CVPR 2023 Open Access Repository

Papers

Back
GFPose: Learning 3D Human Pose Prior With Gradient Fields: Hai Ci,

Mingdong Wu,

Wentao Zhu,

Xiaoxuan Ma,

Hao Dong,

Fangwei Zhong,

Yizhou Wang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ci_2023_CVPR, author = {Ci, Hai and Wu, Mingdong and Zhu, Wentao and Ma, Xiaoxuan and Dong, Hao and Zhong, Fangwei and Wang, Yizhou}, title = {GFPose: Learning 3D Human Pose Prior With Gradient Fields}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4800-4810} }
CXTrack: Improving 3D Point Cloud Tracking With Contextual Information: Tian-Xing Xu,

Yuan-Chen Guo,

Yu-Kun Lai,

Song-Hai Zhang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Xu_2023_CVPR, author = {Xu, Tian-Xing and Guo, Yuan-Chen and Lai, Yu-Kun and Zhang, Song-Hai}, title = {CXTrack: Improving 3D Point Cloud Tracking With Contextual Information}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1084-1093} }
NoisyTwins: Class-Consistent and Diverse Image Generation Through StyleGANs: Harsh Rangwani,

Lavish Bansal,

Kartik Sharma,

Tejan Karmali,

Varun Jampani,

R. Venkatesh Babu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Rangwani_2023_CVPR, author = {Rangwani, Harsh and Bansal, Lavish and Sharma, Kartik and Karmali, Tejan and Jampani, Varun and Babu, R. Venkatesh}, title = {NoisyTwins: Class-Consistent and Diverse Image Generation Through StyleGANs}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5987-5996} }
DisCoScene: Spatially Disentangled Generative Radiance Fields for Controllable 3D-Aware Scene Synthesis: Yinghao Xu,

Menglei Chai,

Zifan Shi,

Sida Peng,

Ivan Skorokhodov,

Aliaksandr Siarohin,

Ceyuan Yang,

Yujun Shen,

Hsin-Ying Lee,

Bolei Zhou,

Sergey Tulyakov; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Xu_2023_CVPR, author = {Xu, Yinghao and Chai, Menglei and Shi, Zifan and Peng, Sida and Skorokhodov, Ivan and Siarohin, Aliaksandr and Yang, Ceyuan and Shen, Yujun and Lee, Hsin-Ying and Zhou, Bolei and Tulyakov, Sergey}, title = {DisCoScene: Spatially Disentangled Generative Radiance Fields for Controllable 3D-Aware Scene Synthesis}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4402-4412} }
Minimizing the Accumulated Trajectory Error To Improve Dataset Distillation: Jiawei Du,

Yidi Jiang,

Vincent Y. F. Tan,

Joey Tianyi Zhou,

Haizhou Li; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Du_2023_CVPR, author = {Du, Jiawei and Jiang, Yidi and Tan, Vincent Y. F. and Zhou, Joey Tianyi and Li, Haizhou}, title = {Minimizing the Accumulated Trajectory Error To Improve Dataset Distillation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3749-3758} }
Implicit Occupancy Flow Fields for Perception and Prediction in Self-Driving: Ben Agro,

Quinlan Sykora,

Sergio Casas,

Raquel Urtasun; [pdf] [supp]
[bibtex]
@InProceedings{Agro_2023_CVPR, author = {Agro, Ben and Sykora, Quinlan and Casas, Sergio and Urtasun, Raquel}, title = {Implicit Occupancy Flow Fields for Perception and Prediction in Self-Driving}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1379-1388} }
CCuantuMM: Cycle-Consistent Quantum-Hybrid Matching of Multiple Shapes: Harshil Bhatia,

Edith Tretschk,

Zorah Lähner,

Marcel Seelbach Benkner,

Michael Moeller,

Christian Theobalt,

Vladislav Golyanik; [pdf] [supp]
[bibtex]
@InProceedings{Bhatia_2023_CVPR, author = {Bhatia, Harshil and Tretschk, Edith and L\"ahner, Zorah and Benkner, Marcel Seelbach and Moeller, Michael and Theobalt, Christian and Golyanik, Vladislav}, title = {CCuantuMM: Cycle-Consistent Quantum-Hybrid Matching of Multiple Shapes}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1296-1305} }
TrojViT: Trojan Insertion in Vision Transformers: Mengxin Zheng,

Qian Lou,

Lei Jiang; [pdf] [arXiv]
[bibtex]
@InProceedings{Zheng_2023_CVPR, author = {Zheng, Mengxin and Lou, Qian and Jiang, Lei}, title = {TrojViT: Trojan Insertion in Vision Transformers}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4025-4034} }
Robust Outlier Rejection for 3D Registration With Variational Bayes: Haobo Jiang,

Zheng Dang,

Zhen Wei,

Jin Xie,

Jian Yang,

Mathieu Salzmann; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Jiang_2023_CVPR, author = {Jiang, Haobo and Dang, Zheng and Wei, Zhen and Xie, Jin and Yang, Jian and Salzmann, Mathieu}, title = {Robust Outlier Rejection for 3D Registration With Variational Bayes}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1148-1157} }
Power Bundle Adjustment for Large-Scale 3D Reconstruction: Simon Weber,

Nikolaus Demmel,

Tin Chon Chan,

Daniel Cremers; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Weber_2023_CVPR, author = {Weber, Simon and Demmel, Nikolaus and Chan, Tin Chon and Cremers, Daniel}, title = {Power Bundle Adjustment for Large-Scale 3D Reconstruction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {281-289} }
Picture That Sketch: Photorealistic Image Generation From Abstract Sketches: Subhadeep Koley,

Ayan Kumar Bhunia,

Aneeshan Sain,

Pinaki Nath Chowdhury,

Tao Xiang,

Yi-Zhe Song; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Koley_2023_CVPR, author = {Koley, Subhadeep and Bhunia, Ayan Kumar and Sain, Aneeshan and Chowdhury, Pinaki Nath and Xiang, Tao and Song, Yi-Zhe}, title = {Picture That Sketch: Photorealistic Image Generation From Abstract Sketches}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6850-6861} }
3D-Aware Object Goal Navigation via Simultaneous Exploration and Identification: Jiazhao Zhang,

Liu Dai,

Fanpeng Meng,

Qingnan Fan,

Xuelin Chen,

Kai Xu,

He Wang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhang_2023_CVPR, author = {Zhang, Jiazhao and Dai, Liu and Meng, Fanpeng and Fan, Qingnan and Chen, Xuelin and Xu, Kai and Wang, He}, title = {3D-Aware Object Goal Navigation via Simultaneous Exploration and Identification}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6672-6682} }
Shape, Pose, and Appearance From a Single Image via Bootstrapped Radiance Field Inversion: Dario Pavllo,

David Joseph Tan,

Marie-Julie Rakotosaona,

Federico Tombari; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Pavllo_2023_CVPR, author = {Pavllo, Dario and Tan, David Joseph and Rakotosaona, Marie-Julie and Tombari, Federico}, title = {Shape, Pose, and Appearance From a Single Image via Bootstrapped Radiance Field Inversion}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4391-4401} }
Unlearnable Clusters: Towards Label-Agnostic Unlearnable Examples: Jiaming Zhang,

Xingjun Ma,

Qi Yi,

Jitao Sang,

Yu-Gang Jiang,

Yaowei Wang,

Changsheng Xu; [pdf] [arXiv]
[bibtex]
@InProceedings{Zhang_2023_CVPR, author = {Zhang, Jiaming and Ma, Xingjun and Yi, Qi and Sang, Jitao and Jiang, Yu-Gang and Wang, Yaowei and Xu, Changsheng}, title = {Unlearnable Clusters: Towards Label-Agnostic Unlearnable Examples}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3984-3993} }
NoPe-NeRF: Optimising Neural Radiance Field With No Pose Prior: Wenjing Bian,

Zirui Wang,

Kejie Li,

Jia-Wang Bian,

Victor Adrian Prisacariu; [pdf] [supp]
[bibtex]
@InProceedings{Bian_2023_CVPR, author = {Bian, Wenjing and Wang, Zirui and Li, Kejie and Bian, Jia-Wang and Prisacariu, Victor Adrian}, title = {NoPe-NeRF: Optimising Neural Radiance Field With No Pose Prior}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4160-4169} }
SIEDOB: Semantic Image Editing by Disentangling Object and Background: Wuyang Luo,

Su Yang,

Xinjian Zhang,

Weishan Zhang; [pdf] [arXiv]
[bibtex]
@InProceedings{Luo_2023_CVPR, author = {Luo, Wuyang and Yang, Su and Zhang, Xinjian and Zhang, Weishan}, title = {SIEDOB: Semantic Image Editing by Disentangling Object and Background}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1868-1878} }
Robust 3D Shape Classification via Non-Local Graph Attention Network: Shengwei Qin,

Zhong Li,

Ligang Liu; [pdf] [supp]
[bibtex]
@InProceedings{Qin_2023_CVPR, author = {Qin, Shengwei and Li, Zhong and Liu, Ligang}, title = {Robust 3D Shape Classification via Non-Local Graph Attention Network}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5374-5383} }
Exploring Structured Semantic Prior for Multi Label Recognition With Incomplete Labels: Zixuan Ding,

Ao Wang,

Hui Chen,

Qiang Zhang,

Pengzhang Liu,

Yongjun Bao,

Weipeng Yan,

Jungong Han; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ding_2023_CVPR, author = {Ding, Zixuan and Wang, Ao and Chen, Hui and Zhang, Qiang and Liu, Pengzhang and Bao, Yongjun and Yan, Weipeng and Han, Jungong}, title = {Exploring Structured Semantic Prior for Multi Label Recognition With Incomplete Labels}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3398-3407} }
Delving Into Shape-Aware Zero-Shot Semantic Segmentation: Xinyu Liu,

Beiwen Tian,

Zhen Wang,

Rui Wang,

Kehua Sheng,

Bo Zhang,

Hao Zhao,

Guyue Zhou; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Liu_2023_CVPR, author = {Liu, Xinyu and Tian, Beiwen and Wang, Zhen and Wang, Rui and Sheng, Kehua and Zhang, Bo and Zhao, Hao and Zhou, Guyue}, title = {Delving Into Shape-Aware Zero-Shot Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2999-3009} }
Post-Training Quantization on Diffusion Models: Yuzhang Shang,

Zhihang Yuan,

Bin Xie,

Bingzhe Wu,

Yan Yan; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Shang_2023_CVPR, author = {Shang, Yuzhang and Yuan, Zhihang and Xie, Bin and Wu, Bingzhe and Yan, Yan}, title = {Post-Training Quantization on Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1972-1981} }
Leveraging Inter-Rater Agreement for Classification in the Presence of Noisy Labels: Maria Sofia Bucarelli,

Lucas Cassano,

Federico Siciliano,

Amin Mantrach,

Fabrizio Silvestri; [pdf] [supp]
[bibtex]
@InProceedings{Bucarelli_2023_CVPR, author = {Bucarelli, Maria Sofia and Cassano, Lucas and Siciliano, Federico and Mantrach, Amin and Silvestri, Fabrizio}, title = {Leveraging Inter-Rater Agreement for Classification in the Presence of Noisy Labels}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3439-3448} }
Analyzing Physical Impacts Using Transient Surface Wave Imaging: Tianyuan Zhang,

Mark Sheinin,

Dorian Chan,

Mark Rau,

Matthew O’Toole,

Srinivasa G. Narasimhan; [pdf] [supp]
[bibtex]
@InProceedings{Zhang_2023_CVPR, author = {Zhang, Tianyuan and Sheinin, Mark and Chan, Dorian and Rau, Mark and O{\textquoteright}Toole, Matthew and Narasimhan, Srinivasa G.}, title = {Analyzing Physical Impacts Using Transient Surface Wave Imaging}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4339-4348} }
ScanDMM: A Deep Markov Model of Scanpath Prediction for 360deg Images: Xiangjie Sui,

Yuming Fang,

Hanwei Zhu,

Shiqi Wang,

Zhou Wang; [pdf]
[bibtex]
@InProceedings{Sui_2023_CVPR, author = {Sui, Xiangjie and Fang, Yuming and Zhu, Hanwei and Wang, Shiqi and Wang, Zhou}, title = {ScanDMM: A Deep Markov Model of Scanpath Prediction for 360deg Images}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6989-6999} }
Continual Semantic Segmentation With Automatic Memory Sample Selection: Lanyun Zhu,

Tianrun Chen,

Jianxiong Yin,

Simon See,

Jun Liu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhu_2023_CVPR, author = {Zhu, Lanyun and Chen, Tianrun and Yin, Jianxiong and See, Simon and Liu, Jun}, title = {Continual Semantic Segmentation With Automatic Memory Sample Selection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3082-3092} }
Meta-Tuning Loss Functions and Data Augmentation for Few-Shot Object Detection: Berkan Demirel,

Orhun Buğra Baran,

Ramazan Gokberk Cinbis; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Demirel_2023_CVPR, author = {Demirel, Berkan and Baran, Orhun Bu\u{g}ra and Cinbis, Ramazan Gokberk}, title = {Meta-Tuning Loss Functions and Data Augmentation for Few-Shot Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7339-7349} }
CLIP2Scene: Towards Label-Efficient 3D Scene Understanding by CLIP: Runnan Chen,

Youquan Liu,

Lingdong Kong,

Xinge Zhu,

Yuexin Ma,

Yikang Li,

Yuenan Hou,

Yu Qiao,

Wenping Wang; [pdf] [arXiv]
[bibtex]
@InProceedings{Chen_2023_CVPR, author = {Chen, Runnan and Liu, Youquan and Kong, Lingdong and Zhu, Xinge and Ma, Yuexin and Li, Yikang and Hou, Yuenan and Qiao, Yu and Wang, Wenping}, title = {CLIP2Scene: Towards Label-Efficient 3D Scene Understanding by CLIP}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7020-7030} }
LOGO: A Long-Form Video Dataset for Group Action Quality Assessment: Shiyi Zhang,

Wenxun Dai,

Sujia Wang,

Xiangwei Shen,

Jiwen Lu,

Jie Zhou,

Yansong Tang; [pdf] [supp]
[bibtex]
@InProceedings{Zhang_2023_CVPR, author = {Zhang, Shiyi and Dai, Wenxun and Wang, Sujia and Shen, Xiangwei and Lu, Jiwen and Zhou, Jie and Tang, Yansong}, title = {LOGO: A Long-Form Video Dataset for Group Action Quality Assessment}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2405-2414} }
UniSim: A Neural Closed-Loop Sensor Simulator: Ze Yang,

Yun Chen,

Jingkang Wang,

Sivabalan Manivasagam,

Wei-Chiu Ma,

Anqi Joyce Yang,

Raquel Urtasun; [pdf]
[bibtex]
@InProceedings{Yang_2023_CVPR, author = {Yang, Ze and Chen, Yun and Wang, Jingkang and Manivasagam, Sivabalan and Ma, Wei-Chiu and Yang, Anqi Joyce and Urtasun, Raquel}, title = {UniSim: A Neural Closed-Loop Sensor Simulator}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1389-1399} }
Prefix Conditioning Unifies Language and Label Supervision: Kuniaki Saito,

Kihyuk Sohn,

Xiang Zhang,

Chun-Liang Li,

Chen-Yu Lee,

Kate Saenko,

Tomas Pfister; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Saito_2023_CVPR, author = {Saito, Kuniaki and Sohn, Kihyuk and Zhang, Xiang and Li, Chun-Liang and Lee, Chen-Yu and Saenko, Kate and Pfister, Tomas}, title = {Prefix Conditioning Unifies Language and Label Supervision}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2861-2870} }
Towards Scalable Neural Representation for Diverse Videos: Bo He,

Xitong Yang,

Hanyu Wang,

Zuxuan Wu,

Hao Chen,

Shuaiyi Huang,

Yixuan Ren,

Ser-Nam Lim,

Abhinav Shrivastava; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{He_2023_CVPR, author = {He, Bo and Yang, Xitong and Wang, Hanyu and Wu, Zuxuan and Chen, Hao and Huang, Shuaiyi and Ren, Yixuan and Lim, Ser-Nam and Shrivastava, Abhinav}, title = {Towards Scalable Neural Representation for Diverse Videos}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6132-6142} }
Towards Robust Tampered Text Detection in Document Image: New Dataset and New Solution: Chenfan Qu,

Chongyu Liu,

Yuliang Liu,

Xinhong Chen,

Dezhi Peng,

Fengjun Guo,

Lianwen Jin; [pdf] [supp]
[bibtex]
@InProceedings{Qu_2023_CVPR, author = {Qu, Chenfan and Liu, Chongyu and Liu, Yuliang and Chen, Xinhong and Peng, Dezhi and Guo, Fengjun and Jin, Lianwen}, title = {Towards Robust Tampered Text Detection in Document Image: New Dataset and New Solution}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5937-5946} }
DeSTSeg: Segmentation Guided Denoising Student-Teacher for Anomaly Detection: Xuan Zhang,

Shiyu Li,

Xi Li,

Ping Huang,

Jiulong Shan,

Ting Chen; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhang_2023_CVPR, author = {Zhang, Xuan and Li, Shiyu and Li, Xi and Huang, Ping and Shan, Jiulong and Chen, Ting}, title = {DeSTSeg: Segmentation Guided Denoising Student-Teacher for Anomaly Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3914-3923} }
Neural Rate Estimator and Unsupervised Learning for Efficient Distributed Image Analytics in Split-DNN Models: Nilesh Ahuja,

Parual Datta,

Bhavya Kanzariya,

V. Srinivasa Somayazulu,

Omesh Tickoo; [pdf] [supp]
[bibtex]
@InProceedings{Ahuja_2023_CVPR, author = {Ahuja, Nilesh and Datta, Parual and Kanzariya, Bhavya and Somayazulu, V. Srinivasa and Tickoo, Omesh}, title = {Neural Rate Estimator and Unsupervised Learning for Efficient Distributed Image Analytics in Split-DNN Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2022-2030} }
Object Pop-Up: Can We Infer 3D Objects and Their Poses From Human Interactions Alone?: Ilya A. Petrov,

Riccardo Marin,

Julian Chibane,

Gerard Pons-Moll; [pdf]
[bibtex]
@InProceedings{Petrov_2023_CVPR, author = {Petrov, Ilya A. and Marin, Riccardo and Chibane, Julian and Pons-Moll, Gerard}, title = {Object Pop-Up: Can We Infer 3D Objects and Their Poses From Human Interactions Alone?}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4726-4736} }
VoP: Text-Video Co-Operative Prompt Tuning for Cross-Modal Retrieval: Siteng Huang,

Biao Gong,

Yulin Pan,

Jianwen Jiang,

Yiliang Lv,

Yuyuan Li,

Donglin Wang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Huang_2023_CVPR, author = {Huang, Siteng and Gong, Biao and Pan, Yulin and Jiang, Jianwen and Lv, Yiliang and Li, Yuyuan and Wang, Donglin}, title = {VoP: Text-Video Co-Operative Prompt Tuning for Cross-Modal Retrieval}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6565-6574} }
Exploiting Unlabelled Photos for Stronger Fine-Grained SBIR: Aneeshan Sain,

Ayan Kumar Bhunia,

Subhadeep Koley,

Pinaki Nath Chowdhury,

Soumitri Chattopadhyay,

Tao Xiang,

Yi-Zhe Song; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Sain_2023_CVPR, author = {Sain, Aneeshan and Bhunia, Ayan Kumar and Koley, Subhadeep and Chowdhury, Pinaki Nath and Chattopadhyay, Soumitri and Xiang, Tao and Song, Yi-Zhe}, title = {Exploiting Unlabelled Photos for Stronger Fine-Grained SBIR}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6873-6883} }
PIP-Net: Patch-Based Intuitive Prototypes for Interpretable Image Classification: Meike Nauta,

Jörg Schlötterer,

Maurice van Keulen,

Christin Seifert; [pdf] [supp]
[bibtex]
@InProceedings{Nauta_2023_CVPR, author = {Nauta, Meike and Schl\"otterer, J\"org and van Keulen, Maurice and Seifert, Christin}, title = {PIP-Net: Patch-Based Intuitive Prototypes for Interpretable Image Classification}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2744-2753} }
CloSET: Modeling Clothed Humans on Continuous Surface With Explicit Template Decomposition: Hongwen Zhang,

Siyou Lin,

Ruizhi Shao,

Yuxiang Zhang,

Zerong Zheng,

Han Huang,

Yandong Guo,

Yebin Liu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhang_2023_CVPR, author = {Zhang, Hongwen and Lin, Siyou and Shao, Ruizhi and Zhang, Yuxiang and Zheng, Zerong and Huang, Han and Guo, Yandong and Liu, Yebin}, title = {CloSET: Modeling Clothed Humans on Continuous Surface With Explicit Template Decomposition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {501-511} }
BUOL: A Bottom-Up Framework With Occupancy-Aware Lifting for Panoptic 3D Scene Reconstruction From a Single Image: Tao Chu,

Pan Zhang,

Qiong Liu,

Jiaqi Wang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chu_2023_CVPR, author = {Chu, Tao and Zhang, Pan and Liu, Qiong and Wang, Jiaqi}, title = {BUOL: A Bottom-Up Framework With Occupancy-Aware Lifting for Panoptic 3D Scene Reconstruction From a Single Image}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4937-4946} }
Seeing What You Miss: Vision-Language Pre-Training With Semantic Completion Learning: Yatai Ji,

Rongcheng Tu,

Jie Jiang,

Weijie Kong,

Chengfei Cai,

Wenzhe Zhao,

Hongfa Wang,

Yujiu Yang,

Wei Liu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ji_2023_CVPR, author = {Ji, Yatai and Tu, Rongcheng and Jiang, Jie and Kong, Weijie and Cai, Chengfei and Zhao, Wenzhe and Wang, Hongfa and Yang, Yujiu and Liu, Wei}, title = {Seeing What You Miss: Vision-Language Pre-Training With Semantic Completion Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6789-6798} }
Differentiable Shadow Mapping for Efficient Inverse Graphics: Markus Worchel,

Marc Alexa; [pdf] [supp]
[bibtex]
@InProceedings{Worchel_2023_CVPR, author = {Worchel, Markus and Alexa, Marc}, title = {Differentiable Shadow Mapping for Efficient Inverse Graphics}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {142-153} }
Understanding and Constructing Latent Modality Structures in Multi-Modal Representation Learning: Qian Jiang,

Changyou Chen,

Han Zhao,

Liqun Chen,

Qing Ping,

Son Dinh Tran,

Yi Xu,

Belinda Zeng,

Trishul Chilimbi; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Jiang_2023_CVPR, author = {Jiang, Qian and Chen, Changyou and Zhao, Han and Chen, Liqun and Ping, Qing and Tran, Son Dinh and Xu, Yi and Zeng, Belinda and Chilimbi, Trishul}, title = {Understanding and Constructing Latent Modality Structures in Multi-Modal Representation Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7661-7671} }
Instant Volumetric Head Avatars: Wojciech Zielonka,

Timo Bolkart,

Justus Thies; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zielonka_2023_CVPR, author = {Zielonka, Wojciech and Bolkart, Timo and Thies, Justus}, title = {Instant Volumetric Head Avatars}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4574-4584} }
Cross-Domain Image Captioning With Discriminative Finetuning: Roberto Dessì,

Michele Bevilacqua,

Eleonora Gualdoni,

Nathanaël Carraz Rakotonirina,

Francesca Franzon,

Marco Baroni; [pdf] [supp]
[bibtex]
@InProceedings{Dessi_2023_CVPR, author = {Dess{\`\i}, Roberto and Bevilacqua, Michele and Gualdoni, Eleonora and Rakotonirina, Nathana\"el Carraz and Franzon, Francesca and Baroni, Marco}, title = {Cross-Domain Image Captioning With Discriminative Finetuning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6935-6944} }
DBARF: Deep Bundle-Adjusting Generalizable Neural Radiance Fields: Yu Chen,

Gim Hee Lee; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chen_2023_CVPR, author = {Chen, Yu and Lee, Gim Hee}, title = {DBARF: Deep Bundle-Adjusting Generalizable Neural Radiance Fields}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {24-34} }
Connecting the Dots: Floorplan Reconstruction Using Two-Level Queries: Yuanwen Yue,

Theodora Kontogianni,

Konrad Schindler,

Francis Engelmann; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yue_2023_CVPR, author = {Yue, Yuanwen and Kontogianni, Theodora and Schindler, Konrad and Engelmann, Francis}, title = {Connecting the Dots: Floorplan Reconstruction Using Two-Level Queries}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {845-854} }
Analyzing and Diagnosing Pose Estimation With Attributions: Qiyuan He,

Linlin Yang,

Kerui Gu,

Qiuxia Lin,

Angela Yao; [pdf] [supp]
[bibtex]
@InProceedings{He_2023_CVPR, author = {He, Qiyuan and Yang, Linlin and Gu, Kerui and Lin, Qiuxia and Yao, Angela}, title = {Analyzing and Diagnosing Pose Estimation With Attributions}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4821-4830} }
Make-a-Story: Visual Memory Conditioned Consistent Story Generation: Tanzila Rahman,

Hsin-Ying Lee,

Jian Ren,

Sergey Tulyakov,

Shweta Mahajan,

Leonid Sigal; [pdf] [supp]
[bibtex]
@InProceedings{Rahman_2023_CVPR, author = {Rahman, Tanzila and Lee, Hsin-Ying and Ren, Jian and Tulyakov, Sergey and Mahajan, Shweta and Sigal, Leonid}, title = {Make-a-Story: Visual Memory Conditioned Consistent Story Generation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2493-2502} }
TinyMIM: An Empirical Study of Distilling MIM Pre-Trained Models: Sucheng Ren,

Fangyun Wei,

Zheng Zhang,

Han Hu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ren_2023_CVPR, author = {Ren, Sucheng and Wei, Fangyun and Zhang, Zheng and Hu, Han}, title = {TinyMIM: An Empirical Study of Distilling MIM Pre-Trained Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3687-3697} }
OneFormer: One Transformer To Rule Universal Image Segmentation: Jitesh Jain,

Jiachen Li,

Mang Tik Chiu,

Ali Hassani,

Nikita Orlov,

Humphrey Shi; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Jain_2023_CVPR, author = {Jain, Jitesh and Li, Jiachen and Chiu, Mang Tik and Hassani, Ali and Orlov, Nikita and Shi, Humphrey}, title = {OneFormer: One Transformer To Rule Universal Image Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2989-2998} }
Finding Geometric Models by Clustering in the Consensus Space: Daniel Barath,

Denys Rozumnyi,

Ivan Eichhardt,

Levente Hajder,

Jiri Matas; [pdf] [supp]
[bibtex]
@InProceedings{Barath_2023_CVPR, author = {Barath, Daniel and Rozumnyi, Denys and Eichhardt, Ivan and Hajder, Levente and Matas, Jiri}, title = {Finding Geometric Models by Clustering in the Consensus Space}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5414-5424} }
Leapfrog Diffusion Model for Stochastic Trajectory Prediction: Weibo Mao,

Chenxin Xu,

Qi Zhu,

Siheng Chen,

Yanfeng Wang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Mao_2023_CVPR, author = {Mao, Weibo and Xu, Chenxin and Zhu, Qi and Chen, Siheng and Wang, Yanfeng}, title = {Leapfrog Diffusion Model for Stochastic Trajectory Prediction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5517-5526} }
GeoLayoutLM: Geometric Pre-Training for Visual Information Extraction: Chuwei Luo,

Changxu Cheng,

Qi Zheng,

Cong Yao; [pdf] [arXiv]
[bibtex]
@InProceedings{Luo_2023_CVPR, author = {Luo, Chuwei and Cheng, Changxu and Zheng, Qi and Yao, Cong}, title = {GeoLayoutLM: Geometric Pre-Training for Visual Information Extraction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7092-7101} }
SFD2: Semantic-Guided Feature Detection and Description: Fei Xue,

Ignas Budvytis,

Roberto Cipolla; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Xue_2023_CVPR, author = {Xue, Fei and Budvytis, Ignas and Cipolla, Roberto}, title = {SFD2: Semantic-Guided Feature Detection and Description}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5206-5216} }
CLIP for All Things Zero-Shot Sketch-Based Image Retrieval, Fine-Grained or Not: Aneeshan Sain,

Ayan Kumar Bhunia,

Pinaki Nath Chowdhury,

Subhadeep Koley,

Tao Xiang,

Yi-Zhe Song; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Sain_2023_CVPR, author = {Sain, Aneeshan and Bhunia, Ayan Kumar and Chowdhury, Pinaki Nath and Koley, Subhadeep and Xiang, Tao and Song, Yi-Zhe}, title = {CLIP for All Things Zero-Shot Sketch-Based Image Retrieval, Fine-Grained or Not}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2765-2775} }
RIAV-MVS: Recurrent-Indexing an Asymmetric Volume for Multi-View Stereo: Changjiang Cai,

Pan Ji,

Qingan Yan,

Yi Xu; [pdf] [supp]
[bibtex]
@InProceedings{Cai_2023_CVPR, author = {Cai, Changjiang and Ji, Pan and Yan, Qingan and Xu, Yi}, title = {RIAV-MVS: Recurrent-Indexing an Asymmetric Volume for Multi-View Stereo}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {919-928} }
3D Video Loops From Asynchronous Input: Li Ma,

Xiaoyu Li,

Jing Liao,

Pedro V. Sander; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ma_2023_CVPR, author = {Ma, Li and Li, Xiaoyu and Liao, Jing and Sander, Pedro V.}, title = {3D Video Loops From Asynchronous Input}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {310-320} }
Style Projected Clustering for Domain Generalized Semantic Segmentation: Wei Huang,

Chang Chen,

Yong Li,

Jiacheng Li,

Cheng Li,

Fenglong Song,

Youliang Yan,

Zhiwei Xiong; [pdf] [supp]
[bibtex]
@InProceedings{Huang_2023_CVPR, author = {Huang, Wei and Chen, Chang and Li, Yong and Li, Jiacheng and Li, Cheng and Song, Fenglong and Yan, Youliang and Xiong, Zhiwei}, title = {Style Projected Clustering for Domain Generalized Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3061-3071} }
DIP: Dual Incongruity Perceiving Network for Sarcasm Detection: Changsong Wen,

Guoli Jia,

Jufeng Yang; [pdf]
[bibtex]
@InProceedings{Wen_2023_CVPR, author = {Wen, Changsong and Jia, Guoli and Yang, Jufeng}, title = {DIP: Dual Incongruity Perceiving Network for Sarcasm Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2540-2550} }
Learning To Generate Language-Supervised and Open-Vocabulary Scene Graph Using Pre-Trained Visual-Semantic Space: Yong Zhang,

Yingwei Pan,

Ting Yao,

Rui Huang,

Tao Mei,

Chang-Wen Chen; [pdf] [supp]
[bibtex]
@InProceedings{Zhang_2023_CVPR, author = {Zhang, Yong and Pan, Yingwei and Yao, Ting and Huang, Rui and Mei, Tao and Chen, Chang-Wen}, title = {Learning To Generate Language-Supervised and Open-Vocabulary Scene Graph Using Pre-Trained Visual-Semantic Space}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2915-2924} }
VectorFloorSeg: Two-Stream Graph Attention Network for Vectorized Roughcast Floorplan Segmentation: Bingchen Yang,

Haiyong Jiang,

Hao Pan,

Jun Xiao; [pdf] [supp]
[bibtex]
@InProceedings{Yang_2023_CVPR, author = {Yang, Bingchen and Jiang, Haiyong and Pan, Hao and Xiao, Jun}, title = {VectorFloorSeg: Two-Stream Graph Attention Network for Vectorized Roughcast Floorplan Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1358-1367} }
Extracting Motion and Appearance via Inter-Frame Attention for Efficient Video Frame Interpolation: Guozhen Zhang,

Yuhan Zhu,

Haonan Wang,

Youxin Chen,

Gangshan Wu,

Limin Wang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhang_2023_CVPR, author = {Zhang, Guozhen and Zhu, Yuhan and Wang, Haonan and Chen, Youxin and Wu, Gangshan and Wang, Limin}, title = {Extracting Motion and Appearance via Inter-Frame Attention for Efficient Video Frame Interpolation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5682-5692} }
Minimizing Maximum Model Discrepancy for Transferable Black-Box Targeted Attacks: Anqi Zhao,

Tong Chu,

Yahao Liu,

Wen Li,

Jingjing Li,

Lixin Duan; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhao_2023_CVPR, author = {Zhao, Anqi and Chu, Tong and Liu, Yahao and Li, Wen and Li, Jingjing and Duan, Lixin}, title = {Minimizing Maximum Model Discrepancy for Transferable Black-Box Targeted Attacks}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8153-8162} }
Efficient Loss Function by Minimizing the Detrimental Effect of Floating-Point Errors on Gradient-Based Attacks: Yunrui Yu,

Cheng-Zhong Xu; [pdf] [supp]
[bibtex]
@InProceedings{Yu_2023_CVPR, author = {Yu, Yunrui and Xu, Cheng-Zhong}, title = {Efficient Loss Function by Minimizing the Detrimental Effect of Floating-Point Errors on Gradient-Based Attacks}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4056-4066} }
BAD-NeRF: Bundle Adjusted Deblur Neural Radiance Fields: Peng Wang,

Lingzhe Zhao,

Ruijie Ma,

Peidong Liu; [pdf] [supp]
[bibtex]
@InProceedings{Wang_2023_CVPR, author = {Wang, Peng and Zhao, Lingzhe and Ma, Ruijie and Liu, Peidong}, title = {BAD-NeRF: Bundle Adjusted Deblur Neural Radiance Fields}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4170-4179} }
QPGesture: Quantization-Based and Phase-Guided Motion Matching for Natural Speech-Driven Gesture Generation: Sicheng Yang,

Zhiyong Wu,

Minglei Li,

Zhensong Zhang,

Lei Hao,

Weihong Bao,

Haolin Zhuang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yang_2023_CVPR, author = {Yang, Sicheng and Wu, Zhiyong and Li, Minglei and Zhang, Zhensong and Hao, Lei and Bao, Weihong and Zhuang, Haolin}, title = {QPGesture: Quantization-Based and Phase-Guided Motion Matching for Natural Speech-Driven Gesture Generation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2321-2330} }
Multiscale Tensor Decomposition and Rendering Equation Encoding for View Synthesis: Kang Han,

Wei Xiang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Han_2023_CVPR, author = {Han, Kang and Xiang, Wei}, title = {Multiscale Tensor Decomposition and Rendering Equation Encoding for View Synthesis}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4232-4241} }
NS3D: Neuro-Symbolic Grounding of 3D Objects and Relations: Joy Hsu,

Jiayuan Mao,

Jiajun Wu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Hsu_2023_CVPR, author = {Hsu, Joy and Mao, Jiayuan and Wu, Jiajun}, title = {NS3D: Neuro-Symbolic Grounding of 3D Objects and Relations}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2614-2623} }
GANmouflage: 3D Object Nondetection With Texture Fields: Rui Guo,

Jasmine Collins,

Oscar de Lima,

Andrew Owens; [pdf] [arXiv]
[bibtex]
@InProceedings{Guo_2023_CVPR, author = {Guo, Rui and Collins, Jasmine and de Lima, Oscar and Owens, Andrew}, title = {GANmouflage: 3D Object Nondetection With Texture Fields}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4702-4712} }
Revisiting Residual Networks for Adversarial Robustness: Shihua Huang,

Zhichao Lu,

Kalyanmoy Deb,

Vishnu Naresh Boddeti; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Huang_2023_CVPR, author = {Huang, Shihua and Lu, Zhichao and Deb, Kalyanmoy and Boddeti, Vishnu Naresh}, title = {Revisiting Residual Networks for Adversarial Robustness}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8202-8211} }
PosterLayout: A New Benchmark and Approach for Content-Aware Visual-Textual Presentation Layout: Hsiao Yuan Hsu,

Xiangteng He,

Yuxin Peng,

Hao Kong,

Qing Zhang; [pdf] [arXiv]
[bibtex]
@InProceedings{Hsu_2023_CVPR, author = {Hsu, Hsiao Yuan and He, Xiangteng and Peng, Yuxin and Kong, Hao and Zhang, Qing}, title = {PosterLayout: A New Benchmark and Approach for Content-Aware Visual-Textual Presentation Layout}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6018-6026} }
A General Regret Bound of Preconditioned Gradient Method for DNN Training: Hongwei Yong,

Ying Sun,

Lei Zhang; [pdf] [supp]
[bibtex]
@InProceedings{Yong_2023_CVPR, author = {Yong, Hongwei and Sun, Ying and Zhang, Lei}, title = {A General Regret Bound of Preconditioned Gradient Method for DNN Training}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7866-7875} }
Optimal Proposal Learning for Deployable End-to-End Pedestrian Detection: Xiaolin Song,

Binghui Chen,

Pengyu Li,

Jun-Yan He,

Biao Wang,

Yifeng Geng,

Xuansong Xie,

Honggang Zhang; [pdf]
[bibtex]
@InProceedings{Song_2023_CVPR, author = {Song, Xiaolin and Chen, Binghui and Li, Pengyu and He, Jun-Yan and Wang, Biao and Geng, Yifeng and Xie, Xuansong and Zhang, Honggang}, title = {Optimal Proposal Learning for Deployable End-to-End Pedestrian Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3250-3260} }
Temporal Interpolation Is All You Need for Dynamic Neural Radiance Fields: Sungheon Park,

Minjung Son,

Seokhwan Jang,

Young Chun Ahn,

Ji-Yeon Kim,

Nahyup Kang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Park_2023_CVPR, author = {Park, Sungheon and Son, Minjung and Jang, Seokhwan and Ahn, Young Chun and Kim, Ji-Yeon and Kang, Nahyup}, title = {Temporal Interpolation Is All You Need for Dynamic Neural Radiance Fields}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4212-4221} }
Graph Transformer GANs for Graph-Constrained House Generation: Hao Tang,

Zhenyu Zhang,

Humphrey Shi,

Bo Li,

Ling Shao,

Nicu Sebe,

Radu Timofte,

Luc Van Gool; [pdf] [arXiv]
[bibtex]
@InProceedings{Tang_2023_CVPR, author = {Tang, Hao and Zhang, Zhenyu and Shi, Humphrey and Li, Bo and Shao, Ling and Sebe, Nicu and Timofte, Radu and Van Gool, Luc}, title = {Graph Transformer GANs for Graph-Constrained House Generation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2173-2182} }
On the Benefits of 3D Pose and Tracking for Human Action Recognition: Jathushan Rajasegaran,

Georgios Pavlakos,

Angjoo Kanazawa,

Christoph Feichtenhofer,

Jitendra Malik; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Rajasegaran_2023_CVPR, author = {Rajasegaran, Jathushan and Pavlakos, Georgios and Kanazawa, Angjoo and Feichtenhofer, Christoph and Malik, Jitendra}, title = {On the Benefits of 3D Pose and Tracking for Human Action Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {640-649} }
How to Backdoor Diffusion Models?: Sheng-Yen Chou,

Pin-Yu Chen,

Tsung-Yi Ho; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chou_2023_CVPR, author = {Chou, Sheng-Yen and Chen, Pin-Yu and Ho, Tsung-Yi}, title = {How to Backdoor Diffusion Models?}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4015-4024} }
PACO: Parts and Attributes of Common Objects: Vignesh Ramanathan,

Anmol Kalia,

Vladan Petrovic,

Yi Wen,

Baixue Zheng,

Baishan Guo,

Rui Wang,

Aaron Marquez,

Rama Kovvuri,

Abhishek Kadian,

Amir Mousavi,

Yiwen Song,

Abhimanyu Dubey,

Dhruv Mahajan; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ramanathan_2023_CVPR, author = {Ramanathan, Vignesh and Kalia, Anmol and Petrovic, Vladan and Wen, Yi and Zheng, Baixue and Guo, Baishan and Wang, Rui and Marquez, Aaron and Kovvuri, Rama and Kadian, Abhishek and Mousavi, Amir and Song, Yiwen and Dubey, Abhimanyu and Mahajan, Dhruv}, title = {PACO: Parts and Attributes of Common Objects}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7141-7151} }
Continuous Sign Language Recognition With Correlation Network: Lianyu Hu,

Liqing Gao,

Zekang Liu,

Wei Feng; [pdf] [arXiv]
[bibtex]
@InProceedings{Hu_2023_CVPR, author = {Hu, Lianyu and Gao, Liqing and Liu, Zekang and Feng, Wei}, title = {Continuous Sign Language Recognition With Correlation Network}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2529-2539} }
A Simple Framework for Text-Supervised Semantic Segmentation: Muyang Yi,

Quan Cui,

Hao Wu,

Cheng Yang,

Osamu Yoshie,

Hongtao Lu; [pdf] [supp]
[bibtex]
@InProceedings{Yi_2023_CVPR, author = {Yi, Muyang and Cui, Quan and Wu, Hao and Yang, Cheng and Yoshie, Osamu and Lu, Hongtao}, title = {A Simple Framework for Text-Supervised Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7071-7080} }
PlenVDB: Memory Efficient VDB-Based Radiance Fields for Fast Training and Rendering: Han Yan,

Celong Liu,

Chao Ma,

Xing Mei; [pdf] [supp]
[bibtex]
@InProceedings{Yan_2023_CVPR, author = {Yan, Han and Liu, Celong and Ma, Chao and Mei, Xing}, title = {PlenVDB: Memory Efficient VDB-Based Radiance Fields for Fast Training and Rendering}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {88-96} }
An Actor-Centric Causality Graph for Asynchronous Temporal Inference in Group Activity: Zhao Xie,

Tian Gao,

Kewei Wu,

Jiao Chang; [pdf] [supp]
[bibtex]
@InProceedings{Xie_2023_CVPR, author = {Xie, Zhao and Gao, Tian and Wu, Kewei and Chang, Jiao}, title = {An Actor-Centric Causality Graph for Asynchronous Temporal Inference in Group Activity}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6652-6661} }
Color Backdoor: A Robust Poisoning Attack in Color Space: Wenbo Jiang,

Hongwei Li,

Guowen Xu,

Tianwei Zhang; [pdf] [supp]
[bibtex]
@InProceedings{Jiang_2023_CVPR, author = {Jiang, Wenbo and Li, Hongwei and Xu, Guowen and Zhang, Tianwei}, title = {Color Backdoor: A Robust Poisoning Attack in Color Space}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8133-8142} }
How You Feelin'? Learning Emotions and Mental States in Movie Scenes: Dhruv Srivastava,

Aditya Kumar Singh,

Makarand Tapaswi; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Srivastava_2023_CVPR, author = {Srivastava, Dhruv and Singh, Aditya Kumar and Tapaswi, Makarand}, title = {How You Feelin'? Learning Emotions and Mental States in Movie Scenes}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2517-2528} }
Dynamic Inference With Grounding Based Vision and Language Models: Burak Uzkent,

Amanmeet Garg,

Wentao Zhu,

Keval Doshi,

Jingru Yi,

Xiaolong Wang,

Mohamed Omar; [pdf] [supp]
[bibtex]
@InProceedings{Uzkent_2023_CVPR, author = {Uzkent, Burak and Garg, Amanmeet and Zhu, Wentao and Doshi, Keval and Yi, Jingru and Wang, Xiaolong and Omar, Mohamed}, title = {Dynamic Inference With Grounding Based Vision and Language Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2624-2633} }
Connecting Vision and Language With Video Localized Narratives: Paul Voigtlaender,

Soravit Changpinyo,

Jordi Pont-Tuset,

Radu Soricut,

Vittorio Ferrari; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Voigtlaender_2023_CVPR, author = {Voigtlaender, Paul and Changpinyo, Soravit and Pont-Tuset, Jordi and Soricut, Radu and Ferrari, Vittorio}, title = {Connecting Vision and Language With Video Localized Narratives}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2461-2471} }
Diverse Embedding Expansion Network and Low-Light Cross-Modality Benchmark for Visible-Infrared Person Re-Identification: Yukang Zhang,

Hanzi Wang; [pdf] [arXiv]
[bibtex]
@InProceedings{Zhang_2023_CVPR, author = {Zhang, Yukang and Wang, Hanzi}, title = {Diverse Embedding Expansion Network and Low-Light Cross-Modality Benchmark for Visible-Infrared Person Re-Identification}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2153-2162} }
Visual-Language Prompt Tuning With Knowledge-Guided Context Optimization: Hantao Yao,

Rui Zhang,

Changsheng Xu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yao_2023_CVPR, author = {Yao, Hantao and Zhang, Rui and Xu, Changsheng}, title = {Visual-Language Prompt Tuning With Knowledge-Guided Context Optimization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6757-6767} }
Weakly Supervised Video Representation Learning With Unaligned Text for Sequential Videos: Sixun Dong,

Huazhang Hu,

Dongze Lian,

Weixin Luo,

Yicheng Qian,

Shenghua Gao; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Dong_2023_CVPR, author = {Dong, Sixun and Hu, Huazhang and Lian, Dongze and Luo, Weixin and Qian, Yicheng and Gao, Shenghua}, title = {Weakly Supervised Video Representation Learning With Unaligned Text for Sequential Videos}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2437-2447} }
Bootstrap Your Own Prior: Towards Distribution-Agnostic Novel Class Discovery: Muli Yang,

Liancheng Wang,

Cheng Deng,

Hanwang Zhang; [pdf] [supp]
[bibtex]
@InProceedings{Yang_2023_CVPR, author = {Yang, Muli and Wang, Liancheng and Deng, Cheng and Zhang, Hanwang}, title = {Bootstrap Your Own Prior: Towards Distribution-Agnostic Novel Class Discovery}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3459-3468} }
Learning To Generate Image Embeddings With User-Level Differential Privacy: Zheng Xu,

Maxwell Collins,

Yuxiao Wang,

Liviu Panait,

Sewoong Oh,

Sean Augenstein,

Ting Liu,

Florian Schroff,

H. Brendan McMahan; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Xu_2023_CVPR, author = {Xu, Zheng and Collins, Maxwell and Wang, Yuxiao and Panait, Liviu and Oh, Sewoong and Augenstein, Sean and Liu, Ting and Schroff, Florian and McMahan, H. Brendan}, title = {Learning To Generate Image Embeddings With User-Level Differential Privacy}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7969-7980} }
Open-Vocabulary Panoptic Segmentation With Text-to-Image Diffusion Models: Jiarui Xu,

Sifei Liu,

Arash Vahdat,

Wonmin Byeon,

Xiaolong Wang,

Shalini De Mello; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Xu_2023_CVPR, author = {Xu, Jiarui and Liu, Sifei and Vahdat, Arash and Byeon, Wonmin and Wang, Xiaolong and De Mello, Shalini}, title = {Open-Vocabulary Panoptic Segmentation With Text-to-Image Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2955-2966} }
Learning Open-Vocabulary Semantic Segmentation Models From Natural Language Supervision: Jilan Xu,

Junlin Hou,

Yuejie Zhang,

Rui Feng,

Yi Wang,

Yu Qiao,

Weidi Xie; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Xu_2023_CVPR, author = {Xu, Jilan and Hou, Junlin and Zhang, Yuejie and Feng, Rui and Wang, Yi and Qiao, Yu and Xie, Weidi}, title = {Learning Open-Vocabulary Semantic Segmentation Models From Natural Language Supervision}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2935-2944} }
OcTr: Octree-Based Transformer for 3D Object Detection: Chao Zhou,

Yanan Zhang,

Jiaxin Chen,

Di Huang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhou_2023_CVPR, author = {Zhou, Chao and Zhang, Yanan and Chen, Jiaxin and Huang, Di}, title = {OcTr: Octree-Based Transformer for 3D Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5166-5175} }
Learning Distortion Invariant Representation for Image Restoration From a Causality Perspective: Xin Li,

Bingchen Li,

Xin Jin,

Cuiling Lan,

Zhibo Chen; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Li_2023_CVPR, author = {Li, Xin and Li, Bingchen and Jin, Xin and Lan, Cuiling and Chen, Zhibo}, title = {Learning Distortion Invariant Representation for Image Restoration From a Causality Perspective}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1714-1724} }
MOT: Masked Optimal Transport for Partial Domain Adaptation: You-Wei Luo,

Chuan-Xian Ren; [pdf] [supp]
[bibtex]
@InProceedings{Luo_2023_CVPR, author = {Luo, You-Wei and Ren, Chuan-Xian}, title = {MOT: Masked Optimal Transport for Partial Domain Adaptation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3531-3540} }
UDE: A Unified Driving Engine for Human Motion Generation: Zixiang Zhou,

Baoyuan Wang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhou_2023_CVPR, author = {Zhou, Zixiang and Wang, Baoyuan}, title = {UDE: A Unified Driving Engine for Human Motion Generation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5632-5641} }
Extracting Class Activation Maps From Non-Discriminative Features As Well: Zhaozheng Chen,

Qianru Sun; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chen_2023_CVPR, author = {Chen, Zhaozheng and Sun, Qianru}, title = {Extracting Class Activation Maps From Non-Discriminative Features As Well}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3135-3144} }
BlendFields: Few-Shot Example-Driven Facial Modeling: Kacper Kania,

Stephan J. Garbin,

Andrea Tagliasacchi,

Virginia Estellers,

Kwang Moo Yi,

Julien Valentin,

Tomasz Trzciński,

Marek Kowalski; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kania_2023_CVPR, author = {Kania, Kacper and Garbin, Stephan J. and Tagliasacchi, Andrea and Estellers, Virginia and Yi, Kwang Moo and Valentin, Julien and Trzci\'nski, Tomasz and Kowalski, Marek}, title = {BlendFields: Few-Shot Example-Driven Facial Modeling}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {404-415} }
NeFII: Inverse Rendering for Reflectance Decomposition With Near-Field Indirect Illumination: Haoqian Wu,

Zhipeng Hu,

Lincheng Li,

Yongqiang Zhang,

Changjie Fan,

Xin Yu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wu_2023_CVPR, author = {Wu, Haoqian and Hu, Zhipeng and Li, Lincheng and Zhang, Yongqiang and Fan, Changjie and Yu, Xin}, title = {NeFII: Inverse Rendering for Reflectance Decomposition With Near-Field Indirect Illumination}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4295-4304} }
Towards Professional Level Crowd Annotation of Expert Domain Data: Pei Wang,

Nuno Vasconcelos; [pdf] [supp]
[bibtex]
@InProceedings{Wang_2023_CVPR, author = {Wang, Pei and Vasconcelos, Nuno}, title = {Towards Professional Level Crowd Annotation of Expert Domain Data}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3166-3175} }
Deep Stereo Video Inpainting: Zhiliang Wu,

Changchang Sun,

Hanyu Xuan,

Yan Yan; [pdf]
[bibtex]
@InProceedings{Wu_2023_CVPR, author = {Wu, Zhiliang and Sun, Changchang and Xuan, Hanyu and Yan, Yan}, title = {Deep Stereo Video Inpainting}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5693-5702} }
IFSeg: Image-Free Semantic Segmentation via Vision-Language Model: Sukmin Yun,

Seong Hyeon Park,

Paul Hongsuck Seo,

Jinwoo Shin; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yun_2023_CVPR, author = {Yun, Sukmin and Park, Seong Hyeon and Seo, Paul Hongsuck and Shin, Jinwoo}, title = {IFSeg: Image-Free Semantic Segmentation via Vision-Language Model}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2967-2977} }
Is BERT Blind? Exploring the Effect of Vision-and-Language Pretraining on Visual Language Understanding: Morris Alper,

Michael Fiman,

Hadar Averbuch-Elor; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Alper_2023_CVPR, author = {Alper, Morris and Fiman, Michael and Averbuch-Elor, Hadar}, title = {Is BERT Blind? Exploring the Effect of Vision-and-Language Pretraining on Visual Language Understanding}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6778-6788} }
3D GAN Inversion With Facial Symmetry Prior: Fei Yin,

Yong Zhang,

Xuan Wang,

Tengfei Wang,

Xiaoyu Li,

Yuan Gong,

Yanbo Fan,

Xiaodong Cun,

Ying Shan,

Cengiz Oztireli,

Yujiu Yang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yin_2023_CVPR, author = {Yin, Fei and Zhang, Yong and Wang, Xuan and Wang, Tengfei and Li, Xiaoyu and Gong, Yuan and Fan, Yanbo and Cun, Xiaodong and Shan, Ying and Oztireli, Cengiz and Yang, Yujiu}, title = {3D GAN Inversion With Facial Symmetry Prior}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {342-351} }
SDFusion: Multimodal 3D Shape Completion, Reconstruction, and Generation: Yen-Chi Cheng,

Hsin-Ying Lee,

Sergey Tulyakov,

Alexander G. Schwing,

Liang-Yan Gui; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Cheng_2023_CVPR, author = {Cheng, Yen-Chi and Lee, Hsin-Ying and Tulyakov, Sergey and Schwing, Alexander G. and Gui, Liang-Yan}, title = {SDFusion: Multimodal 3D Shape Completion, Reconstruction, and Generation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4456-4465} }
SMAE: Few-Shot Learning for HDR Deghosting With Saturation-Aware Masked Autoencoders: Qingsen Yan,

Song Zhang,

Weiye Chen,

Hao Tang,

Yu Zhu,

Jinqiu Sun,

Luc Van Gool,

Yanning Zhang; [pdf] [arXiv]
[bibtex]
@InProceedings{Yan_2023_CVPR, author = {Yan, Qingsen and Zhang, Song and Chen, Weiye and Tang, Hao and Zhu, Yu and Sun, Jinqiu and Van Gool, Luc and Zhang, Yanning}, title = {SMAE: Few-Shot Learning for HDR Deghosting With Saturation-Aware Masked Autoencoders}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5775-5784} }
Learning To Render Novel Views From Wide-Baseline Stereo Pairs: Yilun Du,

Cameron Smith,

Ayush Tewari,

Vincent Sitzmann; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Du_2023_CVPR, author = {Du, Yilun and Smith, Cameron and Tewari, Ayush and Sitzmann, Vincent}, title = {Learning To Render Novel Views From Wide-Baseline Stereo Pairs}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4970-4980} }
TryOnDiffusion: A Tale of Two UNets: Luyang Zhu,

Dawei Yang,

Tyler Zhu,

Fitsum Reda,

William Chan,

Chitwan Saharia,

Mohammad Norouzi,

Ira Kemelmacher-Shlizerman; [pdf] [supp]
[bibtex]
@InProceedings{Zhu_2023_CVPR, author = {Zhu, Luyang and Yang, Dawei and Zhu, Tyler and Reda, Fitsum and Chan, William and Saharia, Chitwan and Norouzi, Mohammad and Kemelmacher-Shlizerman, Ira}, title = {TryOnDiffusion: A Tale of Two UNets}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4606-4615} }
Automatic High Resolution Wire Segmentation and Removal: Mang Tik Chiu,

Xuaner Zhang,

Zijun Wei,

Yuqian Zhou,

Eli Shechtman,

Connelly Barnes,

Zhe Lin,

Florian Kainz,

Sohrab Amirghodsi,

Humphrey Shi; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chiu_2023_CVPR, author = {Chiu, Mang Tik and Zhang, Xuaner and Wei, Zijun and Zhou, Yuqian and Shechtman, Eli and Barnes, Connelly and Lin, Zhe and Kainz, Florian and Amirghodsi, Sohrab and Shi, Humphrey}, title = {Automatic High Resolution Wire Segmentation and Removal}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2183-2192} }
The Resource Problem of Using Linear Layer Leakage Attack in Federated Learning: Joshua C. Zhao,

Ahmed Roushdy Elkordy,

Atul Sharma,

Yahya H. Ezzeldin,

Salman Avestimehr,

Saurabh Bagchi; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhao_2023_CVPR, author = {Zhao, Joshua C. and Elkordy, Ahmed Roushdy and Sharma, Atul and Ezzeldin, Yahya H. and Avestimehr, Salman and Bagchi, Saurabh}, title = {The Resource Problem of Using Linear Layer Leakage Attack in Federated Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3974-3983} }
Seeing a Rose in Five Thousand Ways: Yunzhi Zhang,

Shangzhe Wu,

Noah Snavely,

Jiajun Wu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhang_2023_CVPR, author = {Zhang, Yunzhi and Wu, Shangzhe and Snavely, Noah and Wu, Jiajun}, title = {Seeing a Rose in Five Thousand Ways}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {962-971} }
Neural Residual Radiance Fields for Streamably Free-Viewpoint Videos: Liao Wang,

Qiang Hu,

Qihan He,

Ziyu Wang,

Jingyi Yu,

Tinne Tuytelaars,

Lan Xu,

Minye Wu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2023_CVPR, author = {Wang, Liao and Hu, Qiang and He, Qihan and Wang, Ziyu and Yu, Jingyi and Tuytelaars, Tinne and Xu, Lan and Wu, Minye}, title = {Neural Residual Radiance Fields for Streamably Free-Viewpoint Videos}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {76-87} }
ACSeg: Adaptive Conceptualization for Unsupervised Semantic Segmentation: Kehan Li,

Zhennan Wang,

Zesen Cheng,

Runyi Yu,

Yian Zhao,

Guoli Song,

Chang Liu,

Li Yuan,

Jie Chen; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Li_2023_CVPR, author = {Li, Kehan and Wang, Zhennan and Cheng, Zesen and Yu, Runyi and Zhao, Yian and Song, Guoli and Liu, Chang and Yuan, Li and Chen, Jie}, title = {ACSeg: Adaptive Conceptualization for Unsupervised Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7162-7172} }
Reproducible Scaling Laws for Contrastive Language-Image Learning: Mehdi Cherti,

Romain Beaumont,

Ross Wightman,

Mitchell Wortsman,

Gabriel Ilharco,

Cade Gordon,

Christoph Schuhmann,

Ludwig Schmidt,

Jenia Jitsev; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Cherti_2023_CVPR, author = {Cherti, Mehdi and Beaumont, Romain and Wightman, Ross and Wortsman, Mitchell and Ilharco, Gabriel and Gordon, Cade and Schuhmann, Christoph and Schmidt, Ludwig and Jitsev, Jenia}, title = {Reproducible Scaling Laws for Contrastive Language-Image Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2818-2829} }
PromptCAL: Contrastive Affinity Learning via Auxiliary Prompts for Generalized Novel Category Discovery: Sheng Zhang,

Salman Khan,

Zhiqiang Shen,

Muzammal Naseer,

Guangyi Chen,

Fahad Shahbaz Khan; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhang_2023_CVPR, author = {Zhang, Sheng and Khan, Salman and Shen, Zhiqiang and Naseer, Muzammal and Chen, Guangyi and Khan, Fahad Shahbaz}, title = {PromptCAL: Contrastive Affinity Learning via Auxiliary Prompts for Generalized Novel Category Discovery}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3479-3488} }
A Unified Spatial-Angular Structured Light for Single-View Acquisition of Shape and Reflectance: Xianmin Xu,

Yuxin Lin,

Haoyang Zhou,

Chong Zeng,

Yaxin Yu,

Kun Zhou,

Hongzhi Wu; [pdf] [supp]
[bibtex]
@InProceedings{Xu_2023_CVPR, author = {Xu, Xianmin and Lin, Yuxin and Zhou, Haoyang and Zeng, Chong and Yu, Yaxin and Zhou, Kun and Wu, Hongzhi}, title = {A Unified Spatial-Angular Structured Light for Single-View Acquisition of Shape and Reflectance}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {206-215} }
On the Difficulty of Unpaired Infrared-to-Visible Video Translation: Fine-Grained Content-Rich Patches Transfer: Zhenjie Yu,

Shuang Li,

Yirui Shen,

Chi Harold Liu,

Shuigen Wang; [pdf] [supp]
[bibtex]
@InProceedings{Yu_2023_CVPR, author = {Yu, Zhenjie and Li, Shuang and Shen, Yirui and Liu, Chi Harold and Wang, Shuigen}, title = {On the Difficulty of Unpaired Infrared-to-Visible Video Translation: Fine-Grained Content-Rich Patches Transfer}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1631-1640} }
CLIP the Gap: A Single Domain Generalization Approach for Object Detection: Vidit Vidit,

Martin Engilberge,

Mathieu Salzmann; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Vidit_2023_CVPR, author = {Vidit, Vidit and Engilberge, Martin and Salzmann, Mathieu}, title = {CLIP the Gap: A Single Domain Generalization Approach for Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3219-3229} }
On the Importance of Accurate Geometry Data for Dense 3D Vision Tasks: HyunJun Jung,

Patrick Ruhkamp,

Guangyao Zhai,

Nikolas Brasch,

Yitong Li,

Yannick Verdie,

Jifei Song,

Yiren Zhou,

Anil Armagan,

Slobodan Ilic,

Aleš Leonardis,

Nassir Navab,

Benjamin Busam; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Jung_2023_CVPR, author = {Jung, HyunJun and Ruhkamp, Patrick and Zhai, Guangyao and Brasch, Nikolas and Li, Yitong and Verdie, Yannick and Song, Jifei and Zhou, Yiren and Armagan, Anil and Ilic, Slobodan and Leonardis, Ale\v{s} and Navab, Nassir and Busam, Benjamin}, title = {On the Importance of Accurate Geometry Data for Dense 3D Vision Tasks}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {780-791} }
Understanding Masked Autoencoders via Hierarchical Latent Variable Models: Lingjing Kong,

Martin Q. Ma,

Guangyi Chen,

Eric P. Xing,

Yuejie Chi,

Louis-Philippe Morency,

Kun Zhang; [pdf] [supp]
[bibtex]
@InProceedings{Kong_2023_CVPR, author = {Kong, Lingjing and Ma, Martin Q. and Chen, Guangyi and Xing, Eric P. and Chi, Yuejie and Morency, Louis-Philippe and Zhang, Kun}, title = {Understanding Masked Autoencoders via Hierarchical Latent Variable Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7918-7928} }
Unbalanced Optimal Transport: A Unified Framework for Object Detection: Henri De Plaen,

Pierre-François De Plaen,

Johan A. K. Suykens,

Marc Proesmans,

Tinne Tuytelaars,

Luc Van Gool; [pdf] [supp]
[bibtex]
@InProceedings{De_Plaen_2023_CVPR, author = {De Plaen, Henri and De Plaen, Pierre-Fran\c{c}ois and Suykens, Johan A. K. and Proesmans, Marc and Tuytelaars, Tinne and Van Gool, Luc}, title = {Unbalanced Optimal Transport: A Unified Framework for Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3198-3207} }
Photo Pre-Training, but for Sketch: Ke Li,

Kaiyue Pang,

Yi-Zhe Song; [pdf] [supp]
[bibtex]
@InProceedings{Li_2023_CVPR, author = {Li, Ke and Pang, Kaiyue and Song, Yi-Zhe}, title = {Photo Pre-Training, but for Sketch}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2754-2764} }
NeuralPCI: Spatio-Temporal Neural Field for 3D Point Cloud Multi-Frame Non-Linear Interpolation: Zehan Zheng,

Danni Wu,

Ruisi Lu,

Fan Lu,

Guang Chen,

Changjun Jiang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zheng_2023_CVPR, author = {Zheng, Zehan and Wu, Danni and Lu, Ruisi and Lu, Fan and Chen, Guang and Jiang, Changjun}, title = {NeuralPCI: Spatio-Temporal Neural Field for 3D Point Cloud Multi-Frame Non-Linear Interpolation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {909-918} }
Bidirectional Cross-Modal Knowledge Exploration for Video Recognition With Pre-Trained Vision-Language Models: Wenhao Wu,

Xiaohan Wang,

Haipeng Luo,

Jingdong Wang,

Yi Yang,

Wanli Ouyang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wu_2023_CVPR, author = {Wu, Wenhao and Wang, Xiaohan and Luo, Haipeng and Wang, Jingdong and Yang, Yi and Ouyang, Wanli}, title = {Bidirectional Cross-Modal Knowledge Exploration for Video Recognition With Pre-Trained Vision-Language Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6620-6630} }
Adaptive Plasticity Improvement for Continual Learning: Yan-Shuo Liang,

Wu-Jun Li; [pdf] [supp]
[bibtex]
@InProceedings{Liang_2023_CVPR, author = {Liang, Yan-Shuo and Li, Wu-Jun}, title = {Adaptive Plasticity Improvement for Continual Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7816-7825} }
Semantic Scene Completion With Cleaner Self: Fengyun Wang,

Dong Zhang,

Hanwang Zhang,

Jinhui Tang,

Qianru Sun; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2023_CVPR, author = {Wang, Fengyun and Zhang, Dong and Zhang, Hanwang and Tang, Jinhui and Sun, Qianru}, title = {Semantic Scene Completion With Cleaner Self}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {867-877} }
Deep Factorized Metric Learning: Chengkun Wang,

Wenzhao Zheng,

Junlong Li,

Jie Zhou,

Jiwen Lu; [pdf]
[bibtex]
@InProceedings{Wang_2023_CVPR, author = {Wang, Chengkun and Zheng, Wenzhao and Li, Junlong and Zhou, Jie and Lu, Jiwen}, title = {Deep Factorized Metric Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7672-7682} }
High-Fidelity 3D Face Generation From Natural Language Descriptions: Menghua Wu,

Hao Zhu,

Linjia Huang,

Yiyu Zhuang,

Yuanxun Lu,

Xun Cao; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wu_2023_CVPR, author = {Wu, Menghua and Zhu, Hao and Huang, Linjia and Zhuang, Yiyu and Lu, Yuanxun and Cao, Xun}, title = {High-Fidelity 3D Face Generation From Natural Language Descriptions}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4521-4530} }
Dual-Path Adaptation From Image to Video Transformers: Jungin Park,

Jiyoung Lee,

Kwanghoon Sohn; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Park_2023_CVPR, author = {Park, Jungin and Lee, Jiyoung and Sohn, Kwanghoon}, title = {Dual-Path Adaptation From Image to Video Transformers}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2203-2213} }
Towards Better Decision Forests: Forest Alternating Optimization: Miguel Á. Carreira-Perpiñán,

Magzhan Gabidolla,

Arman Zharmagambetov; [pdf] [supp]
[bibtex]
@InProceedings{Carreira-Perpinan_2023_CVPR, author = {Carreira-Perpi\~n\'an, Miguel \'A. and Gabidolla, Magzhan and Zharmagambetov, Arman}, title = {Towards Better Decision Forests: Forest Alternating Optimization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7589-7598} }
Dynamic Graph Enhanced Contrastive Learning for Chest X-Ray Report Generation: Mingjie Li,

Bingqian Lin,

Zicong Chen,

Haokun Lin,

Xiaodan Liang,

Xiaojun Chang; [pdf]
[bibtex]
@InProceedings{Li_2023_CVPR, author = {Li, Mingjie and Lin, Bingqian and Chen, Zicong and Lin, Haokun and Liang, Xiaodan and Chang, Xiaojun}, title = {Dynamic Graph Enhanced Contrastive Learning for Chest X-Ray Report Generation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3334-3343} }
FrustumFormer: Adaptive Instance-Aware Resampling for Multi-View 3D Detection: Yuqi Wang,

Yuntao Chen,

Zhaoxiang Zhang; [pdf] [arXiv]
[bibtex]
@InProceedings{Wang_2023_CVPR, author = {Wang, Yuqi and Chen, Yuntao and Zhang, Zhaoxiang}, title = {FrustumFormer: Adaptive Instance-Aware Resampling for Multi-View 3D Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5096-5105} }
Class-Conditional Sharpness-Aware Minimization for Deep Long-Tailed Recognition: Zhipeng Zhou,

Lanqing Li,

Peilin Zhao,

Pheng-Ann Heng,

Wei Gong; [pdf] [supp]
[bibtex]
@InProceedings{Zhou_2023_CVPR, author = {Zhou, Zhipeng and Li, Lanqing and Zhao, Peilin and Heng, Pheng-Ann and Gong, Wei}, title = {Class-Conditional Sharpness-Aware Minimization for Deep Long-Tailed Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3499-3509} }
Efficient On-Device Training via Gradient Filtering: Yuedong Yang,

Guihong Li,

Radu Marculescu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yang_2023_CVPR, author = {Yang, Yuedong and Li, Guihong and Marculescu, Radu}, title = {Efficient On-Device Training via Gradient Filtering}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3811-3820} }
3D Human Mesh Estimation From Virtual Markers: Xiaoxuan Ma,

Jiajun Su,

Chunyu Wang,

Wentao Zhu,

Yizhou Wang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ma_2023_CVPR, author = {Ma, Xiaoxuan and Su, Jiajun and Wang, Chunyu and Zhu, Wentao and Wang, Yizhou}, title = {3D Human Mesh Estimation From Virtual Markers}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {534-543} }
CUDA: Convolution-Based Unlearnable Datasets: Vinu Sankar Sadasivan,

Mahdi Soltanolkotabi,

Soheil Feizi; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Sadasivan_2023_CVPR, author = {Sadasivan, Vinu Sankar and Soltanolkotabi, Mahdi and Feizi, Soheil}, title = {CUDA: Convolution-Based Unlearnable Datasets}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3862-3871} }
MIANet: Aggregating Unbiased Instance and General Information for Few-Shot Semantic Segmentation: Yong Yang,

Qiong Chen,

Yuan Feng,

Tianlin Huang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yang_2023_CVPR, author = {Yang, Yong and Chen, Qiong and Feng, Yuan and Huang, Tianlin}, title = {MIANet: Aggregating Unbiased Instance and General Information for Few-Shot Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7131-7140} }
Starting From Non-Parametric Networks for 3D Point Cloud Analysis: Renrui Zhang,

Liuhui Wang,

Yali Wang,

Peng Gao,

Hongsheng Li,

Jianbo Shi; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhang_2023_CVPR, author = {Zhang, Renrui and Wang, Liuhui and Wang, Yali and Gao, Peng and Li, Hongsheng and Shi, Jianbo}, title = {Starting From Non-Parametric Networks for 3D Point Cloud Analysis}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5344-5353} }
Light Source Separation and Intrinsic Image Decomposition Under AC Illumination: Yusaku Yoshida,

Ryo Kawahara,

Takahiro Okabe; [pdf] [supp]
[bibtex]
@InProceedings{Yoshida_2023_CVPR, author = {Yoshida, Yusaku and Kawahara, Ryo and Okabe, Takahiro}, title = {Light Source Separation and Intrinsic Image Decomposition Under AC Illumination}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5735-5743} }
CFA: Class-Wise Calibrated Fair Adversarial Training: Zeming Wei,

Yifei Wang,

Yiwen Guo,

Yisen Wang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wei_2023_CVPR, author = {Wei, Zeming and Wang, Yifei and Guo, Yiwen and Wang, Yisen}, title = {CFA: Class-Wise Calibrated Fair Adversarial Training}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8193-8201} }
3D Human Pose Estimation With Spatio-Temporal Criss-Cross Attention: Zhenhua Tang,

Zhaofan Qiu,

Yanbin Hao,

Richang Hong,

Ting Yao; [pdf] [supp]
[bibtex]
@InProceedings{Tang_2023_CVPR, author = {Tang, Zhenhua and Qiu, Zhaofan and Hao, Yanbin and Hong, Richang and Yao, Ting}, title = {3D Human Pose Estimation With Spatio-Temporal Criss-Cross Attention}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4790-4799} }
Plateau-Reduced Differentiable Path Tracing: Michael Fischer,

Tobias Ritschel; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Fischer_2023_CVPR, author = {Fischer, Michael and Ritschel, Tobias}, title = {Plateau-Reduced Differentiable Path Tracing}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4285-4294} }
Glocal Energy-Based Learning for Few-Shot Open-Set Recognition: Haoyu Wang,

Guansong Pang,

Peng Wang,

Lei Zhang,

Wei Wei,

Yanning Zhang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2023_CVPR, author = {Wang, Haoyu and Pang, Guansong and Wang, Peng and Zhang, Lei and Wei, Wei and Zhang, Yanning}, title = {Glocal Energy-Based Learning for Few-Shot Open-Set Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7507-7516} }
Revisiting Temporal Modeling for CLIP-Based Image-to-Video Knowledge Transferring: Ruyang Liu,

Jingjia Huang,

Ge Li,

Jiashi Feng,

Xinglong Wu,

Thomas H. Li; [pdf] [arXiv]
[bibtex]
@InProceedings{Liu_2023_CVPR, author = {Liu, Ruyang and Huang, Jingjia and Li, Ge and Feng, Jiashi and Wu, Xinglong and Li, Thomas H.}, title = {Revisiting Temporal Modeling for CLIP-Based Image-to-Video Knowledge Transferring}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6555-6564} }
EFEM: Equivariant Neural Field Expectation Maximization for 3D Object Segmentation Without Scene Supervision: Jiahui Lei,

Congyue Deng,

Karl Schmeckpeper,

Leonidas Guibas,

Kostas Daniilidis; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Lei_2023_CVPR, author = {Lei, Jiahui and Deng, Congyue and Schmeckpeper, Karl and Guibas, Leonidas and Daniilidis, Kostas}, title = {EFEM: Equivariant Neural Field Expectation Maximization for 3D Object Segmentation Without Scene Supervision}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4902-4912} }
ECON: Explicit Clothed Humans Optimized via Normal Integration: Yuliang Xiu,

Jinlong Yang,

Xu Cao,

Dimitrios Tzionas,

Michael J. Black; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Xiu_2023_CVPR, author = {Xiu, Yuliang and Yang, Jinlong and Cao, Xu and Tzionas, Dimitrios and Black, Michael J.}, title = {ECON: Explicit Clothed Humans Optimized via Normal Integration}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {512-523} }
F2-NeRF: Fast Neural Radiance Field Training With Free Camera Trajectories: Peng Wang,

Yuan Liu,

Zhaoxi Chen,

Lingjie Liu,

Ziwei Liu,

Taku Komura,

Christian Theobalt,

Wenping Wang; [pdf] [supp]
[bibtex]
@InProceedings{Wang_2023_CVPR, author = {Wang, Peng and Liu, Yuan and Chen, Zhaoxi and Liu, Lingjie and Liu, Ziwei and Komura, Taku and Theobalt, Christian and Wang, Wenping}, title = {F2-NeRF: Fast Neural Radiance Field Training With Free Camera Trajectories}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4150-4159} }
Learning To Detect and Segment for Open Vocabulary Object Detection: Tao Wang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2023_CVPR, author = {Wang, Tao}, title = {Learning To Detect and Segment for Open Vocabulary Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7051-7060} }
Disentangling Writer and Character Styles for Handwriting Generation: Gang Dai,

Yifan Zhang,

Qingfeng Wang,

Qing Du,

Zhuliang Yu,

Zhuoman Liu,

Shuangping Huang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Dai_2023_CVPR, author = {Dai, Gang and Zhang, Yifan and Wang, Qingfeng and Du, Qing and Yu, Zhuliang and Liu, Zhuoman and Huang, Shuangping}, title = {Disentangling Writer and Character Styles for Handwriting Generation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5977-5986} }
StyleSync: High-Fidelity Generalized and Personalized Lip Sync in Style-Based Generator: Jiazhi Guan,

Zhanwang Zhang,

Hang Zhou,

Tianshu Hu,

Kaisiyuan Wang,

Dongliang He,

Haocheng Feng,

Jingtuo Liu,

Errui Ding,

Ziwei Liu,

Jingdong Wang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Guan_2023_CVPR, author = {Guan, Jiazhi and Zhang, Zhanwang and Zhou, Hang and Hu, Tianshu and Wang, Kaisiyuan and He, Dongliang and Feng, Haocheng and Liu, Jingtuo and Ding, Errui and Liu, Ziwei and Wang, Jingdong}, title = {StyleSync: High-Fidelity Generalized and Personalized Lip Sync in Style-Based Generator}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1505-1515} }
Coreset Sampling From Open-Set for Fine-Grained Self-Supervised Learning: Sungnyun Kim,

Sangmin Bae,

Se-Young Yun; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kim_2023_CVPR, author = {Kim, Sungnyun and Bae, Sangmin and Yun, Se-Young}, title = {Coreset Sampling From Open-Set for Fine-Grained Self-Supervised Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7537-7547} }
Generative Semantic Segmentation: Jiaqi Chen,

Jiachen Lu,

Xiatian Zhu,

Li Zhang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chen_2023_CVPR, author = {Chen, Jiaqi and Lu, Jiachen and Zhu, Xiatian and Zhang, Li}, title = {Generative Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7111-7120} }
Instant-NVR: Instant Neural Volumetric Rendering for Human-Object Interactions From Monocular RGBD Stream: Yuheng Jiang,

Kaixin Yao,

Zhuo Su,

Zhehao Shen,

Haimin Luo,

Lan Xu; [pdf]
[bibtex]
@InProceedings{Jiang_2023_CVPR, author = {Jiang, Yuheng and Yao, Kaixin and Su, Zhuo and Shen, Zhehao and Luo, Haimin and Xu, Lan}, title = {Instant-NVR: Instant Neural Volumetric Rendering for Human-Object Interactions From Monocular RGBD Stream}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {595-605} }
Aligning Step-by-Step Instructional Diagrams to Video Demonstrations: Jiahao Zhang,

Anoop Cherian,

Yanbin Liu,

Yizhak Ben-Shabat,

Cristian Rodriguez,

Stephen Gould; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhang_2023_CVPR, author = {Zhang, Jiahao and Cherian, Anoop and Liu, Yanbin and Ben-Shabat, Yizhak and Rodriguez, Cristian and Gould, Stephen}, title = {Aligning Step-by-Step Instructional Diagrams to Video Demonstrations}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2483-2492} }
High-Fidelity and Freely Controllable Talking Head Video Generation: Yue Gao,

Yuan Zhou,

Jinglu Wang,

Xiao Li,

Xiang Ming,

Yan Lu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Gao_2023_CVPR, author = {Gao, Yue and Zhou, Yuan and Wang, Jinglu and Li, Xiao and Ming, Xiang and Lu, Yan}, title = {High-Fidelity and Freely Controllable Talking Head Video Generation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5609-5619} }
Q-DETR: An Efficient Low-Bit Quantized Detection Transformer: Sheng Xu,

Yanjing Li,

Mingbao Lin,

Peng Gao,

Guodong Guo,

Jinhu Lü,

Baochang Zhang; [pdf]
[bibtex]
@InProceedings{Xu_2023_CVPR, author = {Xu, Sheng and Li, Yanjing and Lin, Mingbao and Gao, Peng and Guo, Guodong and L\"u, Jinhu and Zhang, Baochang}, title = {Q-DETR: An Efficient Low-Bit Quantized Detection Transformer}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3842-3851} }
Burstormer: Burst Image Restoration and Enhancement Transformer: Akshay Dudhane,

Syed Waqas Zamir,

Salman Khan,

Fahad Shahbaz Khan,

Ming-Hsuan Yang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Dudhane_2023_CVPR, author = {Dudhane, Akshay and Zamir, Syed Waqas and Khan, Salman and Khan, Fahad Shahbaz and Yang, Ming-Hsuan}, title = {Burstormer: Burst Image Restoration and Enhancement Transformer}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5703-5712} }
Progressive Transformation Learning for Leveraging Virtual Images in Training: Yi-Ting Shen,

Hyungtae Lee,

Heesung Kwon,

Shuvra S. Bhattacharyya; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Shen_2023_CVPR, author = {Shen, Yi-Ting and Lee, Hyungtae and Kwon, Heesung and Bhattacharyya, Shuvra S.}, title = {Progressive Transformation Learning for Leveraging Virtual Images in Training}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {835-844} }
Co-Speech Gesture Synthesis by Reinforcement Learning With Contrastive Pre-Trained Rewards: Mingyang Sun,

Mengchen Zhao,

Yaqing Hou,

Minglei Li,

Huang Xu,

Songcen Xu,

Jianye Hao; [pdf]
[bibtex]
@InProceedings{Sun_2023_CVPR, author = {Sun, Mingyang and Zhao, Mengchen and Hou, Yaqing and Li, Minglei and Xu, Huang and Xu, Songcen and Hao, Jianye}, title = {Co-Speech Gesture Synthesis by Reinforcement Learning With Contrastive Pre-Trained Rewards}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2331-2340} }
SDC-UDA: Volumetric Unsupervised Domain Adaptation Framework for Slice-Direction Continuous Cross-Modality Medical Image Segmentation: Hyungseob Shin,

Hyeongyu Kim,

Sewon Kim,

Yohan Jun,

Taejoon Eo,

Dosik Hwang; [pdf] [supp]
[bibtex]
@InProceedings{Shin_2023_CVPR, author = {Shin, Hyungseob and Kim, Hyeongyu and Kim, Sewon and Jun, Yohan and Eo, Taejoon and Hwang, Dosik}, title = {SDC-UDA: Volumetric Unsupervised Domain Adaptation Framework for Slice-Direction Continuous Cross-Modality Medical Image Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7412-7421} }
Divide and Conquer: Answering Questions With Object Factorization and Compositional Reasoning: Shi Chen,

Qi Zhao; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chen_2023_CVPR, author = {Chen, Shi and Zhao, Qi}, title = {Divide and Conquer: Answering Questions With Object Factorization and Compositional Reasoning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6736-6745} }
Jedi: Entropy-Based Localization and Removal of Adversarial Patches: Bilel Tarchoun,

Anouar Ben Khalifa,

Mohamed Ali Mahjoub,

Nael Abu-Ghazaleh,

Ihsen Alouani; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Tarchoun_2023_CVPR, author = {Tarchoun, Bilel and Ben Khalifa, Anouar and Mahjoub, Mohamed Ali and Abu-Ghazaleh, Nael and Alouani, Ihsen}, title = {Jedi: Entropy-Based Localization and Removal of Adversarial Patches}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4087-4095} }
Localized Semantic Feature Mixers for Efficient Pedestrian Detection in Autonomous Driving: Abdul Hannan Khan,

Mohammed Shariq Nawaz,

Andreas Dengel; [pdf]
[bibtex]
@InProceedings{Khan_2023_CVPR, author = {Khan, Abdul Hannan and Nawaz, Mohammed Shariq and Dengel, Andreas}, title = {Localized Semantic Feature Mixers for Efficient Pedestrian Detection in Autonomous Driving}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5476-5485} }
VDN-NeRF: Resolving Shape-Radiance Ambiguity via View-Dependence Normalization: Bingfan Zhu,

Yanchao Yang,

Xulong Wang,

Youyi Zheng,

Leonidas Guibas; [pdf] [supp]
[bibtex]
@InProceedings{Zhu_2023_CVPR, author = {Zhu, Bingfan and Yang, Yanchao and Wang, Xulong and Zheng, Youyi and Guibas, Leonidas}, title = {VDN-NeRF: Resolving Shape-Radiance Ambiguity via View-Dependence Normalization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {35-45} }
Coaching a Teachable Student: Jimuyang Zhang,

Zanming Huang,

Eshed Ohn-Bar; [pdf]
[bibtex]
@InProceedings{Zhang_2023_CVPR, author = {Zhang, Jimuyang and Huang, Zanming and Ohn-Bar, Eshed}, title = {Coaching a Teachable Student}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7805-7815} }
RealImpact: A Dataset of Impact Sound Fields for Real Objects: Samuel Clarke,

Ruohan Gao,

Mason Wang,

Mark Rau,

Julia Xu,

Jui-Hsien Wang,

Doug L. James,

Jiajun Wu; [pdf] [supp]
[bibtex]
@InProceedings{Clarke_2023_CVPR, author = {Clarke, Samuel and Gao, Ruohan and Wang, Mason and Rau, Mark and Xu, Julia and Wang, Jui-Hsien and James, Doug L. and Wu, Jiajun}, title = {RealImpact: A Dataset of Impact Sound Fields for Real Objects}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1516-1525} }
Uni-Perceiver v2: A Generalist Model for Large-Scale Vision and Vision-Language Tasks: Hao Li,

Jinguo Zhu,

Xiaohu Jiang,

Xizhou Zhu,

Hongsheng Li,

Chun Yuan,

Xiaohua Wang,

Yu Qiao,

Xiaogang Wang,

Wenhai Wang,

Jifeng Dai; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Li_2023_CVPR, author = {Li, Hao and Zhu, Jinguo and Jiang, Xiaohu and Zhu, Xizhou and Li, Hongsheng and Yuan, Chun and Wang, Xiaohua and Qiao, Yu and Wang, Xiaogang and Wang, Wenhai and Dai, Jifeng}, title = {Uni-Perceiver v2: A Generalist Model for Large-Scale Vision and Vision-Language Tasks}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2691-2700} }
Decompose More and Aggregate Better: Two Closer Looks at Frequency Representation Learning for Human Motion Prediction: Xuehao Gao,

Shaoyi Du,

Yang Wu,

Yang Yang; [pdf] [supp]
[bibtex]
@InProceedings{Gao_2023_CVPR, author = {Gao, Xuehao and Du, Shaoyi and Wu, Yang and Yang, Yang}, title = {Decompose More and Aggregate Better: Two Closer Looks at Frequency Representation Learning for Human Motion Prediction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6451-6460} }
Affection: Learning Affective Explanations for Real-World Visual Data: Panos Achlioptas,

Maks Ovsjanikov,

Leonidas Guibas,

Sergey Tulyakov; [pdf] [arXiv]
[bibtex]
@InProceedings{Achlioptas_2023_CVPR, author = {Achlioptas, Panos and Ovsjanikov, Maks and Guibas, Leonidas and Tulyakov, Sergey}, title = {Affection: Learning Affective Explanations for Real-World Visual Data}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6641-6651} }
PLA: Language-Driven Open-Vocabulary 3D Scene Understanding: Runyu Ding,

Jihan Yang,

Chuhui Xue,

Wenqing Zhang,

Song Bai,

Xiaojuan Qi; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ding_2023_CVPR, author = {Ding, Runyu and Yang, Jihan and Xue, Chuhui and Zhang, Wenqing and Bai, Song and Qi, Xiaojuan}, title = {PLA: Language-Driven Open-Vocabulary 3D Scene Understanding}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7010-7019} }
InstMove: Instance Motion for Object-Centric Video Segmentation: Qihao Liu,

Junfeng Wu,

Yi Jiang,

Xiang Bai,

Alan L. Yuille,

Song Bai; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Liu_2023_CVPR, author = {Liu, Qihao and Wu, Junfeng and Jiang, Yi and Bai, Xiang and Yuille, Alan L. and Bai, Song}, title = {InstMove: Instance Motion for Object-Centric Video Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6344-6354} }
Towards Effective Adversarial Textured 3D Meshes on Physical Face Recognition: Xiao Yang,

Chang Liu,

Longlong Xu,

Yikai Wang,

Yinpeng Dong,

Ning Chen,

Hang Su,

Jun Zhu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yang_2023_CVPR, author = {Yang, Xiao and Liu, Chang and Xu, Longlong and Wang, Yikai and Dong, Yinpeng and Chen, Ning and Su, Hang and Zhu, Jun}, title = {Towards Effective Adversarial Textured 3D Meshes on Physical Face Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4119-4128} }
Effective Ambiguity Attack Against Passport-Based DNN Intellectual Property Protection Schemes Through Fully Connected Layer Substitution: Yiming Chen,

Jinyu Tian,

Xiangyu Chen,

Jiantao Zhou; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chen_2023_CVPR, author = {Chen, Yiming and Tian, Jinyu and Chen, Xiangyu and Zhou, Jiantao}, title = {Effective Ambiguity Attack Against Passport-Based DNN Intellectual Property Protection Schemes Through Fully Connected Layer Substitution}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8123-8132} }
TempSAL - Uncovering Temporal Information for Deep Saliency Prediction: Bahar Aydemir,

Ludo Hoffstetter,

Tong Zhang,

Mathieu Salzmann,

Sabine Süsstrunk; [pdf] [supp]
[bibtex]
@InProceedings{Aydemir_2023_CVPR, author = {Aydemir, Bahar and Hoffstetter, Ludo and Zhang, Tong and Salzmann, Mathieu and S\"usstrunk, Sabine}, title = {TempSAL - Uncovering Temporal Information for Deep Saliency Prediction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6461-6470} }
Megahertz Light Steering Without Moving Parts: Adithya Pediredla,

Srinivasa G. Narasimhan,

Maysamreza Chamanzar,

Ioannis Gkioulekas; [pdf] [supp]
[bibtex]
@InProceedings{Pediredla_2023_CVPR, author = {Pediredla, Adithya and Narasimhan, Srinivasa G. and Chamanzar, Maysamreza and Gkioulekas, Ioannis}, title = {Megahertz Light Steering Without Moving Parts}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1-12} }
Iterative Proposal Refinement for Weakly-Supervised Video Grounding: Meng Cao,

Fangyun Wei,

Can Xu,

Xiubo Geng,

Long Chen,

Can Zhang,

Yuexian Zou,

Tao Shen,

Daxin Jiang; [pdf] [supp]
[bibtex]
@InProceedings{Cao_2023_CVPR, author = {Cao, Meng and Wei, Fangyun and Xu, Can and Geng, Xiubo and Chen, Long and Zhang, Can and Zou, Yuexian and Shen, Tao and Jiang, Daxin}, title = {Iterative Proposal Refinement for Weakly-Supervised Video Grounding}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6524-6534} }
SCConv: Spatial and Channel Reconstruction Convolution for Feature Redundancy: Jiafeng Li,

Ying Wen,

Lianghua He; [pdf]
[bibtex]
@InProceedings{Li_2023_CVPR, author = {Li, Jiafeng and Wen, Ying and He, Lianghua}, title = {SCConv: Spatial and Channel Reconstruction Convolution for Feature Redundancy}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6153-6162} }
Positive-Augmented Contrastive Learning for Image and Video Captioning Evaluation: Sara Sarto,

Manuele Barraco,

Marcella Cornia,

Lorenzo Baraldi,

Rita Cucchiara; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Sarto_2023_CVPR, author = {Sarto, Sara and Barraco, Manuele and Cornia, Marcella and Baraldi, Lorenzo and Cucchiara, Rita}, title = {Positive-Augmented Contrastive Learning for Image and Video Captioning Evaluation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6914-6924} }
3D Cinemagraphy From a Single Image: Xingyi Li,

Zhiguo Cao,

Huiqiang Sun,

Jianming Zhang,

Ke Xian,

Guosheng Lin; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Li_2023_CVPR, author = {Li, Xingyi and Cao, Zhiguo and Sun, Huiqiang and Zhang, Jianming and Xian, Ke and Lin, Guosheng}, title = {3D Cinemagraphy From a Single Image}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4595-4605} }
AttriCLIP: A Non-Incremental Learner for Incremental Knowledge Learning: Runqi Wang,

Xiaoyue Duan,

Guoliang Kang,

Jianzhuang Liu,

Shaohui Lin,

Songcen Xu,

Jinhu Lü,

Baochang Zhang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2023_CVPR, author = {Wang, Runqi and Duan, Xiaoyue and Kang, Guoliang and Liu, Jianzhuang and Lin, Shaohui and Xu, Songcen and L\"u, Jinhu and Zhang, Baochang}, title = {AttriCLIP: A Non-Incremental Learner for Incremental Knowledge Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3654-3663} }
StyleRes: Transforming the Residuals for Real Image Editing With StyleGAN: Hamza Pehlivan,

Yusuf Dalva,

Aysegul Dundar; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Pehlivan_2023_CVPR, author = {Pehlivan, Hamza and Dalva, Yusuf and Dundar, Aysegul}, title = {StyleRes: Transforming the Residuals for Real Image Editing With StyleGAN}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1828-1837} }
Diffusion Video Autoencoders: Toward Temporally Consistent Face Video Editing via Disentangled Video Encoding: Gyeongman Kim,

Hajin Shim,

Hyunsu Kim,

Yunjey Choi,

Junho Kim,

Eunho Yang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kim_2023_CVPR, author = {Kim, Gyeongman and Shim, Hajin and Kim, Hyunsu and Choi, Yunjey and Kim, Junho and Yang, Eunho}, title = {Diffusion Video Autoencoders: Toward Temporally Consistent Face Video Editing via Disentangled Video Encoding}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6091-6100} }
SIM: Semantic-Aware Instance Mask Generation for Box-Supervised Instance Segmentation: Ruihuang Li,

Chenhang He,

Yabin Zhang,

Shuai Li,

Liyi Chen,

Lei Zhang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Li_2023_CVPR, author = {Li, Ruihuang and He, Chenhang and Zhang, Yabin and Li, Shuai and Chen, Liyi and Zhang, Lei}, title = {SIM: Semantic-Aware Instance Mask Generation for Box-Supervised Instance Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7193-7203} }
Compression-Aware Video Super-Resolution: Yingwei Wang,

Takashi Isobe,

Xu Jia,

Xin Tao,

Huchuan Lu,

Yu-Wing Tai; [pdf]
[bibtex]
@InProceedings{Wang_2023_CVPR, author = {Wang, Yingwei and Isobe, Takashi and Jia, Xu and Tao, Xin and Lu, Huchuan and Tai, Yu-Wing}, title = {Compression-Aware Video Super-Resolution}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2012-2021} }
Incremental 3D Semantic Scene Graph Prediction From RGB Sequences: Shun-Cheng Wu,

Keisuke Tateno,

Nassir Navab,

Federico Tombari; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wu_2023_CVPR, author = {Wu, Shun-Cheng and Tateno, Keisuke and Navab, Nassir and Tombari, Federico}, title = {Incremental 3D Semantic Scene Graph Prediction From RGB Sequences}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5064-5074} }
VLPD: Context-Aware Pedestrian Detection via Vision-Language Semantic Self-Supervision: Mengyin Liu,

Jie Jiang,

Chao Zhu,

Xu-Cheng Yin; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Liu_2023_CVPR, author = {Liu, Mengyin and Jiang, Jie and Zhu, Chao and Yin, Xu-Cheng}, title = {VLPD: Context-Aware Pedestrian Detection via Vision-Language Semantic Self-Supervision}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6662-6671} }
TexPose: Neural Texture Learning for Self-Supervised 6D Object Pose Estimation: Hanzhi Chen,

Fabian Manhardt,

Nassir Navab,

Benjamin Busam; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chen_2023_CVPR, author = {Chen, Hanzhi and Manhardt, Fabian and Navab, Nassir and Busam, Benjamin}, title = {TexPose: Neural Texture Learning for Self-Supervised 6D Object Pose Estimation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4841-4852} }
DynIBaR: Neural Dynamic Image-Based Rendering: Zhengqi Li,

Qianqian Wang,

Forrester Cole,

Richard Tucker,

Noah Snavely; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Li_2023_CVPR, author = {Li, Zhengqi and Wang, Qianqian and Cole, Forrester and Tucker, Richard and Snavely, Noah}, title = {DynIBaR: Neural Dynamic Image-Based Rendering}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4273-4284} }
Unsupervised Object Localization: Observing the Background To Discover Objects: Oriane Siméoni,

Chloé Sekkat,

Gilles Puy,

Antonín Vobecký,

Éloi Zablocki,

Patrick Pérez; [pdf] [supp]
[bibtex]
@InProceedings{Simeoni_2023_CVPR, author = {Sim\'eoni, Oriane and Sekkat, Chlo\'e and Puy, Gilles and Vobeck\'y, Anton{\'\i}n and Zablocki, \'Eloi and P\'erez, Patrick}, title = {Unsupervised Object Localization: Observing the Background To Discover Objects}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3176-3186} }
BEV-LaneDet: An Efficient 3D Lane Detection Based on Virtual Camera via Key-Points: Ruihao Wang,

Jian Qin,

Kaiying Li,

Yaochen Li,

Dong Cao,

Jintao Xu; [pdf] [supp]
[bibtex]
@InProceedings{Wang_2023_CVPR, author = {Wang, Ruihao and Qin, Jian and Li, Kaiying and Li, Yaochen and Cao, Dong and Xu, Jintao}, title = {BEV-LaneDet: An Efficient 3D Lane Detection Based on Virtual Camera via Key-Points}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1002-1011} }
Self-Supervised 3D Scene Flow Estimation Guided by Superpoints: Yaqi Shen,

Le Hui,

Jin Xie,

Jian Yang; [pdf] [arXiv]
[bibtex]
@InProceedings{Shen_2023_CVPR, author = {Shen, Yaqi and Hui, Le and Xie, Jin and Yang, Jian}, title = {Self-Supervised 3D Scene Flow Estimation Guided by Superpoints}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5271-5280} }
A Unified Pyramid Recurrent Network for Video Frame Interpolation: Xin Jin,

Longhai Wu,

Jie Chen,

Youxin Chen,

Jayoon Koo,

Cheul-hee Hahm; [pdf] [arXiv]
[bibtex]
@InProceedings{Jin_2023_CVPR, author = {Jin, Xin and Wu, Longhai and Chen, Jie and Chen, Youxin and Koo, Jayoon and Hahm, Cheul-hee}, title = {A Unified Pyramid Recurrent Network for Video Frame Interpolation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1578-1587} }
DiffusioNeRF: Regularizing Neural Radiance Fields With Denoising Diffusion Models: Jamie Wynn,

Daniyar Turmukhambetov; [pdf] [arXiv]
[bibtex]
@InProceedings{Wynn_2023_CVPR, author = {Wynn, Jamie and Turmukhambetov, Daniyar}, title = {DiffusioNeRF: Regularizing Neural Radiance Fields With Denoising Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4180-4189} }
Edge-Aware Regional Message Passing Controller for Image Forgery Localization: Dong Li,

Jiaying Zhu,

Menglu Wang,

Jiawei Liu,

Xueyang Fu,

Zheng-Jun Zha; [pdf]
[bibtex]
@InProceedings{Li_2023_CVPR, author = {Li, Dong and Zhu, Jiaying and Wang, Menglu and Liu, Jiawei and Fu, Xueyang and Zha, Zheng-Jun}, title = {Edge-Aware Regional Message Passing Controller for Image Forgery Localization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8222-8232} }
Spatiotemporal Self-Supervised Learning for Point Clouds in the Wild: Yanhao Wu,

Tong Zhang,

Wei Ke,

Sabine Süsstrunk,

Mathieu Salzmann; [pdf] [arXiv]
[bibtex]
@InProceedings{Wu_2023_CVPR, author = {Wu, Yanhao and Zhang, Tong and Ke, Wei and S\"usstrunk, Sabine and Salzmann, Mathieu}, title = {Spatiotemporal Self-Supervised Learning for Point Clouds in the Wild}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5251-5260} }
Semi-Supervised Learning Made Simple With Self-Supervised Clustering: Enrico Fini,

Pietro Astolfi,

Karteek Alahari,

Xavier Alameda-Pineda,

Julien Mairal,

Moin Nabi,

Elisa Ricci; [pdf] [supp]
[bibtex]
@InProceedings{Fini_2023_CVPR, author = {Fini, Enrico and Astolfi, Pietro and Alahari, Karteek and Alameda-Pineda, Xavier and Mairal, Julien and Nabi, Moin and Ricci, Elisa}, title = {Semi-Supervised Learning Made Simple With Self-Supervised Clustering}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3187-3197} }
Frequency-Modulated Point Cloud Rendering With Easy Editing: Yi Zhang,

Xiaoyang Huang,

Bingbing Ni,

Teng Li,

Wenjun Zhang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhang_2023_CVPR, author = {Zhang, Yi and Huang, Xiaoyang and Ni, Bingbing and Li, Teng and Zhang, Wenjun}, title = {Frequency-Modulated Point Cloud Rendering With Easy Editing}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {119-129} }
Few-Shot Referring Relationships in Videos: Yogesh Kumar,

Anand Mishra; [pdf]
[bibtex]
@InProceedings{Kumar_2023_CVPR, author = {Kumar, Yogesh and Mishra, Anand}, title = {Few-Shot Referring Relationships in Videos}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2289-2298} }
3D Human Pose Estimation via Intuitive Physics: Shashank Tripathi,

Lea Müller,

Chun-Hao P. Huang,

Omid Taheri,

Michael J. Black,

Dimitrios Tzionas; [pdf] [supp]
[bibtex]
@InProceedings{Tripathi_2023_CVPR, author = {Tripathi, Shashank and M\"uller, Lea and Huang, Chun-Hao P. and Taheri, Omid and Black, Michael J. and Tzionas, Dimitrios}, title = {3D Human Pose Estimation via Intuitive Physics}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4713-4725} }
SplineCam: Exact Visualization and Characterization of Deep Network Geometry and Decision Boundaries: Ahmed Imtiaz Humayun,

Randall Balestriero,

Guha Balakrishnan,

Richard G. Baraniuk; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Humayun_2023_CVPR, author = {Humayun, Ahmed Imtiaz and Balestriero, Randall and Balakrishnan, Guha and Baraniuk, Richard G.}, title = {SplineCam: Exact Visualization and Characterization of Deep Network Geometry and Decision Boundaries}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3789-3798} }
SE-ORNet: Self-Ensembling Orientation-Aware Network for Unsupervised Point Cloud Shape Correspondence: Jiacheng Deng,

Chuxin Wang,

Jiahao Lu,

Jianfeng He,

Tianzhu Zhang,

Jiyang Yu,

Zhe Zhang; [pdf]
[bibtex]
@InProceedings{Deng_2023_CVPR, author = {Deng, Jiacheng and Wang, Chuxin and Lu, Jiahao and He, Jianfeng and Zhang, Tianzhu and Yu, Jiyang and Zhang, Zhe}, title = {SE-ORNet: Self-Ensembling Orientation-Aware Network for Unsupervised Point Cloud Shape Correspondence}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5364-5373} }
A Bag-of-Prototypes Representation for Dataset-Level Applications: Weijie Tu,

Weijian Deng,

Tom Gedeon,

Liang Zheng; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Tu_2023_CVPR, author = {Tu, Weijie and Deng, Weijian and Gedeon, Tom and Zheng, Liang}, title = {A Bag-of-Prototypes Representation for Dataset-Level Applications}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2881-2892} }
Leverage Interactive Affinity for Affordance Learning: Hongchen Luo,

Wei Zhai,

Jing Zhang,

Yang Cao,

Dacheng Tao; [pdf] [supp]
[bibtex]
@InProceedings{Luo_2023_CVPR, author = {Luo, Hongchen and Zhai, Wei and Zhang, Jing and Cao, Yang and Tao, Dacheng}, title = {Leverage Interactive Affinity for Affordance Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6809-6819} }
Deep Semi-Supervised Metric Learning With Mixed Label Propagation: Furen Zhuang,

Pierre Moulin; [pdf]
[bibtex]
@InProceedings{Zhuang_2023_CVPR, author = {Zhuang, Furen and Moulin, Pierre}, title = {Deep Semi-Supervised Metric Learning With Mixed Label Propagation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3429-3438} }
OVTrack: Open-Vocabulary Multiple Object Tracking: Siyuan Li,

Tobias Fischer,

Lei Ke,

Henghui Ding,

Martin Danelljan,

Fisher Yu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Li_2023_CVPR, author = {Li, Siyuan and Fischer, Tobias and Ke, Lei and Ding, Henghui and Danelljan, Martin and Yu, Fisher}, title = {OVTrack: Open-Vocabulary Multiple Object Tracking}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5567-5577} }
Hyperspherical Embedding for Point Cloud Completion: Junming Zhang,

Haomeng Zhang,

Ram Vasudevan,

Matthew Johnson-Roberson; [pdf] [supp]
[bibtex]
@InProceedings{Zhang_2023_CVPR, author = {Zhang, Junming and Zhang, Haomeng and Vasudevan, Ram and Johnson-Roberson, Matthew}, title = {Hyperspherical Embedding for Point Cloud Completion}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5323-5332} }
QuantArt: Quantizing Image Style Transfer Towards High Visual Fidelity: Siyu Huang,

Jie An,

Donglai Wei,

Jiebo Luo,

Hanspeter Pfister; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Huang_2023_CVPR, author = {Huang, Siyu and An, Jie and Wei, Donglai and Luo, Jiebo and Pfister, Hanspeter}, title = {QuantArt: Quantizing Image Style Transfer Towards High Visual Fidelity}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5947-5956} }
SlowLiDAR: Increasing the Latency of LiDAR-Based Detection Using Adversarial Examples: Han Liu,

Yuhao Wu,

Zhiyuan Yu,

Yevgeniy Vorobeychik,

Ning Zhang; [pdf]
[bibtex]
@InProceedings{Liu_2023_CVPR, author = {Liu, Han and Wu, Yuhao and Yu, Zhiyuan and Vorobeychik, Yevgeniy and Zhang, Ning}, title = {SlowLiDAR: Increasing the Latency of LiDAR-Based Detection Using Adversarial Examples}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5146-5155} }
Learning a Sparse Transformer Network for Effective Image Deraining: Xiang Chen,

Hao Li,

Mingqiang Li,

Jinshan Pan; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chen_2023_CVPR, author = {Chen, Xiang and Li, Hao and Li, Mingqiang and Pan, Jinshan}, title = {Learning a Sparse Transformer Network for Effective Image Deraining}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5896-5905} }
CutMIB: Boosting Light Field Super-Resolution via Multi-View Image Blending: Zeyu Xiao,

Yutong Liu,

Ruisheng Gao,

Zhiwei Xiong; [pdf] [supp]
[bibtex]
@InProceedings{Xiao_2023_CVPR, author = {Xiao, Zeyu and Liu, Yutong and Gao, Ruisheng and Xiong, Zhiwei}, title = {CutMIB: Boosting Light Field Super-Resolution via Multi-View Image Blending}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1672-1682} }
Energy-Efficient Adaptive 3D Sensing: Brevin Tilmon,

Zhanghao Sun,

Sanjeev J. Koppal,

Yicheng Wu,

Georgios Evangelidis,

Ramzi Zahreddine,

Gurunandan Krishnan,

Sizhuo Ma,

Jian Wang; [pdf] [supp]
[bibtex]
@InProceedings{Tilmon_2023_CVPR, author = {Tilmon, Brevin and Sun, Zhanghao and Koppal, Sanjeev J. and Wu, Yicheng and Evangelidis, Georgios and Zahreddine, Ramzi and Krishnan, Gurunandan and Ma, Sizhuo and Wang, Jian}, title = {Energy-Efficient Adaptive 3D Sensing}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5054-5063} }
CR-FIQA: Face Image Quality Assessment by Learning Sample Relative Classifiability: Fadi Boutros,

Meiling Fang,

Marcel Klemt,

Biying Fu,

Naser Damer; [pdf] [supp]
[bibtex]
@InProceedings{Boutros_2023_CVPR, author = {Boutros, Fadi and Fang, Meiling and Klemt, Marcel and Fu, Biying and Damer, Naser}, title = {CR-FIQA: Face Image Quality Assessment by Learning Sample Relative Classifiability}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5836-5845} }
Endpoints Weight Fusion for Class Incremental Semantic Segmentation: Jia-Wen Xiao,

Chang-Bin Zhang,

Jiekang Feng,

Xialei Liu,

Joost van de Weijer,

Ming-Ming Cheng; [pdf] [supp]
[bibtex]
@InProceedings{Xiao_2023_CVPR, author = {Xiao, Jia-Wen and Zhang, Chang-Bin and Feng, Jiekang and Liu, Xialei and van de Weijer, Joost and Cheng, Ming-Ming}, title = {Endpoints Weight Fusion for Class Incremental Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7204-7213} }
GeneCIS: A Benchmark for General Conditional Image Similarity: Sagar Vaze,

Nicolas Carion,

Ishan Misra; [pdf] [supp]
[bibtex]
@InProceedings{Vaze_2023_CVPR, author = {Vaze, Sagar and Carion, Nicolas and Misra, Ishan}, title = {GeneCIS: A Benchmark for General Conditional Image Similarity}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6862-6872} }
MD-VQA: Multi-Dimensional Quality Assessment for UGC Live Videos: Zicheng Zhang,

Wei Wu,

Wei Sun,

Danyang Tu,

Wei Lu,

Xiongkuo Min,

Ying Chen,

Guangtao Zhai; [pdf]
[bibtex]
@InProceedings{Zhang_2023_CVPR, author = {Zhang, Zicheng and Wu, Wei and Sun, Wei and Tu, Danyang and Lu, Wei and Min, Xiongkuo and Chen, Ying and Zhai, Guangtao}, title = {MD-VQA: Multi-Dimensional Quality Assessment for UGC Live Videos}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1746-1755} }
Spring: A High-Resolution High-Detail Dataset and Benchmark for Scene Flow, Optical Flow and Stereo: Lukas Mehl,

Jenny Schmalfuss,

Azin Jahedi,

Yaroslava Nalivayko,

Andrés Bruhn; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Mehl_2023_CVPR, author = {Mehl, Lukas and Schmalfuss, Jenny and Jahedi, Azin and Nalivayko, Yaroslava and Bruhn, Andr\'es}, title = {Spring: A High-Resolution High-Detail Dataset and Benchmark for Scene Flow, Optical Flow and Stereo}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4981-4991} }
MAESTER: Masked Autoencoder Guided Segmentation at Pixel Resolution for Accurate, Self-Supervised Subcellular Structure Recognition: Ronald Xie,

Kuan Pang,

Gary D. Bader,

Bo Wang; [pdf] [supp]
[bibtex]
@InProceedings{Xie_2023_CVPR, author = {Xie, Ronald and Pang, Kuan and Bader, Gary D. and Wang, Bo}, title = {MAESTER: Masked Autoencoder Guided Segmentation at Pixel Resolution for Accurate, Self-Supervised Subcellular Structure Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3292-3301} }
Self-Supervised Image-to-Point Distillation via Semantically Tolerant Contrastive Loss: Anas Mahmoud,

Jordan S. K. Hu,

Tianshu Kuai,

Ali Harakeh,

Liam Paull,

Steven L. Waslander; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Mahmoud_2023_CVPR, author = {Mahmoud, Anas and Hu, Jordan S. K. and Kuai, Tianshu and Harakeh, Ali and Paull, Liam and Waslander, Steven L.}, title = {Self-Supervised Image-to-Point Distillation via Semantically Tolerant Contrastive Loss}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7102-7110} }
Efficient Robust Principal Component Analysis via Block Krylov Iteration and CUR Decomposition: Shun Fang,

Zhengqin Xu,

Shiqian Wu,

Shoulie Xie; [pdf] [supp]
[bibtex]
@InProceedings{Fang_2023_CVPR, author = {Fang, Shun and Xu, Zhengqin and Wu, Shiqian and Xie, Shoulie}, title = {Efficient Robust Principal Component Analysis via Block Krylov Iteration and CUR Decomposition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1348-1357} }
VIVE3D: Viewpoint-Independent Video Editing Using 3D-Aware GANs: Anna Frühstück,

Nikolaos Sarafianos,

Yuanlu Xu,

Peter Wonka,

Tony Tung; [pdf] [supp]
[bibtex]
@InProceedings{Fruhstuck_2023_CVPR, author = {Fr\"uhst\"uck, Anna and Sarafianos, Nikolaos and Xu, Yuanlu and Wonka, Peter and Tung, Tony}, title = {VIVE3D: Viewpoint-Independent Video Editing Using 3D-Aware GANs}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4446-4455} }
DPE: Disentanglement of Pose and Expression for General Video Portrait Editing: Youxin Pang,

Yong Zhang,

Weize Quan,

Yanbo Fan,

Xiaodong Cun,

Ying Shan,

Dong-Ming Yan; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Pang_2023_CVPR, author = {Pang, Youxin and Zhang, Yong and Quan, Weize and Fan, Yanbo and Cun, Xiaodong and Shan, Ying and Yan, Dong-Ming}, title = {DPE: Disentanglement of Pose and Expression for General Video Portrait Editing}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {427-436} }
HexPlane: A Fast Representation for Dynamic Scenes: Ang Cao,

Justin Johnson; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Cao_2023_CVPR, author = {Cao, Ang and Johnson, Justin}, title = {HexPlane: A Fast Representation for Dynamic Scenes}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {130-141} }
Boosting Semi-Supervised Learning by Exploiting All Unlabeled Data: Yuhao Chen,

Xin Tan,

Borui Zhao,

Zhaowei Chen,

Renjie Song,

Jiajun Liang,

Xuequan Lu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chen_2023_CVPR, author = {Chen, Yuhao and Tan, Xin and Zhao, Borui and Chen, Zhaowei and Song, Renjie and Liang, Jiajun and Lu, Xuequan}, title = {Boosting Semi-Supervised Learning by Exploiting All Unlabeled Data}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7548-7557} }
Novel-View Acoustic Synthesis: Changan Chen,

Alexander Richard,

Roman Shapovalov,

Vamsi Krishna Ithapu,

Natalia Neverova,

Kristen Grauman,

Andrea Vedaldi; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chen_2023_CVPR, author = {Chen, Changan and Richard, Alexander and Shapovalov, Roman and Ithapu, Vamsi Krishna and Neverova, Natalia and Grauman, Kristen and Vedaldi, Andrea}, title = {Novel-View Acoustic Synthesis}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6409-6419} }
Constrained Evolutionary Diffusion Filter for Monocular Endoscope Tracking: Xiongbiao Luo; [pdf]
[bibtex]
@InProceedings{Luo_2023_CVPR, author = {Luo, Xiongbiao}, title = {Constrained Evolutionary Diffusion Filter for Monocular Endoscope Tracking}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4747-4756} }
Toward Accurate Post-Training Quantization for Image Super Resolution: Zhijun Tu,

Jie Hu,

Hanting Chen,

Yunhe Wang; [pdf] [supp]
[bibtex]
@InProceedings{Tu_2023_CVPR, author = {Tu, Zhijun and Hu, Jie and Chen, Hanting and Wang, Yunhe}, title = {Toward Accurate Post-Training Quantization for Image Super Resolution}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5856-5865} }
Omnimatte3D: Associating Objects and Their Effects in Unconstrained Monocular Video: Mohammed Suhail,

Erika Lu,

Zhengqi Li,

Noah Snavely,

Leonid Sigal,

Forrester Cole; [pdf] [supp]
[bibtex]
@InProceedings{Suhail_2023_CVPR, author = {Suhail, Mohammed and Lu, Erika and Li, Zhengqi and Snavely, Noah and Sigal, Leonid and Cole, Forrester}, title = {Omnimatte3D: Associating Objects and Their Effects in Unconstrained Monocular Video}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {630-639} }
Incrementer: Transformer for Class-Incremental Semantic Segmentation With Knowledge Distillation Focusing on Old Class: Chao Shang,

Hongliang Li,

Fanman Meng,

Qingbo Wu,

Heqian Qiu,

Lanxiao Wang; [pdf]
[bibtex]
@InProceedings{Shang_2023_CVPR, author = {Shang, Chao and Li, Hongliang and Meng, Fanman and Wu, Qingbo and Qiu, Heqian and Wang, Lanxiao}, title = {Incrementer: Transformer for Class-Incremental Semantic Segmentation With Knowledge Distillation Focusing on Old Class}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7214-7224} }
Patch-Mix Transformer for Unsupervised Domain Adaptation: A Game Perspective: Jinjing Zhu,

Haotian Bai,

Lin Wang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhu_2023_CVPR, author = {Zhu, Jinjing and Bai, Haotian and Wang, Lin}, title = {Patch-Mix Transformer for Unsupervised Domain Adaptation: A Game Perspective}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3561-3571} }
CAMS: CAnonicalized Manipulation Spaces for Category-Level Functional Hand-Object Manipulation Synthesis: Juntian Zheng,

Qingyuan Zheng,

Lixing Fang,

Yun Liu,

Li Yi; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zheng_2023_CVPR, author = {Zheng, Juntian and Zheng, Qingyuan and Fang, Lixing and Liu, Yun and Yi, Li}, title = {CAMS: CAnonicalized Manipulation Spaces for Category-Level Functional Hand-Object Manipulation Synthesis}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {585-594} }
Multiplicative Fourier Level of Detail: Yishun Dou,

Zhong Zheng,

Qiaoqiao Jin,

Bingbing Ni; [pdf] [supp]
[bibtex]
@InProceedings{Dou_2023_CVPR, author = {Dou, Yishun and Zheng, Zhong and Jin, Qiaoqiao and Ni, Bingbing}, title = {Multiplicative Fourier Level of Detail}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1808-1817} }
Relational Context Learning for Human-Object Interaction Detection: Sanghyun Kim,

Deunsol Jung,

Minsu Cho; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kim_2023_CVPR, author = {Kim, Sanghyun and Jung, Deunsol and Cho, Minsu}, title = {Relational Context Learning for Human-Object Interaction Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2925-2934} }
Multi-Label Compound Expression Recognition: C-EXPR Database & Network: Dimitrios Kollias; [pdf] [supp]
[bibtex]
@InProceedings{Kollias_2023_CVPR, author = {Kollias, Dimitrios}, title = {Multi-Label Compound Expression Recognition: C-EXPR Database \& Network}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5589-5598} }
CORA: Adapting CLIP for Open-Vocabulary Detection With Region Prompting and Anchor Pre-Matching: Xiaoshi Wu,

Feng Zhu,

Rui Zhao,

Hongsheng Li; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wu_2023_CVPR, author = {Wu, Xiaoshi and Zhu, Feng and Zhao, Rui and Li, Hongsheng}, title = {CORA: Adapting CLIP for Open-Vocabulary Detection With Region Prompting and Anchor Pre-Matching}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7031-7040} }
3DAvatarGAN: Bridging Domains for Personalized Editable Avatars: Rameen Abdal,

Hsin-Ying Lee,

Peihao Zhu,

Menglei Chai,

Aliaksandr Siarohin,

Peter Wonka,

Sergey Tulyakov; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Abdal_2023_CVPR, author = {Abdal, Rameen and Lee, Hsin-Ying and Zhu, Peihao and Chai, Menglei and Siarohin, Aliaksandr and Wonka, Peter and Tulyakov, Sergey}, title = {3DAvatarGAN: Bridging Domains for Personalized Editable Avatars}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4552-4562} }
Discriminative Co-Saliency and Background Mining Transformer for Co-Salient Object Detection: Long Li,

Junwei Han,

Ni Zhang,

Nian Liu,

Salman Khan,

Hisham Cholakkal,

Rao Muhammad Anwer,

Fahad Shahbaz Khan; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Li_2023_CVPR, author = {Li, Long and Han, Junwei and Zhang, Ni and Liu, Nian and Khan, Salman and Cholakkal, Hisham and Anwer, Rao Muhammad and Khan, Fahad Shahbaz}, title = {Discriminative Co-Saliency and Background Mining Transformer for Co-Salient Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7247-7256} }
Person Image Synthesis via Denoising Diffusion Model: Ankan Kumar Bhunia,

Salman Khan,

Hisham Cholakkal,

Rao Muhammad Anwer,

Jorma Laaksonen,

Mubarak Shah,

Fahad Shahbaz Khan; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Bhunia_2023_CVPR, author = {Bhunia, Ankan Kumar and Khan, Salman and Cholakkal, Hisham and Anwer, Rao Muhammad and Laaksonen, Jorma and Shah, Mubarak and Khan, Fahad Shahbaz}, title = {Person Image Synthesis via Denoising Diffusion Model}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5968-5976} }
Adaptive Assignment for Geometry Aware Local Feature Matching: Dihe Huang,

Ying Chen,

Yong Liu,

Jianlin Liu,

Shang Xu,

Wenlong Wu,

Yikang Ding,

Fan Tang,

Chengjie Wang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Huang_2023_CVPR, author = {Huang, Dihe and Chen, Ying and Liu, Yong and Liu, Jianlin and Xu, Shang and Wu, Wenlong and Ding, Yikang and Tang, Fan and Wang, Chengjie}, title = {Adaptive Assignment for Geometry Aware Local Feature Matching}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5425-5434} }
Initialization Noise in Image Gradients and Saliency Maps: Ann-Christin Woerl,

Jan Disselhoff,

Michael Wand; [pdf] [supp]
[bibtex]
@InProceedings{Woerl_2023_CVPR, author = {Woerl, Ann-Christin and Disselhoff, Jan and Wand, Michael}, title = {Initialization Noise in Image Gradients and Saliency Maps}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1766-1775} }
Implicit Neural Head Synthesis via Controllable Local Deformation Fields: Chuhan Chen,

Matthew O’Toole,

Gaurav Bharaj,

Pablo Garrido; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chen_2023_CVPR, author = {Chen, Chuhan and O{\textquoteright}Toole, Matthew and Bharaj, Gaurav and Garrido, Pablo}, title = {Implicit Neural Head Synthesis via Controllable Local Deformation Fields}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {416-426} }
Curricular Object Manipulation in LiDAR-Based Object Detection: Ziyue Zhu,

Qiang Meng,

Xiao Wang,

Ke Wang,

Liujiang Yan,

Jian Yang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhu_2023_CVPR, author = {Zhu, Ziyue and Meng, Qiang and Wang, Xiao and Wang, Ke and Yan, Liujiang and Yang, Jian}, title = {Curricular Object Manipulation in LiDAR-Based Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1125-1135} }
Shape-Constraint Recurrent Flow for 6D Object Pose Estimation: Yang Hai,

Rui Song,

Jiaojiao Li,

Yinlin Hu; [pdf]
[bibtex]
@InProceedings{Hai_2023_CVPR, author = {Hai, Yang and Song, Rui and Li, Jiaojiao and Hu, Yinlin}, title = {Shape-Constraint Recurrent Flow for 6D Object Pose Estimation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4831-4840} }
Micron-BERT: BERT-Based Facial Micro-Expression Recognition: Xuan-Bac Nguyen,

Chi Nhan Duong,

Xin Li,

Susan Gauch,

Han-Seok Seo,

Khoa Luu; [pdf]
[bibtex]
@InProceedings{Nguyen_2023_CVPR, author = {Nguyen, Xuan-Bac and Duong, Chi Nhan and Li, Xin and Gauch, Susan and Seo, Han-Seok and Luu, Khoa}, title = {Micron-BERT: BERT-Based Facial Micro-Expression Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1482-1492} }
PanelNet: Understanding 360 Indoor Environment via Panel Representation: Haozheng Yu,

Lu He,

Bing Jian,

Weiwei Feng,

Shan Liu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yu_2023_CVPR, author = {Yu, Haozheng and He, Lu and Jian, Bing and Feng, Weiwei and Liu, Shan}, title = {PanelNet: Understanding 360 Indoor Environment via Panel Representation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {878-887} }
PoseExaminer: Automated Testing of Out-of-Distribution Robustness in Human Pose and Shape Estimation: Qihao Liu,

Adam Kortylewski,

Alan L. Yuille; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Liu_2023_CVPR, author = {Liu, Qihao and Kortylewski, Adam and Yuille, Alan L.}, title = {PoseExaminer: Automated Testing of Out-of-Distribution Robustness in Human Pose and Shape Estimation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {672-681} }
GANHead: Towards Generative Animatable Neural Head Avatars: Sijing Wu,

Yichao Yan,

Yunhao Li,

Yuhao Cheng,

Wenhan Zhu,

Ke Gao,

Xiaobo Li,

Guangtao Zhai; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wu_2023_CVPR, author = {Wu, Sijing and Yan, Yichao and Li, Yunhao and Cheng, Yuhao and Zhu, Wenhan and Gao, Ke and Li, Xiaobo and Zhai, Guangtao}, title = {GANHead: Towards Generative Animatable Neural Head Avatars}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {437-447} }
Deep Dive Into Gradients: Better Optimization for 3D Object Detection With Gradient-Corrected IoU Supervision: Qi Ming,

Lingjuan Miao,

Zhe Ma,

Lin Zhao,

Zhiqiang Zhou,

Xuhui Huang,

Yuanpei Chen,

Yufei Guo; [pdf]
[bibtex]
@InProceedings{Ming_2023_CVPR, author = {Ming, Qi and Miao, Lingjuan and Ma, Zhe and Zhao, Lin and Zhou, Zhiqiang and Huang, Xuhui and Chen, Yuanpei and Guo, Yufei}, title = {Deep Dive Into Gradients: Better Optimization for 3D Object Detection With Gradient-Corrected IoU Supervision}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5136-5145} }
Doubly Right Object Recognition: A Why Prompt for Visual Rationales: Chengzhi Mao,

Revant Teotia,

Amrutha Sundar,

Sachit Menon,

Junfeng Yang,

Xin Wang,

Carl Vondrick; [pdf] [arXiv]
[bibtex]
@InProceedings{Mao_2023_CVPR, author = {Mao, Chengzhi and Teotia, Revant and Sundar, Amrutha and Menon, Sachit and Yang, Junfeng and Wang, Xin and Vondrick, Carl}, title = {Doubly Right Object Recognition: A Why Prompt for Visual Rationales}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2722-2732} }
Distilling Neural Fields for Real-Time Articulated Shape Reconstruction: Jeff Tan,

Gengshan Yang,

Deva Ramanan; [pdf]
[bibtex]
@InProceedings{Tan_2023_CVPR, author = {Tan, Jeff and Yang, Gengshan and Ramanan, Deva}, title = {Distilling Neural Fields for Real-Time Articulated Shape Reconstruction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4692-4701} }
IPCC-TP: Utilizing Incremental Pearson Correlation Coefficient for Joint Multi-Agent Trajectory Prediction: Dekai Zhu,

Guangyao Zhai,

Yan Di,

Fabian Manhardt,

Hendrik Berkemeyer,

Tuan Tran,

Nassir Navab,

Federico Tombari,

Benjamin Busam; [pdf] [supp]
[bibtex]
@InProceedings{Zhu_2023_CVPR, author = {Zhu, Dekai and Zhai, Guangyao and Di, Yan and Manhardt, Fabian and Berkemeyer, Hendrik and Tran, Tuan and Navab, Nassir and Tombari, Federico and Busam, Benjamin}, title = {IPCC-TP: Utilizing Incremental Pearson Correlation Coefficient for Joint Multi-Agent Trajectory Prediction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5507-5516} }
MobileOne: An Improved One Millisecond Mobile Backbone: Pavan Kumar Anasosalu Vasu,

James Gabriel,

Jeff Zhu,

Oncel Tuzel,

Anurag Ranjan; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Vasu_2023_CVPR, author = {Vasu, Pavan Kumar Anasosalu and Gabriel, James and Zhu, Jeff and Tuzel, Oncel and Ranjan, Anurag}, title = {MobileOne: An Improved One Millisecond Mobile Backbone}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7907-7917} }
A Data-Based Perspective on Transfer Learning: Saachi Jain,

Hadi Salman,

Alaa Khaddaj,

Eric Wong,

Sung Min Park,

Aleksander Mądry; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Jain_2023_CVPR, author = {Jain, Saachi and Salman, Hadi and Khaddaj, Alaa and Wong, Eric and Park, Sung Min and M\k{a}dry, Aleksander}, title = {A Data-Based Perspective on Transfer Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3613-3622} }
Meta-Explore: Exploratory Hierarchical Vision-and-Language Navigation Using Scene Object Spectrum Grounding: Minyoung Hwang,

Jaeyeon Jeong,

Minsoo Kim,

Yoonseon Oh,

Songhwai Oh; [pdf] [supp]
[bibtex]
@InProceedings{Hwang_2023_CVPR, author = {Hwang, Minyoung and Jeong, Jaeyeon and Kim, Minsoo and Oh, Yoonseon and Oh, Songhwai}, title = {Meta-Explore: Exploratory Hierarchical Vision-and-Language Navigation Using Scene Object Spectrum Grounding}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6683-6693} }
Recovering 3D Hand Mesh Sequence From a Single Blurry Image: A New Dataset and Temporal Unfolding: Yeonguk Oh,

JoonKyu Park,

Jaeha Kim,

Gyeongsik Moon,

Kyoung Mu Lee; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Oh_2023_CVPR, author = {Oh, Yeonguk and Park, JoonKyu and Kim, Jaeha and Moon, Gyeongsik and Lee, Kyoung Mu}, title = {Recovering 3D Hand Mesh Sequence From a Single Blurry Image: A New Dataset and Temporal Unfolding}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {554-563} }
NaQ: Leveraging Narrations As Queries To Supervise Episodic Memory: Santhosh Kumar Ramakrishnan,

Ziad Al-Halah,

Kristen Grauman; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ramakrishnan_2023_CVPR, author = {Ramakrishnan, Santhosh Kumar and Al-Halah, Ziad and Grauman, Kristen}, title = {NaQ: Leveraging Narrations As Queries To Supervise Episodic Memory}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6694-6703} }
FedSeg: Class-Heterogeneous Federated Learning for Semantic Segmentation: Jiaxu Miao,

Zongxin Yang,

Leilei Fan,

Yi Yang; [pdf] [supp]
[bibtex]
@InProceedings{Miao_2023_CVPR, author = {Miao, Jiaxu and Yang, Zongxin and Fan, Leilei and Yang, Yi}, title = {FedSeg: Class-Heterogeneous Federated Learning for Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8042-8052} }
Fast Monocular Scene Reconstruction With Global-Sparse Local-Dense Grids: Wei Dong,

Christopher Choy,

Charles Loop,

Or Litany,

Yuke Zhu,

Anima Anandkumar; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Dong_2023_CVPR, author = {Dong, Wei and Choy, Christopher and Loop, Charles and Litany, Or and Zhu, Yuke and Anandkumar, Anima}, title = {Fast Monocular Scene Reconstruction With Global-Sparse Local-Dense Grids}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4263-4272} }
Thermal Spread Functions (TSF): Physics-Guided Material Classification: Aniket Dashpute,

Vishwanath Saragadam,

Emma Alexander,

Florian Willomitzer,

Aggelos Katsaggelos,

Ashok Veeraraghavan,

Oliver Cossairt; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Dashpute_2023_CVPR, author = {Dashpute, Aniket and Saragadam, Vishwanath and Alexander, Emma and Willomitzer, Florian and Katsaggelos, Aggelos and Veeraraghavan, Ashok and Cossairt, Oliver}, title = {Thermal Spread Functions (TSF): Physics-Guided Material Classification}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1641-1650} }
Unsupervised 3D Point Cloud Representation Learning by Triangle Constrained Contrast for Autonomous Driving: Bo Pang,

Hongchi Xia,

Cewu Lu; [pdf] [supp]
[bibtex]
@InProceedings{Pang_2023_CVPR, author = {Pang, Bo and Xia, Hongchi and Lu, Cewu}, title = {Unsupervised 3D Point Cloud Representation Learning by Triangle Constrained Contrast for Autonomous Driving}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5229-5239} }
Prompt-Guided Zero-Shot Anomaly Action Recognition Using Pretrained Deep Skeleton Features: Fumiaki Sato,

Ryo Hachiuma,

Taiki Sekii; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Sato_2023_CVPR, author = {Sato, Fumiaki and Hachiuma, Ryo and Sekii, Taiki}, title = {Prompt-Guided Zero-Shot Anomaly Action Recognition Using Pretrained Deep Skeleton Features}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6471-6480} }
Efficient Multimodal Fusion via Interactive Prompting: Yaowei Li,

Ruijie Quan,

Linchao Zhu,

Yi Yang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Li_2023_CVPR, author = {Li, Yaowei and Quan, Ruijie and Zhu, Linchao and Yang, Yi}, title = {Efficient Multimodal Fusion via Interactive Prompting}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2604-2613} }
Depth Estimation From Indoor Panoramas With Neural Scene Representation: Wenjie Chang,

Yueyi Zhang,

Zhiwei Xiong; [pdf] [supp]
[bibtex]
@InProceedings{Chang_2023_CVPR, author = {Chang, Wenjie and Zhang, Yueyi and Xiong, Zhiwei}, title = {Depth Estimation From Indoor Panoramas With Neural Scene Representation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {899-908} }
Task-Specific Fine-Tuning via Variational Information Bottleneck for Weakly-Supervised Pathology Whole Slide Image Classification: Honglin Li,

Chenglu Zhu,

Yunlong Zhang,

Yuxuan Sun,

Zhongyi Shui,

Wenwei Kuang,

Sunyi Zheng,

Lin Yang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Li_2023_CVPR, author = {Li, Honglin and Zhu, Chenglu and Zhang, Yunlong and Sun, Yuxuan and Shui, Zhongyi and Kuang, Wenwei and Zheng, Sunyi and Yang, Lin}, title = {Task-Specific Fine-Tuning via Variational Information Bottleneck for Weakly-Supervised Pathology Whole Slide Image Classification}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7454-7463} }
One-Shot Model for Mixed-Precision Quantization: Ivan Koryakovskiy,

Alexandra Yakovleva,

Valentin Buchnev,

Temur Isaev,

Gleb Odinokikh; [pdf] [supp]
[bibtex]
@InProceedings{Koryakovskiy_2023_CVPR, author = {Koryakovskiy, Ivan and Yakovleva, Alexandra and Buchnev, Valentin and Isaev, Temur and Odinokikh, Gleb}, title = {One-Shot Model for Mixed-Precision Quantization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7939-7949} }
MARLIN: Masked Autoencoder for Facial Video Representation LearnINg: Zhixi Cai,

Shreya Ghosh,

Kalin Stefanov,

Abhinav Dhall,

Jianfei Cai,

Hamid Rezatofighi,

Reza Haffari,

Munawar Hayat; [pdf] [arXiv]
[bibtex]
@InProceedings{Cai_2023_CVPR, author = {Cai, Zhixi and Ghosh, Shreya and Stefanov, Kalin and Dhall, Abhinav and Cai, Jianfei and Rezatofighi, Hamid and Haffari, Reza and Hayat, Munawar}, title = {MARLIN: Masked Autoencoder for Facial Video Representation LearnINg}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1493-1504} }
Dynamic Coarse-To-Fine Learning for Oriented Tiny Object Detection: Chang Xu,

Jian Ding,

Jinwang Wang,

Wen Yang,

Huai Yu,

Lei Yu,

Gui-Song Xia; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Xu_2023_CVPR, author = {Xu, Chang and Ding, Jian and Wang, Jinwang and Yang, Wen and Yu, Huai and Yu, Lei and Xia, Gui-Song}, title = {Dynamic Coarse-To-Fine Learning for Oriented Tiny Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7318-7328} }
Controllable Mesh Generation Through Sparse Latent Point Diffusion Models: Zhaoyang Lyu,

Jinyi Wang,

Yuwei An,

Ya Zhang,

Dahua Lin,

Bo Dai; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Lyu_2023_CVPR, author = {Lyu, Zhaoyang and Wang, Jinyi and An, Yuwei and Zhang, Ya and Lin, Dahua and Dai, Bo}, title = {Controllable Mesh Generation Through Sparse Latent Point Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {271-280} }
Look Before You Match: Instance Understanding Matters in Video Object Segmentation: Junke Wang,

Dongdong Chen,

Zuxuan Wu,

Chong Luo,

Chuanxin Tang,

Xiyang Dai,

Yucheng Zhao,

Yujia Xie,

Lu Yuan,

Yu-Gang Jiang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2023_CVPR, author = {Wang, Junke and Chen, Dongdong and Wu, Zuxuan and Luo, Chong and Tang, Chuanxin and Dai, Xiyang and Zhao, Yucheng and Xie, Yujia and Yuan, Lu and Jiang, Yu-Gang}, title = {Look Before You Match: Instance Understanding Matters in Video Object Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2268-2278} }
Boundary Unlearning: Rapid Forgetting of Deep Networks via Shifting the Decision Boundary: Min Chen,

Weizhuo Gao,

Gaoyang Liu,

Kai Peng,

Chen Wang; [pdf]
[bibtex]
@InProceedings{Chen_2023_CVPR, author = {Chen, Min and Gao, Weizhuo and Liu, Gaoyang and Peng, Kai and Wang, Chen}, title = {Boundary Unlearning: Rapid Forgetting of Deep Networks via Shifting the Decision Boundary}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7766-7775} }
Orthogonal Annotation Benefits Barely-Supervised Medical Image Segmentation: Heng Cai,

Shumeng Li,

Lei Qi,

Qian Yu,

Yinghuan Shi,

Yang Gao; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Cai_2023_CVPR, author = {Cai, Heng and Li, Shumeng and Qi, Lei and Yu, Qian and Shi, Yinghuan and Gao, Yang}, title = {Orthogonal Annotation Benefits Barely-Supervised Medical Image Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3302-3311} }
Spectral Enhanced Rectangle Transformer for Hyperspectral Image Denoising: Miaoyu Li,

Ji Liu,

Ying Fu,

Yulun Zhang,

Dejing Dou; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Li_2023_CVPR, author = {Li, Miaoyu and Liu, Ji and Fu, Ying and Zhang, Yulun and Dou, Dejing}, title = {Spectral Enhanced Rectangle Transformer for Hyperspectral Image Denoising}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5805-5814} }
UMat: Uncertainty-Aware Single Image High Resolution Material Capture: Carlos Rodriguez-Pardo,

Henar Domínguez-Elvira,

David Pascual-Hernández,

Elena Garces; [pdf]
[bibtex]
@InProceedings{Rodriguez-Pardo_2023_CVPR, author = {Rodriguez-Pardo, Carlos and Dom{\'\i}nguez-Elvira, Henar and Pascual-Hern\'andez, David and Garces, Elena}, title = {UMat: Uncertainty-Aware Single Image High Resolution Material Capture}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5764-5774} }
Similarity Maps for Self-Training Weakly-Supervised Phrase Grounding: Tal Shaharabany,

Lior Wolf; [pdf]
[bibtex]
@InProceedings{Shaharabany_2023_CVPR, author = {Shaharabany, Tal and Wolf, Lior}, title = {Similarity Maps for Self-Training Weakly-Supervised Phrase Grounding}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6925-6934} }
SCOOP: Self-Supervised Correspondence and Optimization-Based Scene Flow: Itai Lang,

Dror Aiger,

Forrester Cole,

Shai Avidan,

Michael Rubinstein; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Lang_2023_CVPR, author = {Lang, Itai and Aiger, Dror and Cole, Forrester and Avidan, Shai and Rubinstein, Michael}, title = {SCOOP: Self-Supervised Correspondence and Optimization-Based Scene Flow}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5281-5290} }
Human-Art: A Versatile Human-Centric Dataset Bridging Natural and Artificial Scenes: Xuan Ju,

Ailing Zeng,

Jianan Wang,

Qiang Xu,

Lei Zhang; [pdf] [supp]
[bibtex]
@InProceedings{Ju_2023_CVPR, author = {Ju, Xuan and Zeng, Ailing and Wang, Jianan and Xu, Qiang and Zhang, Lei}, title = {Human-Art: A Versatile Human-Centric Dataset Bridging Natural and Artificial Scenes}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {618-629} }
Turning a CLIP Model Into a Scene Text Detector: Wenwen Yu,

Yuliang Liu,

Wei Hua,

Deqiang Jiang,

Bo Ren,

Xiang Bai; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yu_2023_CVPR, author = {Yu, Wenwen and Liu, Yuliang and Hua, Wei and Jiang, Deqiang and Ren, Bo and Bai, Xiang}, title = {Turning a CLIP Model Into a Scene Text Detector}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6978-6988} }
RODIN: A Generative Model for Sculpting 3D Digital Avatars Using Diffusion: Tengfei Wang,

Bo Zhang,

Ting Zhang,

Shuyang Gu,

Jianmin Bao,

Tadas Baltrusaitis,

Jingjing Shen,

Dong Chen,

Fang Wen,

Qifeng Chen,

Baining Guo; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2023_CVPR, author = {Wang, Tengfei and Zhang, Bo and Zhang, Ting and Gu, Shuyang and Bao, Jianmin and Baltrusaitis, Tadas and Shen, Jingjing and Chen, Dong and Wen, Fang and Chen, Qifeng and Guo, Baining}, title = {RODIN: A Generative Model for Sculpting 3D Digital Avatars Using Diffusion}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4563-4573} }
On the Pitfall of Mixup for Uncertainty Calibration: Deng-Bao Wang,

Lanqing Li,

Peilin Zhao,

Pheng-Ann Heng,

Min-Ling Zhang; [pdf] [supp]
[bibtex]
@InProceedings{Wang_2023_CVPR, author = {Wang, Deng-Bao and Li, Lanqing and Zhao, Peilin and Heng, Pheng-Ann and Zhang, Min-Ling}, title = {On the Pitfall of Mixup for Uncertainty Calibration}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7609-7618} }
Feature Shrinkage Pyramid for Camouflaged Object Detection With Transformers: Zhou Huang,

Hang Dai,

Tian-Zhu Xiang,

Shuo Wang,

Huai-Xin Chen,

Jie Qin,

Huan Xiong; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Huang_2023_CVPR, author = {Huang, Zhou and Dai, Hang and Xiang, Tian-Zhu and Wang, Shuo and Chen, Huai-Xin and Qin, Jie and Xiong, Huan}, title = {Feature Shrinkage Pyramid for Camouflaged Object Detection With Transformers}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5557-5566} }
Matching Is Not Enough: A Two-Stage Framework for Category-Agnostic Pose Estimation: Min Shi,

Zihao Huang,

Xianzheng Ma,

Xiaowei Hu,

Zhiguo Cao; [pdf] [supp]
[bibtex]
@InProceedings{Shi_2023_CVPR, author = {Shi, Min and Huang, Zihao and Ma, Xianzheng and Hu, Xiaowei and Cao, Zhiguo}, title = {Matching Is Not Enough: A Two-Stage Framework for Category-Agnostic Pose Estimation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7308-7317} }
High-Fidelity Guided Image Synthesis With Latent Diffusion Models: Jaskirat Singh,

Stephen Gould,

Liang Zheng; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Singh_2023_CVPR, author = {Singh, Jaskirat and Gould, Stephen and Zheng, Liang}, title = {High-Fidelity Guided Image Synthesis With Latent Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5997-6006} }
Semi-Supervised Parametric Real-World Image Harmonization: Ke Wang,

Michaël Gharbi,

He Zhang,

Zhihao Xia,

Eli Shechtman; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2023_CVPR, author = {Wang, Ke and Gharbi, Micha\"el and Zhang, He and Xia, Zhihao and Shechtman, Eli}, title = {Semi-Supervised Parametric Real-World Image Harmonization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5927-5936} }
Learning Visibility Field for Detailed 3D Human Reconstruction and Relighting: Ruichen Zheng,

Peng Li,

Haoqian Wang,

Tao Yu; [pdf] [arXiv]
[bibtex]
@InProceedings{Zheng_2023_CVPR, author = {Zheng, Ruichen and Li, Peng and Wang, Haoqian and Yu, Tao}, title = {Learning Visibility Field for Detailed 3D Human Reconstruction and Relighting}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {216-226} }
Improving Robustness of Vision Transformers by Reducing Sensitivity To Patch Corruptions: Yong Guo,

David Stutz,

Bernt Schiele; [pdf] [supp]
[bibtex]
@InProceedings{Guo_2023_CVPR, author = {Guo, Yong and Stutz, David and Schiele, Bernt}, title = {Improving Robustness of Vision Transformers by Reducing Sensitivity To Patch Corruptions}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4108-4118} }
VecFontSDF: Learning To Reconstruct and Synthesize High-Quality Vector Fonts via Signed Distance Functions: Zeqing Xia,

Bojun Xiong,

Zhouhui Lian; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Xia_2023_CVPR, author = {Xia, Zeqing and Xiong, Bojun and Lian, Zhouhui}, title = {VecFontSDF: Learning To Reconstruct and Synthesize High-Quality Vector Fonts via Signed Distance Functions}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1848-1857} }
MSF: Motion-Guided Sequential Fusion for Efficient 3D Object Detection From Point Cloud Sequences: Chenhang He,

Ruihuang Li,

Yabin Zhang,

Shuai Li,

Lei Zhang; [pdf] [arXiv]
[bibtex]
@InProceedings{He_2023_CVPR, author = {He, Chenhang and Li, Ruihuang and Zhang, Yabin and Li, Shuai and Zhang, Lei}, title = {MSF: Motion-Guided Sequential Fusion for Efficient 3D Object Detection From Point Cloud Sequences}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5196-5205} }
HypLiLoc: Towards Effective LiDAR Pose Regression With Hyperbolic Fusion: Sijie Wang,

Qiyu Kang,

Rui She,

Wei Wang,

Kai Zhao,

Yang Song,

Wee Peng Tay; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2023_CVPR, author = {Wang, Sijie and Kang, Qiyu and She, Rui and Wang, Wei and Zhao, Kai and Song, Yang and Tay, Wee Peng}, title = {HypLiLoc: Towards Effective LiDAR Pose Regression With Hyperbolic Fusion}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5176-5185} }
Robust Model-Based Face Reconstruction Through Weakly-Supervised Outlier Segmentation: Chunlu Li,

Andreas Morel-Forster,

Thomas Vetter,

Bernhard Egger,

Adam Kortylewski; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Li_2023_CVPR, author = {Li, Chunlu and Morel-Forster, Andreas and Vetter, Thomas and Egger, Bernhard and Kortylewski, Adam}, title = {Robust Model-Based Face Reconstruction Through Weakly-Supervised Outlier Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {372-381} }
Not All Image Regions Matter: Masked Vector Quantization for Autoregressive Image Generation: Mengqi Huang,

Zhendong Mao,

Quan Wang,

Yongdong Zhang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Huang_2023_CVPR, author = {Huang, Mengqi and Mao, Zhendong and Wang, Quan and Zhang, Yongdong}, title = {Not All Image Regions Matter: Masked Vector Quantization for Autoregressive Image Generation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2002-2011} }
Masked Video Distillation: Rethinking Masked Feature Modeling for Self-Supervised Video Representation Learning: Rui Wang,

Dongdong Chen,

Zuxuan Wu,

Yinpeng Chen,

Xiyang Dai,

Mengchen Liu,

Lu Yuan,

Yu-Gang Jiang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2023_CVPR, author = {Wang, Rui and Chen, Dongdong and Wu, Zuxuan and Chen, Yinpeng and Dai, Xiyang and Liu, Mengchen and Yuan, Lu and Jiang, Yu-Gang}, title = {Masked Video Distillation: Rethinking Masked Feature Modeling for Self-Supervised Video Representation Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6312-6322} }
Transformer-Based Unified Recognition of Two Hands Manipulating Objects: Hoseong Cho,

Chanwoo Kim,

Jihyeon Kim,

Seongyeong Lee,

Elkhan Ismayilzada,

Seungryul Baek; [pdf] [supp]
[bibtex]
@InProceedings{Cho_2023_CVPR, author = {Cho, Hoseong and Kim, Chanwoo and Kim, Jihyeon and Lee, Seongyeong and Ismayilzada, Elkhan and Baek, Seungryul}, title = {Transformer-Based Unified Recognition of Two Hands Manipulating Objects}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4769-4778} }
RangeViT: Towards Vision Transformers for 3D Semantic Segmentation in Autonomous Driving: Angelika Ando,

Spyros Gidaris,

Andrei Bursuc,

Gilles Puy,

Alexandre Boulch,

Renaud Marlet; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ando_2023_CVPR, author = {Ando, Angelika and Gidaris, Spyros and Bursuc, Andrei and Puy, Gilles and Boulch, Alexandre and Marlet, Renaud}, title = {RangeViT: Towards Vision Transformers for 3D Semantic Segmentation in Autonomous Driving}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5240-5250} }
ProTeGe: Untrimmed Pretraining for Video Temporal Grounding by Video Temporal Grounding: Lan Wang,

Gaurav Mittal,

Sandra Sajeev,

Ye Yu,

Matthew Hall,

Vishnu Naresh Boddeti,

Mei Chen; [pdf] [supp]
[bibtex]
@InProceedings{Wang_2023_CVPR, author = {Wang, Lan and Mittal, Gaurav and Sajeev, Sandra and Yu, Ye and Hall, Matthew and Boddeti, Vishnu Naresh and Chen, Mei}, title = {ProTeGe: Untrimmed Pretraining for Video Temporal Grounding by Video Temporal Grounding}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6575-6585} }
Exploring Incompatible Knowledge Transfer in Few-Shot Image Generation: Yunqing Zhao,

Chao Du,

Milad Abdollahzadeh,

Tianyu Pang,

Min Lin,

Shuicheng Yan,

Ngai-Man Cheung; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhao_2023_CVPR, author = {Zhao, Yunqing and Du, Chao and Abdollahzadeh, Milad and Pang, Tianyu and Lin, Min and Yan, Shuicheng and Cheung, Ngai-Man}, title = {Exploring Incompatible Knowledge Transfer in Few-Shot Image Generation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7380-7391} }
All-in-One Image Restoration for Unknown Degradations Using Adaptive Discriminative Filters for Specific Degradations: Dongwon Park,

Byung Hyun Lee,

Se Young Chun; [pdf] [supp]
[bibtex]
@InProceedings{Park_2023_CVPR, author = {Park, Dongwon and Lee, Byung Hyun and Chun, Se Young}, title = {All-in-One Image Restoration for Unknown Degradations Using Adaptive Discriminative Filters for Specific Degradations}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5815-5824} }
Efficient RGB-T Tracking via Cross-Modality Distillation: Tianlu Zhang,

Hongyuan Guo,

Qiang Jiao,

Qiang Zhang,

Jungong Han; [pdf] [supp]
[bibtex]
@InProceedings{Zhang_2023_CVPR, author = {Zhang, Tianlu and Guo, Hongyuan and Jiao, Qiang and Zhang, Qiang and Han, Jungong}, title = {Efficient RGB-T Tracking via Cross-Modality Distillation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5404-5413} }
Passive Micron-Scale Time-of-Flight With Sunlight Interferometry: Alankar Kotwal,

Anat Levin,

Ioannis Gkioulekas; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kotwal_2023_CVPR, author = {Kotwal, Alankar and Levin, Anat and Gkioulekas, Ioannis}, title = {Passive Micron-Scale Time-of-Flight With Sunlight Interferometry}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4139-4149} }
Behavioral Analysis of Vision-and-Language Navigation Agents: Zijiao Yang,

Arjun Majumdar,

Stefan Lee; [pdf] [supp]
[bibtex]
@InProceedings{Yang_2023_CVPR, author = {Yang, Zijiao and Majumdar, Arjun and Lee, Stefan}, title = {Behavioral Analysis of Vision-and-Language Navigation Agents}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2574-2582} }
Unsupervised Volumetric Animation: Aliaksandr Siarohin,

Willi Menapace,

Ivan Skorokhodov,

Kyle Olszewski,

Jian Ren,

Hsin-Ying Lee,

Menglei Chai,

Sergey Tulyakov; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Siarohin_2023_CVPR, author = {Siarohin, Aliaksandr and Menapace, Willi and Skorokhodov, Ivan and Olszewski, Kyle and Ren, Jian and Lee, Hsin-Ying and Chai, Menglei and Tulyakov, Sergey}, title = {Unsupervised Volumetric Animation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4658-4669} }
Unite and Conquer: Plug & Play Multi-Modal Synthesis Using Diffusion Models: Nithin Gopalakrishnan Nair,

Wele Gedara Chaminda Bandara,

Vishal M. Patel; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Nair_2023_CVPR, author = {Nair, Nithin Gopalakrishnan and Bandara, Wele Gedara Chaminda and Patel, Vishal M.}, title = {Unite and Conquer: Plug \& Play Multi-Modal Synthesis Using Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6070-6079} }
ZBS: Zero-Shot Background Subtraction via Instance-Level Background Modeling and Foreground Selection: Yongqi An,

Xu Zhao,

Tao Yu,

Haiyun Guo,

Chaoyang Zhao,

Ming Tang,

Jinqiao Wang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{An_2023_CVPR, author = {An, Yongqi and Zhao, Xu and Yu, Tao and Guo, Haiyun and Zhao, Chaoyang and Tang, Ming and Wang, Jinqiao}, title = {ZBS: Zero-Shot Background Subtraction via Instance-Level Background Modeling and Foreground Selection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6355-6364} }
MobileBrick: Building LEGO for 3D Reconstruction on Mobile Devices: Kejie Li,

Jia-Wang Bian,

Robert Castle,

Philip H.S. Torr,

Victor Adrian Prisacariu; [pdf] [arXiv]
[bibtex]
@InProceedings{Li_2023_CVPR, author = {Li, Kejie and Bian, Jia-Wang and Castle, Robert and Torr, Philip H.S. and Prisacariu, Victor Adrian}, title = {MobileBrick: Building LEGO for 3D Reconstruction on Mobile Devices}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4892-4901} }
GKEAL: Gaussian Kernel Embedded Analytic Learning for Few-Shot Class Incremental Task: Huiping Zhuang,

Zhenyu Weng,

Run He,

Zhiping Lin,

Ziqian Zeng; [pdf] [supp]
[bibtex]
@InProceedings{Zhuang_2023_CVPR, author = {Zhuang, Huiping and Weng, Zhenyu and He, Run and Lin, Zhiping and Zeng, Ziqian}, title = {GKEAL: Gaussian Kernel Embedded Analytic Learning for Few-Shot Class Incremental Task}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7746-7755} }
Active Exploration of Multimodal Complementarity for Few-Shot Action Recognition: Yuyang Wanyan,

Xiaoshan Yang,

Chaofan Chen,

Changsheng Xu; [pdf]
[bibtex]
@InProceedings{Wanyan_2023_CVPR, author = {Wanyan, Yuyang and Yang, Xiaoshan and Chen, Chaofan and Xu, Changsheng}, title = {Active Exploration of Multimodal Complementarity for Few-Shot Action Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6492-6502} }
Magic3D: High-Resolution Text-to-3D Content Creation: Chen-Hsuan Lin,

Jun Gao,

Luming Tang,

Towaki Takikawa,

Xiaohui Zeng,

Xun Huang,

Karsten Kreis,

Sanja Fidler,

Ming-Yu Liu,

Tsung-Yi Lin; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Lin_2023_CVPR, author = {Lin, Chen-Hsuan and Gao, Jun and Tang, Luming and Takikawa, Towaki and Zeng, Xiaohui and Huang, Xun and Kreis, Karsten and Fidler, Sanja and Liu, Ming-Yu and Lin, Tsung-Yi}, title = {Magic3D: High-Resolution Text-to-3D Content Creation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {300-309} }
Sketch2Saliency: Learning To Detect Salient Objects From Human Drawings: Ayan Kumar Bhunia,

Subhadeep Koley,

Amandeep Kumar,

Aneeshan Sain,

Pinaki Nath Chowdhury,

Tao Xiang,

Yi-Zhe Song; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Bhunia_2023_CVPR, author = {Bhunia, Ayan Kumar and Koley, Subhadeep and Kumar, Amandeep and Sain, Aneeshan and Chowdhury, Pinaki Nath and Xiang, Tao and Song, Yi-Zhe}, title = {Sketch2Saliency: Learning To Detect Salient Objects From Human Drawings}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2733-2743} }
Efficient Frequency Domain-Based Transformers for High-Quality Image Deblurring: Lingshun Kong,

Jiangxin Dong,

Jianjun Ge,

Mingqiang Li,

Jinshan Pan; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kong_2023_CVPR, author = {Kong, Lingshun and Dong, Jiangxin and Ge, Jianjun and Li, Mingqiang and Pan, Jinshan}, title = {Efficient Frequency Domain-Based Transformers for High-Quality Image Deblurring}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5886-5895} }
Distilling Focal Knowledge From Imperfect Expert for 3D Object Detection: Jia Zeng,

Li Chen,

Hanming Deng,

Lewei Lu,

Junchi Yan,

Yu Qiao,

Hongyang Li; [pdf] [supp]
[bibtex]
@InProceedings{Zeng_2023_CVPR, author = {Zeng, Jia and Chen, Li and Deng, Hanming and Lu, Lewei and Yan, Junchi and Qiao, Yu and Li, Hongyang}, title = {Distilling Focal Knowledge From Imperfect Expert for 3D Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {992-1001} }
ULIP: Learning a Unified Representation of Language, Images, and Point Clouds for 3D Understanding: Le Xue,

Mingfei Gao,

Chen Xing,

Roberto Martín-Martín,

Jiajun Wu,

Caiming Xiong,

Ran Xu,

Juan Carlos Niebles,

Silvio Savarese; [pdf] [supp]
[bibtex]
@InProceedings{Xue_2023_CVPR, author = {Xue, Le and Gao, Mingfei and Xing, Chen and Mart{\'\i}n-Mart{\'\i}n, Roberto and Wu, Jiajun and Xiong, Caiming and Xu, Ran and Niebles, Juan Carlos and Savarese, Silvio}, title = {ULIP: Learning a Unified Representation of Language, Images, and Point Clouds for 3D Understanding}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1179-1189} }
Deep Learning of Partial Graph Matching via Differentiable Top-K: Runzhong Wang,

Ziao Guo,

Shaofei Jiang,

Xiaokang Yang,

Junchi Yan; [pdf] [supp]
[bibtex]
@InProceedings{Wang_2023_CVPR, author = {Wang, Runzhong and Guo, Ziao and Jiang, Shaofei and Yang, Xiaokang and Yan, Junchi}, title = {Deep Learning of Partial Graph Matching via Differentiable Top-K}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6272-6281} }
NVTC: Nonlinear Vector Transform Coding: Runsen Feng,

Zongyu Guo,

Weiping Li,

Zhibo Chen; [pdf] [supp]
[bibtex]
@InProceedings{Feng_2023_CVPR, author = {Feng, Runsen and Guo, Zongyu and Li, Weiping and Chen, Zhibo}, title = {NVTC: Nonlinear Vector Transform Coding}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6101-6110} }
On the Effectiveness of Partial Variance Reduction in Federated Learning With Heterogeneous Data: Bo Li,

Mikkel N. Schmidt,

Tommy S. Alstrøm,

Sebastian U. Stich; [pdf] [supp]
[bibtex]
@InProceedings{Li_2023_CVPR, author = {Li, Bo and Schmidt, Mikkel N. and Alstr{\o}m, Tommy S. and Stich, Sebastian U.}, title = {On the Effectiveness of Partial Variance Reduction in Federated Learning With Heterogeneous Data}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3964-3973} }
Point Cloud Forecasting as a Proxy for 4D Occupancy Forecasting: Tarasha Khurana,

Peiyun Hu,

David Held,

Deva Ramanan; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Khurana_2023_CVPR, author = {Khurana, Tarasha and Hu, Peiyun and Held, David and Ramanan, Deva}, title = {Point Cloud Forecasting as a Proxy for 4D Occupancy Forecasting}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1116-1124} }
Masked Representation Learning for Domain Generalized Stereo Matching: Zhibo Rao,

Bangshu Xiong,

Mingyi He,

Yuchao Dai,

Renjie He,

Zhelun Shen,

Xing Li; [pdf] [supp]
[bibtex]
@InProceedings{Rao_2023_CVPR, author = {Rao, Zhibo and Xiong, Bangshu and He, Mingyi and Dai, Yuchao and He, Renjie and Shen, Zhelun and Li, Xing}, title = {Masked Representation Learning for Domain Generalized Stereo Matching}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5435-5444} }
You Can Ground Earlier Than See: An Effective and Efficient Pipeline for Temporal Sentence Grounding in Compressed Videos: Xiang Fang,

Daizong Liu,

Pan Zhou,

Guoshun Nan; [pdf] [arXiv]
[bibtex]
@InProceedings{Fang_2023_CVPR, author = {Fang, Xiang and Liu, Daizong and Zhou, Pan and Nan, Guoshun}, title = {You Can Ground Earlier Than See: An Effective and Efficient Pipeline for Temporal Sentence Grounding in Compressed Videos}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2448-2460} }
EqMotion: Equivariant Multi-Agent Motion Prediction With Invariant Interaction Reasoning: Chenxin Xu,

Robby T. Tan,

Yuhong Tan,

Siheng Chen,

Yu Guang Wang,

Xinchao Wang,

Yanfeng Wang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Xu_2023_CVPR, author = {Xu, Chenxin and Tan, Robby T. and Tan, Yuhong and Chen, Siheng and Wang, Yu Guang and Wang, Xinchao and Wang, Yanfeng}, title = {EqMotion: Equivariant Multi-Agent Motion Prediction With Invariant Interaction Reasoning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1410-1420} }
FlowFormer++: Masked Cost Volume Autoencoding for Pretraining Optical Flow Estimation: Xiaoyu Shi,

Zhaoyang Huang,

Dasong Li,

Manyuan Zhang,

Ka Chun Cheung,

Simon See,

Hongwei Qin,

Jifeng Dai,

Hongsheng Li; [pdf]
[bibtex]
@InProceedings{Shi_2023_CVPR, author = {Shi, Xiaoyu and Huang, Zhaoyang and Li, Dasong and Zhang, Manyuan and Cheung, Ka Chun and See, Simon and Qin, Hongwei and Dai, Jifeng and Li, Hongsheng}, title = {FlowFormer++: Masked Cost Volume Autoencoding for Pretraining Optical Flow Estimation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1599-1610} }
3D Human Keypoints Estimation From Point Clouds in the Wild Without Human Labels: Zhenzhen Weng,

Alexander S. Gorban,

Jingwei Ji,

Mahyar Najibi,

Yin Zhou,

Dragomir Anguelov; [pdf]
[bibtex]
@InProceedings{Weng_2023_CVPR, author = {Weng, Zhenzhen and Gorban, Alexander S. and Ji, Jingwei and Najibi, Mahyar and Zhou, Yin and Anguelov, Dragomir}, title = {3D Human Keypoints Estimation From Point Clouds in the Wild Without Human Labels}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1158-1167} }
Where Is My Spot? Few-Shot Image Generation via Latent Subspace Optimization: Chenxi Zheng,

Bangzhen Liu,

Huaidong Zhang,

Xuemiao Xu,

Shengfeng He; [pdf] [supp]
[bibtex]
@InProceedings{Zheng_2023_CVPR, author = {Zheng, Chenxi and Liu, Bangzhen and Zhang, Huaidong and Xu, Xuemiao and He, Shengfeng}, title = {Where Is My Spot? Few-Shot Image Generation via Latent Subspace Optimization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3272-3281} }
TopNet: Transformer-Based Object Placement Network for Image Compositing: Sijie Zhu,

Zhe Lin,

Scott Cohen,

Jason Kuen,

Zhifei Zhang,

Chen Chen; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhu_2023_CVPR, author = {Zhu, Sijie and Lin, Zhe and Cohen, Scott and Kuen, Jason and Zhang, Zhifei and Chen, Chen}, title = {TopNet: Transformer-Based Object Placement Network for Image Compositing}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1838-1847} }
Gloss Attention for Gloss-Free Sign Language Translation: Aoxiong Yin,

Tianyun Zhong,

Li Tang,

Weike Jin,

Tao Jin,

Zhou Zhao; [pdf] [supp]
[bibtex]
@InProceedings{Yin_2023_CVPR, author = {Yin, Aoxiong and Zhong, Tianyun and Tang, Li and Jin, Weike and Jin, Tao and Zhao, Zhou}, title = {Gloss Attention for Gloss-Free Sign Language Translation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2551-2562} }
Revisiting Rolling Shutter Bundle Adjustment: Toward Accurate and Fast Solution: Bangyan Liao,

Delin Qu,

Yifei Xue,

Huiqing Zhang,

Yizhen Lao; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Liao_2023_CVPR, author = {Liao, Bangyan and Qu, Delin and Xue, Yifei and Zhang, Huiqing and Lao, Yizhen}, title = {Revisiting Rolling Shutter Bundle Adjustment: Toward Accurate and Fast Solution}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4863-4871} }
Context-Aware Relative Object Queries To Unify Video Instance and Panoptic Segmentation: Anwesa Choudhuri,

Girish Chowdhary,

Alexander G. Schwing; [pdf] [supp]
[bibtex]
@InProceedings{Choudhuri_2023_CVPR, author = {Choudhuri, Anwesa and Chowdhary, Girish and Schwing, Alexander G.}, title = {Context-Aware Relative Object Queries To Unify Video Instance and Panoptic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6377-6386} }
Enhancing Deformable Local Features by Jointly Learning To Detect and Describe Keypoints: Guilherme Potje,

Felipe Cadar,

André Araujo,

Renato Martins,

Erickson R. Nascimento; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Potje_2023_CVPR, author = {Potje, Guilherme and Cadar, Felipe and Araujo, Andr\'e and Martins, Renato and Nascimento, Erickson R.}, title = {Enhancing Deformable Local Features by Jointly Learning To Detect and Describe Keypoints}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1306-1315} }
Siamese Image Modeling for Self-Supervised Vision Representation Learning: Chenxin Tao,

Xizhou Zhu,

Weijie Su,

Gao Huang,

Bin Li,

Jie Zhou,

Yu Qiao,

Xiaogang Wang,

Jifeng Dai; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Tao_2023_CVPR, author = {Tao, Chenxin and Zhu, Xizhou and Su, Weijie and Huang, Gao and Li, Bin and Zhou, Jie and Qiao, Yu and Wang, Xiaogang and Dai, Jifeng}, title = {Siamese Image Modeling for Self-Supervised Vision Representation Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2132-2141} }
Generating Part-Aware Editable 3D Shapes Without 3D Supervision: Konstantinos Tertikas,

Despoina Paschalidou,

Boxiao Pan,

Jeong Joon Park,

Mikaela Angelina Uy,

Ioannis Emiris,

Yannis Avrithis,

Leonidas Guibas; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Tertikas_2023_CVPR, author = {Tertikas, Konstantinos and Paschalidou, Despoina and Pan, Boxiao and Park, Jeong Joon and Uy, Mikaela Angelina and Emiris, Ioannis and Avrithis, Yannis and Guibas, Leonidas}, title = {Generating Part-Aware Editable 3D Shapes Without 3D Supervision}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4466-4478} }
High-Fidelity Facial Avatar Reconstruction From Monocular Video With Generative Priors: Yunpeng Bai,

Yanbo Fan,

Xuan Wang,

Yong Zhang,

Jingxiang Sun,

Chun Yuan,

Ying Shan; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Bai_2023_CVPR, author = {Bai, Yunpeng and Fan, Yanbo and Wang, Xuan and Zhang, Yong and Sun, Jingxiang and Yuan, Chun and Shan, Ying}, title = {High-Fidelity Facial Avatar Reconstruction From Monocular Video With Generative Priors}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4541-4551} }
CABM: Content-Aware Bit Mapping for Single Image Super-Resolution Network With Large Input: Senmao Tian,

Ming Lu,

Jiaming Liu,

Yandong Guo,

Yurong Chen,

Shunli Zhang; [pdf] [arXiv]
[bibtex]
@InProceedings{Tian_2023_CVPR, author = {Tian, Senmao and Lu, Ming and Liu, Jiaming and Guo, Yandong and Chen, Yurong and Zhang, Shunli}, title = {CABM: Content-Aware Bit Mapping for Single Image Super-Resolution Network With Large Input}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1756-1765} }
Decoupling MaxLogit for Out-of-Distribution Detection: Zihan Zhang,

Xiang Xiang; [pdf] [supp]
[bibtex]
@InProceedings{Zhang_2023_CVPR, author = {Zhang, Zihan and Xiang, Xiang}, title = {Decoupling MaxLogit for Out-of-Distribution Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3388-3397} }
Generalizing Dataset Distillation via Deep Generative Prior: George Cazenavette,

Tongzhou Wang,

Antonio Torralba,

Alexei A. Efros,

Jun-Yan Zhu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Cazenavette_2023_CVPR, author = {Cazenavette, George and Wang, Tongzhou and Torralba, Antonio and Efros, Alexei A. and Zhu, Jun-Yan}, title = {Generalizing Dataset Distillation via Deep Generative Prior}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3739-3748} }
Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo: Yuesong Wang,

Zhaojie Zeng,

Tao Guan,

Wei Yang,

Zhuo Chen,

Wenkai Liu,

Luoyuan Xu,

Yawei Luo; [pdf] [supp]
[bibtex]
@InProceedings{Wang_2023_CVPR, author = {Wang, Yuesong and Zeng, Zhaojie and Guan, Tao and Yang, Wei and Chen, Zhuo and Liu, Wenkai and Xu, Luoyuan and Luo, Yawei}, title = {Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1621-1630} }
Detection of Out-of-Distribution Samples Using Binary Neuron Activation Patterns: Bartłomiej Olber,

Krystian Radlak,

Adam Popowicz,

Michal Szczepankiewicz,

Krystian Chachuła; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Olber_2023_CVPR, author = {Olber, Bart{\l}omiej and Radlak, Krystian and Popowicz, Adam and Szczepankiewicz, Michal and Chachu{\l}a, Krystian}, title = {Detection of Out-of-Distribution Samples Using Binary Neuron Activation Patterns}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3378-3387} }
SeaThru-NeRF: Neural Radiance Fields in Scattering Media: Deborah Levy,

Amit Peleg,

Naama Pearl,

Dan Rosenbaum,

Derya Akkaynak,

Simon Korman,

Tali Treibitz; [pdf] [supp]
[bibtex]
@InProceedings{Levy_2023_CVPR, author = {Levy, Deborah and Peleg, Amit and Pearl, Naama and Rosenbaum, Dan and Akkaynak, Derya and Korman, Simon and Treibitz, Tali}, title = {SeaThru-NeRF: Neural Radiance Fields in Scattering Media}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {56-65} }
MixMAE: Mixed and Masked Autoencoder for Efficient Pretraining of Hierarchical Vision Transformers: Jihao Liu,

Xin Huang,

Jinliang Zheng,

Yu Liu,

Hongsheng Li; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Liu_2023_CVPR, author = {Liu, Jihao and Huang, Xin and Zheng, Jinliang and Liu, Yu and Li, Hongsheng}, title = {MixMAE: Mixed and Masked Autoencoder for Efficient Pretraining of Hierarchical Vision Transformers}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6252-6261} }
Human Pose Estimation in Extremely Low-Light Conditions: Sohyun Lee,

Jaesung Rim,

Boseung Jeong,

Geonu Kim,

Byungju Woo,

Haechan Lee,

Sunghyun Cho,

Suha Kwak; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Lee_2023_CVPR, author = {Lee, Sohyun and Rim, Jaesung and Jeong, Boseung and Kim, Geonu and Woo, Byungju and Lee, Haechan and Cho, Sunghyun and Kwak, Suha}, title = {Human Pose Estimation in Extremely Low-Light Conditions}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {704-714} }
EventNeRF: Neural Radiance Fields From a Single Colour Event Camera: Viktor Rudnev,

Mohamed Elgharib,

Christian Theobalt,

Vladislav Golyanik; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Rudnev_2023_CVPR, author = {Rudnev, Viktor and Elgharib, Mohamed and Theobalt, Christian and Golyanik, Vladislav}, title = {EventNeRF: Neural Radiance Fields From a Single Colour Event Camera}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4992-5002} }
Neighborhood Attention Transformer: Ali Hassani,

Steven Walton,

Jiachen Li,

Shen Li,

Humphrey Shi; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Hassani_2023_CVPR, author = {Hassani, Ali and Walton, Steven and Li, Jiachen and Li, Shen and Shi, Humphrey}, title = {Neighborhood Attention Transformer}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6185-6194} }
Progressive Spatio-Temporal Alignment for Efficient Event-Based Motion Estimation: Xueyan Huang,

Yueyi Zhang,

Zhiwei Xiong; [pdf] [supp]
[bibtex]
@InProceedings{Huang_2023_CVPR, author = {Huang, Xueyan and Zhang, Yueyi and Xiong, Zhiwei}, title = {Progressive Spatio-Temporal Alignment for Efficient Event-Based Motion Estimation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1537-1546} }
Trap Attention: Monocular Depth Estimation With Manual Traps: Chao Ning,

Hongping Gan; [pdf] [supp]
[bibtex]
@InProceedings{Ning_2023_CVPR, author = {Ning, Chao and Gan, Hongping}, title = {Trap Attention: Monocular Depth Estimation With Manual Traps}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5033-5043} }
Representing Volumetric Videos As Dynamic MLP Maps: Sida Peng,

Yunzhi Yan,

Qing Shuai,

Hujun Bao,

Xiaowei Zhou; [pdf] [arXiv]
[bibtex]
@InProceedings{Peng_2023_CVPR, author = {Peng, Sida and Yan, Yunzhi and Shuai, Qing and Bao, Hujun and Zhou, Xiaowei}, title = {Representing Volumetric Videos As Dynamic MLP Maps}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4252-4262} }
Video-Text As Game Players: Hierarchical Banzhaf Interaction for Cross-Modal Representation Learning: Peng Jin,

Jinfa Huang,

Pengfei Xiong,

Shangxuan Tian,

Chang Liu,

Xiangyang Ji,

Li Yuan,

Jie Chen; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Jin_2023_CVPR, author = {Jin, Peng and Huang, Jinfa and Xiong, Pengfei and Tian, Shangxuan and Liu, Chang and Ji, Xiangyang and Yuan, Li and Chen, Jie}, title = {Video-Text As Game Players: Hierarchical Banzhaf Interaction for Cross-Modal Representation Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2472-2482} }
Blur Interpolation Transformer for Real-World Motion From Blur: Zhihang Zhong,

Mingdeng Cao,

Xiang Ji,

Yinqiang Zheng,

Imari Sato; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhong_2023_CVPR, author = {Zhong, Zhihang and Cao, Mingdeng and Ji, Xiang and Zheng, Yinqiang and Sato, Imari}, title = {Blur Interpolation Transformer for Real-World Motion From Blur}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5713-5723} }
Rethinking Few-Shot Medical Segmentation: A Vector Quantization View: Shiqi Huang,

Tingfa Xu,

Ning Shen,

Feng Mu,

Jianan Li; [pdf] [supp]
[bibtex]
@InProceedings{Huang_2023_CVPR, author = {Huang, Shiqi and Xu, Tingfa and Shen, Ning and Mu, Feng and Li, Jianan}, title = {Rethinking Few-Shot Medical Segmentation: A Vector Quantization View}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3072-3081} }
Event-Based Shape From Polarization: Manasi Muglikar,

Leonard Bauersfeld,

Diederik Paul Moeys,

Davide Scaramuzza; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Muglikar_2023_CVPR, author = {Muglikar, Manasi and Bauersfeld, Leonard and Moeys, Diederik Paul and Scaramuzza, Davide}, title = {Event-Based Shape From Polarization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1547-1556} }
ARO-Net: Learning Implicit Fields From Anchored Radial Observations: Yizhi Wang,

Zeyu Huang,

Ariel Shamir,

Hui Huang,

Hao Zhang,

Ruizhen Hu; [pdf] [supp]
[bibtex]
@InProceedings{Wang_2023_CVPR, author = {Wang, Yizhi and Huang, Zeyu and Shamir, Ariel and Huang, Hui and Zhang, Hao and Hu, Ruizhen}, title = {ARO-Net: Learning Implicit Fields From Anchored Radial Observations}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3572-3581} }
All in One: Exploring Unified Video-Language Pre-Training: Jinpeng Wang,

Yixiao Ge,

Rui Yan,

Yuying Ge,

Kevin Qinghong Lin,

Satoshi Tsutsui,

Xudong Lin,

Guanyu Cai,

Jianping Wu,

Ying Shan,

Xiaohu Qie,

Mike Zheng Shou; [pdf] [arXiv]
[bibtex]
@InProceedings{Wang_2023_CVPR, author = {Wang, Jinpeng and Ge, Yixiao and Yan, Rui and Ge, Yuying and Lin, Kevin Qinghong and Tsutsui, Satoshi and Lin, Xudong and Cai, Guanyu and Wu, Jianping and Shan, Ying and Qie, Xiaohu and Shou, Mike Zheng}, title = {All in One: Exploring Unified Video-Language Pre-Training}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6598-6608} }
Making Vision Transformers Efficient From a Token Sparsification View: Shuning Chang,

Pichao Wang,

Ming Lin,

Fan Wang,

David Junhao Zhang,

Rong Jin,

Mike Zheng Shou; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chang_2023_CVPR, author = {Chang, Shuning and Wang, Pichao and Lin, Ming and Wang, Fan and Zhang, David Junhao and Jin, Rong and Shou, Mike Zheng}, title = {Making Vision Transformers Efficient From a Token Sparsification View}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6195-6205} }
RefCLIP: A Universal Teacher for Weakly Supervised Referring Expression Comprehension: Lei Jin,

Gen Luo,

Yiyi Zhou,

Xiaoshuai Sun,

Guannan Jiang,

Annan Shu,

Rongrong Ji; [pdf]
[bibtex]
@InProceedings{Jin_2023_CVPR, author = {Jin, Lei and Luo, Gen and Zhou, Yiyi and Sun, Xiaoshuai and Jiang, Guannan and Shu, Annan and Ji, Rongrong}, title = {RefCLIP: A Universal Teacher for Weakly Supervised Referring Expression Comprehension}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2681-2690} }
Re-IQA: Unsupervised Learning for Image Quality Assessment in the Wild: Avinab Saha,

Sandeep Mishra,

Alan C. Bovik; [pdf] [supp]
[bibtex]
@InProceedings{Saha_2023_CVPR, author = {Saha, Avinab and Mishra, Sandeep and Bovik, Alan C.}, title = {Re-IQA: Unsupervised Learning for Image Quality Assessment in the Wild}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5846-5855} }
Catch Missing Details: Image Reconstruction With Frequency Augmented Variational Autoencoder: Xinmiao Lin,

Yikang Li,

Jenhao Hsiao,

Chiuman Ho,

Yu Kong; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Lin_2023_CVPR, author = {Lin, Xinmiao and Li, Yikang and Hsiao, Jenhao and Ho, Chiuman and Kong, Yu}, title = {Catch Missing Details: Image Reconstruction With Frequency Augmented Variational Autoencoder}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1736-1745} }
Rotation-Invariant Transformer for Point Cloud Matching: Hao Yu,

Zheng Qin,

Ji Hou,

Mahdi Saleh,

Dongsheng Li,

Benjamin Busam,

Slobodan Ilic; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yu_2023_CVPR, author = {Yu, Hao and Qin, Zheng and Hou, Ji and Saleh, Mahdi and Li, Dongsheng and Busam, Benjamin and Ilic, Slobodan}, title = {Rotation-Invariant Transformer for Point Cloud Matching}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5384-5393} }
Habitat-Matterport 3D Semantics Dataset: Karmesh Yadav,

Ram Ramrakhya,

Santhosh Kumar Ramakrishnan,

Theo Gervet,

John Turner,

Aaron Gokaslan,

Noah Maestre,

Angel Xuan Chang,

Dhruv Batra,

Manolis Savva,

Alexander William Clegg,

Devendra Singh Chaplot; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yadav_2023_CVPR, author = {Yadav, Karmesh and Ramrakhya, Ram and Ramakrishnan, Santhosh Kumar and Gervet, Theo and Turner, John and Gokaslan, Aaron and Maestre, Noah and Chang, Angel Xuan and Batra, Dhruv and Savva, Manolis and Clegg, Alexander William and Chaplot, Devendra Singh}, title = {Habitat-Matterport 3D Semantics Dataset}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4927-4936} }
EDGE: Editable Dance Generation From Music: Jonathan Tseng,

Rodrigo Castellon,

Karen Liu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Tseng_2023_CVPR, author = {Tseng, Jonathan and Castellon, Rodrigo and Liu, Karen}, title = {EDGE: Editable Dance Generation From Music}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {448-458} }
Curricular Contrastive Regularization for Physics-Aware Single Image Dehazing: Yu Zheng,

Jiahui Zhan,

Shengfeng He,

Junyu Dong,

Yong Du; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zheng_2023_CVPR, author = {Zheng, Yu and Zhan, Jiahui and He, Shengfeng and Dong, Junyu and Du, Yong}, title = {Curricular Contrastive Regularization for Physics-Aware Single Image Dehazing}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5785-5794} }
Sharpness-Aware Gradient Matching for Domain Generalization: Pengfei Wang,

Zhaoxiang Zhang,

Zhen Lei,

Lei Zhang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2023_CVPR, author = {Wang, Pengfei and Zhang, Zhaoxiang and Lei, Zhen and Zhang, Lei}, title = {Sharpness-Aware Gradient Matching for Domain Generalization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3769-3778} }
Bi-Directional Feature Fusion Generative Adversarial Network for Ultra-High Resolution Pathological Image Virtual Re-Staining: Kexin Sun,

Zhineng Chen,

Gongwei Wang,

Jun Liu,

Xiongjun Ye,

Yu-Gang Jiang; [pdf] [supp]
[bibtex]
@InProceedings{Sun_2023_CVPR, author = {Sun, Kexin and Chen, Zhineng and Wang, Gongwei and Liu, Jun and Ye, Xiongjun and Jiang, Yu-Gang}, title = {Bi-Directional Feature Fusion Generative Adversarial Network for Ultra-High Resolution Pathological Image Virtual Re-Staining}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3904-3913} }
Towards Practical Plug-and-Play Diffusion Models: Hyojun Go,

Yunsung Lee,

Jin-Young Kim,

Seunghyun Lee,

Myeongho Jeong,

Hyun Seung Lee,

Seungtaek Choi; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Go_2023_CVPR, author = {Go, Hyojun and Lee, Yunsung and Kim, Jin-Young and Lee, Seunghyun and Jeong, Myeongho and Lee, Hyun Seung and Choi, Seungtaek}, title = {Towards Practical Plug-and-Play Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1962-1971} }
YOLOv7: Trainable Bag-of-Freebies Sets New State-of-the-Art for Real-Time Object Detectors: Chien-Yao Wang,

Alexey Bochkovskiy,

Hong-Yuan Mark Liao; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2023_CVPR, author = {Wang, Chien-Yao and Bochkovskiy, Alexey and Liao, Hong-Yuan Mark}, title = {YOLOv7: Trainable Bag-of-Freebies Sets New State-of-the-Art for Real-Time Object Detectors}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7464-7475} }
PartDistillation: Learning Parts From Instance Segmentation: Jang Hyun Cho,

Philipp Krähenbühl,

Vignesh Ramanathan; [pdf] [supp]
[bibtex]
@InProceedings{Cho_2023_CVPR, author = {Cho, Jang Hyun and Kr\"ahenb\"uhl, Philipp and Ramanathan, Vignesh}, title = {PartDistillation: Learning Parts From Instance Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7152-7161} }
Boosting Video Object Segmentation via Space-Time Correspondence Learning: Yurong Zhang,

Liulei Li,

Wenguan Wang,

Rong Xie,

Li Song,

Wenjun Zhang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhang_2023_CVPR, author = {Zhang, Yurong and Li, Liulei and Wang, Wenguan and Xie, Rong and Song, Li and Zhang, Wenjun}, title = {Boosting Video Object Segmentation via Space-Time Correspondence Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2246-2256} }
Towards Realistic Long-Tailed Semi-Supervised Learning: Consistency Is All You Need: Tong Wei,

Kai Gan; [pdf] [supp]
[bibtex]
@InProceedings{Wei_2023_CVPR, author = {Wei, Tong and Gan, Kai}, title = {Towards Realistic Long-Tailed Semi-Supervised Learning: Consistency Is All You Need}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3469-3478} }
GAPartNet: Cross-Category Domain-Generalizable Object Perception and Manipulation via Generalizable and Actionable Parts: Haoran Geng,

Helin Xu,

Chengyang Zhao,

Chao Xu,

Li Yi,

Siyuan Huang,

He Wang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Geng_2023_CVPR, author = {Geng, Haoran and Xu, Helin and Zhao, Chengyang and Xu, Chao and Yi, Li and Huang, Siyuan and Wang, He}, title = {GAPartNet: Cross-Category Domain-Generalizable Object Perception and Manipulation via Generalizable and Actionable Parts}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7081-7091} }
OmniObject3D: Large-Vocabulary 3D Object Dataset for Realistic Perception, Reconstruction and Generation: Tong Wu,

Jiarui Zhang,

Xiao Fu,

Yuxin Wang,

Jiawei Ren,

Liang Pan,

Wayne Wu,

Lei Yang,

Jiaqi Wang,

Chen Qian,

Dahua Lin,

Ziwei Liu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wu_2023_CVPR, author = {Wu, Tong and Zhang, Jiarui and Fu, Xiao and Wang, Yuxin and Ren, Jiawei and Pan, Liang and Wu, Wayne and Yang, Lei and Wang, Jiaqi and Qian, Chen and Lin, Dahua and Liu, Ziwei}, title = {OmniObject3D: Large-Vocabulary 3D Object Dataset for Realistic Perception, Reconstruction and Generation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {803-814} }
Uncovering the Disentanglement Capability in Text-to-Image Diffusion Models: Qiucheng Wu,

Yujian Liu,

Handong Zhao,

Ajinkya Kale,

Trung Bui,

Tong Yu,

Zhe Lin,

Yang Zhang,

Shiyu Chang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wu_2023_CVPR, author = {Wu, Qiucheng and Liu, Yujian and Zhao, Handong and Kale, Ajinkya and Bui, Trung and Yu, Tong and Lin, Zhe and Zhang, Yang and Chang, Shiyu}, title = {Uncovering the Disentanglement Capability in Text-to-Image Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1900-1910} }
EXIF As Language: Learning Cross-Modal Associations Between Images and Camera Metadata: Chenhao Zheng,

Ayush Shrivastava,

Andrew Owens; [pdf] [arXiv]
[bibtex]
@InProceedings{Zheng_2023_CVPR, author = {Zheng, Chenhao and Shrivastava, Ayush and Owens, Andrew}, title = {EXIF As Language: Learning Cross-Modal Associations Between Images and Camera Metadata}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6945-6956} }
TrojDiff: Trojan Attacks on Diffusion Models With Diverse Targets: Weixin Chen,

Dawn Song,

Bo Li; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chen_2023_CVPR, author = {Chen, Weixin and Song, Dawn and Li, Bo}, title = {TrojDiff: Trojan Attacks on Diffusion Models With Diverse Targets}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4035-4044} }
Mitigating Task Interference in Multi-Task Learning via Explicit Task Routing With Non-Learnable Primitives: Chuntao Ding,

Zhichao Lu,

Shangguang Wang,

Ran Cheng,

Vishnu Naresh Boddeti; [pdf] [supp]
[bibtex]
@InProceedings{Ding_2023_CVPR, author = {Ding, Chuntao and Lu, Zhichao and Wang, Shangguang and Cheng, Ran and Boddeti, Vishnu Naresh}, title = {Mitigating Task Interference in Multi-Task Learning via Explicit Task Routing With Non-Learnable Primitives}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7756-7765} }
Neural Kernel Surface Reconstruction: Jiahui Huang,

Zan Gojcic,

Matan Atzmon,

Or Litany,

Sanja Fidler,

Francis Williams; [pdf] [supp]
[bibtex]
@InProceedings{Huang_2023_CVPR, author = {Huang, Jiahui and Gojcic, Zan and Atzmon, Matan and Litany, Or and Fidler, Sanja and Williams, Francis}, title = {Neural Kernel Surface Reconstruction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4369-4379} }
Multilateral Semantic Relations Modeling for Image Text Retrieval: Zheng Wang,

Zhenwei Gao,

Kangshuai Guo,

Yang Yang,

Xiaoming Wang,

Heng Tao Shen; [pdf]
[bibtex]
@InProceedings{Wang_2023_CVPR, author = {Wang, Zheng and Gao, Zhenwei and Guo, Kangshuai and Yang, Yang and Wang, Xiaoming and Shen, Heng Tao}, title = {Multilateral Semantic Relations Modeling for Image Text Retrieval}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2830-2839} }
Optimization-Inspired Cross-Attention Transformer for Compressive Sensing: Jiechong Song,

Chong Mou,

Shiqi Wang,

Siwei Ma,

Jian Zhang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Song_2023_CVPR, author = {Song, Jiechong and Mou, Chong and Wang, Shiqi and Ma, Siwei and Zhang, Jian}, title = {Optimization-Inspired Cross-Attention Transformer for Compressive Sensing}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6174-6184} }
Normalizing Flow Based Feature Synthesis for Outlier-Aware Object Detection: Nishant Kumar,

Siniša Šegvić,

Abouzar Eslami,

Stefan Gumhold; [pdf] [supp]
[bibtex]
@InProceedings{Kumar_2023_CVPR, author = {Kumar, Nishant and \v{S}egvi\'c, Sini\v{s}a and Eslami, Abouzar and Gumhold, Stefan}, title = {Normalizing Flow Based Feature Synthesis for Outlier-Aware Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5156-5165} }
DivClust: Controlling Diversity in Deep Clustering: Ioannis Maniadis Metaxas,

Georgios Tzimiropoulos,

Ioannis Patras; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Metaxas_2023_CVPR, author = {Metaxas, Ioannis Maniadis and Tzimiropoulos, Georgios and Patras, Ioannis}, title = {DivClust: Controlling Diversity in Deep Clustering}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3418-3428} }
Topology-Guided Multi-Class Cell Context Generation for Digital Pathology: Shahira Abousamra,

Rajarsi Gupta,

Tahsin Kurc,

Dimitris Samaras,

Joel Saltz,

Chao Chen; [pdf] [arXiv]
[bibtex]
@InProceedings{Abousamra_2023_CVPR, author = {Abousamra, Shahira and Gupta, Rajarsi and Kurc, Tahsin and Samaras, Dimitris and Saltz, Joel and Chen, Chao}, title = {Topology-Guided Multi-Class Cell Context Generation for Digital Pathology}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3323-3333} }
Adaptive Graph Convolutional Subspace Clustering: Lai Wei,

Zhengwei Chen,

Jun Yin,

Changming Zhu,

Rigui Zhou,

Jin Liu; [pdf] [arXiv]
[bibtex]
@InProceedings{Wei_2023_CVPR, author = {Wei, Lai and Chen, Zhengwei and Yin, Jun and Zhu, Changming and Zhou, Rigui and Liu, Jin}, title = {Adaptive Graph Convolutional Subspace Clustering}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6262-6271} }
Learning Steerable Function for Efficient Image Resampling: Jiacheng Li,

Chang Chen,

Wei Huang,

Zhiqiang Lang,

Fenglong Song,

Youliang Yan,

Zhiwei Xiong; [pdf] [supp]
[bibtex]
@InProceedings{Li_2023_CVPR, author = {Li, Jiacheng and Chen, Chang and Huang, Wei and Lang, Zhiqiang and Song, Fenglong and Yan, Youliang and Xiong, Zhiwei}, title = {Learning Steerable Function for Efficient Image Resampling}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5866-5875} }
Cut and Learn for Unsupervised Object Detection and Instance Segmentation: Xudong Wang,

Rohit Girdhar,

Stella X. Yu,

Ishan Misra; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2023_CVPR, author = {Wang, Xudong and Girdhar, Rohit and Yu, Stella X. and Misra, Ishan}, title = {Cut and Learn for Unsupervised Object Detection and Instance Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3124-3134} }
Privacy-Preserving Adversarial Facial Features: Zhibo Wang,

He Wang,

Shuaifan Jin,

Wenwen Zhang,

Jiahui Hu,

Yan Wang,

Peng Sun,

Wei Yuan,

Kaixin Liu,

Kui Ren; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2023_CVPR, author = {Wang, Zhibo and Wang, He and Jin, Shuaifan and Zhang, Wenwen and Hu, Jiahui and Wang, Yan and Sun, Peng and Yuan, Wei and Liu, Kaixin and Ren, Kui}, title = {Privacy-Preserving Adversarial Facial Features}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8212-8221} }
Exploring the Relationship Between Architectural Design and Adversarially Robust Generalization: Aishan Liu,

Shiyu Tang,

Siyuan Liang,

Ruihao Gong,

Boxi Wu,

Xianglong Liu,

Dacheng Tao; [pdf] [supp]
[bibtex]
@InProceedings{Liu_2023_CVPR, author = {Liu, Aishan and Tang, Shiyu and Liang, Siyuan and Gong, Ruihao and Wu, Boxi and Liu, Xianglong and Tao, Dacheng}, title = {Exploring the Relationship Between Architectural Design and Adversarially Robust Generalization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4096-4107} }
Side Adapter Network for Open-Vocabulary Semantic Segmentation: Mengde Xu,

Zheng Zhang,

Fangyun Wei,

Han Hu,

Xiang Bai; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Xu_2023_CVPR, author = {Xu, Mengde and Zhang, Zheng and Wei, Fangyun and Hu, Han and Bai, Xiang}, title = {Side Adapter Network for Open-Vocabulary Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2945-2954} }
Multi-Centroid Task Descriptor for Dynamic Class Incremental Inference: Tenghao Cai,

Zhizhong Zhang,

Xin Tan,

Yanyun Qu,

Guannan Jiang,

Chengjie Wang,

Yuan Xie; [pdf] [supp]
[bibtex]
@InProceedings{Cai_2023_CVPR, author = {Cai, Tenghao and Zhang, Zhizhong and Tan, Xin and Qu, Yanyun and Jiang, Guannan and Wang, Chengjie and Xie, Yuan}, title = {Multi-Centroid Task Descriptor for Dynamic Class Incremental Inference}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7298-7307} }
Physics-Guided ISO-Dependent Sensor Noise Modeling for Extreme Low-Light Photography: Yue Cao,

Ming Liu,

Shuai Liu,

Xiaotao Wang,

Lei Lei,

Wangmeng Zuo; [pdf] [supp]
[bibtex]
@InProceedings{Cao_2023_CVPR, author = {Cao, Yue and Liu, Ming and Liu, Shuai and Wang, Xiaotao and Lei, Lei and Zuo, Wangmeng}, title = {Physics-Guided ISO-Dependent Sensor Noise Modeling for Extreme Low-Light Photography}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5744-5753} }
DiGeo: Discriminative Geometry-Aware Learning for Generalized Few-Shot Object Detection: Jiawei Ma,

Yulei Niu,

Jincheng Xu,

Shiyuan Huang,

Guangxing Han,

Shih-Fu Chang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ma_2023_CVPR, author = {Ma, Jiawei and Niu, Yulei and Xu, Jincheng and Huang, Shiyuan and Han, Guangxing and Chang, Shih-Fu}, title = {DiGeo: Discriminative Geometry-Aware Learning for Generalized Few-Shot Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3208-3218} }
A Soma Segmentation Benchmark in Full Adult Fly Brain: Xiaoyu Liu,

Bo Hu,

Mingxing Li,

Wei Huang,

Yueyi Zhang,

Zhiwei Xiong; [pdf] [supp]
[bibtex]
@InProceedings{Liu_2023_CVPR, author = {Liu, Xiaoyu and Hu, Bo and Li, Mingxing and Huang, Wei and Zhang, Yueyi and Xiong, Zhiwei}, title = {A Soma Segmentation Benchmark in Full Adult Fly Brain}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7402-7411} }
CaPriDe Learning: Confidential and Private Decentralized Learning Based on Encryption-Friendly Distillation Loss: Nurbek Tastan,

Karthik Nandakumar; [pdf] [supp]
[bibtex]
@InProceedings{Tastan_2023_CVPR, author = {Tastan, Nurbek and Nandakumar, Karthik}, title = {CaPriDe Learning: Confidential and Private Decentralized Learning Based on Encryption-Friendly Distillation Loss}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8084-8092} }
vMAP: Vectorised Object Mapping for Neural Field SLAM: Xin Kong,

Shikun Liu,

Marwan Taher,

Andrew J. Davison; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kong_2023_CVPR, author = {Kong, Xin and Liu, Shikun and Taher, Marwan and Davison, Andrew J.}, title = {vMAP: Vectorised Object Mapping for Neural Field SLAM}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {952-961} }
Images Speak in Images: A Generalist Painter for In-Context Visual Learning: Xinlong Wang,

Wen Wang,

Yue Cao,

Chunhua Shen,

Tiejun Huang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2023_CVPR, author = {Wang, Xinlong and Wang, Wen and Cao, Yue and Shen, Chunhua and Huang, Tiejun}, title = {Images Speak in Images: A Generalist Painter for In-Context Visual Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6830-6839} }
StyLess: Boosting the Transferability of Adversarial Examples: Kaisheng Liang,

Bin Xiao; [pdf] [arXiv]
[bibtex]
@InProceedings{Liang_2023_CVPR, author = {Liang, Kaisheng and Xiao, Bin}, title = {StyLess: Boosting the Transferability of Adversarial Examples}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8163-8172} }
Uncertainty-Aware Optimal Transport for Semantically Coherent Out-of-Distribution Detection: Fan Lu,

Kai Zhu,

Wei Zhai,

Kecheng Zheng,

Yang Cao; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Lu_2023_CVPR, author = {Lu, Fan and Zhu, Kai and Zhai, Wei and Zheng, Kecheng and Cao, Yang}, title = {Uncertainty-Aware Optimal Transport for Semantically Coherent Out-of-Distribution Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3282-3291} }
MISC210K: A Large-Scale Dataset for Multi-Instance Semantic Correspondence: Yixuan Sun,

Yiwen Huang,

Haijing Guo,

Yuzhou Zhao,

Runmin Wu,

Yizhou Yu,

Weifeng Ge,

Wenqiang Zhang; [pdf] [supp]
[bibtex]
@InProceedings{Sun_2023_CVPR, author = {Sun, Yixuan and Huang, Yiwen and Guo, Haijing and Zhao, Yuzhou and Wu, Runmin and Yu, Yizhou and Ge, Weifeng and Zhang, Wenqiang}, title = {MISC210K: A Large-Scale Dataset for Multi-Instance Semantic Correspondence}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7121-7130} }
MAGE: MAsked Generative Encoder To Unify Representation Learning and Image Synthesis: Tianhong Li,

Huiwen Chang,

Shlok Mishra,

Han Zhang,

Dina Katabi,

Dilip Krishnan; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Li_2023_CVPR, author = {Li, Tianhong and Chang, Huiwen and Mishra, Shlok and Zhang, Han and Katabi, Dina and Krishnan, Dilip}, title = {MAGE: MAsked Generative Encoder To Unify Representation Learning and Image Synthesis}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2142-2152} }
Lift3D: Synthesize 3D Training Data by Lifting 2D GAN to 3D Generative Radiance Field: Leheng Li,

Qing Lian,

Luozhou Wang,

Ningning Ma,

Ying-Cong Chen; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Li_2023_CVPR, author = {Li, Leheng and Lian, Qing and Wang, Luozhou and Ma, Ningning and Chen, Ying-Cong}, title = {Lift3D: Synthesize 3D Training Data by Lifting 2D GAN to 3D Generative Radiance Field}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {332-341} }
Hunting Sparsity: Density-Guided Contrastive Learning for Semi-Supervised Semantic Segmentation: Xiaoyang Wang,

Bingfeng Zhang,

Limin Yu,

Jimin Xiao; [pdf] [supp]
[bibtex]
@InProceedings{Wang_2023_CVPR, author = {Wang, Xiaoyang and Zhang, Bingfeng and Yu, Limin and Xiao, Jimin}, title = {Hunting Sparsity: Density-Guided Contrastive Learning for Semi-Supervised Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3114-3123} }
An Erudite Fine-Grained Visual Classification Model: Dongliang Chang,

Yujun Tong,

Ruoyi Du,

Timothy Hospedales,

Yi-Zhe Song,