}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {4871-4881} }
TCOVIS: Temporally Consistent Online Video Instance Segmentation-
[pdf]
[arXiv]
[bibtex]@InProceedings{Li_2023_ICCV, author = {Li, Junlong and Yu, Bingyao and Rao, Yongming and Zhou, Jie and Lu, Jiwen}, title = {TCOVIS: Temporally Consistent Online Video Instance Segmentation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {1097-1107} }
Long-Term Photometric Consistent Novel View Synthesis with Diffusion Models-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Yu_2023_ICCV, author = {Yu, Jason J. and Forghani, Fereshteh and Derpanis, Konstantinos G. and Brubaker, Marcus A.}, title = {Long-Term Photometric Consistent Novel View Synthesis with Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {7094-7104} }
Benchmarking Algorithmic Bias in Face Recognition: An Experimental Approach Using Synthetic Faces and Human Evaluation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Liang_2023_ICCV, author = {Liang, Hao and Perona, Pietro and Balakrishnan, Guha}, title = {Benchmarking Algorithmic Bias in Face Recognition: An Experimental Approach Using Synthetic Faces and Human Evaluation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {4977-4987} }
Spatial-Aware Token for Weakly Supervised Object Localization-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Wu_2023_ICCV, author = {Wu, Pingyu and Zhai, Wei and Cao, Yang and Luo, Jiebo and Zha, Zheng-Jun}, title = {Spatial-Aware Token for Weakly Supervised Object Localization}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {1844-1854} }
Harnessing the Spatial-Temporal Attention of Diffusion Models for High-Fidelity Text-to-Image Synthesis-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Wu_2023_ICCV, author = {Wu, Qiucheng and Liu, Yujian and Zhao, Handong and Bui, Trung and Lin, Zhe and Zhang, Yang and Chang, Shiyu}, title = {Harnessing the Spatial-Temporal Attention of Diffusion Models for High-Fidelity Text-to-Image Synthesis}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {7766-7776} }
GraphAlign: Enhancing Accurate Feature Alignment by Graph matching for Multi-Modal 3D Object Detection-
[pdf]
[bibtex]@InProceedings{Song_2023_ICCV, author = {Song, Ziying and Wei, Haiyue and Bai, Lin and Yang, Lei and Jia, Caiyan}, title = {GraphAlign: Enhancing Accurate Feature Alignment by Graph matching for Multi-Modal 3D Object Detection}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {3358-3369} }
NEMTO: Neural Environment Matting for Novel View and Relighting Synthesis of Transparent Objects-
[pdf]
[supp]
[bibtex]@InProceedings{Wang_2023_ICCV, author = {Wang, Dongqing and Zhang, Tong and S\"usstrunk, Sabine}, title = {NEMTO: Neural Environment Matting for Novel View and Relighting Synthesis of Transparent Objects}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {317-327} }
USAGE: A Unified Seed Area Generation Paradigm for Weakly Supervised Semantic Segmentation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Peng_2023_ICCV, author = {Peng, Zelin and Wang, Guanchun and Xie, Lingxi and Jiang, Dongsheng and Shen, Wei and Tian, Qi}, title = {USAGE: A Unified Seed Area Generation Paradigm for Weakly Supervised Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {624-634} }
NeuS2: Fast Learning of Neural Implicit Surfaces for Multi-view Reconstruction-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Wang_2023_ICCV, author = {Wang, Yiming and Han, Qin and Habermann, Marc and Daniilidis, Kostas and Theobalt, Christian and Liu, Lingjie}, title = {NeuS2: Fast Learning of Neural Implicit Surfaces for Multi-view Reconstruction}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {3295-3306} }
Gender Artifacts in Visual Datasets-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Meister_2023_ICCV, author = {Meister, Nicole and Zhao, Dora and Wang, Angelina and Ramaswamy, Vikram V. and Fong, Ruth and Russakovsky, Olga}, title = {Gender Artifacts in Visual Datasets}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {4837-4848} }
SuS-X: Training-Free Name-Only Transfer of Vision-Language Models-
[pdf]
[supp]
[bibtex]@InProceedings{Udandarao_2023_ICCV, author = {Udandarao, Vishaal and Gupta, Ankush and Albanie, Samuel}, title = {SuS-X: Training-Free Name-Only Transfer of Vision-Language Models}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {2725-2736} }
Beating Backdoor Attack at Its Own Game-
[pdf]
[arXiv]
[bibtex]@InProceedings{Liu_2023_ICCV, author = {Liu, Min and Sangiovanni-Vincentelli, Alberto and Yue, Xiangyu}, title = {Beating Backdoor Attack at Its Own Game}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {4620-4629} }
Do DALL-E and Flamingo Understand Each Other?-
[pdf]
[supp]
[bibtex]@InProceedings{Li_2023_ICCV, author = {Li, Hang and Gu, Jindong and Koner, Rajat and Sharifzadeh, Sahand and Tresp, Volker}, title = {Do DALL-E and Flamingo Understand Each Other?}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {1999-2010} }
Prototype-based Dataset Comparison-
[pdf]
[supp]
[bibtex]@InProceedings{van_Noord_2023_ICCV, author = {van Noord, Nanne}, title = {Prototype-based Dataset Comparison}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {1944-1954} }
FreeCOS: Self-Supervised Learning from Fractals and Unlabeled Images for Curvilinear Object Segmentation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Shi_2023_ICCV, author = {Shi, Tianyi and Ding, Xiaohuan and Zhang, Liang and Yang, Xin}, title = {FreeCOS: Self-Supervised Learning from Fractals and Unlabeled Images for Curvilinear Object Segmentation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {876-886} }
Generating Dynamic Kernels via Transformers for Lane Detection-
[pdf]
[bibtex]@InProceedings{Chen_2023_ICCV, author = {Chen, Ziye and Liu, Yu and Gong, Mingming and Du, Bo and Qian, Guoqi and Smith-Miles, Kate}, title = {Generating Dynamic Kernels via Transformers for Lane Detection}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {6835-6844} }
Boosting Long-tailed Object Detection via Step-wise Learning on Smooth-tail Data-
[pdf]
[arXiv]
[bibtex]@InProceedings{Dong_2023_ICCV, author = {Dong, Na and Zhang, Yongqiang and Ding, Mingli and Lee, Gim Hee}, title = {Boosting Long-tailed Object Detection via Step-wise Learning on Smooth-tail Data}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {6940-6949} }
Talking Head Generation with Probabilistic Audio-to-Visual Diffusion Priors-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Yu_2023_ICCV, author = {Yu, Zhentao and Yin, Zixin and Zhou, Deyu and Wang, Duomin and Wong, Finn and Wang, Baoyuan}, title = {Talking Head Generation with Probabilistic Audio-to-Visual Diffusion Priors}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {7645-7655} }
Learning Cross-Modal Affinity for Referring Video Object Segmentation Targeting Limited Samples-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Li_2023_ICCV, author = {Li, Guanghui and Gao, Mingqi and Liu, Heng and Zhen, Xiantong and Zheng, Feng}, title = {Learning Cross-Modal Affinity for Referring Video Object Segmentation Targeting Limited Samples}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {2684-2693} }
Divide and Conquer: a Two-Step Method for High Quality Face De-identification with Model Explainability-
[pdf]
[bibtex]@InProceedings{Wen_2023_ICCV, author = {Wen, Yunqian and Liu, Bo and Cao, Jingyi and Xie, Rong and Song, Li}, title = {Divide and Conquer: a Two-Step Method for High Quality Face De-identification with Model Explainability}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {5148-5157} }
Set-level Guidance Attack: Boosting Adversarial Transferability of Vision-Language Pre-training Models-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Lu_2023_ICCV, author = {Lu, Dong and Wang, Zhiqiang and Wang, Teng and Guan, Weili and Gao, Hongchang and Zheng, Feng}, title = {Set-level Guidance Attack: Boosting Adversarial Transferability of Vision-Language Pre-training Models}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {102-111} }
Multimodal Distillation for Egocentric Action Recognition-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Radevski_2023_ICCV, author = {Radevski, Gorjan and Grujicic, Dusan and Blaschko, Matthew and Moens, Marie-Francine and Tuytelaars, Tinne}, title = {Multimodal Distillation for Egocentric Action Recognition}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {5213-5224} }
Perceptual Artifacts Localization for Image Synthesis Tasks-
[pdf]
[supp]
[bibtex]@InProceedings{Zhang_2023_ICCV, author = {Zhang, Lingzhi and Xu, Zhengjie and Barnes, Connelly and Zhou, Yuqian and Liu, Qing and Zhang, He and Amirghodsi, Sohrab and Lin, Zhe and Shechtman, Eli and Shi, Jianbo}, title = {Perceptual Artifacts Localization for Image Synthesis Tasks}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {7579-7590} }
Better May Not Be Fairer: A Study on Subgroup Discrepancy in Image Classification-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Chiu_2023_ICCV, author = {Chiu, Ming-Chang and Chen, Pin-Yu and Ma, Xuezhe}, title = {Better May Not Be Fairer: A Study on Subgroup Discrepancy in Image Classification}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {4956-4966} }
3D Implicit Transporter for Temporally Consistent Keypoint Discovery-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Zhong_2023_ICCV, author = {Zhong, Chengliang and Zheng, Yuhang and Zheng, Yupeng and Zhao, Hao and Yi, Li and Mu, Xiaodong and Wang, Ling and Li, Pengfei and Zhou, Guyue and Yang, Chao and Zhang, Xinliang and Zhao, Jian}, title = {3D Implicit Transporter for Temporally Consistent Keypoint Discovery}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {3869-3880} }
Adaptive Rotated Convolution for Rotated Object Detection-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Pu_2023_ICCV, author = {Pu, Yifan and Wang, Yiru and Xia, Zhuofan and Han, Yizeng and Wang, Yulin and Gan, Weihao and Wang, Zidong and Song, Shiji and Huang, Gao}, title = {Adaptive Rotated Convolution for Rotated Object Detection}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {6589-6600} }
UniVTG: Towards Unified Video-Language Temporal Grounding-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Lin_2023_ICCV, author = {Lin, Kevin Qinghong and Zhang, Pengchuan and Chen, Joya and Pramanick, Shraman and Gao, Difei and Wang, Alex Jinpeng and Yan, Rui and Shou, Mike Zheng}, title = {UniVTG: Towards Unified Video-Language Temporal Grounding}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {2794-2804} }
Fast Globally Optimal Surface Normal Estimation from an Affine Correspondence-
[pdf]
[supp]
[bibtex]@InProceedings{Hajder_2023_ICCV, author = {Hajder, Levente and L\'oczi, Lajos and Barath, Daniel}, title = {Fast Globally Optimal Surface Normal Estimation from an Affine Correspondence}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {3390-3401} }
Frequency-aware GAN for Adversarial Manipulation Generation-
[pdf]
[bibtex]@InProceedings{Zhu_2023_ICCV, author = {Zhu, Peifei and Osada, Genki and Kataoka, Hirokatsu and Takahashi, Tsubasa}, title = {Frequency-aware GAN for Adversarial Manipulation Generation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {4315-4324} }
Template-guided Hierarchical Feature Restoration for Anomaly Detection-
[pdf]
[supp]
[bibtex]@InProceedings{Guo_2023_ICCV, author = {Guo, Hewei and Ren, Liping and Fu, Jingjing and Wang, Yuwang and Zhang, Zhizheng and Lan, Cuiling and Wang, Haoqian and Hou, Xinwen}, title = {Template-guided Hierarchical Feature Restoration for Anomaly Detection}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {6447-6458} }
PourIt!: Weakly-Supervised Liquid Perception from a Single Image for Visual Closed-Loop Robotic Pouring-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Lin_2023_ICCV, author = {Lin, Haitao and Fu, Yanwei and Xue, Xiangyang}, title = {PourIt!: Weakly-Supervised Liquid Perception from a Single Image for Visual Closed-Loop Robotic Pouring}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {241-251} }
A Latent Space of Stochastic Diffusion Models for Zero-Shot Image Editing and Guidance-
[pdf]
[bibtex]@InProceedings{Wu_2023_ICCV, author = {Wu, Chen Henry and De la Torre, Fernando}, title = {A Latent Space of Stochastic Diffusion Models for Zero-Shot Image Editing and Guidance}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {7378-7387} }
Open Set Video HOI detection from Action-Centric Chain-of-Look Prompting-
[pdf]
[supp]
[bibtex]@InProceedings{Xi_2023_ICCV, author = {Xi, Nan and Meng, Jingjing and Yuan, Junsong}, title = {Open Set Video HOI detection from Action-Centric Chain-of-Look Prompting}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {3079-3089} }
Robust Mixture-of-Expert Training for Convolutional Neural Networks-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Zhang_2023_ICCV, author = {Zhang, Yihua and Cai, Ruisi and Chen, Tianlong and Zhang, Guanhua and Zhang, Huan and Chen, Pin-Yu and Chang, Shiyu and Wang, Zhangyang and Liu, Sijia}, title = {Robust Mixture-of-Expert Training for Convolutional Neural Networks}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {90-101} }
UniTR: A Unified and Efficient Multi-Modal Transformer for Bird's-Eye-View Representation-
[pdf]
[supp]
[bibtex]@InProceedings{Wang_2023_ICCV, author = {Wang, Haiyang and Tang, Hao and Shi, Shaoshuai and Li, Aoxue and Li, Zhenguo and Schiele, Bernt and Wang, Liwei}, title = {UniTR: A Unified and Efficient Multi-Modal Transformer for Bird's-Eye-View Representation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {6792-6802} }
R3D3: Dense 3D Reconstruction of Dynamic Scenes from Multiple Cameras-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Schmied_2023_ICCV, author = {Schmied, Aron and Fischer, Tobias and Danelljan, Martin and Pollefeys, Marc and Yu, Fisher}, title = {R3D3: Dense 3D Reconstruction of Dynamic Scenes from Multiple Cameras}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {3216-3226} }
Focus the Discrepancy: Intra- and Inter-Correlation Learning for Image Anomaly Detection-
[pdf]
[supp]
[bibtex]@InProceedings{Yao_2023_ICCV, author = {Yao, Xincheng and Li, Ruoqi and Qian, Zefeng and Luo, Yan and Zhang, Chongyang}, title = {Focus the Discrepancy: Intra- and Inter-Correlation Learning for Image Anomaly Detection}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {6803-6813} }
Make Encoder Great Again in 3D GAN Inversion through Geometry and Occlusion-Aware Encoding-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Yuan_2023_ICCV, author = {Yuan, Ziyang and Zhu, Yiming and Li, Yu and Liu, Hongyu and Yuan, Chun}, title = {Make Encoder Great Again in 3D GAN Inversion through Geometry and Occlusion-Aware Encoding}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {2437-2447} }
DLT: Conditioned layout generation with Joint Discrete-Continuous Diffusion Layout Transformer-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Levi_2023_ICCV, author = {Levi, Elad and Brosh, Eli and Mykhailych, Mykola and Perez, Meir}, title = {DLT: Conditioned layout generation with Joint Discrete-Continuous Diffusion Layout Transformer}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {2106-2115} }
Open-Vocabulary Semantic Segmentation with Decoupled One-Pass Network-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Han_2023_ICCV, author = {Han, Cong and Zhong, Yujie and Li, Dengjie and Han, Kai and Ma, Lin}, title = {Open-Vocabulary Semantic Segmentation with Decoupled One-Pass Network}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {1086-1096} }
Human-Inspired Facial Sketch Synthesis with Dynamic Adaptation-
[pdf]
[arXiv]
[bibtex]@InProceedings{Gao_2023_ICCV, author = {Gao, Fei and Zhu, Yifan and Jiang, Chang and Wang, Nannan}, title = {Human-Inspired Facial Sketch Synthesis with Dynamic Adaptation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {7237-7247} }
DS-Fusion: Artistic Typography via Discriminated and Stylized Diffusion-
[pdf]
[supp]
[bibtex]@InProceedings{Tanveer_2023_ICCV, author = {Tanveer, Maham and Wang, Yizhi and Mahdavi-Amiri, Ali and Zhang, Hao}, title = {DS-Fusion: Artistic Typography via Discriminated and Stylized Diffusion}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {374-384} }
Distilling DETR with Visual-Linguistic Knowledge for Open-Vocabulary Object Detection-
[pdf]
[bibtex]@InProceedings{Li_2023_ICCV, author = {Li, Liangqi and Miao, Jiaxu and Shi, Dahu and Tan, Wenming and Ren, Ye and Yang, Yi and Pu, Shiliang}, title = {Distilling DETR with Visual-Linguistic Knowledge for Open-Vocabulary Object Detection}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {6501-6510} }
Scale-MAE: A Scale-Aware Masked Autoencoder for Multiscale Geospatial Representation Learning-
[pdf]
[supp]
[bibtex]@InProceedings{Reed_2023_ICCV, author = {Reed, Colorado J and Gupta, Ritwik and Li, Shufan and Brockman, Sarah and Funk, Christopher and Clipp, Brian and Keutzer, Kurt and Candido, Salvatore and Uyttendaele, Matt and Darrell, Trevor}, title = {Scale-MAE: A Scale-Aware Masked Autoencoder for Multiscale Geospatial Representation Learning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {4088-4099} }
A Unified Framework for Robustness on Diverse Sampling Errors-
[pdf]
[supp]
[bibtex]@InProceedings{Jeon_2023_ICCV, author = {Jeon, Myeongho and Kang, Myungjoo and Lee, Joonseok}, title = {A Unified Framework for Robustness on Diverse Sampling Errors}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {1464-1472} }
LiDAR-Camera Panoptic Segmentation via Geometry-Consistent and Semantic-Aware Alignment-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Zhang_2023_ICCV, author = {Zhang, Zhiwei and Zhang, Zhizhong and Yu, Qian and Yi, Ran and Xie, Yuan and Ma, Lizhuang}, title = {LiDAR-Camera Panoptic Segmentation via Geometry-Consistent and Semantic-Aware Alignment}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {3662-3671} }
Scene-Aware Label Graph Learning for Multi-Label Image Classification-
[pdf]
[supp]
[bibtex]@InProceedings{Zhu_2023_ICCV, author = {Zhu, Xuelin and Liu, Jian and Liu, Weijia and Ge, Jiawei and Liu, Bo and Cao, Jiuxin}, title = {Scene-Aware Label Graph Learning for Multi-Label Image Classification}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {1473-1482} }
Fcaformer: Forward Cross Attention in Hybrid Vision Transformer-
[pdf]
[arXiv]
[bibtex]@InProceedings{Zhang_2023_ICCV, author = {Zhang, Haokui and Hu, Wenze and Wang, Xiaoyu}, title = {Fcaformer: Forward Cross Attention in Hybrid Vision Transformer}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {6060-6069} }
Progressive Spatio-Temporal Prototype Matching for Text-Video Retrieval-
[pdf]
[supp]
[bibtex]@InProceedings{Li_2023_ICCV, author = {Li, Pandeng and Xie, Chen-Wei and Zhao, Liming and Xie, Hongtao and Ge, Jiannan and Zheng, Yun and Zhao, Deli and Zhang, Yongdong}, title = {Progressive Spatio-Temporal Prototype Matching for Text-Video Retrieval}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {4100-4110} }
Data Augmented Flatness-aware Gradient Projection for Continual Learning-
[pdf]
[supp]
[bibtex]@InProceedings{Yang_2023_ICCV, author = {Yang, Enneng and Shen, Li and Wang, Zhenyi and Liu, Shiwei and Guo, Guibing and Wang, Xingwei}, title = {Data Augmented Flatness-aware Gradient Projection for Continual Learning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {5630-5639} }
Sample-wise Label Confidence Incorporation for Learning with Noisy Labels-
[pdf]
[supp]
[bibtex]@InProceedings{Ahn_2023_ICCV, author = {Ahn, Chanho and Kim, Kikyung and Baek, Ji-won and Lim, Jongin and Han, Seungju}, title = {Sample-wise Label Confidence Incorporation for Learning with Noisy Labels}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {1823-1832} }
CLIPTrans: Transferring Visual Knowledge with Pre-trained Models for Multimodal Machine Translation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Gupta_2023_ICCV, author = {Gupta, Devaansh and Kharbanda, Siddhant and Zhou, Jiawei and Li, Wanhua and Pfister, Hanspeter and Wei, Donglai}, title = {CLIPTrans: Transferring Visual Knowledge with Pre-trained Models for Multimodal Machine Translation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {2875-2886} }
Ego-Only: Egocentric Action Detection without Exocentric Transferring-
[pdf]
[supp]
[bibtex]@InProceedings{Wang_2023_ICCV, author = {Wang, Huiyu and Singh, Mitesh Kumar and Torresani, Lorenzo}, title = {Ego-Only: Egocentric Action Detection without Exocentric Transferring}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {5250-5261} }
CoinSeg: Contrast Inter- and Intra- Class Representations for Incremental Segmentation-
[pdf]
[supp]
[bibtex]@InProceedings{Zhang_2023_ICCV, author = {Zhang, Zekang and Gao, Guangyu and Jiao, Jianbo and Liu, Chi Harold and Wei, Yunchao}, title = {CoinSeg: Contrast Inter- and Intra- Class Representations for Incremental Segmentation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {843-853} }
Multi-View Active Fine-Grained Visual Recognition-
[pdf]
[bibtex]@InProceedings{Du_2023_ICCV, author = {Du, Ruoyi and Yu, Wenqing and Wang, Heqing and Lin, Ting-En and Chang, Dongliang and Ma, Zhanyu}, title = {Multi-View Active Fine-Grained Visual Recognition}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {1568-1578} }
Variational Causal Inference Network for Explanatory Visual Question Answering-
[pdf]
[supp]
[bibtex]@InProceedings{Xue_2023_ICCV, author = {Xue, Dizhan and Qian, Shengsheng and Xu, Changsheng}, title = {Variational Causal Inference Network for Explanatory Visual Question Answering}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {2515-2525} }
Enhancing Generalization of Universal Adversarial Perturbation through Gradient Aggregation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Liu_2023_ICCV, author = {Liu, Xuannan and Zhong, Yaoyao and Zhang, Yuhang and Qin, Lixiong and Deng, Weihong}, title = {Enhancing Generalization of Universal Adversarial Perturbation through Gradient Aggregation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {4435-4444} }
Parallel Attention Interaction Network for Few-Shot Skeleton-Based Action Recognition-
[pdf]
[bibtex]@InProceedings{Liu_2023_ICCV, author = {Liu, Xingyu and Zhou, Sanping and Wang, Le and Hua, Gang}, title = {Parallel Attention Interaction Network for Few-Shot Skeleton-Based Action Recognition}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {1379-1388} }
Not All Features Matter: Enhancing Few-shot CLIP with Adaptive Prior Refinement-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Zhu_2023_ICCV, author = {Zhu, Xiangyang and Zhang, Renrui and He, Bowei and Zhou, Aojun and Wang, Dong and Zhao, Bin and Gao, Peng}, title = {Not All Features Matter: Enhancing Few-shot CLIP with Adaptive Prior Refinement}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {2605-2615} }
EgoVLPv2: Egocentric Video-Language Pre-training with Fusion in the Backbone-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Pramanick_2023_ICCV, author = {Pramanick, Shraman and Song, Yale and Nag, Sayan and Lin, Kevin Qinghong and Shah, Hardik and Shou, Mike Zheng and Chellappa, Rama and Zhang, Pengchuan}, title = {EgoVLPv2: Egocentric Video-Language Pre-training with Fusion in the Backbone}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {5285-5297} }
Deep Equilibrium Object Detection-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Wang_2023_ICCV, author = {Wang, Shuai and Teng, Yao and Wang, Limin}, title = {Deep Equilibrium Object Detection}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {6296-6306} }
SMAUG: Sparse Masked Autoencoder for Efficient Video-Language Pre-Training-
[pdf]
[arXiv]
[bibtex]@InProceedings{Lin_2023_ICCV, author = {Lin, Yuanze and Wei, Chen and Wang, Huiyu and Yuille, Alan and Xie, Cihang}, title = {SMAUG: Sparse Masked Autoencoder for Efficient Video-Language Pre-Training}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {2459-2469} }
Communication-Efficient Vertical Federated Learning with Limited Overlapping Samples-
[pdf]
[arXiv]
[bibtex]@InProceedings{Sun_2023_ICCV, author = {Sun, Jingwei and Xu, Ziyue and Yang, Dong and Nath, Vishwesh and Li, Wenqi and Zhao, Can and Xu, Daguang and Chen, Yiran and Roth, Holger R.}, title = {Communication-Efficient Vertical Federated Learning with Limited Overlapping Samples}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {5203-5212} }
On the Audio-visual Synchronization for Lip-to-Speech Synthesis-
[pdf]
[arXiv]
[bibtex]@InProceedings{Niu_2023_ICCV, author = {Niu, Zhe and Mak, Brian}, title = {On the Audio-visual Synchronization for Lip-to-Speech Synthesis}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {7843-7852} }
BallGAN: 3D-aware Image Synthesis with a Spherical Background-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Shin_2023_ICCV, author = {Shin, Minjung and Seo, Yunji and Bae, Jeongmin and Choi, Young Sun and Kim, Hyunsu and Byun, Hyeran and Uh, Youngjung}, title = {BallGAN: 3D-aware Image Synthesis with a Spherical Background}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {7268-7279} }
AttT2M: Text-Driven Human Motion Generation with Multi-Perspective Attention Mechanism-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Zhong_2023_ICCV, author = {Zhong, Chongyang and Hu, Lei and Zhang, Zihao and Xia, Shihong}, title = {AttT2M: Text-Driven Human Motion Generation with Multi-Perspective Attention Mechanism}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {509-519} }
A Theory of Topological Derivatives for Inverse Rendering of Geometry-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Mehta_2023_ICCV, author = {Mehta, Ishit and Chandraker, Manmohan and Ramamoorthi, Ravi}, title = {A Theory of Topological Derivatives for Inverse Rendering of Geometry}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {419-429} }
Canonical Factors for Hybrid Neural Fields-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Yi_2023_ICCV, author = {Yi, Brent and Zeng, Weijia and Buchanan, Sam and Ma, Yi}, title = {Canonical Factors for Hybrid Neural Fields}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {3414-3426} }
GET: Group Event Transformer for Event-Based Vision-
[pdf]
[supp]
[bibtex]@InProceedings{Peng_2023_ICCV, author = {Peng, Yansong and Zhang, Yueyi and Xiong, Zhiwei and Sun, Xiaoyan and Wu, Feng}, title = {GET: Group Event Transformer for Event-Based Vision}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {6038-6048} }
When Do Curricula Work in Federated Learning?-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Vahidian_2023_ICCV, author = {Vahidian, Saeed and Kadaveru, Sreevatsank and Baek, Woonjoon and Wang, Weijia and Kungurtsev, Vyacheslav and Chen, Chen and Shah, Mubarak and Lin, Bill}, title = {When Do Curricula Work in Federated Learning?}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {5084-5094} }
Audio-Visual Class-Incremental Learning-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Pian_2023_ICCV, author = {Pian, Weiguo and Mo, Shentong and Guo, Yunhui and Tian, Yapeng}, title = {Audio-Visual Class-Incremental Learning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {7799-7811} }
Towards Viewpoint-Invariant Visual Recognition via Adversarial Training-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Ruan_2023_ICCV, author = {Ruan, Shouwei and Dong, Yinpeng and Su, Hang and Peng, Jianteng and Chen, Ning and Wei, Xingxing}, title = {Towards Viewpoint-Invariant Visual Recognition via Adversarial Training}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {4709-4719} }
Multi-Metrics Adaptively Identifies Backdoors in Federated Learning-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Huang_2023_ICCV, author = {Huang, Siquan and Li, Yijiang and Chen, Chong and Shi, Leyu and Gao, Ying}, title = {Multi-Metrics Adaptively Identifies Backdoors in Federated Learning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {4652-4662} }
FPR: False Positive Rectification for Weakly Supervised Semantic Segmentation-
[pdf]
[supp]
[bibtex]@InProceedings{Chen_2023_ICCV, author = {Chen, Liyi and Lei, Chenyang and Li, Ruihuang and Li, Shuai and Zhang, Zhaoxiang and Zhang, Lei}, title = {FPR: False Positive Rectification for Weakly Supervised Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {1108-1118} }
DETRDistill: A Universal Knowledge Distillation Framework for DETR-families-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Chang_2023_ICCV, author = {Chang, Jiahao and Wang, Shuo and Xu, Hai-Ming and Chen, Zehui and Yang, Chenhongyi and Zhao, Feng}, title = {DETRDistill: A Universal Knowledge Distillation Framework for DETR-families}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {6898-6908} }
F&F Attack: Adversarial Attack against Multiple Object Trackers by Inducing False Negatives and False Positives-
[pdf]
[supp]
[bibtex]@InProceedings{Zhou_2023_ICCV, author = {Zhou, Tao and Ye, Qi and Luo, Wenhan and Zhang, Kaihao and Shi, Zhiguo and Chen, Jiming}, title = {F\&F Attack: Adversarial Attack against Multiple Object Trackers by Inducing False Negatives and False Positives}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {4573-4583} }
Transferable Decoding with Visual Entities for Zero-Shot Image Captioning-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Fei_2023_ICCV, author = {Fei, Junjie and Wang, Teng and Zhang, Jinrui and He, Zhenyu and Wang, Chengjie and Zheng, Feng}, title = {Transferable Decoding with Visual Entities for Zero-Shot Image Captioning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {3136-3146} }
ReMoDiffuse: Retrieval-Augmented Motion Diffusion Model-
[pdf]
[arXiv]
[bibtex]@InProceedings{Zhang_2023_ICCV, author = {Zhang, Mingyuan and Guo, Xinying and Pan, Liang and Cai, Zhongang and Hong, Fangzhou and Li, Huirong and Yang, Lei and Liu, Ziwei}, title = {ReMoDiffuse: Retrieval-Augmented Motion Diffusion Model}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {364-373} }
Advancing Referring Expression Segmentation Beyond Single Image-
[pdf]
[arXiv]
[bibtex]@InProceedings{Wu_2023_ICCV, author = {Wu, Yixuan and Zhang, Zhao and Xie, Chi and Zhu, Feng and Zhao, Rui}, title = {Advancing Referring Expression Segmentation Beyond Single Image}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {2628-2638} }
LogicSeg: Parsing Visual Semantics with Neural Logic Learning and Reasoning-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Li_2023_ICCV, author = {Li, Liulei and Wang, Wenguan and Yang, Yi}, title = {LogicSeg: Parsing Visual Semantics with Neural Logic Learning and Reasoning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {4122-4133} }
Texture Learning Domain Randomization for Domain Generalized Segmentation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Kim_2023_ICCV, author = {Kim, Sunghwan and Kim, Dae-hwan and Kim, Hoseong}, title = {Texture Learning Domain Randomization for Domain Generalized Segmentation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {677-687} }
Learning Concise and Descriptive Attributes for Visual Recognition-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Yan_2023_ICCV, author = {Yan, An and Wang, Yu and Zhong, Yiwu and Dong, Chengyu and He, Zexue and Lu, Yujie and Wang, William Yang and Shang, Jingbo and McAuley, Julian}, title = {Learning Concise and Descriptive Attributes for Visual Recognition}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {3090-3100} }
Label-Noise Learning with Intrinsically Long-Tailed Data-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Lu_2023_ICCV, author = {Lu, Yang and Zhang, Yiliang and Han, Bo and Cheung, Yiu-ming and Wang, Hanzi}, title = {Label-Noise Learning with Intrinsically Long-Tailed Data}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {1369-1378} }
Rethinking Range View Representation for LiDAR Segmentation-
[pdf]
[arXiv]
[bibtex]@InProceedings{Kong_2023_ICCV, author = {Kong, Lingdong and Liu, Youquan and Chen, Runnan and Ma, Yuexin and Zhu, Xinge and Li, Yikang and Hou, Yuenan and Qiao, Yu and Liu, Ziwei}, title = {Rethinking Range View Representation for LiDAR Segmentation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {228-240} }
Divide and Conquer: 3D Point Cloud Instance Segmentation With Point-Wise Binarization-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Zhao_2023_ICCV, author = {Zhao, Weiguang and Yan, Yuyao and Yang, Chaolong and Ye, Jianan and Yang, Xi and Huang, Kaizhu}, title = {Divide and Conquer: 3D Point Cloud Instance Segmentation With Point-Wise Binarization}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {562-571} }
BANSAC: A Dynamic BAyesian Network for Adaptive SAmple Consensus-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Piedade_2023_ICCV, author = {Piedade, Valter and Miraldo, Pedro}, title = {BANSAC: A Dynamic BAyesian Network for Adaptive SAmple Consensus}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {3738-3747} }
ShapeScaffolder: Structure-Aware 3D Shape Generation from Text-
[pdf]
[supp]
[bibtex]@InProceedings{Tian_2023_ICCV, author = {Tian, Xi and Yang, Yong-Liang and Wu, Qi}, title = {ShapeScaffolder: Structure-Aware 3D Shape Generation from Text}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {2715-2724} }
Read-only Prompt Optimization for Vision-Language Few-shot Learning-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Lee_2023_ICCV, author = {Lee, Dongjun and Song, Seokwon and Suh, Jihee and Choi, Joonmyeong and Lee, Sanghyeok and Kim, Hyunwoo J.}, title = {Read-only Prompt Optimization for Vision-Language Few-shot Learning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {1401-1411} }
COCO-O: A Benchmark for Object Detectors under Natural Distribution Shifts-
[pdf]
[supp]
[bibtex]@InProceedings{Mao_2023_ICCV, author = {Mao, Xiaofeng and Chen, Yuefeng and Zhu, Yao and Chen, Da and Su, Hang and Zhang, Rong and Xue, Hui}, title = {COCO-O: A Benchmark for Object Detectors under Natural Distribution Shifts}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {6339-6350} }
StageInteractor: Query-based Object Detector with Cross-stage Interaction-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Teng_2023_ICCV, author = {Teng, Yao and Liu, Haisong and Guo, Sheng and Wang, Limin}, title = {StageInteractor: Query-based Object Detector with Cross-stage Interaction}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {6577-6588} }
Moment Detection in Long Tutorial Videos-
[pdf]
[supp]
[bibtex]@InProceedings{Croitoru_2023_ICCV, author = {Croitoru, Ioana and Bogolin, Simion-Vlad and Albanie, Samuel and Liu, Yang and Wang, Zhaowen and Yoon, Seunghyun and Dernoncourt, Franck and Jin, Hailin and Bui, Trung}, title = {Moment Detection in Long Tutorial Videos}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {2594-2604} }
DFA3D: 3D Deformable Attention For 2D-to-3D Feature Lifting-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Li_2023_ICCV, author = {Li, Hongyang and Zhang, Hao and Zeng, Zhaoyang and Liu, Shilong and Li, Feng and Ren, Tianhe and Zhang, Lei}, title = {DFA3D: 3D Deformable Attention For 2D-to-3D Feature Lifting}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {6684-6693} }
Rosetta Neurons: Mining the Common Units in a Model Zoo-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Dravid_2023_ICCV, author = {Dravid, Amil and Gandelsman, Yossi and Efros, Alexei A. and Shocher, Assaf}, title = {Rosetta Neurons: Mining the Common Units in a Model Zoo}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {1934-1943} }
Semi-Supervised Semantic Segmentation under Label Noise via Diverse Learning Groups-
[pdf]
[supp]
[bibtex]@InProceedings{Li_2023_ICCV, author = {Li, Peixia and Purkait, Pulak and Ajanthan, Thalaiyasingam and Abdolshah, Majid and Garg, Ravi and Husain, Hisham and Xu, Chenchen and Gould, Stephen and Ouyang, Wanli and van den Hengel, Anton}, title = {Semi-Supervised Semantic Segmentation under Label Noise via Diverse Learning Groups}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {1229-1238} }
Segment Anything-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Kirillov_2023_ICCV, author = {Kirillov, Alexander and Mintun, Eric and Ravi, Nikhila and Mao, Hanzi and Rolland, Chloe and Gustafson, Laura and Xiao, Tete and Whitehead, Spencer and Berg, Alexander C. and Lo, Wan-Yen and Dollar, Piotr and Girshick, Ross}, title = {Segment Anything}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {4015-4026} }
Unsupervised Prompt Tuning for Text-Driven Object Detection-
[pdf]
[bibtex]@InProceedings{He_2023_ICCV, author = {He, Weizhen and Chen, Weijie and Chen, Binbin and Yang, Shicai and Xie, Di and Lin, Luojun and Qi, Donglian and Zhuang, Yueting}, title = {Unsupervised Prompt Tuning for Text-Driven Object Detection}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {2651-2661} }
Re-ReND: Real-Time Rendering of NeRFs across Devices-
[pdf]
[supp]
[bibtex]@InProceedings{Rojas_2023_ICCV, author = {Rojas, Sara and Zarzar, Jesus and P\'erez, Juan C. and Sanakoyeu, Artsiom and Thabet, Ali and Pumarola, Albert and Ghanem, Bernard}, title = {Re-ReND: Real-Time Rendering of NeRFs across Devices}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {3632-3641} }
Handwritten and Printed Text Segmentation: A Signature Case Study-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Gholamian_2023_ICCV, author = {Gholamian, Sina and Vahdat, Ali}, title = {Handwritten and Printed Text Segmentation: A Signature Case Study}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {582-592} }
RbA: Segmenting Unknown Regions Rejected by All-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Nayal_2023_ICCV, author = {Nayal, Nazir and Yavuz, Misra and Henriques, Jo\~ao F. and G\"uney, Fatma}, title = {RbA: Segmenting Unknown Regions Rejected by All}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {711-722} }
Towards Open-Vocabulary Video Instance Segmentation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Wang_2023_ICCV, author = {Wang, Haochen and Yan, Cilin and Wang, Shuai and Jiang, Xiaolong and Tang, Xu and Hu, Yao and Xie, Weidi and Gavves, Efstratios}, title = {Towards Open-Vocabulary Video Instance Segmentation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {4057-4066} }
Unleashing the Power of Gradient Signal-to-Noise Ratio for Zero-Shot NAS-
[pdf]
[supp]
[bibtex]@InProceedings{Sun_2023_ICCV, author = {Sun, Zihao and Sun, Yu and Yang, Longxing and Lu, Shun and Mei, Jilin and Zhao, Wenxiao and Hu, Yu}, title = {Unleashing the Power of Gradient Signal-to-Noise Ratio for Zero-Shot NAS}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {5763-5773} }
BiViT: Extremely Compressed Binary Vision Transformers-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{He_2023_ICCV, author = {He, Yefei and Lou, Zhenyu and Zhang, Luoming and Liu, Jing and Wu, Weijia and Zhou, Hong and Zhuang, Bohan}, title = {BiViT: Extremely Compressed Binary Vision Transformers}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {5651-5663} }
Tree-Structured Shading Decomposition-
[pdf]
[arXiv]
[bibtex]@InProceedings{Geng_2023_ICCV, author = {Geng, Chen and Yu, Hong-Xing and Zhang, Sharon and Agrawala, Maneesh and Wu, Jiajun}, title = {Tree-Structured Shading Decomposition}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {488-498} }
EfficientTrain: Exploring Generalized Curriculum Learning for Training Visual Backbones-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Wang_2023_ICCV, author = {Wang, Yulin and Yue, Yang and Lu, Rui and Liu, Tianjiao and Zhong, Zhao and Song, Shiji and Huang, Gao}, title = {EfficientTrain: Exploring Generalized Curriculum Learning for Training Visual Backbones}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {5852-5864} }
IntrinsicNeRF: Learning Intrinsic Neural Radiance Fields for Editable Novel View Synthesis-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Ye_2023_ICCV, author = {Ye, Weicai and Chen, Shuo and Bao, Chong and Bao, Hujun and Pollefeys, Marc and Cui, Zhaopeng and Zhang, Guofeng}, title = {IntrinsicNeRF: Learning Intrinsic Neural Radiance Fields for Editable Novel View Synthesis}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {339-351} }
Multi-Object Discovery by Low-Dimensional Object Motion-
[pdf]
[supp]
[bibtex]@InProceedings{Safadoust_2023_ICCV, author = {Safadoust, Sadra and G\"uney, Fatma}, title = {Multi-Object Discovery by Low-Dimensional Object Motion}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {734-744} }
GACE: Geometry Aware Confidence Enhancement for Black-Box 3D Object Detectors on LiDAR-Data-
[pdf]
[supp]
[bibtex]@InProceedings{Schinagl_2023_ICCV, author = {Schinagl, David and Krispel, Georg and Fruhwirth-Reisinger, Christian and Possegger, Horst and Bischof, Horst}, title = {GACE: Geometry Aware Confidence Enhancement for Black-Box 3D Object Detectors on LiDAR-Data}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {6566-6576} }
ToonTalker: Cross-Domain Face Reenactment-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Gong_2023_ICCV, author = {Gong, Yuan and Zhang, Yong and Cun, Xiaodong and Yin, Fei and Fan, Yanbo and Wang, Xuan and Wu, Baoyuan and Yang, Yujiu}, title = {ToonTalker: Cross-Domain Face Reenactment}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {7690-7700} }
Source-free Domain Adaptive Human Pose Estimation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Peng_2023_ICCV, author = {Peng, Qucheng and Zheng, Ce and Chen, Chen}, title = {Source-free Domain Adaptive Human Pose Estimation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {4826-4836} }
DOT: A Distillation-Oriented Trainer-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Zhao_2023_ICCV, author = {Zhao, Borui and Cui, Quan and Song, Renjie and Liang, Jiajun}, title = {DOT: A Distillation-Oriented Trainer}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {6189-6198} }
Neural Collage Transfer: Artistic Reconstruction via Material Manipulation-
[pdf]
[supp]
[bibtex]@InProceedings{Lee_2023_ICCV, author = {Lee, Ganghun and Kim, Minji and Lee, Yunsu and Lee, Minsu and Zhang, Byoung-Tak}, title = {Neural Collage Transfer: Artistic Reconstruction via Material Manipulation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {2394-2405} }
Informative Data Mining for One-Shot Cross-Domain Semantic Segmentation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Wang_2023_ICCV, author = {Wang, Yuxi and Liang, Jian and Xiao, Jun and Mei, Shuqi and Yang, Yuran and Zhang, Zhaoxiang}, title = {Informative Data Mining for One-Shot Cross-Domain Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {1064-1074} }
Householder Projector for Unsupervised Latent Semantics Discovery-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Song_2023_ICCV, author = {Song, Yue and Zhang, Jichao and Sebe, Nicu and Wang, Wei}, title = {Householder Projector for Unsupervised Latent Semantics Discovery}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {7712-7722} }
Bayesian Optimization Meets Self-Distillation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Lee_2023_ICCV, author = {Lee, HyunJae and Song, Heon and Lee, Hyeonsoo and Lee, Gi-hyeon and Park, Suyeong and Yoo, Donggeun}, title = {Bayesian Optimization Meets Self-Distillation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {1696-1705} }
No Fear of Classifier Biases: Neural Collapse Inspired Federated Learning with Synthetic and Fixed Classifier-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Li_2023_ICCV, author = {Li, Zexi and Shang, Xinyi and He, Rui and Lin, Tao and Wu, Chao}, title = {No Fear of Classifier Biases: Neural Collapse Inspired Federated Learning with Synthetic and Fixed Classifier}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {5319-5329} }
MemorySeg: Online LiDAR Semantic Segmentation with a Latent Memory-
[pdf]
[supp]
[bibtex]@InProceedings{Li_2023_ICCV, author = {Li, Enxu and Casas, Sergio and Urtasun, Raquel}, title = {MemorySeg: Online LiDAR Semantic Segmentation with a Latent Memory}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {745-754} }
Hashing Neural Video Decomposition with Multiplicative Residuals in Space-Time-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Chan_2023_ICCV, author = {Chan, Cheng-Hung and Yuan, Cheng-Yang and Sun, Cheng and Chen, Hwann-Tzong}, title = {Hashing Neural Video Decomposition with Multiplicative Residuals in Space-Time}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {7743-7753} }
Multimodal Variational Auto-encoder based Audio-Visual Segmentation-
[pdf]
[supp]
[bibtex]@InProceedings{Mao_2023_ICCV, author = {Mao, Yuxin and Zhang, Jing and Xiang, Mochu and Zhong, Yiran and Dai, Yuchao}, title = {Multimodal Variational Auto-encoder based Audio-Visual Segmentation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {954-965} }
DynaMITe: Dynamic Query Bootstrapping for Multi-object Interactive Segmentation Transformer-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Rana_2023_ICCV, author = {Rana, Amit Kumar and Mahadevan, Sabarinath and Hermans, Alexander and Leibe, Bastian}, title = {DynaMITe: Dynamic Query Bootstrapping for Multi-object Interactive Segmentation Transformer}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {1043-1052} }
FRAug: Tackling Federated Learning with Non-IID Features via Representation Augmentation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Chen_2023_ICCV, author = {Chen, Haokun and Frikha, Ahmed and Krompass, Denis and Gu, Jindong and Tresp, Volker}, title = {FRAug: Tackling Federated Learning with Non-IID Features via Representation Augmentation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {4849-4859} }
Homography Guided Temporal Fusion for Road Line and Marking Segmentation-
[pdf]
[supp]
[bibtex]@InProceedings{Wang_2023_ICCV, author = {Wang, Shan and Nguyen, Chuong and Liu, Jiawei and Zhang, Kaihao and Luo, Wenhan and Zhang, Yanhao and Muthu, Sundaram and Maken, Fahira Afzal and Li, Hongdong}, title = {Homography Guided Temporal Fusion for Road Line and Marking Segmentation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {1075-1085} }
NeuRBF: A Neural Fields Representation with Adaptive Radial Basis Functions-
[pdf]
[supp]
[bibtex]@InProceedings{Chen_2023_ICCV, author = {Chen, Zhang and Li, Zhong and Song, Liangchen and Chen, Lele and Yu, Jingyi and Yuan, Junsong and Xu, Yi}, title = {NeuRBF: A Neural Fields Representation with Adaptive Radial Basis Functions}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {4182-4194} }
Multi-granularity Interaction Simulation for Unsupervised Interactive Segmentation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Li_2023_ICCV, author = {Li, Kehan and Zhao, Yian and Wang, Zhennan and Cheng, Zesen and Jin, Peng and Ji, Xiangyang and Yuan, Li and Liu, Chang and Chen, Jie}, title = {Multi-granularity Interaction Simulation for Unsupervised Interactive Segmentation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {666-676} }
RecursiveDet: End-to-End Region-Based Recursive Object Detection-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Zhao_2023_ICCV, author = {Zhao, Jing and Sun, Li and Li, Qingli}, title = {RecursiveDet: End-to-End Region-Based Recursive Object Detection}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {6307-6316} }
Structure Invariant Transformation for better Adversarial Transferability-
[pdf]
[supp]
[bibtex]@InProceedings{Wang_2023_ICCV, author = {Wang, Xiaosen and Zhang, Zeliang and Zhang, Jianping}, title = {Structure Invariant Transformation for better Adversarial Transferability}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {4607-4619} }
FULLER: Unified Multi-modality Multi-task 3D Perception via Multi-level Gradient Calibration-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Huang_2023_ICCV, author = {Huang, Zhijian and Lin, Sihao and Liu, Guiyu and Luo, Mukun and Ye, Chaoqiang and Xu, Hang and Chang, Xiaojun and Liang, Xiaodan}, title = {FULLER: Unified Multi-modality Multi-task 3D Perception via Multi-level Gradient Calibration}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {3502-3511} }
Cross-Domain Product Representation Learning for Rich-Content E-Commerce-
[pdf]
[supp]
[bibtex]@InProceedings{Bai_2023_ICCV, author = {Bai, Xuehan and Li, Yan and Cheng, Yanhua and Yang, Wenjie and Chen, Quan and Li, Han}, title = {Cross-Domain Product Representation Learning for Rich-Content E-Commerce}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {5697-5706} }
Detection Transformer with Stable Matching-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Liu_2023_ICCV, author = {Liu, Shilong and Ren, Tianhe and Chen, Jiayu and Zeng, Zhaoyang and Zhang, Hao and Li, Feng and Li, Hongyang and Huang, Jun and Su, Hang and Zhu, Jun and Zhang, Lei}, title = {Detection Transformer with Stable Matching}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {6491-6500} }
Be Everywhere - Hear Everything (BEE): Audio Scene Reconstruction by Sparse Audio-Visual Samples-
[pdf]
[supp]
[bibtex]@InProceedings{Chen_2023_ICCV, author = {Chen, Mingfei and Su, Kun and Shlizerman, Eli}, title = {Be Everywhere - Hear Everything (BEE): Audio Scene Reconstruction by Sparse Audio-Visual Samples}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {7853-7862} }
Story Visualization by Online Text Augmentation with Context Memory-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Ahn_2023_ICCV, author = {Ahn, Daechul and Kim, Daneul and Song, Gwangmo and Kim, Seung Hwan and Lee, Honglak and Kang, Dongyeop and Choi, Jonghyun}, title = {Story Visualization by Online Text Augmentation with Context Memory}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {3125-3135} }
Global Balanced Experts for Federated Long-Tailed Learning-
[pdf]
[supp]
[bibtex]@InProceedings{Zeng_2023_ICCV, author = {Zeng, Yaopei and Liu, Lei and Liu, Li and Shen, Li and Liu, Shaoguo and Wu, Baoyuan}, title = {Global Balanced Experts for Federated Long-Tailed Learning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {4815-4825} }
Cascade-DETR: Delving into High-Quality Universal Object Detection-
[pdf]
[supp]
[bibtex]@InProceedings{Ye_2023_ICCV, author = {Ye, Mingqiao and Ke, Lei and Li, Siyuan and Tai, Yu-Wing and Tang, Chi-Keung and Danelljan, Martin and Yu, Fisher}, title = {Cascade-DETR: Delving into High-Quality Universal Object Detection}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {6704-6714} }
ACLS: Adaptive and Conditional Label Smoothing for Network Calibration-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Park_2023_ICCV, author = {Park, Hyekang and Noh, Jongyoun and Oh, Youngmin and Baek, Donghyeon and Ham, Bumsub}, title = {ACLS: Adaptive and Conditional Label Smoothing for Network Calibration}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {3936-3945} }
EMR-MSF: Self-Supervised Recurrent Monocular Scene Flow Exploiting Ego-Motion Rigidity-
[pdf]
[supp]
[bibtex]@InProceedings{Jiang_2023_ICCV, author = {Jiang, Zijie and Okutomi, Masatoshi}, title = {EMR-MSF: Self-Supervised Recurrent Monocular Scene Flow Exploiting Ego-Motion Rigidity}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {69-78} }
Evaluation and Improvement of Interpretability for Self-Explainable Part-Prototype Networks-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Huang_2023_ICCV, author = {Huang, Qihan and Xue, Mengqi and Huang, Wenqi and Zhang, Haofei and Song, Jie and Jing, Yongcheng and Song, Mingli}, title = {Evaluation and Improvement of Interpretability for Self-Explainable Part-Prototype Networks}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {2011-2020} }
Mitigating Adversarial Vulnerability through Causal Parameter Estimation by Adversarial Double Machine Learning-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Lee_2023_ICCV, author = {Lee, Byung-Kwan and Kim, Junho and Ro, Yong Man}, title = {Mitigating Adversarial Vulnerability through Causal Parameter Estimation by Adversarial Double Machine Learning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {4499-4509} }
Dynamic Token Pruning in Plain Vision Transformers for Semantic Segmentation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Tang_2023_ICCV, author = {Tang, Quan and Zhang, Bowen and Liu, Jiajun and Liu, Fagui and Liu, Yifan}, title = {Dynamic Token Pruning in Plain Vision Transformers for Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {777-786} }
DiffFit: Unlocking Transferability of Large Diffusion Models via Simple Parameter-efficient Fine-Tuning-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Xie_2023_ICCV, author = {Xie, Enze and Yao, Lewei and Shi, Han and Liu, Zhili and Zhou, Daquan and Liu, Zhaoqiang and Li, Jiawei and Li, Zhenguo}, title = {DiffFit: Unlocking Transferability of Large Diffusion Models via Simple Parameter-efficient Fine-Tuning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {4230-4239} }
QD-BEV : Quantization-aware View-guided Distillation for Multi-view 3D Object Detection-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Zhang_2023_ICCV, author = {Zhang, Yifan and Dong, Zhen and Yang, Huanrui and Lu, Ming and Tseng, Cheng-Ching and Du, Yuan and Keutzer, Kurt and Du, Li and Zhang, Shanghang}, title = {QD-BEV : Quantization-aware View-guided Distillation for Multi-view 3D Object Detection}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {3825-3835} }
CLIPascene: Scene Sketching with Different Types and Levels of Abstraction-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Vinker_2023_ICCV, author = {Vinker, Yael and Alaluf, Yuval and Cohen-Or, Daniel and Shamir, Ariel}, title = {CLIPascene: Scene Sketching with Different Types and Levels of Abstraction}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {4146-4156} }
Multi-Directional Subspace Editing in Style-Space-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Naveh_2023_ICCV, author = {Naveh, Chen}, title = {Multi-Directional Subspace Editing in Style-Space}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {7138-7148} }
Adaptive Superpixel for Active Learning in Semantic Segmentation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Kim_2023_ICCV, author = {Kim, Hoyoung and Oh, Minhyeon and Hwang, Sehyun and Kwak, Suha and Ok, Jungseul}, title = {Adaptive Superpixel for Active Learning in Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {943-953} }
Parametric Information Maximization for Generalized Category Discovery-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Chiaroni_2023_ICCV, author = {Chiaroni, Florent and Dolz, Jose and Masud, Ziko Imtiaz and Mitiche, Amar and Ben Ayed, Ismail}, title = {Parametric Information Maximization for Generalized Category Discovery}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {1729-1739} }
A Generalist Framework for Panoptic Segmentation of Images and Videos-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Chen_2023_ICCV, author = {Chen, Ting and Li, Lala and Saxena, Saurabh and Hinton, Geoffrey and Fleet, David J.}, title = {A Generalist Framework for Panoptic Segmentation of Images and Videos}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {909-919} }
DALL-Eval: Probing the Reasoning Skills and Social Biases of Text-to-Image Generation Models-
[pdf]
[supp]
[bibtex]@InProceedings{Cho_2023_ICCV, author = {Cho, Jaemin and Zala, Abhay and Bansal, Mohit}, title = {DALL-Eval: Probing the Reasoning Skills and Social Biases of Text-to-Image Generation Models}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {3043-3054} }
Scale-Aware Modulation Meet Transformer-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Lin_2023_ICCV, author = {Lin, Weifeng and Wu, Ziheng and Chen, Jiayu and Huang, Jun and Jin, Lianwen}, title = {Scale-Aware Modulation Meet Transformer}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {6015-6026} }
SUMMIT: Source-Free Adaptation of Uni-Modal Models to Multi-Modal Targets-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Simons_2023_ICCV, author = {Simons, Cody and Raychaudhuri, Dripta S. and Ahmed, Sk Miraj and You, Suya and Karydis, Konstantinos and Roy-Chowdhury, Amit K.}, title = {SUMMIT: Source-Free Adaptation of Uni-Modal Models to Multi-Modal Targets}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {1239-1249} }
Learning a More Continuous Zero Level Set in Unsigned Distance Fields through Level Set Projection-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Zhou_2023_ICCV, author = {Zhou, Junsheng and Ma, Baorui and Li, Shujuan and Liu, Yu-Shen and Han, Zhizhong}, title = {Learning a More Continuous Zero Level Set in Unsigned Distance Fields through Level Set Projection}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {3181-3192} }
HairNeRF: Geometry-Aware Image Synthesis for Hairstyle Transfer-
[pdf]
[bibtex]@InProceedings{Chang_2023_ICCV, author = {Chang, Seunggyu and Kim, Gihoon and Kim, Hayeon}, title = {HairNeRF: Geometry-Aware Image Synthesis for Hairstyle Transfer}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {2448-2458} }
GETAvatar: Generative Textured Meshes for Animatable Human Avatars-
[pdf]
[supp]
[bibtex]@InProceedings{Zhang_2023_ICCV, author = {Zhang, Xuanmeng and Zhang, Jianfeng and Chacko, Rohan and Xu, Hongyi and Song, Guoxian and Yang, Yi and Feng, Jiashi}, title = {GETAvatar: Generative Textured Meshes for Animatable Human Avatars}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {2273-2282} }
StylerDALLE: Language-Guided Style Transfer Using a Vector-Quantized Tokenizer of a Large-Scale Generative Model-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Xu_2023_ICCV, author = {Xu, Zipeng and Sangineto, Enver and Sebe, Nicu}, title = {StylerDALLE: Language-Guided Style Transfer Using a Vector-Quantized Tokenizer of a Large-Scale Generative Model}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {7601-7611} }
Deep Image Harmonization with Learnable Augmentation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Niu_2023_ICCV, author = {Niu, Li and Cao, Junyan and Cong, Wenyan and Zhang, Liqing}, title = {Deep Image Harmonization with Learnable Augmentation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {7482-7491} }
Scalable Diffusion Models with Transformers-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Peebles_2023_ICCV, author = {Peebles, William and Xie, Saining}, title = {Scalable Diffusion Models with Transformers}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {4195-4205} }
MMST-ViT: Climate Change-aware Crop Yield Prediction via Multi-Modal Spatial-Temporal Vision Transformer-
[pdf]
[bibtex]@InProceedings{Lin_2023_ICCV, author = {Lin, Fudong and Crawford, Summer and Guillot, Kaleb and Zhang, Yihe and Chen, Yan and Yuan, Xu and Chen, Li and Williams, Shelby and Minvielle, Robert and Xiao, Xiangming and Gholson, Drew and Ashwell, Nicolas and Setiyono, Tri and Tubana, Brenda and Peng, Lu and Bayoumi, Magdy and Tzeng, Nian-Feng}, title = {MMST-ViT: Climate Change-aware Crop Yield Prediction via Multi-Modal Spatial-Temporal Vision Transformer}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {5774-5784} }
Grounded Image Text Matching with Mismatched Relation Reasoning-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Wu_2023_ICCV, author = {Wu, Yu and Wei, Yana and Wang, Haozhe and Liu, Yongfei and Yang, Sibei and He, Xuming}, title = {Grounded Image Text Matching with Mismatched Relation Reasoning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {2976-2987} }
UniKD: Universal Knowledge Distillation for Mimicking Homogeneous or Heterogeneous Object Detectors-
[pdf]
[supp]
[bibtex]@InProceedings{Lao_2023_ICCV, author = {Lao, Shanshan and Song, Guanglu and Liu, Boxiao and Liu, Yu and Yang, Yujiu}, title = {UniKD: Universal Knowledge Distillation for Mimicking Homogeneous or Heterogeneous Object Detectors}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {6362-6372} }
BoxDiff: Text-to-Image Synthesis with Training-Free Box-Constrained Diffusion-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Xie_2023_ICCV, author = {Xie, Jinheng and Li, Yuexiang and Huang, Yawen and Liu, Haozhe and Zhang, Wentian and Zheng, Yefeng and Shou, Mike Zheng}, title = {BoxDiff: Text-to-Image Synthesis with Training-Free Box-Constrained Diffusion}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {7452-7461} }
Rapid Network Adaptation: Learning to Adapt Neural Networks Using Test-Time Feedback-
[pdf]
[bibtex]@InProceedings{Yeo_2023_ICCV, author = {Yeo, Teresa and Kar, O\u{g}uzhan Fatih and Sodagar, Zahra and Zamir, Amir}, title = {Rapid Network Adaptation: Learning to Adapt Neural Networks Using Test-Time Feedback}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {4674-4687} }
Theoretical and Numerical Analysis of 3D Reconstruction Using Point and Line Incidences-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Rydell_2023_ICCV, author = {Rydell, Felix and Shehu, Elima and Torres, Ang\'elica}, title = {Theoretical and Numerical Analysis of 3D Reconstruction Using Point and Line Incidences}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {3748-3757} }
Explaining Adversarial Robustness of Neural Networks from Clustering Effect Perspective-
[pdf]
[bibtex]@InProceedings{Jin_2023_ICCV, author = {Jin, Yulin and Zhang, Xiaoyu and Lou, Jian and Ma, Xu and Wang, Zilong and Chen, Xiaofeng}, title = {Explaining Adversarial Robustness of Neural Networks from Clustering Effect Perspective}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {4522-4531} }
Leaping Into Memories: Space-Time Deep Feature Synthesis-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Stergiou_2023_ICCV, author = {Stergiou, Alexandros and Deligiannis, Nikos}, title = {Leaping Into Memories: Space-Time Deep Feature Synthesis}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {1966-1976} }
WDiscOOD: Out-of-Distribution Detection via Whitened Linear Discriminant Analysis-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Chen_2023_ICCV, author = {Chen, Yiye and Lin, Yunzhi and Xu, Ruinian and Vela, Patricio A.}, title = {WDiscOOD: Out-of-Distribution Detection via Whitened Linear Discriminant Analysis}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {5298-5307} }
Boosting Few-shot Action Recognition with Graph-guided Hybrid Matching-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Xing_2023_ICCV, author = {Xing, Jiazheng and Wang, Mengmeng and Ruan, Yudi and Chen, Bofan and Guo, Yaowei and Mu, Boyu and Dai, Guang and Wang, Jingdong and Liu, Yong}, title = {Boosting Few-shot Action Recognition with Graph-guided Hybrid Matching}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {1740-1750} }
Diffusion in Style-
[pdf]
[supp]
[bibtex]@InProceedings{Everaert_2023_ICCV, author = {Everaert, Martin Nicolas and Bocchio, Marco and Arpa, Sami and S\"usstrunk, Sabine and Achanta, Radhakrishna}, title = {Diffusion in Style}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {2251-2261} }
FunnyBirds: A Synthetic Vision Dataset for a Part-Based Analysis of Explainable AI Methods-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Hesse_2023_ICCV, author = {Hesse, Robin and Schaub-Meyer, Simone and Roth, Stefan}, title = {FunnyBirds: A Synthetic Vision Dataset for a Part-Based Analysis of Explainable AI Methods}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {3981-3991} }
Deformable Neural Radiance Fields using RGB and Event Cameras-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Ma_2023_ICCV, author = {Ma, Qi and Paudel, Danda Pani and Chhatkuli, Ajad and Van Gool, Luc}, title = {Deformable Neural Radiance Fields using RGB and Event Cameras}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {3590-3600} }
BeLFusion: Latent Diffusion for Behavior-Driven Human Motion Prediction-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Barquero_2023_ICCV, author = {Barquero, German and Escalera, Sergio and Palmero, Cristina}, title = {BeLFusion: Latent Diffusion for Behavior-Driven Human Motion Prediction}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {2317-2327} }
CleanCLIP: Mitigating Data Poisoning Attacks in Multimodal Contrastive Learning-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Bansal_2023_ICCV, author = {Bansal, Hritik and Singhi, Nishad and Yang, Yu and Yin, Fan and Grover, Aditya and Chang, Kai-Wei}, title = {CleanCLIP: Mitigating Data Poisoning Attacks in Multimodal Contrastive Learning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {112-123} }
Cumulative Spatial Knowledge Distillation for Vision Transformers-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Zhao_2023_ICCV, author = {Zhao, Borui and Song, Renjie and Liang, Jiajun}, title = {Cumulative Spatial Knowledge Distillation for Vision Transformers}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {6146-6155} }
Less is More: Focus Attention for Efficient DETR-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Zheng_2023_ICCV, author = {Zheng, Dehua and Dong, Wenhui and Hu, Hailin and Chen, Xinghao and Wang, Yunhe}, title = {Less is More: Focus Attention for Efficient DETR}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {6674-6683} }
Efficient Controllable Multi-Task Architectures-
[pdf]
[arXiv]
[bibtex]@InProceedings{Aich_2023_ICCV, author = {Aich, Abhishek and Schulter, Samuel and Roy-Chowdhury, Amit K. and Chandraker, Manmohan and Suh, Yumin}, title = {Efficient Controllable Multi-Task Architectures}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {5740-5751} }
Lens Parameter Estimation for Realistic Depth of Field Modeling-
[pdf]
[supp]
[bibtex]@InProceedings{Piche-Meunier_2023_ICCV, author = {Pich\'e-Meunier, Dominique and Hold-Geoffroy, Yannick and Zhang, Jianming and Lalonde, Jean-Fran\c{c}ois}, title = {Lens Parameter Estimation for Realistic Depth of Field Modeling}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {499-508} }
Semantic-Aware Implicit Template Learning via Part Deformation Consistency-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Kim_2023_ICCV, author = {Kim, Sihyeon and Joo, Minseok and Lee, Jaewon and Ko, Juyeon and Cha, Juhan and Kim, Hyunwoo J.}, title = {Semantic-Aware Implicit Template Learning via Part Deformation Consistency}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {593-603} }
GRAM-HD: 3D-Consistent Image Generation at High Resolution with Generative Radiance Manifolds-
[pdf]
[supp]
[bibtex]@InProceedings{Xiang_2023_ICCV, author = {Xiang, Jianfeng and Yang, Jiaolong and Deng, Yu and Tong, Xin}, title = {GRAM-HD: 3D-Consistent Image Generation at High Resolution with Generative Radiance Manifolds}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {2195-2205} }
Small Object Detection via Coarse-to-fine Proposal Generation and Imitation Learning-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Yuan_2023_ICCV, author = {Yuan, Xiang and Cheng, Gong and Yan, Kebing and Zeng, Qinghua and Han, Junwei}, title = {Small Object Detection via Coarse-to-fine Proposal Generation and Imitation Learning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {6317-6327} }
Anomaly Detection Under Distribution Shift-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Cao_2023_ICCV, author = {Cao, Tri and Zhu, Jiawen and Pang, Guansong}, title = {Anomaly Detection Under Distribution Shift}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {6511-6523} }
Enhancing Privacy Preservation in Federated Learning via Learning Rate Perturbation-
[pdf]
[supp]
[bibtex]@InProceedings{Wan_2023_ICCV, author = {Wan, Guangnian and Du, Haitao and Yuan, Xuejing and Yang, Jun and Chen, Meiling and Xu, Jie}, title = {Enhancing Privacy Preservation in Federated Learning via Learning Rate Perturbation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {4772-4781} }
ImGeoNet: Image-induced Geometry-aware Voxel Representation for Multi-view 3D Object Detection-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Tu_2023_ICCV, author = {Tu, Tao and Chuang, Shun-Po and Liu, Yu-Lun and Sun, Cheng and Zhang, Ke and Roy, Donna and Kuo, Cheng-Hao and Sun, Min}, title = {ImGeoNet: Image-induced Geometry-aware Voxel Representation for Multi-view 3D Object Detection}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {6996-7007} }
Diffusion-based Image Translation with Label Guidance for Domain Adaptive Semantic Segmentation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Peng_2023_ICCV, author = {Peng, Duo and Hu, Ping and Ke, Qiuhong and Liu, Jun}, title = {Diffusion-based Image Translation with Label Guidance for Domain Adaptive Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {808-820} }
Isomer: Isomerous Transformer for Zero-shot Video Object Segmentation-
[pdf]
[arXiv]
[bibtex]@InProceedings{Yuan_2023_ICCV, author = {Yuan, Yichen and Wang, Yifan and Wang, Lijun and Zhao, Xiaoqi and Lu, Huchuan and Wang, Yu and Su, Weibo and Zhang, Lei}, title = {Isomer: Isomerous Transformer for Zero-shot Video Object Segmentation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {966-976} }
X-Mesh: Towards Fast and Accurate Text-driven 3D Stylization via Dynamic Textual Guidance-
[pdf]
[bibtex]@InProceedings{Ma_2023_ICCV, author = {Ma, Yiwei and Zhang, Xiaoqing and Sun, Xiaoshuai and Ji, Jiayi and Wang, Haowei and Jiang, Guannan and Zhuang, Weilin and Ji, Rongrong}, title = {X-Mesh: Towards Fast and Accurate Text-driven 3D Stylization via Dynamic Textual Guidance}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {2749-2760} }
ViLTA: Enhancing Vision-Language Pre-training through Textual Augmentation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Wang_2023_ICCV, author = {Wang, Weihan and Yang, Zhen and Xu, Bin and Li, Juanzi and Sun, Yankui}, title = {ViLTA: Enhancing Vision-Language Pre-training through Textual Augmentation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {3158-3169} }
Not Every Side Is Equal: Localization Uncertainty Estimation for Semi-Supervised 3D Object Detection-
[pdf]
[supp]
[bibtex]@InProceedings{Wang_2023_ICCV, author = {Wang, Chuxin and Yang, Wenfei and Zhang, Tianzhu}, title = {Not Every Side Is Equal: Localization Uncertainty Estimation for Semi-Supervised 3D Object Detection}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {3814-3824} }
Teaching CLIP to Count to Ten-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Paiss_2023_ICCV, author = {Paiss, Roni and Ephrat, Ariel and Tov, Omer and Zada, Shiran and Mosseri, Inbar and Irani, Michal and Dekel, Tali}, title = {Teaching CLIP to Count to Ten}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {3170-3180} }
Domain Generalization Guided by Gradient Signal to Noise Ratio of Parameters-
[pdf]
[supp]
[bibtex]@InProceedings{Michalkiewicz_2023_ICCV, author = {Michalkiewicz, Mateusz and Faraki, Masoud and Yu, Xiang and Chandraker, Manmohan and Baktashmotlagh, Mahsa}, title = {Domain Generalization Guided by Gradient Signal to Noise Ratio of Parameters}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {6177-6188} }
Counterfactual-based Saliency Map: Towards Visual Contrastive Explanations for Neural Networks-
[pdf]
[supp]
[bibtex]@InProceedings{Wang_2023_ICCV, author = {Wang, Xue and Wang, Zhibo and Weng, Haiqin and Guo, Hengchang and Zhang, Zhifei and Jin, Lu and Wei, Tao and Ren, Kui}, title = {Counterfactual-based Saliency Map: Towards Visual Contrastive Explanations for Neural Networks}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {2042-2051} }
MST-compression: Compressing and Accelerating Binary Neural Networks with Minimum Spanning Tree-
[pdf]
[supp]
[bibtex]@InProceedings{Vo_2023_ICCV, author = {Vo, Quang Hieu and Tran, Linh-Tam and Bae, Sung-Ho and Kim, Lok-Won and Hong, Choong Seon}, title = {MST-compression: Compressing and Accelerating Binary Neural Networks with Minimum Spanning Tree}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {6091-6100} }
IIEU: Rethinking Neural Feature Activation from Decision-Making-
[pdf]
[supp]
[bibtex]@InProceedings{Cai_2023_ICCV, author = {Cai, Sudong}, title = {IIEU: Rethinking Neural Feature Activation from Decision-Making}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {5796-5806} }
Integrally Migrating Pre-trained Transformer Encoder-decoders for Visual Object Detection-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Liu_2023_ICCV, author = {Liu, Feng and Zhang, Xiaosong and Peng, Zhiliang and Guo, Zonghao and Wan, Fang and Ji, Xiangyang and Ye, Qixiang}, title = {Integrally Migrating Pre-trained Transformer Encoder-decoders for Visual Object Detection}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {6825-6834} }
V-FUSE: Volumetric Depth Map Fusion with Long-Range Constraints-
[pdf]
[supp]
[bibtex]@InProceedings{Burgdorfer_2023_ICCV, author = {Burgdorfer, Nathaniel and Mordohai, Philippos}, title = {V-FUSE: Volumetric Depth Map Fusion with Long-Range Constraints}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {3449-3458} }
GECCO: Geometrically-Conditioned Point Diffusion Models-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Tyszkiewicz_2023_ICCV, author = {Tyszkiewicz, Micha{\l} J and Fua, Pascal and Trulls, Eduard}, title = {GECCO: Geometrically-Conditioned Point Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {2128-2138} }
PETRv2: A Unified Framework for 3D Perception from Multi-Camera Images-
[pdf]
[arXiv]
[bibtex]@InProceedings{Liu_2023_ICCV, author = {Liu, Yingfei and Yan, Junjie and Jia, Fan and Li, Shuailin and Gao, Aqi and Wang, Tiancai and Zhang, Xiangyu}, title = {PETRv2: A Unified Framework for 3D Perception from Multi-Camera Images}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {3262-3272} }
Out-of-Domain GAN Inversion via Invertibility Decomposition for Photo-Realistic Human Face Manipulation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Yang_2023_ICCV, author = {Yang, Xin and XU, Xiaogang and Chen, Yingcong}, title = {Out-of-Domain GAN Inversion via Invertibility Decomposition for Photo-Realistic Human Face Manipulation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {7492-7501} }
Learning Trajectory-Word Alignments for Video-Language Tasks-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Yang_2023_ICCV, author = {Yang, Xu and Li, Zhangzikang and Xu, Haiyang and Zhang, Hanwang and Ye, Qinghao and Li, Chenliang and Yan, Ming and Zhang, Yu and Huang, Fei and Huang, Songfang}, title = {Learning Trajectory-Word Alignments for Video-Language Tasks}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {2504-2514} }
Geometry-guided Feature Learning and Fusion for Indoor Scene Reconstruction-
[pdf]
[supp]
[bibtex]@InProceedings{Yin_2023_ICCV, author = {Yin, Ruihong and Karaoglu, Sezer and Gevers, Theo}, title = {Geometry-guided Feature Learning and Fusion for Indoor Scene Reconstruction}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {3652-3661} }
Atmospheric Transmission and Thermal Inertia Induced Blind Road Segmentation with a Large-Scale Dataset TBRSD-
[pdf]
[supp]
[bibtex]@InProceedings{Chen_2023_ICCV, author = {Chen, Junzhang and Bai, Xiangzhi}, title = {Atmospheric Transmission and Thermal Inertia Induced Blind Road Segmentation with a Large-Scale Dataset TBRSD}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {1053-1063} }
Efficient-VQGAN: Towards High-Resolution Image Generation with Efficient Vision Transformers-
[pdf]
[bibtex]@InProceedings{Cao_2023_ICCV, author = {Cao, Shiyue and Yin, Yueqin and Huang, Lianghua and Liu, Yu and Zhao, Xin and Zhao, Deli and Huang, Kaigi}, title = {Efficient-VQGAN: Towards High-Resolution Image Generation with Efficient Vision Transformers}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {7368-7377} }
Towards Fair and Comprehensive Comparisons for Image-Based 3D Object Detection-
[pdf]
[supp]
[bibtex]@InProceedings{Ma_2023_ICCV, author = {Ma, Xinzhu and Wang, Yongtao and Zhang, Yinmin and Xia, Zhiyi and Meng, Yuan and Wang, Zhihui and Li, Haojie and Ouyang, Wanli}, title = {Towards Fair and Comprehensive Comparisons for Image-Based 3D Object Detection}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {6425-6435} }
Random Boxes Are Open-world Object Detectors-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Wang_2023_ICCV, author = {Wang, Yanghao and Yue, Zhongqi and Hua, Xian-Sheng and Zhang, Hanwang}, title = {Random Boxes Are Open-world Object Detectors}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {6233-6243} }
DiffDreamer: Towards Consistent Unsupervised Single-view Scene Extrapolation with Conditional Diffusion Models-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Cai_2023_ICCV, author = {Cai, Shengqu and Chan, Eric Ryan and Peng, Songyou and Shahbazi, Mohamad and Obukhov, Anton and Van Gool, Luc and Wetzstein, Gordon}, title = {DiffDreamer: Towards Consistent Unsupervised Single-view Scene Extrapolation with Conditional Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {2139-2150} }
Enhancing Adversarial Robustness in Low-Label Regime via Adaptively Weighted Regularization and Knowledge Distillation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Yang_2023_ICCV, author = {Yang, Dongyoon and Kong, Insung and Kim, Yongdai}, title = {Enhancing Adversarial Robustness in Low-Label Regime via Adaptively Weighted Regularization and Knowledge Distillation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {4552-4561} }
MIMO-NeRF: Fast Neural Rendering with Multi-input Multi-output Neural Radiance Fields-
[pdf]
[supp]
[bibtex]@InProceedings{Kaneko_2023_ICCV, author = {Kaneko, Takuhiro}, title = {MIMO-NeRF: Fast Neural Rendering with Multi-input Multi-output Neural Radiance Fields}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {3273-3283} }
Instance Neural Radiance Field-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Liu_2023_ICCV, author = {Liu, Yichen and Hu, Benran and Huang, Junkai and Tai, Yu-Wing and Tang, Chi-Keung}, title = {Instance Neural Radiance Field}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {787-796} }
One-bit Flip is All You Need: When Bit-flip Attack Meets Model Training-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Dong_2023_ICCV, author = {Dong, Jianshuo and Qiu, Han and Li, Yiming and Zhang, Tianwei and Li, Yuanjie and Lai, Zeqi and Zhang, Chao and Xia, Shu-Tao}, title = {One-bit Flip is All You Need: When Bit-flip Attack Meets Model Training}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {4688-4698} }
Improving CLIP Fine-tuning Performance-
[pdf]
[supp]
[bibtex]@InProceedings{Wei_2023_ICCV, author = {Wei, Yixuan and Hu, Han and Xie, Zhenda and Liu, Ze and Zhang, Zheng and Cao, Yue and Bao, Jianmin and Chen, Dong and Guo, Baining}, title = {Improving CLIP Fine-tuning Performance}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {5439-5449} }
The Power of Sound (TPoS): Audio Reactive Video Generation with Stable Diffusion-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Jeong_2023_ICCV, author = {Jeong, Yujin and Ryoo, Wonjeong and Lee, Seunghyun and Seo, Dabin and Byeon, Wonmin and Kim, Sangpil and Kim, Jinkyu}, title = {The Power of Sound (TPoS): Audio Reactive Video Generation with Stable Diffusion}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {7822-7832} }
DINAR: Diffusion Inpainting of Neural Textures for One-Shot Human Avatars-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Svitov_2023_ICCV, author = {Svitov, David and Gudkov, Dmitrii and Bashirov, Renat and Lempitsky, Victor}, title = {DINAR: Diffusion Inpainting of Neural Textures for One-Shot Human Avatars}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {7062-7072} }
ElasticViT: Conflict-aware Supernet Training for Deploying Fast Vision Transformer on Diverse Mobile Devices-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Tang_2023_ICCV, author = {Tang, Chen and Zhang, Li Lyna and Jiang, Huiqiang and Xu, Jiahang and Cao, Ting and Zhang, Quanlu and Yang, Yuqing and Wang, Zhi and Yang, Mao}, title = {ElasticViT: Conflict-aware Supernet Training for Deploying Fast Vision Transformer on Diverse Mobile Devices}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {5829-5840} }
Noise-Aware Learning from Web-Crawled Image-Text Data for Image Captioning-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Kang_2023_ICCV, author = {Kang, Wooyoung and Mun, Jonghwan and Lee, Sungjun and Roh, Byungseok}, title = {Noise-Aware Learning from Web-Crawled Image-Text Data for Image Captioning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {2942-2952} }
Detecting Objects with Context-Likelihood Graphs and Graph Refinement-
[pdf]
[bibtex]@InProceedings{Bhowmik_2023_ICCV, author = {Bhowmik, Aritra and Wang, Yu and Baka, Nora and Oswald, Martin R. and Snoek, Cees G. M.}, title = {Detecting Objects with Context-Likelihood Graphs and Graph Refinement}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {6524-6533} }
Coarse-to-Fine Amodal Segmentation with Shape Prior-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Gao_2023_ICCV, author = {Gao, Jianxiong and Qian, Xuelin and Wang, Yikai and Xiao, Tianjun and He, Tong and Zhang, Zheng and Fu, Yanwei}, title = {Coarse-to-Fine Amodal Segmentation with Shape Prior}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {1262-1271} }
AdVerb: Visually Guided Audio Dereverberation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Chowdhury_2023_ICCV, author = {Chowdhury, Sanjoy and Ghosh, Sreyan and Dasgupta, Subhrajyoti and Ratnarajah, Anton and Tyagi, Utkarsh and Manocha, Dinesh}, title = {AdVerb: Visually Guided Audio Dereverberation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {7884-7896} }
Open-vocabulary Object Segmentation with Diffusion Models-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Li_2023_ICCV, author = {Li, Ziyi and Zhou, Qinye and Zhang, Xiaoyun and Zhang, Ya and Wang, Yanfeng and Xie, Weidi}, title = {Open-vocabulary Object Segmentation with Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {7667-7676} }
With a Little Help from Your Own Past: Prototypical Memory Networks for Image Captioning-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Barraco_2023_ICCV, author = {Barraco, Manuele and Sarto, Sara and Cornia, Marcella and Baraldi, Lorenzo and Cucchiara, Rita}, title = {With a Little Help from Your Own Past: Prototypical Memory Networks for Image Captioning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {3021-3031} }
PDiscoNet: Semantically consistent part discovery for fine-grained recognition-
[pdf]
[arXiv]
[bibtex]@InProceedings{van_der_Klis_2023_ICCV, author = {van der Klis, Robert and Alaniz, Stephan and Mancini, Massimiliano and Dantas, Cassio F. and Ienco, Dino and Akata, Zeynep and Marcos, Diego}, title = {PDiscoNet: Semantically consistent part discovery for fine-grained recognition}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {1866-1876} }
How to Choose your Best Allies for a Transferable Attack?-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Maho_2023_ICCV, author = {Maho, Thibault and Moosavi-Dezfooli, Seyed-Mohsen and Furon, Teddy}, title = {How to Choose your Best Allies for a Transferable Attack?}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {4542-4551} }
Self-Supervised Object Detection from Egocentric Videos-
[pdf]
[supp]
[bibtex]@InProceedings{Akiva_2023_ICCV, author = {Akiva, Peri and Huang, Jing and Liang, Kevin J and Kovvuri, Rama and Chen, Xingyu and Feiszli, Matt and Dana, Kristin and Hassner, Tal}, title = {Self-Supervised Object Detection from Egocentric Videos}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {5225-5237} }
Cross Contrasting Feature Perturbation for Domain Generalization-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Li_2023_ICCV, author = {Li, Chenming and Zhang, Daoan and Huang, Wenjian and Zhang, Jianguo}, title = {Cross Contrasting Feature Perturbation for Domain Generalization}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {1327-1337} }
DiffusionRet: Generative Text-Video Retrieval with Diffusion Model-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Jin_2023_ICCV, author = {Jin, Peng and Li, Hao and Cheng, Zesen and Li, Kehan and Ji, Xiangyang and Liu, Chang and Yuan, Li and Chen, Jie}, title = {DiffusionRet: Generative Text-Video Retrieval with Diffusion Model}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {2470-2481} }
Adversarial Finetuning with Latent Representation Constraint to Mitigate Accuracy-Robustness Tradeoff-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Suzuki_2023_ICCV, author = {Suzuki, Satoshi and Yamaguchi, Shin'ya and Takeda, Shoichiro and Kanai, Sekitoshi and Makishima, Naoki and Ando, Atsushi and Masumura, Ryo}, title = {Adversarial Finetuning with Latent Representation Constraint to Mitigate Accuracy-Robustness Tradeoff}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {4390-4401} }
MULLER: Multilayer Laplacian Resizer for Vision-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Tu_2023_ICCV, author = {Tu, Zhengzhong and Milanfar, Peyman and Talebi, Hossein}, title = {MULLER: Multilayer Laplacian Resizer for Vision}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {6877-6887} }
X-VoE: Measuring eXplanatory Violation of Expectation in Physical Events-
[pdf]
[supp]
[bibtex]@InProceedings{Dai_2023_ICCV, author = {Dai, Bo and Wang, Linge and Jia, Baoxiong and Zhang, Zeyu and Zhu, Song-Chun and Zhang, Chi and Zhu, Yixin}, title = {X-VoE: Measuring eXplanatory Violation of Expectation in Physical Events}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {3992-4002} }
COOP: Decoupling and Coupling of Whole-Body Grasping Pose Generation-
[pdf]
[bibtex]@InProceedings{Zheng_2023_ICCV, author = {Zheng, Yanzhao and Shi, Yunzhou and Cui, Yuhao and Zhao, Zhongzhou and Luo, Zhiling and Zhou, Wei}, title = {COOP: Decoupling and Coupling of Whole-Body Grasping Pose Generation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {2163-2173} }
Model Calibration in Dense Classification with Adaptive Label Perturbation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Liu_2023_ICCV, author = {Liu, Jiawei and Ye, Changkun and Wang, Shan and Cui, Ruikai and Zhang, Jing and Zhang, Kaihao and Barnes, Nick}, title = {Model Calibration in Dense Classification with Adaptive Label Perturbation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {1173-1184} }
Semantic Information in Contrastive Learning-
[pdf]
[supp]
[bibtex]@InProceedings{Quan_2023_ICCV, author = {Quan, Shengjiang and Hirano, Masahiro and Yamakawa, Yuji}, title = {Semantic Information in Contrastive Learning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {5686-5696} }
Structure and Content-Guided Video Synthesis with Diffusion Models-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Esser_2023_ICCV, author = {Esser, Patrick and Chiu, Johnathan and Atighehchian, Parmida and Granskog, Jonathan and Germanidis, Anastasis}, title = {Structure and Content-Guided Video Synthesis with Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {7346-7356} }
Beyond Skin Tone: A Multidimensional Measure of Apparent Skin Color-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Thong_2023_ICCV, author = {Thong, William and Joniak, Przemyslaw and Xiang, Alice}, title = {Beyond Skin Tone: A Multidimensional Measure of Apparent Skin Color}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {4903-4913} }
NeILF++: Inter-Reflectable Light Fields for Geometry and Material Estimation-
[pdf]
[supp]
[bibtex]@InProceedings{Zhang_2023_ICCV, author = {Zhang, Jingyang and Yao, Yao and Li, Shiwei and Liu, Jingbo and Fang, Tian and McKinnon, David and Tsin, Yanghai and Quan, Long}, title = {NeILF++: Inter-Reflectable Light Fields for Geometry and Material Estimation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {3601-3610} }
MAGI: Multi-Annotated Explanation-Guided Learning-
[pdf]
[bibtex]@InProceedings{Zhang_2023_ICCV, author = {Zhang, Yifei and Gu, Siyi and Gao, Yuyang and Pan, Bo and Yang, Xiaofeng and Zhao, Liang}, title = {MAGI: Multi-Annotated Explanation-Guided Learning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {1977-1987} }
Adaptive Positional Encoding for Bundle-Adjusting Neural Radiance Fields-
[pdf]
[bibtex]@InProceedings{Gao_2023_ICCV, author = {Gao, Zelin and Dai, Weichen and Zhang, Yu}, title = {Adaptive Positional Encoding for Bundle-Adjusting Neural Radiance Fields}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {3284-3294} }
Inducing Neural Collapse to a Fixed Hierarchy-Aware Frame for Reducing Mistake Severity-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Liang_2023_ICCV, author = {Liang, Tong and Davis, Jim}, title = {Inducing Neural Collapse to a Fixed Hierarchy-Aware Frame for Reducing Mistake Severity}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {1443-1452} }
Factorized Inverse Path Tracing for Efficient and Accurate Material-Lighting Estimation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Wu_2023_ICCV, author = {Wu, Liwen and Zhu, Rui and Yaldiz, Mustafa B. and Zhu, Yinhao and Cai, Hong and Matai, Janarbek and Porikli, Fatih and Li, Tzu-Mao and Chandraker, Manmohan and Ramamoorthi, Ravi}, title = {Factorized Inverse Path Tracing for Efficient and Accurate Material-Lighting Estimation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {3848-3858} }
Overwriting Pretrained Bias with Finetuning Data-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Wang_2023_ICCV, author = {Wang, Angelina and Russakovsky, Olga}, title = {Overwriting Pretrained Bias with Finetuning Data}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {3957-3968} }
Anti-DreamBooth: Protecting Users from Personalized Text-to-image Synthesis-
[pdf]
[supp]
[bibtex]@InProceedings{Van_Le_2023_ICCV, author = {Van Le, Thanh and Phung, Hao and Nguyen, Thuan Hoang and Dao, Quan and Tran, Ngoc N. and Tran, Anh}, title = {Anti-DreamBooth: Protecting Users from Personalized Text-to-image Synthesis}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {2116-2127} }
Contrastive Continuity on Augmentation Stability Rehearsal for Continual Self-Supervised Learning-
[pdf]
[supp]
[bibtex]@InProceedings{Cheng_2023_ICCV, author = {Cheng, Haoyang and Wen, Haitao and Zhang, Xiaoliang and Qiu, Heqian and Wang, Lanxiao and Li, Hongliang}, title = {Contrastive Continuity on Augmentation Stability Rehearsal for Continual Self-Supervised Learning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {5707-5717} }
Treating Pseudo-labels Generation as Image Matting for Weakly Supervised Semantic Segmentation-
[pdf]
[supp]
[bibtex]@InProceedings{Wang_2023_ICCV, author = {Wang, Changwei and Xu, Rongtao and Xu, Shibiao and Meng, Weiliang and Zhang, Xiaopeng}, title = {Treating Pseudo-labels Generation as Image Matting for Weakly Supervised Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {755-765} }
UMFuse: Unified Multi View Fusion for Human Editing Applications-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Jain_2023_ICCV, author = {Jain, Rishabh and Hemani, Mayur and Ceylan, Duygu and Singh, Krishna Kumar and Lu, Jingwan and Sarkar, Mausoom and Krishnamurthy, Balaji}, title = {UMFuse: Unified Multi View Fusion for Human Editing Applications}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {7182-7191} }
CROSSFIRE: Camera Relocalization On Self-Supervised Features from an Implicit Representation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Moreau_2023_ICCV, author = {Moreau, Arthur and Piasco, Nathan and Bennehar, Moussab and Tsishkou, Dzmitry and Stanciulescu, Bogdan and de La Fortelle, Arnaud}, title = {CROSSFIRE: Camera Relocalization On Self-Supervised Features from an Implicit Representation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {252-262} }
Unmasking Anomalies in Road-Scene Segmentation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Rai_2023_ICCV, author = {Rai, Shyam Nandan and Cermelli, Fabio and Fontanel, Dario and Masone, Carlo and Caputo, Barbara}, title = {Unmasking Anomalies in Road-Scene Segmentation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {4037-4046} }
Self-Calibrated Cross Attention Network for Few-Shot Segmentation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Xu_2023_ICCV, author = {Xu, Qianxiong and Zhao, Wenting and Lin, Guosheng and Long, Cheng}, title = {Self-Calibrated Cross Attention Network for Few-Shot Segmentation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {655-665} }
Learning Global-aware Kernel for Image Harmonization-
[pdf]
[arXiv]
[bibtex]@InProceedings{Shen_2023_ICCV, author = {Shen, Xintian and Zhang, Jiangning and Chen, Jun and Bai, Shipeng and Han, Yue and Wang, Yabiao and Wang, Chengjie and Liu, Yong}, title = {Learning Global-aware Kernel for Image Harmonization}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {7535-7544} }
Chordal Averaging on Flag Manifolds and Its Applications-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Mankovich_2023_ICCV, author = {Mankovich, Nathan and Birdal, Tolga}, title = {Chordal Averaging on Flag Manifolds and Its Applications}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {3881-3890} }
Towards Building More Robust Models with Frequency Bias-
[pdf]
[arXiv]
[bibtex]@InProceedings{Bu_2023_ICCV, author = {Bu, Qingwen and Huang, Dong and Cui, Heming}, title = {Towards Building More Robust Models with Frequency Bias}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {4402-4411} }
PolicyCleanse: Backdoor Detection and Mitigation for Competitive Reinforcement Learning-
[pdf]
[supp]
[bibtex]@InProceedings{Guo_2023_ICCV, author = {Guo, Junfeng and Li, Ang and Wang, Lixu and Liu, Cong}, title = {PolicyCleanse: Backdoor Detection and Mitigation for Competitive Reinforcement Learning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {4699-4708} }
Ref-NeuS: Ambiguity-Reduced Neural Implicit Surface Learning for Multi-View Reconstruction with Reflection-
[pdf]
[supp]
[bibtex]@InProceedings{Ge_2023_ICCV, author = {Ge, Wenhang and Hu, Tao and Zhao, Haoyu and Liu, Shu and Chen, Ying-Cong}, title = {Ref-NeuS: Ambiguity-Reduced Neural Implicit Surface Learning for Multi-View Reconstruction with Reflection}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {4251-4260} }
Class-incremental Continual Learning for Instance Segmentation with Image-level Weak Supervision-
[pdf]
[supp]
[bibtex]@InProceedings{Hsieh_2023_ICCV, author = {Hsieh, Yu-Hsing and Chen, Guan-Sheng and Cai, Shun-Xian and Wei, Ting-Yun and Yang, Huei-Fang and Chen, Chu-Song}, title = {Class-incremental Continual Learning for Instance Segmentation with Image-level Weak Supervision}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {1250-1261} }
When Prompt-based Incremental Learning Does Not Meet Strong Pretraining-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Tang_2023_ICCV, author = {Tang, Yu-Ming and Peng, Yi-Xing and Zheng, Wei-Shi}, title = {When Prompt-based Incremental Learning Does Not Meet Strong Pretraining}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {1706-1716} }
Exploring Transformers for Open-world Instance Segmentation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Wu_2023_ICCV, author = {Wu, Jiannan and Jiang, Yi and Yan, Bin and Lu, Huchuan and Yuan, Zehuan and Luo, Ping}, title = {Exploring Transformers for Open-world Instance Segmentation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {6611-6621} }
SSF: Accelerating Training of Spiking Neural Networks with Stabilized Spiking Flow-
[pdf]
[supp]
[bibtex]@InProceedings{Wang_2023_ICCV, author = {Wang, Jingtao and Song, Zengjie and Wang, Yuxi and Xiao, Jun and Yang, Yuran and Mei, Shuqi and Zhang, Zhaoxiang}, title = {SSF: Accelerating Training of Spiking Neural Networks with Stabilized Spiking Flow}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {5982-5991} }
Manipulate by Seeing: Creating Manipulation Controllers from Pre-Trained Representations-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Wang_2023_ICCV, author = {Wang, Jianren and Dasari, Sudeep and Srirama, Mohan Kumar and Tulsiani, Shubham and Gupta, Abhinav}, title = {Manipulate by Seeing: Creating Manipulation Controllers from Pre-Trained Representations}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {3859-3868} }
Learning Human-Human Interactions in Images from Weak Textual Supervision-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Alper_2023_ICCV, author = {Alper, Morris and Averbuch-Elor, Hadar}, title = {Learning Human-Human Interactions in Images from Weak Textual Supervision}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {2887-2899} }
Prototype Reminiscence and Augmented Asymmetric Knowledge Aggregation for Non-Exemplar Class-Incremental Learning-
[pdf]
[supp]
[bibtex]@InProceedings{Shi_2023_ICCV, author = {Shi, Wuxuan and Ye, Mang}, title = {Prototype Reminiscence and Augmented Asymmetric Knowledge Aggregation for Non-Exemplar Class-Incremental Learning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {1772-1781} }
Exemplar-Free Continual Transformer with Convolutions-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Roy_2023_ICCV, author = {Roy, Anurag and Verma, Vinay K. and Voonna, Sravan and Ghosh, Kripabandhu and Ghosh, Saptarshi and Das, Abir}, title = {Exemplar-Free Continual Transformer with Convolutions}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {5897-5907} }
Efficient Decision-based Black-box Patch Attacks on Video Recognition-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Jiang_2023_ICCV, author = {Jiang, Kaixun and Chen, Zhaoyu and Huang, Hao and Wang, Jiafeng and Yang, Dingkang and Li, Bo and Wang, Yan and Zhang, Wenqiang}, title = {Efficient Decision-based Black-box Patch Attacks on Video Recognition}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {4379-4389} }
MetaGCD: Learning to Continually Learn in Generalized Category Discovery-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Wu_2023_ICCV, author = {Wu, Yanan and Chi, Zhixiang and Wang, Yang and Feng, Songhe}, title = {MetaGCD: Learning to Continually Learn in Generalized Category Discovery}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {1655-1665} }
Strip-MLP: Efficient Token Interaction for Vision MLP-
[pdf]
[bibtex]@InProceedings{Cao_2023_ICCV, author = {Cao, Guiping and Luo, Shengda and Huang, Wenjian and Lan, Xiangyuan and Jiang, Dongmei and Wang, Yaowei and Zhang, Jianguo}, title = {Strip-MLP: Efficient Token Interaction for Vision MLP}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {1494-1504} }
SAFARI: Versatile and Efficient Evaluations for Robustness of Interpretability-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Huang_2023_ICCV, author = {Huang, Wei and Zhao, Xingyu and Jin, Gaojie and Huang, Xiaowei}, title = {SAFARI: Versatile and Efficient Evaluations for Robustness of Interpretability}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {1988-1998} }
Combating Noisy Labels with Sample Selection by Mining High-Discrepancy Examples-
[pdf]
[supp]
[bibtex]@InProceedings{Xia_2023_ICCV, author = {Xia, Xiaobo and Han, Bo and Zhan, Yibing and Yu, Jun and Gong, Mingming and Gong, Chen and Liu, Tongliang}, title = {Combating Noisy Labels with Sample Selection by Mining High-Discrepancy Examples}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {1833-1843} }
What can Discriminator do? Towards Box-free Ownership Verification of Generative Adversarial Networks-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Huang_2023_ICCV, author = {Huang, Ziheng and Li, Boheng and Cai, Yan and Wang, Run and Guo, Shangwei and Fang, Liming and Chen, Jing and Wang, Lina}, title = {What can Discriminator do? Towards Box-free Ownership Verification of Generative Adversarial Networks}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {5009-5019} }
An Adaptive Model Ensemble Adversarial Attack for Boosting Adversarial Transferability-
[pdf]
[arXiv]
[bibtex]@InProceedings{Chen_2023_ICCV, author = {Chen, Bin and Yin, Jiali and Chen, Shukai and Chen, Bohao and Liu, Ximeng}, title = {An Adaptive Model Ensemble Adversarial Attack for Boosting Adversarial Transferability}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {4489-4498} }
3D-VisTA: Pre-trained Transformer for 3D Vision and Text Alignment-
[pdf]
[supp]
[bibtex]@InProceedings{Zhu_2023_ICCV, author = {Zhu, Ziyu and Ma, Xiaojian and Chen, Yixin and Deng, Zhidong and Huang, Siyuan and Li, Qing}, title = {3D-VisTA: Pre-trained Transformer for 3D Vision and Text Alignment}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {2911-2921} }
SparseDet: Improving Sparsely Annotated Object Detection with Pseudo-positive Mining-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Suri_2023_ICCV, author = {Suri, Saksham and Rambhatla, Saketh and Chellappa, Rama and Shrivastava, Abhinav}, title = {SparseDet: Improving Sparsely Annotated Object Detection with Pseudo-positive Mining}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {6770-6781} }
Among Us: Adversarially Robust Collaborative Perception by Consensus-
[pdf]
[arXiv]
[bibtex]@InProceedings{Li_2023_ICCV, author = {Li, Yiming and Fang, Qi and Bai, Jiamu and Chen, Siheng and Juefei-Xu, Felix and Feng, Chen}, title = {Among Us: Adversarially Robust Collaborative Perception by Consensus}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {186-195} }
BUS: Efficient and Effective Vision-Language Pre-Training with Bottom-Up Patch Summarization.-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Jiang_2023_ICCV, author = {Jiang, Chaoya and Xu, Haiyang and Ye, Wei and Ye, Qinghao and Li, Chenliang and Yan, Ming and Bi, Bin and Zhang, Shikun and Huang, Fei and Huang, Songfang}, title = {BUS: Efficient and Effective Vision-Language Pre-Training with Bottom-Up Patch Summarization.}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {2900-2910} }
SegPrompt: Boosting Open-World Segmentation via Category-Level Prompt Learning-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Zhu_2023_ICCV, author = {Zhu, Muzhi and Li, Hengtao and Chen, Hao and Fan, Chengxiang and Mao, Weian and Jing, Chenchen and Liu, Yifan and Shen, Chunhua}, title = {SegPrompt: Boosting Open-World Segmentation via Category-Level Prompt Learning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {999-1008} }
CL-MVSNet: Unsupervised Multi-View Stereo with Dual-Level Contrastive Learning-
[pdf]
[supp]
[bibtex]@InProceedings{Xiong_2023_ICCV, author = {Xiong, Kaiqiang and Peng, Rui and Zhang, Zhe and Feng, Tianxing and Jiao, Jianbo and Gao, Feng and Wang, Ronggang}, title = {CL-MVSNet: Unsupervised Multi-View Stereo with Dual-Level Contrastive Learning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {3769-3780} }
TF-ICON: Diffusion-Based Training-Free Cross-Domain Image Composition-
[pdf]
[supp]
[bibtex]@InProceedings{Lu_2023_ICCV, author = {Lu, Shilin and Liu, Yanzhu and Kong, Adams Wai-Kin}, title = {TF-ICON: Diffusion-Based Training-Free Cross-Domain Image Composition}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {2294-2305} }
Landscape Learning for Neural Network Inversion-
[pdf]
[arXiv]
[bibtex]@InProceedings{Liu_2023_ICCV, author = {Liu, Ruoshi and Mao, Chengzhi and Tendulkar, Purva and Wang, Hao and Vondrick, Carl}, title = {Landscape Learning for Neural Network Inversion}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {2239-2250} }
PPR: Physically Plausible Reconstruction from Monocular Videos-
[pdf]
[supp]
[bibtex]@InProceedings{Yang_2023_ICCV, author = {Yang, Gengshan and Yang, Shuo and Zhang, John Z. and Manchester, Zachary and Ramanan, Deva}, title = {PPR: Physically Plausible Reconstruction from Monocular Videos}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {3914-3924} }
Robust Heterogeneous Federated Learning under Data Corruption-
[pdf]
[supp]
[bibtex]@InProceedings{Fang_2023_ICCV, author = {Fang, Xiuwen and Ye, Mang and Yang, Xiyuan}, title = {Robust Heterogeneous Federated Learning under Data Corruption}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {5020-5030} }
Cyclic-Bootstrap Labeling for Weakly Supervised Object Detection-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Yin_2023_ICCV, author = {Yin, Yufei and Deng, Jiajun and Zhou, Wengang and Li, Li and Li, Houqiang}, title = {Cyclic-Bootstrap Labeling for Weakly Supervised Object Detection}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {7008-7018} }
Tangent Sampson Error: Fast Approximate Two-view Reprojection Error for Central Camera Models-
[pdf]
[supp]
[bibtex]@InProceedings{Terekhov_2023_ICCV, author = {Terekhov, Mikhail and Larsson, Viktor}, title = {Tangent Sampson Error: Fast Approximate Two-view Reprojection Error for Central Camera Models}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {3370-3378} }
MPCViT: Searching for Accurate and Efficient MPC-Friendly Vision Transformer with Heterogeneous Attention-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Zeng_2023_ICCV, author = {Zeng, Wenxuan and Li, Meng and Xiong, Wenjie and Tong, Tong and Lu, Wen-jie and Tan, Jin and Wang, Runsheng and Huang, Ru}, title = {MPCViT: Searching for Accurate and Efficient MPC-Friendly Vision Transformer with Heterogeneous Attention}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {5052-5063} }
Masked Spiking Transformer-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Wang_2023_ICCV, author = {Wang, Ziqing and Fang, Yuetong and Cao, Jiahang and Zhang, Qiang and Wang, Zhongrui and Xu, Renjing}, title = {Masked Spiking Transformer}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {1761-1771} }
Joint Implicit Neural Representation for High-fidelity and Compact Vector Fonts-
[pdf]
[supp]
[bibtex]@InProceedings{Chen_2023_ICCV, author = {Chen, Chia-Hao and Liu, Ying-Tian and Zhang, Zhifei and Guo, Yuan-Chen and Zhang, Song-Hai}, title = {Joint Implicit Neural Representation for High-fidelity and Compact Vector Fonts}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {5538-5548} }
Neural Characteristic Function Learning for Conditional Image Generation-
[pdf]
[supp]
[bibtex]@InProceedings{Li_2023_ICCV, author = {Li, Shengxi and Zhang, Jialu and Li, Yifei and Xu, Mai and Deng, Xin and Li, Li}, title = {Neural Characteristic Function Learning for Conditional Image Generation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {7204-7214} }
Holistic Label Correction for Noisy Multi-Label Classification-
[pdf]
[supp]
[bibtex]@InProceedings{Xia_2023_ICCV, author = {Xia, Xiaobo and Deng, Jiankang and Bao, Wei and Du, Yuxuan and Han, Bo and Shan, Shiguang and Liu, Tongliang}, title = {Holistic Label Correction for Noisy Multi-Label Classification}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {1483-1493} }
Unified Data-Free Compression: Pruning and Quantization without Fine-Tuning-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Bai_2023_ICCV, author = {Bai, Shipeng and Chen, Jun and Shen, Xintian and Qian, Yixuan and Liu, Yong}, title = {Unified Data-Free Compression: Pruning and Quantization without Fine-Tuning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {5876-5885} }
Temporal Enhanced Training of Multi-view 3D Object Detector via Historical Object Prediction-
[pdf]
[arXiv]
[bibtex]@InProceedings{Zong_2023_ICCV, author = {Zong, Zhuofan and Jiang, Dongzhi and Song, Guanglu and Xue, Zeyue and Su, Jingyong and Li, Hongsheng and Liu, Yu}, title = {Temporal Enhanced Training of Multi-view 3D Object Detector via Historical Object Prediction}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {3781-3790} }
PARIS: Part-level Reconstruction and Motion Analysis for Articulated Objects-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Liu_2023_ICCV, author = {Liu, Jiayi and Mahdavi-Amiri, Ali and Savva, Manolis}, title = {PARIS: Part-level Reconstruction and Motion Analysis for Articulated Objects}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {352-363} }
OnlineRefer: A Simple Online Baseline for Referring Video Object Segmentation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Wu_2023_ICCV, author = {Wu, Dongming and Wang, Tiancai and Zhang, Yuang and Zhang, Xiangyu and Shen, Jianbing}, title = {OnlineRefer: A Simple Online Baseline for Referring Video Object Segmentation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {2761-2770} }
Environment Agnostic Representation for Visual Reinforcement Learning-
[pdf]
[supp]
[bibtex]@InProceedings{Choi_2023_ICCV, author = {Choi, Hyesong and Lee, Hunsang and Jeong, Seongwon and Min, Dongbo}, title = {Environment Agnostic Representation for Visual Reinforcement Learning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {263-273} }
Mimic3D: Thriving 3D-Aware GANs via 3D-to-2D Imitation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Chen_2023_ICCV, author = {Chen, Xingyu and Deng, Yu and Wang, Baoyuan}, title = {Mimic3D: Thriving 3D-Aware GANs via 3D-to-2D Imitation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {2338-2348} }
Does Physical Adversarial Example Really Matter to Autonomous Driving? Towards System-Level Effect of Adversarial Object Evasion Attack-
[pdf]
[arXiv]
[bibtex]@InProceedings{Wang_2023_ICCV, author = {Wang, Ningfei and Luo, Yunpeng and Sato, Takami and Xu, Kaidi and Chen, Qi Alfred}, title = {Does Physical Adversarial Example Really Matter to Autonomous Driving? Towards System-Level Effect of Adversarial Object Evasion Attack}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {4412-4423} }
Generalizable Neural Fields as Partially Observed Neural Processes-
[pdf]
[arXiv]
[bibtex]@InProceedings{Gu_2023_ICCV, author = {Gu, Jeffrey and Wang, Kuan-Chieh and Yeung, Serena}, title = {Generalizable Neural Fields as Partially Observed Neural Processes}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {5330-5339} }
Adding Conditional Control to Text-to-Image Diffusion Models-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Zhang_2023_ICCV, author = {Zhang, Lvmin and Rao, Anyi and Agrawala, Maneesh}, title = {Adding Conditional Control to Text-to-Image Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {3836-3847} }
3D Instance Segmentation via Enhanced Spatial and Semantic Supervision-
[pdf]
[bibtex]@InProceedings{Al_Khatib_2023_ICCV, author = {Al Khatib, Salwa and El Amine Boudjoghra, Mohamed and Lahoud, Jean and Khan, Fahad Shahbaz}, title = {3D Instance Segmentation via Enhanced Spatial and Semantic Supervision}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {541-550} }
Unleashing Text-to-Image Diffusion Models for Visual Perception-
[pdf]
[arXiv]
[bibtex]@InProceedings{Zhao_2023_ICCV, author = {Zhao, Wenliang and Rao, Yongming and Liu, Zuyan and Liu, Benlin and Zhou, Jie and Lu, Jiwen}, title = {Unleashing Text-to-Image Diffusion Models for Visual Perception}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {5729-5739} }
Transferable Adversarial Attack for Both Vision Transformers and Convolutional Networks via Momentum Integrated Gradients-
[pdf]
[supp]
[bibtex]@InProceedings{Ma_2023_ICCV, author = {Ma, Wenshuo and Li, Yidong and Jia, Xiaofeng and Xu, Wei}, title = {Transferable Adversarial Attack for Both Vision Transformers and Convolutional Networks via Momentum Integrated Gradients}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {4630-4639} }
Adaptive Image Anonymization in the Context of Image Classification with Neural Networks-
[pdf]
[bibtex]@InProceedings{Shvai_2023_ICCV, author = {Shvai, Nadiya and Carmona, Arcadi Llanza and Nakib, Amir}, title = {Adaptive Image Anonymization in the Context of Image Classification with Neural Networks}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {5074-5083} }
Efficient Neural Supersampling on a Novel Gaming Dataset-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Mercier_2023_ICCV, author = {Mercier, Antoine and Erasmus, Ruan and Savani, Yashesh and Dhingra, Manik and Porikli, Fatih and Berger, Guillaume}, title = {Efficient Neural Supersampling on a Novel Gaming Dataset}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {296-306} }
Walking Your LiDOG: A Journey Through Multiple Domains for LiDAR Semantic Segmentation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Saltori_2023_ICCV, author = {Saltori, Cristiano and Osep, Aljosa and Ricci, Elisa and Leal-Taix\'e, Laura}, title = {Walking Your LiDOG: A Journey Through Multiple Domains for LiDAR Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {196-206} }
Explore and Tell: Embodied Visual Captioning in 3D Environments-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Hu_2023_ICCV, author = {Hu, Anwen and Chen, Shizhe and Zhang, Liang and Jin, Qin}, title = {Explore and Tell: Embodied Visual Captioning in 3D Environments}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {2482-2491} }
FastViT: A Fast Hybrid Vision Transformer Using Structural Reparameterization-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Vasu_2023_ICCV, author = {Vasu, Pavan Kumar Anasosalu and Gabriel, James and Zhu, Jeff and Tuzel, Oncel and Ranjan, Anurag}, title = {FastViT: A Fast Hybrid Vision Transformer Using Structural Reparameterization}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {5785-5795} }
OFVL-MS: Once for Visual Localization across Multiple Indoor Scenes-
[pdf]
[supp]
[bibtex]@InProceedings{Xie_2023_ICCV, author = {Xie, Tao and Dai, Kun and Lu, Siyi and Wang, Ke and Jiang, Zhiqiang and Gao, Jinghan and Liu, Dedong and Xu, Jie and Zhao, Lijun and Li, Ruifeng}, title = {OFVL-MS: Once for Visual Localization across Multiple Indoor Scenes}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {5516-5526} }
Inter-Realization Channels: Unsupervised Anomaly Detection Beyond One-Class Classification-
[pdf]
[supp]
[bibtex]@InProceedings{McIntosh_2023_ICCV, author = {McIntosh, Declan and Albu, Alexandra Branzan}, title = {Inter-Realization Channels: Unsupervised Anomaly Detection Beyond One-Class Classification}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {6285-6295} }
High Quality Entity Segmentation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Qi_2023_ICCV, author = {Qi, Lu and Kuen, Jason and Shen, Tiancheng and Gu, Jiuxiang and Li, Wenbo and Guo, Weidong and Jia, Jiaya and Lin, Zhe and Yang, Ming-Hsuan}, title = {High Quality Entity Segmentation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {4047-4056} }
CoTDet: Affordance Knowledge Prompting for Task Driven Object Detection-
[pdf]
[arXiv]
[bibtex]@InProceedings{Tang_2023_ICCV, author = {Tang, Jiajin and Zheng, Ge and Yu, Jingyi and Yang, Sibei}, title = {CoTDet: Affordance Knowledge Prompting for Task Driven Object Detection}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {3068-3078} }
Rendering Humans from Object-Occluded Monocular Videos-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Xiang_2023_ICCV, author = {Xiang, Tiange and Sun, Adam and Wu, Jiajun and Adeli, Ehsan and Fei-Fei, Li}, title = {Rendering Humans from Object-Occluded Monocular Videos}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {3239-3250} }
Out-of-Distribution Detection for Monocular Depth Estimation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Hornauer_2023_ICCV, author = {Hornauer, Julia and Holzbock, Adrian and Belagiannis, Vasileios}, title = {Out-of-Distribution Detection for Monocular Depth Estimation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {1911-1921} }
LLM-Planner: Few-Shot Grounded Planning for Embodied Agents with Large Language Models-
[pdf]
[supp]
[bibtex]@InProceedings{Song_2023_ICCV, author = {Song, Chan Hee and Wu, Jiaman and Washington, Clayton and Sadler, Brian M and Chao, Wei-Lun and Su, Yu}, title = {LLM-Planner: Few-Shot Grounded Planning for Embodied Agents with Large Language Models}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {2998-3009} }
Exploring Model Transferability through the Lens of Potential Energy-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Li_2023_ICCV, author = {Li, Xiaotong and Hu, Zixuan and Ge, Yixiao and Shan, Ying and Duan, Ling-Yu}, title = {Exploring Model Transferability through the Lens of Potential Energy}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {5429-5438} }
Back