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,

Zhanyu Ma

[pdf]

[bibtex]

@InProceedings{Chang_2023_CVPR, author = {Chang, Dongliang and Tong, Yujun and Du, Ruoyi and Hospedales, Timothy and Song, Yi-Zhe and Ma, Zhanyu}, title = {An Erudite Fine-Grained Visual Classification Model}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7268-7277} }

Adversarially Robust Neural Architecture Search for Graph Neural Networks

Beini Xie,

Heng Chang,

Ziwei Zhang,

Xin Wang,

Daixin Wang,

Zhiqiang Zhang,

Rex Ying,

Wenwu Zhu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Xie_2023_CVPR, author = {Xie, Beini and Chang, Heng and Zhang, Ziwei and Wang, Xin and Wang, Daixin and Zhang, Zhiqiang and Ying, Rex and Zhu, Wenwu}, title = {Adversarially Robust Neural Architecture Search for Graph Neural Networks}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8143-8152} }

Affordance Grounding From Demonstration Video To Target Image

Joya Chen,

Difei Gao,

Kevin Qinghong Lin,

Mike Zheng Shou

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Chen_2023_CVPR, author = {Chen, Joya and Gao, Difei and Lin, Kevin Qinghong and Shou, Mike Zheng}, title = {Affordance Grounding From Demonstration Video To Target Image}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6799-6808} }

DeepMAD: Mathematical Architecture Design for Deep Convolutional Neural Network

Xuan Shen,

Yaohua Wang,

Ming Lin,

Yilun Huang,

Hao Tang,

Xiuyu Sun,

Yanzhi Wang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Shen_2023_CVPR, author = {Shen, Xuan and Wang, Yaohua and Lin, Ming and Huang, Yilun and Tang, Hao and Sun, Xiuyu and Wang, Yanzhi}, title = {DeepMAD: Mathematical Architecture Design for Deep Convolutional Neural Network}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6163-6173} }

BBDM: Image-to-Image Translation With Brownian Bridge Diffusion Models

Bo Li,

Kaitao Xue,

Bin Liu,

Yu-Kun Lai

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Li_2023_CVPR, author = {Li, Bo and Xue, Kaitao and Liu, Bin and Lai, Yu-Kun}, title = {BBDM: Image-to-Image Translation With Brownian Bridge Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1952-1961} }

Probing Neural Representations of Scene Perception in a Hippocampally Dependent Task Using Artificial Neural Networks

Markus Frey,

Christian F. Doeller,

Caswell Barry

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Frey_2023_CVPR, author = {Frey, Markus and Doeller, Christian F. and Barry, Caswell}, title = {Probing Neural Representations of Scene Perception in a Hippocampally Dependent Task Using Artificial Neural Networks}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2113-2121} }

A Probabilistic Framework for Lifelong Test-Time Adaptation

Dhanajit Brahma,

Piyush Rai

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Brahma_2023_CVPR, author = {Brahma, Dhanajit and Rai, Piyush}, title = {A Probabilistic Framework for Lifelong Test-Time Adaptation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3582-3591} }

Sound to Visual Scene Generation by Audio-to-Visual Latent Alignment

Kim Sung-Bin,

Arda Senocak,

Hyunwoo Ha,

Andrew Owens,

Tae-Hyun Oh

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Sung-Bin_2023_CVPR, author = {Sung-Bin, Kim and Senocak, Arda and Ha, Hyunwoo and Owens, Andrew and Oh, Tae-Hyun}, title = {Sound to Visual Scene Generation by Audio-to-Visual Latent Alignment}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6430-6440} }

Filtering, Distillation, and Hard Negatives for Vision-Language Pre-Training

Filip Radenovic,

Abhimanyu Dubey,

Abhishek Kadian,

Todor Mihaylov,

Simon Vandenhende,

Yash Patel,

Yi Wen,

Vignesh Ramanathan,

Dhruv Mahajan

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Radenovic_2023_CVPR, author = {Radenovic, Filip and Dubey, Abhimanyu and Kadian, Abhishek and Mihaylov, Todor and Vandenhende, Simon and Patel, Yash and Wen, Yi and Ramanathan, Vignesh and Mahajan, Dhruv}, title = {Filtering, Distillation, and Hard Negatives for Vision-Language Pre-Training}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6967-6977} }

PointCMP: Contrastive Mask Prediction for Self-Supervised Learning on Point Cloud Videos

Zhiqiang Shen,

Xiaoxiao Sheng,

Longguang Wang,

Yulan Guo,

Qiong Liu,

Xi Zhou

[pdf] [arXiv]

[bibtex]

@InProceedings{Shen_2023_CVPR, author = {Shen, Zhiqiang and Sheng, Xiaoxiao and Wang, Longguang and Guo, Yulan and Liu, Qiong and Zhou, Xi}, title = {PointCMP: Contrastive Mask Prediction for Self-Supervised Learning on Point Cloud Videos}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1212-1222} }

IS-GGT: Iterative Scene Graph Generation With Generative Transformers

Sanjoy Kundu,

Sathyanarayanan N. Aakur

[pdf] [supp]

[bibtex]

@InProceedings{Kundu_2023_CVPR, author = {Kundu, Sanjoy and Aakur, Sathyanarayanan N.}, title = {IS-GGT: Iterative Scene Graph Generation With Generative Transformers}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6292-6301} }

Meta Omnium: A Benchmark for General-Purpose Learning-To-Learn

Ondrej Bohdal,

Yinbing Tian,

Yongshuo Zong,

Ruchika Chavhan,

Da Li,

Henry Gouk,

Li Guo,

Timothy Hospedales

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Bohdal_2023_CVPR, author = {Bohdal, Ondrej and Tian, Yinbing and Zong, Yongshuo and Chavhan, Ruchika and Li, Da and Gouk, Henry and Guo, Li and Hospedales, Timothy}, title = {Meta Omnium: A Benchmark for General-Purpose Learning-To-Learn}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7693-7703} }

Multimodal Industrial Anomaly Detection via Hybrid Fusion

Yue Wang,

Jinlong Peng,

Jiangning Zhang,

Ran Yi,

Yabiao Wang,

Chengjie Wang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Yue and Peng, Jinlong and Zhang, Jiangning and Yi, Ran and Wang, Yabiao and Wang, Chengjie}, title = {Multimodal Industrial Anomaly Detection via Hybrid Fusion}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8032-8041} }

BoxTeacher: Exploring High-Quality Pseudo Labels for Weakly Supervised Instance Segmentation

Tianheng Cheng,

Xinggang Wang,

Shaoyu Chen,

Qian Zhang,

Wenyu Liu

[pdf] [arXiv]

[bibtex]

@InProceedings{Cheng_2023_CVPR, author = {Cheng, Tianheng and Wang, Xinggang and Chen, Shaoyu and Zhang, Qian and Liu, Wenyu}, title = {BoxTeacher: Exploring High-Quality Pseudo Labels for Weakly Supervised Instance Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3145-3154} }

Change-Aware Sampling and Contrastive Learning for Satellite Images

Utkarsh Mall,

Bharath Hariharan,

Kavita Bala

[pdf] [supp]

[bibtex]

@InProceedings{Mall_2023_CVPR, author = {Mall, Utkarsh and Hariharan, Bharath and Bala, Kavita}, title = {Change-Aware Sampling and Contrastive Learning for Satellite Images}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5261-5270} }

KD-DLGAN: Data Limited Image Generation via Knowledge Distillation

Kaiwen Cui,

Yingchen Yu,

Fangneng Zhan,

Shengcai Liao,

Shijian Lu,

Eric P. Xing

[pdf] [supp]

[bibtex]

@InProceedings{Cui_2023_CVPR, author = {Cui, Kaiwen and Yu, Yingchen and Zhan, Fangneng and Liao, Shengcai and Lu, Shijian and Xing, Eric P.}, title = {KD-DLGAN: Data Limited Image Generation via Knowledge Distillation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3872-3882} }

Batch Model Consolidation: A Multi-Task Model Consolidation Framework

Iordanis Fostiropoulos,

Jiaye Zhu,

Laurent Itti

[pdf] [supp]

[bibtex]

@InProceedings{Fostiropoulos_2023_CVPR, author = {Fostiropoulos, Iordanis and Zhu, Jiaye and Itti, Laurent}, title = {Batch Model Consolidation: A Multi-Task Model Consolidation Framework}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3664-3676} }

DR2: Diffusion-Based Robust Degradation Remover for Blind Face Restoration

Zhixin Wang,

Ziying Zhang,

Xiaoyun Zhang,

Huangjie Zheng,

Mingyuan Zhou,

Ya Zhang,

Yanfeng Wang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Zhixin and Zhang, Ziying and Zhang, Xiaoyun and Zheng, Huangjie and Zhou, Mingyuan and Zhang, Ya and Wang, Yanfeng}, title = {DR2: Diffusion-Based Robust Degradation Remover for Blind Face Restoration}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1704-1713} }

LiDAR2Map: In Defense of LiDAR-Based Semantic Map Construction Using Online Camera Distillation

Song Wang,

Wentong Li,

Wenyu Liu,

Xiaolu Liu,

Jianke Zhu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Song and Li, Wentong and Liu, Wenyu and Liu, Xiaolu and Zhu, Jianke}, title = {LiDAR2Map: In Defense of LiDAR-Based Semantic Map Construction Using Online Camera Distillation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5186-5195} }

Token Contrast for Weakly-Supervised Semantic Segmentation

Lixiang Ru,

Heliang Zheng,

Yibing Zhan,

Bo Du

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Ru_2023_CVPR, author = {Ru, Lixiang and Zheng, Heliang and Zhan, Yibing and Du, Bo}, title = {Token Contrast for Weakly-Supervised Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3093-3102} }

LightedDepth: Video Depth Estimation in Light of Limited Inference View Angles

Shengjie Zhu,

Xiaoming Liu

[pdf] [supp]

[bibtex]

@InProceedings{Zhu_2023_CVPR, author = {Zhu, Shengjie and Liu, Xiaoming}, title = {LightedDepth: Video Depth Estimation in Light of Limited Inference View Angles}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5003-5012} }

HouseDiffusion: Vector Floorplan Generation via a Diffusion Model With Discrete and Continuous Denoising

Mohammad Amin Shabani,

Sepidehsadat Hosseini,

Yasutaka Furukawa

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Shabani_2023_CVPR, author = {Shabani, Mohammad Amin and Hosseini, Sepidehsadat and Furukawa, Yasutaka}, title = {HouseDiffusion: Vector Floorplan Generation via a Diffusion Model With Discrete and Continuous Denoising}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5466-5475} }

V2X-Seq: A Large-Scale Sequential Dataset for Vehicle-Infrastructure Cooperative Perception and Forecasting

Haibao Yu,

Wenxian Yang,

Hongzhi Ruan,

Zhenwei Yang,

Yingjuan Tang,

Xu Gao,

Xin Hao,

Yifeng Shi,

Yifeng Pan,

Ning Sun,

Juan Song,

Jirui Yuan,

Ping Luo,

Zaiqing Nie

[pdf] [supp]

[bibtex]

@InProceedings{Yu_2023_CVPR, author = {Yu, Haibao and Yang, Wenxian and Ruan, Hongzhi and Yang, Zhenwei and Tang, Yingjuan and Gao, Xu and Hao, Xin and Shi, Yifeng and Pan, Yifeng and Sun, Ning and Song, Juan and Yuan, Jirui and Luo, Ping and Nie, Zaiqing}, title = {V2X-Seq: A Large-Scale Sequential Dataset for Vehicle-Infrastructure Cooperative Perception and Forecasting}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5486-5495} }

Bridging the Gap Between Model Explanations in Partially Annotated Multi-Label Classification

Youngwook Kim,

Jae Myung Kim,

Jieun Jeong,

Cordelia Schmid,

Zeynep Akata,

Jungwoo Lee

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Kim_2023_CVPR, author = {Kim, Youngwook and Kim, Jae Myung and Jeong, Jieun and Schmid, Cordelia and Akata, Zeynep and Lee, Jungwoo}, title = {Bridging the Gap Between Model Explanations in Partially Annotated Multi-Label Classification}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3408-3417} }

Learning Audio-Visual Source Localization via False Negative Aware Contrastive Learning

Weixuan Sun,

Jiayi Zhang,

Jianyuan Wang,

Zheyuan Liu,

Yiran Zhong,

Tianpeng Feng,

Yandong Guo,

Yanhao Zhang,

Nick Barnes

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Sun_2023_CVPR, author = {Sun, Weixuan and Zhang, Jiayi and Wang, Jianyuan and Liu, Zheyuan and Zhong, Yiran and Feng, Tianpeng and Guo, Yandong and Zhang, Yanhao and Barnes, Nick}, title = {Learning Audio-Visual Source Localization via False Negative Aware Contrastive Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6420-6429} }

MMG-Ego4D: Multimodal Generalization in Egocentric Action Recognition

Xinyu Gong,

Sreyas Mohan,

Naina Dhingra,

Jean-Charles Bazin,

Yilei Li,

Zhangyang Wang,

Rakesh Ranjan

[pdf] [supp]

[bibtex]

@InProceedings{Gong_2023_CVPR, author = {Gong, Xinyu and Mohan, Sreyas and Dhingra, Naina and Bazin, Jean-Charles and Li, Yilei and Wang, Zhangyang and Ranjan, Rakesh}, title = {MMG-Ego4D: Multimodal Generalization in Egocentric Action Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6481-6491} }

3D Video Object Detection With Learnable Object-Centric Global Optimization

Jiawei He,

Yuntao Chen,

Naiyan Wang,

Zhaoxiang Zhang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{He_2023_CVPR, author = {He, Jiawei and Chen, Yuntao and Wang, Naiyan and Zhang, Zhaoxiang}, title = {3D Video Object Detection With Learnable Object-Centric Global Optimization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5106-5115} }

Improving the Transferability of Adversarial Samples by Path-Augmented Method

Jianping Zhang,

Jen-tse Huang,

Wenxuan Wang,

Yichen Li,

Weibin Wu,

Xiaosen Wang,

Yuxin Su,

Michael R. Lyu

[pdf] [arXiv]

[bibtex]

@InProceedings{Zhang_2023_CVPR, author = {Zhang, Jianping and Huang, Jen-tse and Wang, Wenxuan and Li, Yichen and Wu, Weibin and Wang, Xiaosen and Su, Yuxin and Lyu, Michael R.}, title = {Improving the Transferability of Adversarial Samples by Path-Augmented Method}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8173-8182} }

Robust Mean Teacher for Continual and Gradual Test-Time Adaptation

Mario Döbler,

Robert A. Marsden,

Bin Yang

[pdf] [supp]

[bibtex]

@InProceedings{Dobler_2023_CVPR, author = {D\"obler, Mario and Marsden, Robert A. and Yang, Bin}, title = {Robust Mean Teacher for Continual and Gradual Test-Time Adaptation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7704-7714} }

MOVES: Manipulated Objects in Video Enable Segmentation

Richard E. L. Higgins,

David F. Fouhey

[pdf]

[bibtex]

@InProceedings{Higgins_2023_CVPR, author = {Higgins, Richard E. L. and Fouhey, David F.}, title = {MOVES: Manipulated Objects in Video Enable Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6334-6343} }

Generating Holistic 3D Human Motion From Speech

Hongwei Yi,

Hualin Liang,

Yifei Liu,

Qiong Cao,

Yandong Wen,

Timo Bolkart,

Dacheng Tao,

Michael J. Black

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Yi_2023_CVPR, author = {Yi, Hongwei and Liang, Hualin and Liu, Yifei and Cao, Qiong and Wen, Yandong and Bolkart, Timo and Tao, Dacheng and Black, Michael J.}, title = {Generating Holistic 3D Human Motion From Speech}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {469-480} }

ShadowNeuS: Neural SDF Reconstruction by Shadow Ray Supervision

Jingwang Ling,

Zhibo Wang,

Feng Xu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Ling_2023_CVPR, author = {Ling, Jingwang and Wang, Zhibo and Xu, Feng}, title = {ShadowNeuS: Neural SDF Reconstruction by Shadow Ray Supervision}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {175-185} }

Generalized UAV Object Detection via Frequency Domain Disentanglement

Kunyu Wang,

Xueyang Fu,

Yukun Huang,

Chengzhi Cao,

Gege Shi,

Zheng-Jun Zha

[pdf] [supp]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Kunyu and Fu, Xueyang and Huang, Yukun and Cao, Chengzhi and Shi, Gege and Zha, Zheng-Jun}, title = {Generalized UAV Object Detection via Frequency Domain Disentanglement}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1064-1073} }

DINER: Disorder-Invariant Implicit Neural Representation

Shaowen Xie,

Hao Zhu,

Zhen Liu,

Qi Zhang,

You Zhou,

Xun Cao,

Zhan Ma

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Xie_2023_CVPR, author = {Xie, Shaowen and Zhu, Hao and Liu, Zhen and Zhang, Qi and Zhou, You and Cao, Xun and Ma, Zhan}, title = {DINER: Disorder-Invariant Implicit Neural Representation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6143-6152} }

A Light Touch Approach to Teaching Transformers Multi-View Geometry

Yash Bhalgat,

João F. Henriques,

Andrew Zisserman

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Bhalgat_2023_CVPR, author = {Bhalgat, Yash and Henriques, Jo\~ao F. and Zisserman, Andrew}, title = {A Light Touch Approach to Teaching Transformers Multi-View Geometry}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4958-4969} }

Trade-Off Between Robustness and Accuracy of Vision Transformers

Yanxi Li,

Chang Xu

[pdf] [supp]

[bibtex]

@InProceedings{Li_2023_CVPR, author = {Li, Yanxi and Xu, Chang}, title = {Trade-Off Between Robustness and Accuracy of Vision Transformers}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7558-7568} }

Deep Graph-Based Spatial Consistency for Robust Non-Rigid Point Cloud Registration

Zheng Qin,

Hao Yu,

Changjian Wang,

Yuxing Peng,

Kai Xu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Qin_2023_CVPR, author = {Qin, Zheng and Yu, Hao and Wang, Changjian and Peng, Yuxing and Xu, Kai}, title = {Deep Graph-Based Spatial Consistency for Robust Non-Rigid Point Cloud Registration}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5394-5403} }

Slide-Transformer: Hierarchical Vision Transformer With Local Self-Attention

Xuran Pan,

Tianzhu Ye,

Zhuofan Xia,

Shiji Song,

Gao Huang

[pdf] [supp]

[bibtex]

@InProceedings{Pan_2023_CVPR, author = {Pan, Xuran and Ye, Tianzhu and Xia, Zhuofan and Song, Shiji and Huang, Gao}, title = {Slide-Transformer: Hierarchical Vision Transformer With Local Self-Attention}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2082-2091} }

NeRF-Supervised Deep Stereo

Fabio Tosi,

Alessio Tonioni,

Daniele De Gregorio,

Matteo Poggi

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Tosi_2023_CVPR, author = {Tosi, Fabio and Tonioni, Alessio and De Gregorio, Daniele and Poggi, Matteo}, title = {NeRF-Supervised Deep Stereo}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {855-866} }

Decoupled Multimodal Distilling for Emotion Recognition

Yong Li,

Yuanzhi Wang,

Zhen Cui

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Li_2023_CVPR, author = {Li, Yong and Wang, Yuanzhi and Cui, Zhen}, title = {Decoupled Multimodal Distilling for Emotion Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6631-6640} }

DualRefine: Self-Supervised Depth and Pose Estimation Through Iterative Epipolar Sampling and Refinement Toward Equilibrium

Antyanta Bangunharcana,

Ahmed Magd,

Kyung-Soo Kim

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Bangunharcana_2023_CVPR, author = {Bangunharcana, Antyanta and Magd, Ahmed and Kim, Kyung-Soo}, title = {DualRefine: Self-Supervised Depth and Pose Estimation Through Iterative Epipolar Sampling and Refinement Toward Equilibrium}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {726-738} }

Improving Generalization of Meta-Learning With Inverted Regularization at Inner-Level

Lianzhe Wang,

Shiji Zhou,

Shanghang Zhang,

Xu Chu,

Heng Chang,

Wenwu Zhu

[pdf] [supp]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Lianzhe and Zhou, Shiji and Zhang, Shanghang and Chu, Xu and Chang, Heng and Zhu, Wenwu}, title = {Improving Generalization of Meta-Learning With Inverted Regularization at Inner-Level}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7826-7835} }

SmallCap: Lightweight Image Captioning Prompted With Retrieval Augmentation

Rita Ramos,

Bruno Martins,

Desmond Elliott,

Yova Kementchedjhieva

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Ramos_2023_CVPR, author = {Ramos, Rita and Martins, Bruno and Elliott, Desmond and Kementchedjhieva, Yova}, title = {SmallCap: Lightweight Image Captioning Prompted With Retrieval Augmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2840-2849} }

Unifying Layout Generation With a Decoupled Diffusion Model

Mude Hui,

Zhizheng Zhang,

Xiaoyi Zhang,

Wenxuan Xie,

Yuwang Wang,

Yan Lu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Hui_2023_CVPR, author = {Hui, Mude and Zhang, Zhizheng and Zhang, Xiaoyi and Xie, Wenxuan and Wang, Yuwang and Lu, Yan}, title = {Unifying Layout Generation With a Decoupled Diffusion Model}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1942-1951} }

Dynamic Neural Network for Multi-Task Learning Searching Across Diverse Network Topologies

Wonhyeok Choi,

Sunghoon Im

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Choi_2023_CVPR, author = {Choi, Wonhyeok and Im, Sunghoon}, title = {Dynamic Neural Network for Multi-Task Learning Searching Across Diverse Network Topologies}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3779-3788} }

Relightable Neural Human Assets From Multi-View Gradient Illuminations

Taotao Zhou,

Kai He,

Di Wu,

Teng Xu,

Qixuan Zhang,

Kuixiang Shao,

Wenzheng Chen,

Lan Xu,

Jingyi Yu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Zhou_2023_CVPR, author = {Zhou, Taotao and He, Kai and Wu, Di and Xu, Teng and Zhang, Qixuan and Shao, Kuixiang and Chen, Wenzheng and Xu, Lan and Yu, Jingyi}, title = {Relightable Neural Human Assets From Multi-View Gradient Illuminations}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4315-4327} }

Probing Sentiment-Oriented Pre-Training Inspired by Human Sentiment Perception Mechanism

Tinglei Feng,

Jiaxuan Liu,

Jufeng Yang

[pdf]

[bibtex]

@InProceedings{Feng_2023_CVPR, author = {Feng, Tinglei and Liu, Jiaxuan and Yang, Jufeng}, title = {Probing Sentiment-Oriented Pre-Training Inspired by Human Sentiment Perception Mechanism}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2850-2860} }

Imitation Learning As State Matching via Differentiable Physics

Siwei Chen,

Xiao Ma,

Zhongwen Xu

[pdf] [supp]

[bibtex]

@InProceedings{Chen_2023_CVPR, author = {Chen, Siwei and Ma, Xiao and Xu, Zhongwen}, title = {Imitation Learning As State Matching via Differentiable Physics}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7846-7855} }

TOPLight: Lightweight Neural Networks With Task-Oriented Pretraining for Visible-Infrared Recognition

Hao Yu,

Xu Cheng,

Wei Peng

[pdf] [supp]

[bibtex]

@InProceedings{Yu_2023_CVPR, author = {Yu, Hao and Cheng, Xu and Peng, Wei}, title = {TOPLight: Lightweight Neural Networks With Task-Oriented Pretraining for Visible-Infrared Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3541-3550} }

DeFeeNet: Consecutive 3D Human Motion Prediction With Deviation Feedback

Xiaoning Sun,

Huaijiang Sun,

Bin Li,

Dong Wei,

Weiqing Li,

Jianfeng Lu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Sun_2023_CVPR, author = {Sun, Xiaoning and Sun, Huaijiang and Li, Bin and Wei, Dong and Li, Weiqing and Lu, Jianfeng}, title = {DeFeeNet: Consecutive 3D Human Motion Prediction With Deviation Feedback}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5527-5536} }

Mask DINO: Towards a Unified Transformer-Based Framework for Object Detection and Segmentation

Feng Li,

Hao Zhang,

Huaizhe Xu,

Shilong Liu,

Lei Zhang,

Lionel M. Ni,

Heung-Yeung Shum

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Li_2023_CVPR, author = {Li, Feng and Zhang, Hao and Xu, Huaizhe and Liu, Shilong and Zhang, Lei and Ni, Lionel M. and Shum, Heung-Yeung}, title = {Mask DINO: Towards a Unified Transformer-Based Framework for Object Detection and Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3041-3050} }

FAME-ViL: Multi-Tasking Vision-Language Model for Heterogeneous Fashion Tasks

Xiao Han,

Xiatian Zhu,

Licheng Yu,

Li Zhang,

Yi-Zhe Song,

Tao Xiang

[pdf] [supp]

[bibtex]

@InProceedings{Han_2023_CVPR, author = {Han, Xiao and Zhu, Xiatian and Yu, Licheng and Zhang, Li and Song, Yi-Zhe and Xiang, Tao}, title = {FAME-ViL: Multi-Tasking Vision-Language Model for Heterogeneous Fashion Tasks}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2669-2680} }

Rate Gradient Approximation Attack Threats Deep Spiking Neural Networks

Tong Bu,

Jianhao Ding,

Zecheng Hao,

Zhaofei Yu

[pdf] [supp]

[bibtex]

@InProceedings{Bu_2023_CVPR, author = {Bu, Tong and Ding, Jianhao and Hao, Zecheng and Yu, Zhaofei}, title = {Rate Gradient Approximation Attack Threats Deep Spiking Neural Networks}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7896-7906} }

Adaptive Data-Free Quantization

Biao Qian,

Yang Wang,

Richang Hong,

Meng Wang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Qian_2023_CVPR, author = {Qian, Biao and Wang, Yang and Hong, Richang and Wang, Meng}, title = {Adaptive Data-Free Quantization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7960-7968} }

Overcoming the Trade-Off Between Accuracy and Plausibility in 3D Hand Shape Reconstruction

Ziwei Yu,

Chen Li,

Linlin Yang,

Xiaoxu Zheng,

Michael Bi Mi,

Gim Hee Lee,

Angela Yao

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Yu_2023_CVPR, author = {Yu, Ziwei and Li, Chen and Yang, Linlin and Zheng, Xiaoxu and Mi, Michael Bi and Lee, Gim Hee and Yao, Angela}, title = {Overcoming the Trade-Off Between Accuracy and Plausibility in 3D Hand Shape Reconstruction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {544-553} }

Open-Vocabulary Attribute Detection

María A. Bravo,

Sudhanshu Mittal,

Simon Ging,

Thomas Brox

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Bravo_2023_CVPR, author = {Bravo, Mar{\'\i}a A. and Mittal, Sudhanshu and Ging, Simon and Brox, Thomas}, title = {Open-Vocabulary Attribute Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7041-7050} }

TBP-Former: Learning Temporal Bird's-Eye-View Pyramid for Joint Perception and Prediction in Vision-Centric Autonomous Driving

Shaoheng Fang,

Zi Wang,

Yiqi Zhong,

Junhao Ge,

Siheng Chen

[pdf] [supp]

[bibtex]

@InProceedings{Fang_2023_CVPR, author = {Fang, Shaoheng and Wang, Zi and Zhong, Yiqi and Ge, Junhao and Chen, Siheng}, title = {TBP-Former: Learning Temporal Bird's-Eye-View Pyramid for Joint Perception and Prediction in Vision-Centric Autonomous Driving}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1368-1378} }

Test of Time: Instilling Video-Language Models With a Sense of Time

Piyush Bagad,

Makarand Tapaswi,

Cees G. M. Snoek

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Bagad_2023_CVPR, author = {Bagad, Piyush and Tapaswi, Makarand and Snoek, Cees G. M.}, title = {Test of Time: Instilling Video-Language Models With a Sense of Time}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2503-2516} }

Learning To Segment Every Referring Object Point by Point

Mengxue Qu,

Yu Wu,

Yunchao Wei,

Wu Liu,

Xiaodan Liang,

Yao Zhao

[pdf] [supp]

[bibtex]

@InProceedings{Qu_2023_CVPR, author = {Qu, Mengxue and Wu, Yu and Wei, Yunchao and Liu, Wu and Liang, Xiaodan and Zhao, Yao}, title = {Learning To Segment Every Referring Object Point by Point}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3021-3030} }

Seeing With Sound: Long-range Acoustic Beamforming for Multimodal Scene Understanding

Praneeth Chakravarthula,

Jim Aldon D’Souza,

Ethan Tseng,

Joe Bartusek,

Felix Heide

[pdf] [supp]

[bibtex]

@InProceedings{Chakravarthula_2023_CVPR, author = {Chakravarthula, Praneeth and D{\textquoteright}Souza, Jim Aldon and Tseng, Ethan and Bartusek, Joe and Heide, Felix}, title = {Seeing With Sound: Long-range Acoustic Beamforming for Multimodal Scene Understanding}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {982-991} }

OpenScene: 3D Scene Understanding With Open Vocabularies

Songyou Peng,

Kyle Genova,

Chiyu “Max” Jiang,

Andrea Tagliasacchi,

Marc Pollefeys,

Thomas Funkhouser

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Peng_2023_CVPR, author = {Peng, Songyou and Genova, Kyle and Jiang, Chiyu {\textquotedblleft}Max{\textquotedblright} and Tagliasacchi, Andrea and Pollefeys, Marc and Funkhouser, Thomas}, title = {OpenScene: 3D Scene Understanding With Open Vocabularies}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {815-824} }

Movies2Scenes: Using Movie Metadata To Learn Scene Representation

Shixing Chen,

Chun-Hao Liu,

Xiang Hao,

Xiaohan Nie,

Maxim Arap,

Raffay Hamid

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Chen_2023_CVPR, author = {Chen, Shixing and Liu, Chun-Hao and Hao, Xiang and Nie, Xiaohan and Arap, Maxim and Hamid, Raffay}, title = {Movies2Scenes: Using Movie Metadata To Learn Scene Representation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6535-6544} }

Joint Token Pruning and Squeezing Towards More Aggressive Compression of Vision Transformers

Siyuan Wei,

Tianzhu Ye,

Shen Zhang,

Yao Tang,

Jiajun Liang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Wei_2023_CVPR, author = {Wei, Siyuan and Ye, Tianzhu and Zhang, Shen and Tang, Yao and Liang, Jiajun}, title = {Joint Token Pruning and Squeezing Towards More Aggressive Compression of Vision Transformers}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2092-2101} }

Solving Oscillation Problem in Post-Training Quantization Through a Theoretical Perspective

Yuexiao Ma,

Huixia Li,

Xiawu Zheng,

Xuefeng Xiao,

Rui Wang,

Shilei Wen,

Xin Pan,

Fei Chao,

Rongrong Ji

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Ma_2023_CVPR, author = {Ma, Yuexiao and Li, Huixia and Zheng, Xiawu and Xiao, Xuefeng and Wang, Rui and Wen, Shilei and Pan, Xin and Chao, Fei and Ji, Rongrong}, title = {Solving Oscillation Problem in Post-Training Quantization Through a Theoretical Perspective}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7950-7959} }

Masked Image Modeling With Local Multi-Scale Reconstruction

Haoqing Wang,

Yehui Tang,

Yunhe Wang,

Jianyuan Guo,

Zhi-Hong Deng,

Kai Han

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Haoqing and Tang, Yehui and Wang, Yunhe and Guo, Jianyuan and Deng, Zhi-Hong and Han, Kai}, title = {Masked Image Modeling With Local Multi-Scale Reconstruction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2122-2131} }

Flexible-Cm GAN: Towards Precise 3D Dose Prediction in Radiotherapy

Riqiang Gao,

Bin Lou,

Zhoubing Xu,

Dorin Comaniciu,

Ali Kamen

[pdf] [supp]

[bibtex]

@InProceedings{Gao_2023_CVPR, author = {Gao, Riqiang and Lou, Bin and Xu, Zhoubing and Comaniciu, Dorin and Kamen, Ali}, title = {Flexible-Cm GAN: Towards Precise 3D Dose Prediction in Radiotherapy}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {715-725} }

Handy: Towards a High Fidelity 3D Hand Shape and Appearance Model

Rolandos Alexandros Potamias,

Stylianos Ploumpis,

Stylianos Moschoglou,

Vasileios Triantafyllou,

Stefanos Zafeiriou

[pdf] [supp]

[bibtex]

@InProceedings{Potamias_2023_CVPR, author = {Potamias, Rolandos Alexandros and Ploumpis, Stylianos and Moschoglou, Stylianos and Triantafyllou, Vasileios and Zafeiriou, Stefanos}, title = {Handy: Towards a High Fidelity 3D Hand Shape and Appearance Model}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4670-4680} }

Learning To Zoom and Unzoom

Chittesh Thavamani,

Mengtian Li,

Francesco Ferroni,

Deva Ramanan

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Thavamani_2023_CVPR, author = {Thavamani, Chittesh and Li, Mengtian and Ferroni, Francesco and Ramanan, Deva}, title = {Learning To Zoom and Unzoom}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5086-5095} }

Task Difficulty Aware Parameter Allocation & Regularization for Lifelong Learning

Wenjin Wang,

Yunqing Hu,

Qianglong Chen,

Yin Zhang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Wenjin and Hu, Yunqing and Chen, Qianglong and Zhang, Yin}, title = {Task Difficulty Aware Parameter Allocation \& Regularization for Lifelong Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7776-7785} }

From Node Interaction To Hop Interaction: New Effective and Scalable Graph Learning Paradigm

Jie Chen,

Zilong Li,

Yin Zhu,

Junping Zhang,

Jian Pu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Chen_2023_CVPR, author = {Chen, Jie and Li, Zilong and Zhu, Yin and Zhang, Junping and Pu, Jian}, title = {From Node Interaction To Hop Interaction: New Effective and Scalable Graph Learning Paradigm}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7876-7885} }

Understanding and Improving Features Learned in Deep Functional Maps

Souhaib Attaiki,

Maks Ovsjanikov

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Attaiki_2023_CVPR, author = {Attaiki, Souhaib and Ovsjanikov, Maks}, title = {Understanding and Improving Features Learned in Deep Functional Maps}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1316-1326} }

PartManip: Learning Cross-Category Generalizable Part Manipulation Policy From Point Cloud Observations

Haoran Geng,

Ziming Li,

Yiran Geng,

Jiayi Chen,

Hao Dong,

He Wang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Geng_2023_CVPR, author = {Geng, Haoran and Li, Ziming and Geng, Yiran and Chen, Jiayi and Dong, Hao and Wang, He}, title = {PartManip: Learning Cross-Category Generalizable Part Manipulation Policy From Point Cloud Observations}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2978-2988} }

Polynomial Implicit Neural Representations for Large Diverse Datasets

Rajhans Singh,

Ankita Shukla,

Pavan Turaga

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Singh_2023_CVPR, author = {Singh, Rajhans and Shukla, Ankita and Turaga, Pavan}, title = {Polynomial Implicit Neural Representations for Large Diverse Datasets}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2041-2051} }

High-Frequency Stereo Matching Network

Haoliang Zhao,

Huizhou Zhou,

Yongjun Zhang,

Jie Chen,

Yitong Yang,

Yong Zhao

[pdf]

[bibtex]

@InProceedings{Zhao_2023_CVPR, author = {Zhao, Haoliang and Zhou, Huizhou and Zhang, Yongjun and Chen, Jie and Yang, Yitong and Zhao, Yong}, title = {High-Frequency Stereo Matching Network}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1327-1336} }

Spatial-Then-Temporal Self-Supervised Learning for Video Correspondence

Rui Li,

Dong Liu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Li_2023_CVPR, author = {Li, Rui and Liu, Dong}, title = {Spatial-Then-Temporal Self-Supervised Learning for Video Correspondence}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2279-2288} }

Unsupervised Contour Tracking of Live Cells by Mechanical and Cycle Consistency Losses

Junbong Jang,

Kwonmoo Lee,

Tae-Kyun Kim

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Jang_2023_CVPR, author = {Jang, Junbong and Lee, Kwonmoo and Kim, Tae-Kyun}, title = {Unsupervised Contour Tracking of Live Cells by Mechanical and Cycle Consistency Losses}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {227-236} }

Distribution Shift Inversion for Out-of-Distribution Prediction

Runpeng Yu,

Songhua Liu,

Xingyi Yang,

Xinchao Wang

[pdf] [supp]

[bibtex]

@InProceedings{Yu_2023_CVPR, author = {Yu, Runpeng and Liu, Songhua and Yang, Xingyi and Wang, Xinchao}, title = {Distribution Shift Inversion for Out-of-Distribution Prediction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3592-3602} }

Parallel Diffusion Models of Operator and Image for Blind Inverse Problems

Hyungjin Chung,

Jeongsol Kim,

Sehui Kim,

Jong Chul Ye

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Chung_2023_CVPR, author = {Chung, Hyungjin and Kim, Jeongsol and Kim, Sehui and Ye, Jong Chul}, title = {Parallel Diffusion Models of Operator and Image for Blind Inverse Problems}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6059-6069} }

Semidefinite Relaxations for Robust Multiview Triangulation

Linus Härenstam-Nielsen,

Niclas Zeller,

Daniel Cremers

[pdf] [supp]

[bibtex]

@InProceedings{Harenstam-Nielsen_2023_CVPR, author = {H\"arenstam-Nielsen, Linus and Zeller, Niclas and Cremers, Daniel}, title = {Semidefinite Relaxations for Robust Multiview Triangulation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {749-757} }

Modeling Video As Stochastic Processes for Fine-Grained Video Representation Learning

Heng Zhang,

Daqing Liu,

Qi Zheng,

Bing Su

[pdf] [supp]

[bibtex]

@InProceedings{Zhang_2023_CVPR, author = {Zhang, Heng and Liu, Daqing and Zheng, Qi and Su, Bing}, title = {Modeling Video As Stochastic Processes for Fine-Grained Video Representation Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2225-2234} }

Relational Space-Time Query in Long-Form Videos

Xitong Yang,

Fu-Jen Chu,

Matt Feiszli,

Raghav Goyal,

Lorenzo Torresani,

Du Tran

[pdf] [supp]

[bibtex]

@InProceedings{Yang_2023_CVPR, author = {Yang, Xitong and Chu, Fu-Jen and Feiszli, Matt and Goyal, Raghav and Torresani, Lorenzo and Tran, Du}, title = {Relational Space-Time Query in Long-Form Videos}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6398-6408} }

BiFormer: Learning Bilateral Motion Estimation via Bilateral Transformer for 4K Video Frame Interpolation

Junheum Park,

Jintae Kim,

Chang-Su Kim

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Park_2023_CVPR, author = {Park, Junheum and Kim, Jintae and Kim, Chang-Su}, title = {BiFormer: Learning Bilateral Motion Estimation via Bilateral Transformer for 4K Video Frame Interpolation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1568-1577} }

Learning From Unique Perspectives: User-Aware Saliency Modeling

Shi Chen,

Nachiappan Valliappan,

Shaolei Shen,

Xinyu Ye,

Kai Kohlhoff,

Junfeng He

[pdf] [supp]

[bibtex]

@InProceedings{Chen_2023_CVPR, author = {Chen, Shi and Valliappan, Nachiappan and Shen, Shaolei and Ye, Xinyu and Kohlhoff, Kai and He, Junfeng}, title = {Learning From Unique Perspectives: User-Aware Saliency Modeling}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2701-2710} }

MaskSketch: Unpaired Structure-Guided Masked Image Generation

Dina Bashkirova,

José Lezama,

Kihyuk Sohn,

Kate Saenko,

Irfan Essa

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Bashkirova_2023_CVPR, author = {Bashkirova, Dina and Lezama, Jos\'e and Sohn, Kihyuk and Saenko, Kate and Essa, Irfan}, title = {MaskSketch: Unpaired Structure-Guided Masked Image Generation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1879-1889} }

Open-Vocabulary Point-Cloud Object Detection Without 3D Annotation

Yuheng Lu,

Chenfeng Xu,

Xiaobao Wei,

Xiaodong Xie,

Masayoshi Tomizuka,

Kurt Keutzer,

Shanghang Zhang

[pdf] [arXiv]

[bibtex]

@InProceedings{Lu_2023_CVPR, author = {Lu, Yuheng and Xu, Chenfeng and Wei, Xiaobao and Xie, Xiaodong and Tomizuka, Masayoshi and Keutzer, Kurt and Zhang, Shanghang}, title = {Open-Vocabulary Point-Cloud Object Detection Without 3D Annotation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1190-1199} }

Lookahead Diffusion Probabilistic Models for Refining Mean Estimation

Guoqiang Zhang,

Kenta Niwa,

W. Bastiaan Kleijn

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Zhang_2023_CVPR, author = {Zhang, Guoqiang and Niwa, Kenta and Kleijn, W. Bastiaan}, title = {Lookahead Diffusion Probabilistic Models for Refining Mean Estimation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1421-1429} }

TensoIR: Tensorial Inverse Rendering

Haian Jin,

Isabella Liu,

Peijia Xu,

Xiaoshuai Zhang,

Songfang Han,

Sai Bi,

Xiaowei Zhou,

Zexiang Xu,

Hao Su

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Jin_2023_CVPR, author = {Jin, Haian and Liu, Isabella and Xu, Peijia and Zhang, Xiaoshuai and Han, Songfang and Bi, Sai and Zhou, Xiaowei and Xu, Zexiang and Su, Hao}, title = {TensoIR: Tensorial Inverse Rendering}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {165-174} }

NIPQ: Noise Proxy-Based Integrated Pseudo-Quantization

Juncheol Shin,

Junhyuk So,

Sein Park,

Seungyeop Kang,

Sungjoo Yoo,

Eunhyeok Park

[pdf] [supp]

[bibtex]

@InProceedings{Shin_2023_CVPR, author = {Shin, Juncheol and So, Junhyuk and Park, Sein and Kang, Seungyeop and Yoo, Sungjoo and Park, Eunhyeok}, title = {NIPQ: Noise Proxy-Based Integrated Pseudo-Quantization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3852-3861} }

Object-Goal Visual Navigation via Effective Exploration of Relations Among Historical Navigation States

Heming Du,

Lincheng Li,

Zi Huang,

Xin Yu

[pdf]

[bibtex]

@InProceedings{Du_2023_CVPR, author = {Du, Heming and Li, Lincheng and Huang, Zi and Yu, Xin}, title = {Object-Goal Visual Navigation via Effective Exploration of Relations Among Historical Navigation States}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2563-2573} }

Probabilistic Knowledge Distillation of Face Ensembles

Jianqing Xu,

Shen Li,

Ailin Deng,

Miao Xiong,

Jiaying Wu,

Jiaxiang Wu,

Shouhong Ding,

Bryan Hooi

[pdf] [supp]

[bibtex]

@InProceedings{Xu_2023_CVPR, author = {Xu, Jianqing and Li, Shen and Deng, Ailin and Xiong, Miao and Wu, Jiaying and Wu, Jiaxiang and Ding, Shouhong and Hooi, Bryan}, title = {Probabilistic Knowledge Distillation of Face Ensembles}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3489-3498} }

MeMaHand: Exploiting Mesh-Mano Interaction for Single Image Two-Hand Reconstruction

Congyi Wang,

Feida Zhu,

Shilei Wen

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Congyi and Zhu, Feida and Wen, Shilei}, title = {MeMaHand: Exploiting Mesh-Mano Interaction for Single Image Two-Hand Reconstruction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {564-573} }

DSFNet: Dual Space Fusion Network for Occlusion-Robust 3D Dense Face Alignment

Heyuan Li,

Bo Wang,

Yu Cheng,

Mohan Kankanhalli,

Robby T. Tan

[pdf] [supp]

[bibtex]

@InProceedings{Li_2023_CVPR, author = {Li, Heyuan and Wang, Bo and Cheng, Yu and Kankanhalli, Mohan and Tan, Robby T.}, title = {DSFNet: Dual Space Fusion Network for Occlusion-Robust 3D Dense Face Alignment}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4531-4540} }

MoStGAN-V: Video Generation With Temporal Motion Styles

Xiaoqian Shen,

Xiang Li,

Mohamed Elhoseiny

[pdf] [supp]

[bibtex]

@InProceedings{Shen_2023_CVPR, author = {Shen, Xiaoqian and Li, Xiang and Elhoseiny, Mohamed}, title = {MoStGAN-V: Video Generation With Temporal Motion Styles}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5652-5661} }

Poly-PC: A Polyhedral Network for Multiple Point Cloud Tasks at Once

Tao Xie,

Shiguang Wang,

Ke Wang,

Linqi Yang,

Zhiqiang Jiang,

Xingcheng Zhang,

Kun Dai,

Ruifeng Li,

Jian Cheng

[pdf] [supp]

[bibtex]

@InProceedings{Xie_2023_CVPR, author = {Xie, Tao and Wang, Shiguang and Wang, Ke and Yang, Linqi and Jiang, Zhiqiang and Zhang, Xingcheng and Dai, Kun and Li, Ruifeng and Cheng, Jian}, title = {Poly-PC: A Polyhedral Network for Multiple Point Cloud Tasks at Once}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1233-1243} }

HandsOff: Labeled Dataset Generation With No Additional Human Annotations

Austin Xu,

Mariya I. Vasileva,

Achal Dave,

Arjun Seshadri

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Xu_2023_CVPR, author = {Xu, Austin and Vasileva, Mariya I. and Dave, Achal and Seshadri, Arjun}, title = {HandsOff: Labeled Dataset Generation With No Additional Human Annotations}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7991-8000} }

Semi-Supervised 2D Human Pose Estimation Driven by Position Inconsistency Pseudo Label Correction Module

Linzhi Huang,

Yulong Li,

Hongbo Tian,

Yue Yang,

Xiangang Li,

Weihong Deng,

Jieping Ye

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Huang_2023_CVPR, author = {Huang, Linzhi and Li, Yulong and Tian, Hongbo and Yang, Yue and Li, Xiangang and Deng, Weihong and Ye, Jieping}, title = {Semi-Supervised 2D Human Pose Estimation Driven by Position Inconsistency Pseudo Label Correction Module}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {693-703} }

ARKitTrack: A New Diverse Dataset for Tracking Using Mobile RGB-D Data

Haojie Zhao,

Junsong Chen,

Lijun Wang,

Huchuan Lu

[pdf] [supp]

[bibtex]

@InProceedings{Zhao_2023_CVPR, author = {Zhao, Haojie and Chen, Junsong and Wang, Lijun and Lu, Huchuan}, title = {ARKitTrack: A New Diverse Dataset for Tracking Using Mobile RGB-D Data}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5126-5135} }

Efficient Verification of Neural Networks Against LVM-Based Specifications

Harleen Hanspal,

Alessio Lomuscio

[pdf] [supp]

[bibtex]

@InProceedings{Hanspal_2023_CVPR, author = {Hanspal, Harleen and Lomuscio, Alessio}, title = {Efficient Verification of Neural Networks Against LVM-Based Specifications}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3894-3903} }

Feature Aggregated Queries for Transformer-Based Video Object Detectors

Yiming Cui

[pdf] [arXiv]

[bibtex]

@InProceedings{Cui_2023_CVPR, author = {Cui, Yiming}, title = {Feature Aggregated Queries for Transformer-Based Video Object Detectors}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6365-6376} }

Decomposed Cross-Modal Distillation for RGB-Based Temporal Action Detection

Pilhyeon Lee,

Taeoh Kim,

Minho Shim,

Dongyoon Wee,

Hyeran Byun

[pdf] [arXiv]

[bibtex]

@InProceedings{Lee_2023_CVPR, author = {Lee, Pilhyeon and Kim, Taeoh and Shim, Minho and Wee, Dongyoon and Byun, Hyeran}, title = {Decomposed Cross-Modal Distillation for RGB-Based Temporal Action Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2373-2383} }

A Unified Knowledge Distillation Framework for Deep Directed Graphical Models

Yizhuo Chen,

Kaizhao Liang,

Zhe Zeng,

Shuochao Yao,

Huajie Shao

[pdf] [supp]

[bibtex]

@InProceedings{Chen_2023_CVPR, author = {Chen, Yizhuo and Liang, Kaizhao and Zeng, Zhe and Yao, Shuochao and Shao, Huajie}, title = {A Unified Knowledge Distillation Framework for Deep Directed Graphical Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7795-7804} }

Blemish-Aware and Progressive Face Retouching With Limited Paired Data

Lianxin Xie,

Wen Xue,

Zhen Xu,

Si Wu,

Zhiwen Yu,

Hau San Wong

[pdf]

[bibtex]

@InProceedings{Xie_2023_CVPR, author = {Xie, Lianxin and Xue, Wen and Xu, Zhen and Wu, Si and Yu, Zhiwen and Wong, Hau San}, title = {Blemish-Aware and Progressive Face Retouching With Limited Paired Data}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5599-5608} }

Detecting and Grounding Multi-Modal Media Manipulation

Rui Shao,

Tianxing Wu,

Ziwei Liu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Shao_2023_CVPR, author = {Shao, Rui and Wu, Tianxing and Liu, Ziwei}, title = {Detecting and Grounding Multi-Modal Media Manipulation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6904-6913} }

Human Pose As Compositional Tokens

Zigang Geng,

Chunyu Wang,

Yixuan Wei,

Ze Liu,

Houqiang Li,

Han Hu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Geng_2023_CVPR, author = {Geng, Zigang and Wang, Chunyu and Wei, Yixuan and Liu, Ze and Li, Houqiang and Hu, Han}, title = {Human Pose As Compositional Tokens}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {660-671} }

Synthesizing Photorealistic Virtual Humans Through Cross-Modal Disentanglement

Siddarth Ravichandran,

Ondřej Texler,

Dimitar Dinev,

Hyun Jae Kang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Ravichandran_2023_CVPR, author = {Ravichandran, Siddarth and Texler, Ond\v{r}ej and Dinev, Dimitar and Kang, Hyun Jae}, title = {Synthesizing Photorealistic Virtual Humans Through Cross-Modal Disentanglement}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4585-4594} }

Test Time Adaptation With Regularized Loss for Weakly Supervised Salient Object Detection

Olga Veksler

[pdf] [supp]

[bibtex]

@InProceedings{Veksler_2023_CVPR, author = {Veksler, Olga}, title = {Test Time Adaptation With Regularized Loss for Weakly Supervised Salient Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7360-7369} }

Self-Supervised Pre-Training With Masked Shape Prediction for 3D Scene Understanding

Li Jiang,

Zetong Yang,

Shaoshuai Shi,

Vladislav Golyanik,

Dengxin Dai,

Bernt Schiele

[pdf] [arXiv]

[bibtex]

@InProceedings{Jiang_2023_CVPR, author = {Jiang, Li and Yang, Zetong and Shi, Shaoshuai and Golyanik, Vladislav and Dai, Dengxin and Schiele, Bernt}, title = {Self-Supervised Pre-Training With Masked Shape Prediction for 3D Scene Understanding}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1168-1178} }

Guiding Pseudo-Labels With Uncertainty Estimation for Source-Free Unsupervised Domain Adaptation

Mattia Litrico,

Alessio Del Bue,

Pietro Morerio

[pdf] [arXiv]

[bibtex]

@InProceedings{Litrico_2023_CVPR, author = {Litrico, Mattia and Del Bue, Alessio and Morerio, Pietro}, title = {Guiding Pseudo-Labels With Uncertainty Estimation for Source-Free Unsupervised Domain Adaptation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7640-7650} }

HuManiFlow: Ancestor-Conditioned Normalising Flows on SO(3) Manifolds for Human Pose and Shape Distribution Estimation

Akash Sengupta,

Ignas Budvytis,

Roberto Cipolla

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Sengupta_2023_CVPR, author = {Sengupta, Akash and Budvytis, Ignas and Cipolla, Roberto}, title = {HuManiFlow: Ancestor-Conditioned Normalising Flows on SO(3) Manifolds for Human Pose and Shape Distribution Estimation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4779-4789} }

EC2: Emergent Communication for Embodied Control

Yao Mu,

Shunyu Yao,

Mingyu Ding,

Ping Luo,

Chuang Gan

[pdf] [supp]

[bibtex]

@InProceedings{Mu_2023_CVPR, author = {Mu, Yao and Yao, Shunyu and Ding, Mingyu and Luo, Ping and Gan, Chuang}, title = {EC2: Emergent Communication for Embodied Control}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6704-6714} }

DynamicDet: A Unified Dynamic Architecture for Object Detection

Zhihao Lin,

Yongtao Wang,

Jinhe Zhang,

Xiaojie Chu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Lin_2023_CVPR, author = {Lin, Zhihao and Wang, Yongtao and Zhang, Jinhe and Chu, Xiaojie}, title = {DynamicDet: A Unified Dynamic Architecture for Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6282-6291} }

Common Pets in 3D: Dynamic New-View Synthesis of Real-Life Deformable Categories

Samarth Sinha,

Roman Shapovalov,

Jeremy Reizenstein,

Ignacio Rocco,

Natalia Neverova,

Andrea Vedaldi,

David Novotny

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Sinha_2023_CVPR, author = {Sinha, Samarth and Shapovalov, Roman and Reizenstein, Jeremy and Rocco, Ignacio and Neverova, Natalia and Vedaldi, Andrea and Novotny, David}, title = {Common Pets in 3D: Dynamic New-View Synthesis of Real-Life Deformable Categories}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4881-4891} }

Normal-Guided Garment UV Prediction for Human Re-Texturing

Yasamin Jafarian,

Tuanfeng Y. Wang,

Duygu Ceylan,

Jimei Yang,

Nathan Carr,

Yi Zhou,

Hyun Soo Park

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Jafarian_2023_CVPR, author = {Jafarian, Yasamin and Wang, Tuanfeng Y. and Ceylan, Duygu and Yang, Jimei and Carr, Nathan and Zhou, Yi and Park, Hyun Soo}, title = {Normal-Guided Garment UV Prediction for Human Re-Texturing}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4627-4636} }

Learning Compact Representations for LiDAR Completion and Generation

Yuwen Xiong,

Wei-Chiu Ma,

Jingkang Wang,

Raquel Urtasun

[pdf] [supp]

[bibtex]

@InProceedings{Xiong_2023_CVPR, author = {Xiong, Yuwen and Ma, Wei-Chiu and Wang, Jingkang and Urtasun, Raquel}, title = {Learning Compact Representations for LiDAR Completion and Generation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1074-1083} }

Hubs and Hyperspheres: Reducing Hubness and Improving Transductive Few-Shot Learning With Hyperspherical Embeddings

Daniel J. Trosten,

Rwiddhi Chakraborty,

Sigurd Løkse,

Kristoffer Knutsen Wickstrøm,

Robert Jenssen,

Michael C. Kampffmeyer

[pdf] [supp]

[bibtex]

@InProceedings{Trosten_2023_CVPR, author = {Trosten, Daniel J. and Chakraborty, Rwiddhi and L{\o}kse, Sigurd and Wickstr{\o}m, Kristoffer Knutsen and Jenssen, Robert and Kampffmeyer, Michael C.}, title = {Hubs and Hyperspheres: Reducing Hubness and Improving Transductive Few-Shot Learning With Hyperspherical Embeddings}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7527-7536} }

Improving Graph Representation for Point Cloud Segmentation via Attentive Filtering

Nan Zhang,

Zhiyi Pan,

Thomas H. Li,

Wei Gao,

Ge Li

[pdf] [supp]

[bibtex]

@InProceedings{Zhang_2023_CVPR, author = {Zhang, Nan and Pan, Zhiyi and Li, Thomas H. and Gao, Wei and Li, Ge}, title = {Improving Graph Representation for Point Cloud Segmentation via Attentive Filtering}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1244-1254} }

PCT-Net: Full Resolution Image Harmonization Using Pixel-Wise Color Transformations

Julian Jorge Andrade Guerreiro,

Mitsuru Nakazawa,

Björn Stenger

[pdf] [supp]

[bibtex]

@InProceedings{Guerreiro_2023_CVPR, author = {Guerreiro, Julian Jorge Andrade and Nakazawa, Mitsuru and Stenger, Bj\"orn}, title = {PCT-Net: Full Resolution Image Harmonization Using Pixel-Wise Color Transformations}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5917-5926} }

Architecture, Dataset and Model-Scale Agnostic Data-Free Meta-Learning

Zixuan Hu,

Li Shen,

Zhenyi Wang,

Tongliang Liu,

Chun Yuan,

Dacheng Tao

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Hu_2023_CVPR, author = {Hu, Zixuan and Shen, Li and Wang, Zhenyi and Liu, Tongliang and Yuan, Chun and Tao, Dacheng}, title = {Architecture, Dataset and Model-Scale Agnostic Data-Free Meta-Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7736-7745} }

Egocentric Video Task Translation

Zihui Xue,

Yale Song,

Kristen Grauman,

Lorenzo Torresani

[pdf] [supp]

[bibtex]

@InProceedings{Xue_2023_CVPR, author = {Xue, Zihui and Song, Yale and Grauman, Kristen and Torresani, Lorenzo}, title = {Egocentric Video Task Translation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2310-2320} }

Gaussian Label Distribution Learning for Spherical Image Object Detection

Hang Xu,

Xinyuan Liu,

Qiang Zhao,

Yike Ma,

Chenggang Yan,

Feng Dai

[pdf] [supp]

[bibtex]

@InProceedings{Xu_2023_CVPR, author = {Xu, Hang and Liu, Xinyuan and Zhao, Qiang and Ma, Yike and Yan, Chenggang and Dai, Feng}, title = {Gaussian Label Distribution Learning for Spherical Image Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1033-1042} }

Better "CMOS" Produces Clearer Images: Learning Space-Variant Blur Estimation for Blind Image Super-Resolution

Xuhai Chen,

Jiangning Zhang,

Chao Xu,

Yabiao Wang,

Chengjie Wang,

Yong Liu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Chen_2023_CVPR, author = {Chen, Xuhai and Zhang, Jiangning and Xu, Chao and Wang, Yabiao and Wang, Chengjie and Liu, Yong}, title = {Better ''CMOS'' Produces Clearer Images: Learning Space-Variant Blur Estimation for Blind Image Super-Resolution}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1651-1661} }

MixTeacher: Mining Promising Labels With Mixed Scale Teacher for Semi-Supervised Object Detection

Liang Liu,

Boshen Zhang,

Jiangning Zhang,

Wuhao Zhang,

Zhenye Gan,

Guanzhong Tian,

Wenbing Zhu,

Yabiao Wang,

Chengjie Wang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Liu_2023_CVPR, author = {Liu, Liang and Zhang, Boshen and Zhang, Jiangning and Zhang, Wuhao and Gan, Zhenye and Tian, Guanzhong and Zhu, Wenbing and Wang, Yabiao and Wang, Chengjie}, title = {MixTeacher: Mining Promising Labels With Mixed Scale Teacher for Semi-Supervised Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7370-7379} }

NeuMap: Neural Coordinate Mapping by Auto-Transdecoder for Camera Localization

Shitao Tang,

Sicong Tang,

Andrea Tagliasacchi,

Ping Tan,

Yasutaka Furukawa

[pdf] [arXiv]

[bibtex]

@InProceedings{Tang_2023_CVPR, author = {Tang, Shitao and Tang, Sicong and Tagliasacchi, Andrea and Tan, Ping and Furukawa, Yasutaka}, title = {NeuMap: Neural Coordinate Mapping by Auto-Transdecoder for Camera Localization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {929-939} }

AShapeFormer: Semantics-Guided Object-Level Active Shape Encoding for 3D Object Detection via Transformers

Zechuan Li,

Hongshan Yu,

Zhengeng Yang,

Tongjia Chen,

Naveed Akhtar

[pdf] [supp]

[bibtex]

@InProceedings{Li_2023_CVPR, author = {Li, Zechuan and Yu, Hongshan and Yang, Zhengeng and Chen, Tongjia and Akhtar, Naveed}, title = {AShapeFormer: Semantics-Guided Object-Level Active Shape Encoding for 3D Object Detection via Transformers}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1012-1021} }

SeSDF: Self-Evolved Signed Distance Field for Implicit 3D Clothed Human Reconstruction

Yukang Cao,

Kai Han,

Kwan-Yee K. Wong

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Cao_2023_CVPR, author = {Cao, Yukang and Han, Kai and Wong, Kwan-Yee K.}, title = {SeSDF: Self-Evolved Signed Distance Field for Implicit 3D Clothed Human Reconstruction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4647-4657} }

Deep Depth Estimation From Thermal Image

Ukcheol Shin,

Jinsun Park,

In So Kweon

[pdf] [supp]

[bibtex]

@InProceedings{Shin_2023_CVPR, author = {Shin, Ukcheol and Park, Jinsun and Kweon, In So}, title = {Deep Depth Estimation From Thermal Image}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1043-1053} }

Cross-GAN Auditing: Unsupervised Identification of Attribute Level Similarities and Differences Between Pretrained Generative Models

Matthew L. Olson,

Shusen Liu,

Rushil Anirudh,

Jayaraman J. Thiagarajan,

Peer-Timo Bremer,

Weng-Keen Wong

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Olson_2023_CVPR, author = {Olson, Matthew L. and Liu, Shusen and Anirudh, Rushil and Thiagarajan, Jayaraman J. and Bremer, Peer-Timo and Wong, Weng-Keen}, title = {Cross-GAN Auditing: Unsupervised Identification of Attribute Level Similarities and Differences Between Pretrained Generative Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7981-7990} }

Backdoor Defense via Adaptively Splitting Poisoned Dataset

Kuofeng Gao,

Yang Bai,

Jindong Gu,

Yong Yang,

Shu-Tao Xia

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Gao_2023_CVPR, author = {Gao, Kuofeng and Bai, Yang and Gu, Jindong and Yang, Yong and Xia, Shu-Tao}, title = {Backdoor Defense via Adaptively Splitting Poisoned Dataset}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4005-4014} }

Towards Stable Human Pose Estimation via Cross-View Fusion and Foot Stabilization

Li’an Zhuo,

Jian Cao,

Qi Wang,

Bang Zhang,

Liefeng Bo

[pdf] [supp]

[bibtex]

@InProceedings{Zhuo_2023_CVPR, author = {Zhuo, Li{\textquoteright}an and Cao, Jian and Wang, Qi and Zhang, Bang and Bo, Liefeng}, title = {Towards Stable Human Pose Estimation via Cross-View Fusion and Foot Stabilization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {650-659} }

SINE: SINgle Image Editing With Text-to-Image Diffusion Models

Zhixing Zhang,

Ligong Han,

Arnab Ghosh,

Dimitris N. Metaxas,

Jian Ren

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Zhang_2023_CVPR, author = {Zhang, Zhixing and Han, Ligong and Ghosh, Arnab and Metaxas, Dimitris N. and Ren, Jian}, title = {SINE: SINgle Image Editing 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 = {6027-6037} }

OSAN: A One-Stage Alignment Network To Unify Multimodal Alignment and Unsupervised Domain Adaptation

Ye Liu,

Lingfeng Qiao,

Changchong Lu,

Di Yin,

Chen Lin,

Haoyuan Peng,

Bo Ren

[pdf]

[bibtex]

@InProceedings{Liu_2023_CVPR, author = {Liu, Ye and Qiao, Lingfeng and Lu, Changchong and Yin, Di and Lin, Chen and Peng, Haoyuan and Ren, Bo}, title = {OSAN: A One-Stage Alignment Network To Unify Multimodal Alignment and Unsupervised Domain Adaptation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3551-3560} }

Heat Diffusion Based Multi-Scale and Geometric Structure-Aware Transformer for Mesh Segmentation

Chi-Chong Wong

[pdf]

[bibtex]

@InProceedings{Wong_2023_CVPR, author = {Wong, Chi-Chong}, title = {Heat Diffusion Based Multi-Scale and Geometric Structure-Aware Transformer for Mesh Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4413-4422} }

Multi-Granularity Archaeological Dating of Chinese Bronze Dings Based on a Knowledge-Guided Relation Graph

Rixin Zhou,

Jiafu Wei,

Qian Zhang,

Ruihua Qi,

Xi Yang,

Chuntao Li

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Zhou_2023_CVPR, author = {Zhou, Rixin and Wei, Jiafu and Zhang, Qian and Qi, Ruihua and Yang, Xi and Li, Chuntao}, title = {Multi-Granularity Archaeological Dating of Chinese Bronze Dings Based on a Knowledge-Guided Relation Graph}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3103-3113} }

CASP-Net: Rethinking Video Saliency Prediction From an Audio-Visual Consistency Perceptual Perspective

Junwen Xiong,

Ganglai Wang,

Peng Zhang,

Wei Huang,

Yufei Zha,

Guangtao Zhai

[pdf]

[bibtex]

@InProceedings{Xiong_2023_CVPR, author = {Xiong, Junwen and Wang, Ganglai and Zhang, Peng and Huang, Wei and Zha, Yufei and Zhai, Guangtao}, title = {CASP-Net: Rethinking Video Saliency Prediction From an Audio-Visual Consistency Perceptual Perspective}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6441-6450} }

Learning Expressive Prompting With Residuals for Vision Transformers

Rajshekhar Das,

Yonatan Dukler,

Avinash Ravichandran,

Ashwin Swaminathan

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Das_2023_CVPR, author = {Das, Rajshekhar and Dukler, Yonatan and Ravichandran, Avinash and Swaminathan, Ashwin}, title = {Learning Expressive Prompting With Residuals for Vision Transformers}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3366-3377} }

AnyFlow: Arbitrary Scale Optical Flow With Implicit Neural Representation

Hyunyoung Jung,

Zhuo Hui,

Lei Luo,

Haitao Yang,

Feng Liu,

Sungjoo Yoo,

Rakesh Ranjan,

Denis Demandolx

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Jung_2023_CVPR, author = {Jung, Hyunyoung and Hui, Zhuo and Luo, Lei and Yang, Haitao and Liu, Feng and Yoo, Sungjoo and Ranjan, Rakesh and Demandolx, Denis}, title = {AnyFlow: Arbitrary Scale Optical Flow With Implicit Neural Representation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5455-5465} }

Federated Domain Generalization With Generalization Adjustment

Ruipeng Zhang,

Qinwei Xu,

Jiangchao Yao,

Ya Zhang,

Qi Tian,

Yanfeng Wang

[pdf] [supp]

[bibtex]

@InProceedings{Zhang_2023_CVPR, author = {Zhang, Ruipeng and Xu, Qinwei and Yao, Jiangchao and Zhang, Ya and Tian, Qi and Wang, Yanfeng}, title = {Federated Domain Generalization With Generalization Adjustment}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3954-3963} }

CoMFormer: Continual Learning in Semantic and Panoptic Segmentation

Fabio Cermelli,

Matthieu Cord,

Arthur Douillard

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Cermelli_2023_CVPR, author = {Cermelli, Fabio and Cord, Matthieu and Douillard, Arthur}, title = {CoMFormer: Continual Learning in Semantic and Panoptic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3010-3020} }

Conditional Generation of Audio From Video via Foley Analogies

Yuexi Du,

Ziyang Chen,

Justin Salamon,

Bryan Russell,

Andrew Owens

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Du_2023_CVPR, author = {Du, Yuexi and Chen, Ziyang and Salamon, Justin and Russell, Bryan and Owens, Andrew}, title = {Conditional Generation of Audio From Video via Foley Analogies}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2426-2436} }

Diverse 3D Hand Gesture Prediction From Body Dynamics by Bilateral Hand Disentanglement

Xingqun Qi,

Chen Liu,

Muyi Sun,

Lincheng Li,

Changjie Fan,

Xin Yu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Qi_2023_CVPR, author = {Qi, Xingqun and Liu, Chen and Sun, Muyi and Li, Lincheng and Fan, Changjie and Yu, Xin}, title = {Diverse 3D Hand Gesture Prediction From Body Dynamics by Bilateral Hand Disentanglement}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4616-4626} }

Learning Video Representations From Large Language Models

Yue Zhao,

Ishan Misra,

Philipp Krähenbühl,

Rohit Girdhar

[pdf] [supp]

[bibtex]

@InProceedings{Zhao_2023_CVPR, author = {Zhao, Yue and Misra, Ishan and Kr\"ahenb\"uhl, Philipp and Girdhar, Rohit}, title = {Learning Video Representations From Large Language Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6586-6597} }

Open-Vocabulary Semantic Segmentation With Mask-Adapted CLIP

Feng Liang,

Bichen Wu,

Xiaoliang Dai,

Kunpeng Li,

Yinan Zhao,

Hang Zhang,

Peizhao Zhang,

Peter Vajda,

Diana Marculescu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Liang_2023_CVPR, author = {Liang, Feng and Wu, Bichen and Dai, Xiaoliang and Li, Kunpeng and Zhao, Yinan and Zhang, Hang and Zhang, Peizhao and Vajda, Peter and Marculescu, Diana}, title = {Open-Vocabulary Semantic Segmentation With Mask-Adapted CLIP}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7061-7070} }

A Loopback Network for Explainable Microvascular Invasion Classification

Shengxuming Zhang,

Tianqi Shi,

Yang Jiang,

Xiuming Zhang,

Jie Lei,

Zunlei Feng,

Mingli Song

[pdf] [supp]

[bibtex]

@InProceedings{Zhang_2023_CVPR, author = {Zhang, Shengxuming and Shi, Tianqi and Jiang, Yang and Zhang, Xiuming and Lei, Jie and Feng, Zunlei and Song, Mingli}, title = {A Loopback Network for Explainable Microvascular Invasion Classification}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7443-7453} }

Exact-NeRF: An Exploration of a Precise Volumetric Parameterization for Neural Radiance Fields

Brian K. S. Isaac-Medina,

Chris G. Willcocks,

Toby P. Breckon

[pdf] [supp]

[bibtex]

@InProceedings{Isaac-Medina_2023_CVPR, author = {Isaac-Medina, Brian K. S. and Willcocks, Chris G. and Breckon, Toby P.}, title = {Exact-NeRF: An Exploration of a Precise Volumetric Parameterization for Neural Radiance Fields}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {66-75} }

WildLight: In-the-Wild Inverse Rendering With a Flashlight

Ziang Cheng,

Junxuan Li,

Hongdong Li

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Cheng_2023_CVPR, author = {Cheng, Ziang and Li, Junxuan and Li, Hongdong}, title = {WildLight: In-the-Wild Inverse Rendering With a Flashlight}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4305-4314} }

A Probabilistic Attention Model With Occlusion-Aware Texture Regression for 3D Hand Reconstruction From a Single RGB Image

Zheheng Jiang,

Hossein Rahmani,

Sue Black,

Bryan M. Williams

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Jiang_2023_CVPR, author = {Jiang, Zheheng and Rahmani, Hossein and Black, Sue and Williams, Bryan M.}, title = {A Probabilistic Attention Model With Occlusion-Aware Texture Regression for 3D Hand Reconstruction From a Single RGB Image}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {758-767} }

Attribute-Preserving Face Dataset Anonymization via Latent Code Optimization

Simone Barattin,

Christos Tzelepis,

Ioannis Patras,

Nicu Sebe

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Barattin_2023_CVPR, author = {Barattin, Simone and Tzelepis, Christos and Patras, Ioannis and Sebe, Nicu}, title = {Attribute-Preserving Face Dataset Anonymization via Latent Code Optimization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8001-8010} }

Ensemble-Based Blackbox Attacks on Dense Prediction

Zikui Cai,

Yaoteng Tan,

M. Salman Asif

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Cai_2023_CVPR, author = {Cai, Zikui and Tan, Yaoteng and Asif, M. Salman}, title = {Ensemble-Based Blackbox Attacks on Dense Prediction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4045-4055} }

Improving Fairness in Facial Albedo Estimation via Visual-Textual Cues

Xingyu Ren,

Jiankang Deng,

Chao Ma,

Yichao Yan,

Xiaokang Yang

[pdf]

[bibtex]

@InProceedings{Ren_2023_CVPR, author = {Ren, Xingyu and Deng, Jiankang and Ma, Chao and Yan, Yichao and Yang, Xiaokang}, title = {Improving Fairness in Facial Albedo Estimation via Visual-Textual Cues}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4511-4520} }

SmartAssign: Learning a Smart Knowledge Assignment Strategy for Deraining and Desnowing

Yinglong Wang,

Chao Ma,

Jianzhuang Liu

[pdf]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Yinglong and Ma, Chao and Liu, Jianzhuang}, title = {SmartAssign: Learning a Smart Knowledge Assignment Strategy for Deraining and Desnowing}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3677-3686} }

sRGB Real Noise Synthesizing With Neighboring Correlation-Aware Noise Model

Zixuan Fu,

Lanqing Guo,

Bihan Wen

[pdf] [supp]

[bibtex]

@InProceedings{Fu_2023_CVPR, author = {Fu, Zixuan and Guo, Lanqing and Wen, Bihan}, title = {sRGB Real Noise Synthesizing With Neighboring Correlation-Aware Noise Model}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1683-1691} }

Revisiting Weak-to-Strong Consistency in Semi-Supervised Semantic Segmentation

Lihe Yang,

Lei Qi,

Litong Feng,

Wayne Zhang,

Yinghuan Shi

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Yang_2023_CVPR, author = {Yang, Lihe and Qi, Lei and Feng, Litong and Zhang, Wayne and Shi, Yinghuan}, title = {Revisiting Weak-to-Strong Consistency in Semi-Supervised Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7236-7246} }

Implicit View-Time Interpolation of Stereo Videos Using Multi-Plane Disparities and Non-Uniform Coordinates

Avinash Paliwal,

Andrii Tsarov,

Nima Khademi Kalantari

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Paliwal_2023_CVPR, author = {Paliwal, Avinash and Tsarov, Andrii and Kalantari, Nima Khademi}, title = {Implicit View-Time Interpolation of Stereo Videos Using Multi-Plane Disparities and Non-Uniform Coordinates}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {888-898} }

Soft-Landing Strategy for Alleviating the Task Discrepancy Problem in Temporal Action Localization Tasks

Hyolim Kang,

Hanjung Kim,

Joungbin An,

Minsu Cho,

Seon Joo Kim

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Kang_2023_CVPR, author = {Kang, Hyolim and Kim, Hanjung and An, Joungbin and Cho, Minsu and Kim, Seon Joo}, title = {Soft-Landing Strategy for Alleviating the Task Discrepancy Problem in Temporal Action Localization Tasks}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6514-6523} }

Visibility Aware Human-Object Interaction Tracking From Single RGB Camera

Xianghui Xie,

Bharat Lal Bhatnagar,

Gerard Pons-Moll

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Xie_2023_CVPR, author = {Xie, Xianghui and Bhatnagar, Bharat Lal and Pons-Moll, Gerard}, title = {Visibility Aware Human-Object Interaction Tracking From Single RGB Camera}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4757-4768} }

Rethinking Gradient Projection Continual Learning: Stability / Plasticity Feature Space Decoupling

Zhen Zhao,

Zhizhong Zhang,

Xin Tan,

Jun Liu,

Yanyun Qu,

Yuan Xie,

Lizhuang Ma

[pdf] [supp]

[bibtex]

@InProceedings{Zhao_2023_CVPR, author = {Zhao, Zhen and Zhang, Zhizhong and Tan, Xin and Liu, Jun and Qu, Yanyun and Xie, Yuan and Ma, Lizhuang}, title = {Rethinking Gradient Projection Continual Learning: Stability / Plasticity Feature Space Decoupling}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3718-3727} }

FlatFormer: Flattened Window Attention for Efficient Point Cloud Transformer

Zhijian Liu,

Xinyu Yang,

Haotian Tang,

Shang Yang,

Song Han

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Liu_2023_CVPR, author = {Liu, Zhijian and Yang, Xinyu and Tang, Haotian and Yang, Shang and Han, Song}, title = {FlatFormer: Flattened Window Attention for Efficient Point Cloud Transformer}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1200-1211} }

Dynamic Graph Learning With Content-Guided Spatial-Frequency Relation Reasoning for Deepfake Detection

Yuan Wang,

Kun Yu,

Chen Chen,

Xiyuan Hu,

Silong Peng

[pdf] [supp]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Yuan and Yu, Kun and Chen, Chen and Hu, Xiyuan and Peng, Silong}, title = {Dynamic Graph Learning With Content-Guided Spatial-Frequency Relation Reasoning for Deepfake Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7278-7287} }

Two-Stage Co-Segmentation Network Based on Discriminative Representation for Recovering Human Mesh From Videos

Boyang Zhang,

Kehua Ma,

Suping Wu,

Zhixiang Yuan

[pdf] [supp]

[bibtex]

@InProceedings{Zhang_2023_CVPR, author = {Zhang, Boyang and Ma, Kehua and Wu, Suping and Yuan, Zhixiang}, title = {Two-Stage Co-Segmentation Network Based on Discriminative Representation for Recovering Human Mesh From Videos}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5662-5670} }

Learning Anchor Transformations for 3D Garment Animation

Fang Zhao,

Zekun Li,

Shaoli Huang,

Junwu Weng,

Tianfei Zhou,

Guo-Sen Xie,

Jue Wang,

Ying Shan

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Zhao_2023_CVPR, author = {Zhao, Fang and Li, Zekun and Huang, Shaoli and Weng, Junwu and Zhou, Tianfei and Xie, Guo-Sen and Wang, Jue and Shan, Ying}, title = {Learning Anchor Transformations for 3D Garment Animation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {491-500} }

Actionlet-Dependent Contrastive Learning for Unsupervised Skeleton-Based Action Recognition

Lilang Lin,

Jiahang Zhang,

Jiaying Liu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Lin_2023_CVPR, author = {Lin, Lilang and Zhang, Jiahang and Liu, Jiaying}, title = {Actionlet-Dependent Contrastive Learning for Unsupervised Skeleton-Based Action Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2363-2372} }

Ref-NPR: Reference-Based Non-Photorealistic Radiance Fields for Controllable Scene Stylization

Yuechen Zhang,

Zexin He,

Jinbo Xing,

Xufeng Yao,

Jiaya Jia

[pdf] [supp]

[bibtex]

@InProceedings{Zhang_2023_CVPR, author = {Zhang, Yuechen and He, Zexin and Xing, Jinbo and Yao, Xufeng and Jia, Jiaya}, title = {Ref-NPR: Reference-Based Non-Photorealistic Radiance Fields for Controllable Scene Stylization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4242-4251} }

Tree Instance Segmentation With Temporal Contour Graph

Adnan Firoze,

Cameron Wingren,

Raymond A. Yeh,

Bedrich Benes,

Daniel Aliaga

[pdf] [supp]

[bibtex]

@InProceedings{Firoze_2023_CVPR, author = {Firoze, Adnan and Wingren, Cameron and Yeh, Raymond A. and Benes, Bedrich and Aliaga, Daniel}, title = {Tree Instance Segmentation With Temporal Contour Graph}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2193-2202} }

Meta-Causal Learning for Single Domain Generalization

Jin Chen,

Zhi Gao,

Xinxiao Wu,

Jiebo Luo

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Chen_2023_CVPR, author = {Chen, Jin and Gao, Zhi and Wu, Xinxiao and Luo, Jiebo}, title = {Meta-Causal Learning for Single Domain Generalization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7683-7692} }

Grad-PU: Arbitrary-Scale Point Cloud Upsampling via Gradient Descent With Learned Distance Functions

Yun He,

Danhang Tang,

Yinda Zhang,

Xiangyang Xue,

Yanwei Fu

[pdf] [supp]

[bibtex]

@InProceedings{He_2023_CVPR, author = {He, Yun and Tang, Danhang and Zhang, Yinda and Xue, Xiangyang and Fu, Yanwei}, title = {Grad-PU: Arbitrary-Scale Point Cloud Upsampling via Gradient Descent With Learned Distance Functions}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5354-5363} }

Trainable Projected Gradient Method for Robust Fine-Tuning

Junjiao Tian,

Zecheng He,

Xiaoliang Dai,

Chih-Yao Ma,

Yen-Cheng Liu,

Zsolt Kira

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Tian_2023_CVPR, author = {Tian, Junjiao and He, Zecheng and Dai, Xiaoliang and Ma, Chih-Yao and Liu, Yen-Cheng and Kira, Zsolt}, title = {Trainable Projected Gradient Method for Robust Fine-Tuning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7836-7845} }

Text2Scene: Text-Driven Indoor Scene Stylization With Part-Aware Details

Inwoo Hwang,

Hyeonwoo Kim,

Young Min Kim

[pdf] [supp]

[bibtex]

@InProceedings{Hwang_2023_CVPR, author = {Hwang, Inwoo and Kim, Hyeonwoo and Kim, Young Min}, title = {Text2Scene: Text-Driven Indoor Scene Stylization With Part-Aware Details}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1890-1899} }

FEND: A Future Enhanced Distribution-Aware Contrastive Learning Framework for Long-Tail Trajectory Prediction

Yuning Wang,

Pu Zhang,

Lei Bai,

Jianru Xue

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Yuning and Zhang, Pu and Bai, Lei and Xue, Jianru}, title = {FEND: A Future Enhanced Distribution-Aware Contrastive Learning Framework for Long-Tail Trajectory Prediction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1400-1409} }

HDR Imaging With Spatially Varying Signal-to-Noise Ratios

Yiheng Chi,

Xingguang Zhang,

Stanley H. Chan

[pdf] [arXiv]

[bibtex]

@InProceedings{Chi_2023_CVPR, author = {Chi, Yiheng and Zhang, Xingguang and Chan, Stanley H.}, title = {HDR Imaging With Spatially Varying Signal-to-Noise Ratios}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5724-5734} }

Reliability in Semantic Segmentation: Are We on the Right Track?

Pau de Jorge,

Riccardo Volpi,

Philip H.S. Torr,

Grégory Rogez

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{de_Jorge_2023_CVPR, author = {de Jorge, Pau and Volpi, Riccardo and Torr, Philip H.S. and Rogez, Gr\'egory}, title = {Reliability in Semantic Segmentation: Are We on the Right Track?}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7173-7182} }

Blowing in the Wind: CycleNet for Human Cinemagraphs From Still Images

Hugo Bertiche,

Niloy J. Mitra,

Kuldeep Kulkarni,

Chun-Hao P. Huang,

Tuanfeng Y. Wang,

Meysam Madadi,

Sergio Escalera,

Duygu Ceylan

[pdf] [arXiv]

[bibtex]

@InProceedings{Bertiche_2023_CVPR, author = {Bertiche, Hugo and Mitra, Niloy J. and Kulkarni, Kuldeep and Huang, Chun-Hao P. and Wang, Tuanfeng Y. and Madadi, Meysam and Escalera, Sergio and Ceylan, Duygu}, title = {Blowing in the Wind: CycleNet for Human Cinemagraphs From Still Images}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {459-468} }

Panoptic Compositional Feature Field for Editable Scene Rendering With Network-Inferred Labels via Metric Learning

Xinhua Cheng,

Yanmin Wu,

Mengxi Jia,

Qian Wang,

Jian Zhang

[pdf] [supp]

[bibtex]

@InProceedings{Cheng_2023_CVPR, author = {Cheng, Xinhua and Wu, Yanmin and Jia, Mengxi and Wang, Qian and Zhang, Jian}, title = {Panoptic Compositional Feature Field for Editable Scene Rendering With Network-Inferred Labels via Metric Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4947-4957} }

Neural Kaleidoscopic Space Sculpting

Byeongjoo Ahn,

Michael De Zeeuw,

Ioannis Gkioulekas,

Aswin C. Sankaranarayanan

[pdf] [supp]

[bibtex]

@InProceedings{Ahn_2023_CVPR, author = {Ahn, Byeongjoo and De Zeeuw, Michael and Gkioulekas, Ioannis and Sankaranarayanan, Aswin C.}, title = {Neural Kaleidoscopic Space Sculpting}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4349-4358} }

Implicit Identity Driven Deepfake Face Swapping Detection

Baojin Huang,

Zhongyuan Wang,

Jifan Yang,

Jiaxin Ai,

Qin Zou,

Qian Wang,

Dengpan Ye

[pdf]

[bibtex]

@InProceedings{Huang_2023_CVPR, author = {Huang, Baojin and Wang, Zhongyuan and Yang, Jifan and Ai, Jiaxin and Zou, Qin and Wang, Qian and Ye, Dengpan}, title = {Implicit Identity Driven Deepfake Face Swapping Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4490-4499} }

Class Relationship Embedded Learning for Source-Free Unsupervised Domain Adaptation

Yixin Zhang,

Zilei Wang,

Weinan He

[pdf] [supp]

[bibtex]

@InProceedings{Zhang_2023_CVPR, author = {Zhang, Yixin and Wang, Zilei and He, Weinan}, title = {Class Relationship Embedded Learning for Source-Free Unsupervised Domain Adaptation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7619-7629} }

One-to-Few Label Assignment for End-to-End Dense Detection

Shuai Li,

Minghan Li,

Ruihuang Li,

Chenhang He,

Lei Zhang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Li_2023_CVPR, author = {Li, Shuai and Li, Minghan and Li, Ruihuang and He, Chenhang and Zhang, Lei}, title = {One-to-Few Label Assignment for End-to-End Dense Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7350-7359} }

Fake It Till You Make It: Learning Transferable Representations From Synthetic ImageNet Clones

Mert Bülent Sarıyıldız,

Karteek Alahari,

Diane Larlus,

Yannis Kalantidis

[pdf] [supp]

[bibtex]

@InProceedings{Sariyildiz_2023_CVPR, author = {Sar{\i}y{\i}ld{\i}z, Mert B\"ulent and Alahari, Karteek and Larlus, Diane and Kalantidis, Yannis}, title = {Fake It Till You Make It: Learning Transferable Representations From Synthetic ImageNet Clones}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8011-8021} }

Interactive and Explainable Region-Guided Radiology Report Generation

Tim Tanida,

Philip Müller,

Georgios Kaissis,

Daniel Rueckert

[pdf] [supp]

[bibtex]

@InProceedings{Tanida_2023_CVPR, author = {Tanida, Tim and M\"uller, Philip and Kaissis, Georgios and Rueckert, Daniel}, title = {Interactive and Explainable Region-Guided Radiology Report Generation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7433-7442} }

MED-VT: Multiscale Encoder-Decoder Video Transformer With Application To Object Segmentation

Rezaul Karim,

He Zhao,

Richard P. Wildes,

Mennatullah Siam

[pdf] [supp]

[bibtex]

@InProceedings{Karim_2023_CVPR, author = {Karim, Rezaul and Zhao, He and Wildes, Richard P. and Siam, Mennatullah}, title = {MED-VT: Multiscale Encoder-Decoder Video Transformer With Application To Object Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6323-6333} }

Benchmarking Self-Supervised Learning on Diverse Pathology Datasets

Mingu Kang,

Heon Song,

Seonwook Park,

Donggeun Yoo,

Sérgio Pereira

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Kang_2023_CVPR, author = {Kang, Mingu and Song, Heon and Park, Seonwook and Yoo, Donggeun and Pereira, S\'ergio}, title = {Benchmarking Self-Supervised Learning on Diverse Pathology Datasets}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3344-3354} }

Document Image Shadow Removal Guided by Color-Aware Background

Ling Zhang,

Yinghao He,

Qing Zhang,

Zheng Liu,

Xiaolong Zhang,

Chunxia Xiao

[pdf] [supp]

[bibtex]

@InProceedings{Zhang_2023_CVPR, author = {Zhang, Ling and He, Yinghao and Zhang, Qing and Liu, Zheng and Zhang, Xiaolong and Xiao, Chunxia}, title = {Document Image Shadow Removal Guided by Color-Aware Background}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1818-1827} }

Improved Distribution Matching for Dataset Condensation

Ganlong Zhao,

Guanbin Li,

Yipeng Qin,

Yizhou Yu

[pdf] [supp]

[bibtex]

@InProceedings{Zhao_2023_CVPR, author = {Zhao, Ganlong and Li, Guanbin and Qin, Yipeng and Yu, Yizhou}, title = {Improved Distribution Matching for Dataset Condensation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7856-7865} }

Feature Separation and Recalibration for Adversarial Robustness

Woo Jae Kim,

Yoonki Cho,

Junsik Jung,

Sung-Eui Yoon

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Kim_2023_CVPR, author = {Kim, Woo Jae and Cho, Yoonki and Jung, Junsik and Yoon, Sung-Eui}, title = {Feature Separation and Recalibration for Adversarial Robustness}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8183-8192} }

Slimmable Dataset Condensation

Songhua Liu,

Jingwen Ye,

Runpeng Yu,

Xinchao Wang

[pdf] [supp]

[bibtex]

@InProceedings{Liu_2023_CVPR, author = {Liu, Songhua and Ye, Jingwen and Yu, Runpeng and Wang, Xinchao}, title = {Slimmable Dataset Condensation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3759-3768} }

Multi-View Azimuth Stereo via Tangent Space Consistency

Xu Cao,

Hiroaki Santo,

Fumio Okura,

Yasuyuki Matsushita

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Cao_2023_CVPR, author = {Cao, Xu and Santo, Hiroaki and Okura, Fumio and Matsushita, Yasuyuki}, title = {Multi-View Azimuth Stereo via Tangent Space Consistency}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {825-834} }

VectorFusion: Text-to-SVG by Abstracting Pixel-Based Diffusion Models

Ajay Jain,

Amber Xie,

Pieter Abbeel

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Jain_2023_CVPR, author = {Jain, Ajay and Xie, Amber and Abbeel, Pieter}, title = {VectorFusion: Text-to-SVG by Abstracting Pixel-Based Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1911-1920} }

The Dialog Must Go On: Improving Visual Dialog via Generative Self-Training

Gi-Cheon Kang,

Sungdong Kim,

Jin-Hwa Kim,

Donghyun Kwak,

Byoung-Tak Zhang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Kang_2023_CVPR, author = {Kang, Gi-Cheon and Kim, Sungdong and Kim, Jin-Hwa and Kwak, Donghyun and Zhang, Byoung-Tak}, title = {The Dialog Must Go On: Improving Visual Dialog via Generative Self-Training}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6746-6756} }

Binarizing Sparse Convolutional Networks for Efficient Point Cloud Analysis

Xiuwei Xu,

Ziwei Wang,

Jie Zhou,

Jiwen Lu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Xu_2023_CVPR, author = {Xu, Xiuwei and Wang, Ziwei and Zhou, Jie and Lu, Jiwen}, title = {Binarizing Sparse Convolutional Networks for Efficient Point Cloud Analysis}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5313-5322} }

Diffusion Art or Digital Forgery? Investigating Data Replication in Diffusion Models

Gowthami Somepalli,

Vasu Singla,

Micah Goldblum,

Jonas Geiping,

Tom Goldstein

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Somepalli_2023_CVPR, author = {Somepalli, Gowthami and Singla, Vasu and Goldblum, Micah and Geiping, Jonas and Goldstein, Tom}, title = {Diffusion Art or Digital Forgery? Investigating Data Replication in Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6048-6058} }

Neuralizer: General Neuroimage Analysis Without Re-Training

Steffen Czolbe,

Adrian V. Dalca

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Czolbe_2023_CVPR, author = {Czolbe, Steffen and Dalca, Adrian V.}, title = {Neuralizer: General Neuroimage Analysis Without Re-Training}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6217-6230} }

UniDexGrasp: Universal Robotic Dexterous Grasping via Learning Diverse Proposal Generation and Goal-Conditioned Policy

Yinzhen Xu,

Weikang Wan,

Jialiang Zhang,

Haoran Liu,

Zikang Shan,

Hao Shen,

Ruicheng Wang,

Haoran Geng,

Yijia Weng,

Jiayi Chen,

Tengyu Liu,

Li Yi,

He Wang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Xu_2023_CVPR, author = {Xu, Yinzhen and Wan, Weikang and Zhang, Jialiang and Liu, Haoran and Shan, Zikang and Shen, Hao and Wang, Ruicheng and Geng, Haoran and Weng, Yijia and Chen, Jiayi and Liu, Tengyu and Yi, Li and Wang, He}, title = {UniDexGrasp: Universal Robotic Dexterous Grasping via Learning Diverse Proposal Generation and Goal-Conditioned Policy}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4737-4746} }

A Rotation-Translation-Decoupled Solution for Robust and Efficient Visual-Inertial Initialization

Yijia He,

Bo Xu,

Zhanpeng Ouyang,

Hongdong Li

[pdf] [supp]

[bibtex]

@InProceedings{He_2023_CVPR, author = {He, Yijia and Xu, Bo and Ouyang, Zhanpeng and Li, Hongdong}, title = {A Rotation-Translation-Decoupled Solution for Robust and Efficient Visual-Inertial Initialization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {739-748} }

BundleSDF: Neural 6-DoF Tracking and 3D Reconstruction of Unknown Objects

Bowen Wen,

Jonathan Tremblay,

Valts Blukis,

Stephen Tyree,

Thomas Müller,

Alex Evans,

Dieter Fox,

Jan Kautz,

Stan Birchfield

[pdf] [supp]

[bibtex]

@InProceedings{Wen_2023_CVPR, author = {Wen, Bowen and Tremblay, Jonathan and Blukis, Valts and Tyree, Stephen and M\"uller, Thomas and Evans, Alex and Fox, Dieter and Kautz, Jan and Birchfield, Stan}, title = {BundleSDF: Neural 6-DoF Tracking and 3D Reconstruction of Unknown Objects}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {606-617} }

Texture-Guided Saliency Distilling for Unsupervised Salient Object Detection

Huajun Zhou,

Bo Qiao,

Lingxiao Yang,

Jianhuang Lai,

Xiaohua Xie

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Zhou_2023_CVPR, author = {Zhou, Huajun and Qiao, Bo and Yang, Lingxiao and Lai, Jianhuang and Xie, Xiaohua}, title = {Texture-Guided Saliency Distilling for Unsupervised Salient Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7257-7267} }

AltFreezing for More General Video Face Forgery Detection

Zhendong Wang,

Jianmin Bao,

Wengang Zhou,

Weilun Wang,

Houqiang Li

[pdf] [supp]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Zhendong and Bao, Jianmin and Zhou, Wengang and Wang, Weilun and Li, Houqiang}, title = {AltFreezing for More General Video Face Forgery Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4129-4138} }

Learning Partial Correlation Based Deep Visual Representation for Image Classification

Saimunur Rahman,

Piotr Koniusz,

Lei Wang,

Luping Zhou,

Peyman Moghadam,

Changming Sun

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Rahman_2023_CVPR, author = {Rahman, Saimunur and Koniusz, Piotr and Wang, Lei and Zhou, Luping and Moghadam, Peyman and Sun, Changming}, title = {Learning Partial Correlation Based Deep Visual Representation for Image Classification}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6231-6240} }

Hi-LASSIE: High-Fidelity Articulated Shape and Skeleton Discovery From Sparse Image Ensemble

Chun-Han Yao,

Wei-Chih Hung,

Yuanzhen Li,

Michael Rubinstein,

Ming-Hsuan Yang,

Varun Jampani

[pdf] [supp]

[bibtex]

@InProceedings{Yao_2023_CVPR, author = {Yao, Chun-Han and Hung, Wei-Chih and Li, Yuanzhen and Rubinstein, Michael and Yang, Ming-Hsuan and Jampani, Varun}, title = {Hi-LASSIE: High-Fidelity Articulated Shape and Skeleton Discovery From Sparse Image Ensemble}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4853-4862} }

Computationally Budgeted Continual Learning: What Does Matter?

Ameya Prabhu,

Hasan Abed Al Kader Hammoud,

Puneet K. Dokania,

Philip H.S. Torr,

Ser-Nam Lim,

Bernard Ghanem,

Adel Bibi

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Prabhu_2023_CVPR, author = {Prabhu, Ameya and Al Kader Hammoud, Hasan Abed and Dokania, Puneet K. and Torr, Philip H.S. and Lim, Ser-Nam and Ghanem, Bernard and Bibi, Adel}, title = {Computationally Budgeted Continual Learning: What Does Matter?}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3698-3707} }

Decentralized Learning With Multi-Headed Distillation

Andrey Zhmoginov,

Mark Sandler,

Nolan Miller,

Gus Kristiansen,

Max Vladymyrov

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Zhmoginov_2023_CVPR, author = {Zhmoginov, Andrey and Sandler, Mark and Miller, Nolan and Kristiansen, Gus and Vladymyrov, Max}, title = {Decentralized Learning With Multi-Headed Distillation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8053-8063} }

CF-Font: Content Fusion for Few-Shot Font Generation

Chi Wang,

Min Zhou,

Tiezheng Ge,

Yuning Jiang,

Hujun Bao,

Weiwei Xu

[pdf] [supp]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Chi and Zhou, Min and Ge, Tiezheng and Jiang, Yuning and Bao, Hujun and Xu, Weiwei}, title = {CF-Font: Content Fusion for Few-Shot Font Generation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1858-1867} }

3Mformer: Multi-Order Multi-Mode Transformer for Skeletal Action Recognition

Lei Wang,

Piotr Koniusz

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Lei and Koniusz, Piotr}, title = {3Mformer: Multi-Order Multi-Mode Transformer for Skeletal Action Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5620-5631} }

Transformer Scale Gate for Semantic Segmentation

Hengcan Shi,

Munawar Hayat,

Jianfei Cai

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Shi_2023_CVPR, author = {Shi, Hengcan and Hayat, Munawar and Cai, Jianfei}, title = {Transformer Scale Gate for Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3051-3060} }

EMT-NAS:Transferring Architectural Knowledge Between Tasks From Different Datasets

Peng Liao,

Yaochu Jin,

Wenli Du

[pdf] [supp]

[bibtex]

@InProceedings{Liao_2023_CVPR, author = {Liao, Peng and Jin, Yaochu and Du, Wenli}, title = {EMT-NAS:Transferring Architectural Knowledge Between Tasks From Different Datasets}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3643-3653} }

Learning Joint Latent Space EBM Prior Model for Multi-Layer Generator

Jiali Cui,

Ying Nian Wu,

Tian Han

[pdf] [supp]

[bibtex]

@InProceedings{Cui_2023_CVPR, author = {Cui, Jiali and Wu, Ying Nian and Han, Tian}, title = {Learning Joint Latent Space EBM Prior Model for Multi-Layer Generator}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3603-3612} }

Benchmarking Robustness of 3D Object Detection to Common Corruptions

Yinpeng Dong,

Caixin Kang,

Jinlai Zhang,

Zijian Zhu,

Yikai Wang,

Xiao Yang,

Hang Su,

Xingxing Wei,

Jun Zhu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Dong_2023_CVPR, author = {Dong, Yinpeng and Kang, Caixin and Zhang, Jinlai and Zhu, Zijian and Wang, Yikai and Yang, Xiao and Su, Hang and Wei, Xingxing and Zhu, Jun}, title = {Benchmarking Robustness of 3D Object Detection to Common Corruptions}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1022-1032} }

STMT: A Spatial-Temporal Mesh Transformer for MoCap-Based Action Recognition

Xiaoyu Zhu,

Po-Yao Huang,

Junwei Liang,

Celso M. de Melo,

Alexander G. Hauptmann

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Zhu_2023_CVPR, author = {Zhu, Xiaoyu and Huang, Po-Yao and Liang, Junwei and de Melo, Celso M. and Hauptmann, Alexander G.}, title = {STMT: A Spatial-Temporal Mesh Transformer for MoCap-Based Action Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1526-1536} }

High-Fidelity Generalized Emotional Talking Face Generation With Multi-Modal Emotion Space Learning

Chao Xu,

Junwei Zhu,

Jiangning Zhang,

Yue Han,

Wenqing Chu,

Ying Tai,

Chengjie Wang,

Zhifeng Xie,

Yong Liu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Xu_2023_CVPR, author = {Xu, Chao and Zhu, Junwei and Zhang, Jiangning and Han, Yue and Chu, Wenqing and Tai, Ying and Wang, Chengjie and Xie, Zhifeng and Liu, Yong}, title = {High-Fidelity Generalized Emotional Talking Face Generation With Multi-Modal Emotion Space Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6609-6619} }

Teaching Matters: Investigating the Role of Supervision in Vision Transformers

Matthew Walmer,

Saksham Suri,

Kamal Gupta,

Abhinav Shrivastava

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Walmer_2023_CVPR, author = {Walmer, Matthew and Suri, Saksham and Gupta, Kamal and Shrivastava, Abhinav}, title = {Teaching Matters: Investigating the Role of Supervision in Vision Transformers}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7486-7496} }

Imagic: Text-Based Real Image Editing With Diffusion Models

Bahjat Kawar,

Shiran Zada,

Oran Lang,

Omer Tov,

Huiwen Chang,

Tali Dekel,

Inbar Mosseri,

Michal Irani

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Kawar_2023_CVPR, author = {Kawar, Bahjat and Zada, Shiran and Lang, Oran and Tov, Omer and Chang, Huiwen and Dekel, Tali and Mosseri, Inbar and Irani, Michal}, title = {Imagic: Text-Based Real Image Editing With Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6007-6017} }

LightPainter: Interactive Portrait Relighting With Freehand Scribble

Yiqun Mei,

He Zhang,

Xuaner Zhang,

Jianming Zhang,

Zhixin Shu,

Yilin Wang,

Zijun Wei,

Shi Yan,

HyunJoon Jung,

Vishal M. Patel

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Mei_2023_CVPR, author = {Mei, Yiqun and Zhang, He and Zhang, Xuaner and Zhang, Jianming and Shu, Zhixin and Wang, Yilin and Wei, Zijun and Yan, Shi and Jung, HyunJoon and Patel, Vishal M.}, title = {LightPainter: Interactive Portrait Relighting With Freehand Scribble}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {195-205} }

Vision Transformers Are Parameter-Efficient Audio-Visual Learners

Yan-Bo Lin,

Yi-Lin Sung,

Jie Lei,

Mohit Bansal,

Gedas Bertasius

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Lin_2023_CVPR, author = {Lin, Yan-Bo and Sung, Yi-Lin and Lei, Jie and Bansal, Mohit and Bertasius, Gedas}, title = {Vision Transformers Are Parameter-Efficient Audio-Visual Learners}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2299-2309} }

Training Debiased Subnetworks With Contrastive Weight Pruning

Geon Yeong Park,

Sangmin Lee,

Sang Wan Lee,

Jong Chul Ye

[pdf] [supp]

[bibtex]

@InProceedings{Park_2023_CVPR, author = {Park, Geon Yeong and Lee, Sangmin and Lee, Sang Wan and Ye, Jong Chul}, title = {Training Debiased Subnetworks With Contrastive Weight Pruning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7929-7938} }

SparseViT: Revisiting Activation Sparsity for Efficient High-Resolution Vision Transformer

Xuanyao Chen,

Zhijian Liu,

Haotian Tang,

Li Yi,

Hang Zhao,

Song Han

[pdf] [arXiv]

[bibtex]

@InProceedings{Chen_2023_CVPR, author = {Chen, Xuanyao and Liu, Zhijian and Tang, Haotian and Yi, Li and Zhao, Hang and Han, Song}, title = {SparseViT: Revisiting Activation Sparsity for Efficient High-Resolution Vision Transformer}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2061-2070} }

Multispectral Video Semantic Segmentation: A Benchmark Dataset and Baseline

Wei Ji,

Jingjing Li,

Cheng Bian,

Zongwei Zhou,

Jiaying Zhao,

Alan L. Yuille,

Li Cheng

[pdf] [supp]

[bibtex]

@InProceedings{Ji_2023_CVPR, author = {Ji, Wei and Li, Jingjing and Bian, Cheng and Zhou, Zongwei and Zhao, Jiaying and Yuille, Alan L. and Cheng, Li}, title = {Multispectral Video Semantic Segmentation: A Benchmark Dataset and Baseline}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1094-1104} }

Reducing the Label Bias for Timestamp Supervised Temporal Action Segmentation

Kaiyuan Liu,

Yunheng Li,

Shenglan Liu,

Chenwei Tan,

Zihang Shao

[pdf] [supp]

[bibtex]

@InProceedings{Liu_2023_CVPR, author = {Liu, Kaiyuan and Li, Yunheng and Liu, Shenglan and Tan, Chenwei and Shao, Zihang}, title = {Reducing the Label Bias for Timestamp Supervised Temporal Action Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6503-6513} }

A Meta-Learning Approach to Predicting Performance and Data Requirements

Achin Jain,

Gurumurthy Swaminathan,

Paolo Favaro,

Hao Yang,

Avinash Ravichandran,

Hrayr Harutyunyan,

Alessandro Achille,

Onkar Dabeer,

Bernt Schiele,

Ashwin Swaminathan,

Stefano Soatto

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Jain_2023_CVPR, author = {Jain, Achin and Swaminathan, Gurumurthy and Favaro, Paolo and Yang, Hao and Ravichandran, Avinash and Harutyunyan, Hrayr and Achille, Alessandro and Dabeer, Onkar and Schiele, Bernt and Swaminathan, Ashwin and Soatto, Stefano}, title = {A Meta-Learning Approach to Predicting Performance and Data Requirements}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3623-3632} }

Deep Curvilinear Editing: Commutative and Nonlinear Image Manipulation for Pretrained Deep Generative Model

Takehiro Aoshima,

Takashi Matsubara

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Aoshima_2023_CVPR, author = {Aoshima, Takehiro and Matsubara, Takashi}, title = {Deep Curvilinear Editing: Commutative and Nonlinear Image Manipulation for Pretrained Deep Generative Model}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5957-5967} }

Learning Semantic-Aware Knowledge Guidance for Low-Light Image Enhancement

Yuhui Wu,

Chen Pan,

Guoqing Wang,

Yang Yang,

Jiwei Wei,

Chongyi Li,

Heng Tao Shen

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Wu_2023_CVPR, author = {Wu, Yuhui and Pan, Chen and Wang, Guoqing and Yang, Yang and Wei, Jiwei and Li, Chongyi and Shen, Heng Tao}, title = {Learning Semantic-Aware Knowledge Guidance for Low-Light Image Enhancement}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1662-1671} }

Deep Arbitrary-Scale Image Super-Resolution via Scale-Equivariance Pursuit

Xiaohang Wang,

Xuanhong Chen,

Bingbing Ni,

Hang Wang,

Zhengyan Tong,

Yutian Liu

[pdf] [supp]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Xiaohang and Chen, Xuanhong and Ni, Bingbing and Wang, Hang and Tong, Zhengyan and Liu, Yutian}, title = {Deep Arbitrary-Scale Image Super-Resolution via Scale-Equivariance Pursuit}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1786-1795} }

OmniAL: A Unified CNN Framework for Unsupervised Anomaly Localization

Ying Zhao

[pdf] [supp]

[bibtex]

@InProceedings{Zhao_2023_CVPR, author = {Zhao, Ying}, title = {OmniAL: A Unified CNN Framework for Unsupervised Anomaly Localization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3924-3933} }

Canonical Fields: Self-Supervised Learning of Pose-Canonicalized Neural Fields

Rohith Agaram,

Shaurya Dewan,

Rahul Sajnani,

Adrien Poulenard,

Madhava Krishna,

Srinath Sridhar

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Agaram_2023_CVPR, author = {Agaram, Rohith and Dewan, Shaurya and Sajnani, Rahul and Poulenard, Adrien and Krishna, Madhava and Sridhar, Srinath}, title = {Canonical Fields: Self-Supervised Learning of Pose-Canonicalized Neural Fields}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4500-4510} }

BiasAdv: Bias-Adversarial Augmentation for Model Debiasing

Jongin Lim,

Youngdong Kim,

Byungjai Kim,

Chanho Ahn,

Jinwoo Shin,

Eunho Yang,

Seungju Han

[pdf] [supp]

[bibtex]

@InProceedings{Lim_2023_CVPR, author = {Lim, Jongin and Kim, Youngdong and Kim, Byungjai and Ahn, Chanho and Shin, Jinwoo and Yang, Eunho and Han, Seungju}, title = {BiasAdv: Bias-Adversarial Augmentation for Model Debiasing}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3832-3841} }

CDDFuse: Correlation-Driven Dual-Branch Feature Decomposition for Multi-Modality Image Fusion

Zixiang Zhao,

Haowen Bai,

Jiangshe Zhang,

Yulun Zhang,

Shuang Xu,

Zudi Lin,

Radu Timofte,

Luc Van Gool

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Zhao_2023_CVPR, author = {Zhao, Zixiang and Bai, Haowen and Zhang, Jiangshe and Zhang, Yulun and Xu, Shuang and Lin, Zudi and Timofte, Radu and Van Gool, Luc}, title = {CDDFuse: Correlation-Driven Dual-Branch Feature Decomposition for Multi-Modality Image Fusion}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5906-5916} }

Cross-Modal Implicit Relation Reasoning and Aligning for Text-to-Image Person Retrieval

Ding Jiang,

Mang Ye

[pdf] [arXiv]

[bibtex]

@InProceedings{Jiang_2023_CVPR, author = {Jiang, Ding and Ye, Mang}, title = {Cross-Modal Implicit Relation Reasoning and Aligning for Text-to-Image Person Retrieval}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2787-2797} }

Learning To Retain While Acquiring: Combating Distribution-Shift in Adversarial Data-Free Knowledge Distillation

Gaurav Patel,

Konda Reddy Mopuri,

Qiang Qiu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Patel_2023_CVPR, author = {Patel, Gaurav and Mopuri, Konda Reddy and Qiu, Qiang}, title = {Learning To Retain While Acquiring: Combating Distribution-Shift in Adversarial Data-Free Knowledge Distillation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7786-7794} }

Good Is Bad: Causality Inspired Cloth-Debiasing for Cloth-Changing Person Re-Identification

Zhengwei Yang,

Meng Lin,

Xian Zhong,

Yu Wu,

Zheng Wang

[pdf] [supp]

[bibtex]

@InProceedings{Yang_2023_CVPR, author = {Yang, Zhengwei and Lin, Meng and Zhong, Xian and Wu, Yu and Wang, Zheng}, title = {Good Is Bad: Causality Inspired Cloth-Debiasing for Cloth-Changing Person Re-Identification}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1472-1481} }

Use Your Head: Improving Long-Tail Video Recognition

Toby Perrett,

Saptarshi Sinha,

Tilo Burghardt,

Majid Mirmehdi,

Dima Damen

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Perrett_2023_CVPR, author = {Perrett, Toby and Sinha, Saptarshi and Burghardt, Tilo and Mirmehdi, Majid and Damen, Dima}, title = {Use Your Head: Improving Long-Tail Video Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2415-2425} }

Revisiting the P3P Problem

Yaqing Ding,

Jian Yang,

Viktor Larsson,

Carl Olsson,

Kalle Åström

[pdf] [supp]

[bibtex]

@InProceedings{Ding_2023_CVPR, author = {Ding, Yaqing and Yang, Jian and Larsson, Viktor and Olsson, Carl and \r{A}str\"om, Kalle}, title = {Revisiting the P3P Problem}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4872-4880} }

TimeBalance: Temporally-Invariant and Temporally-Distinctive Video Representations for Semi-Supervised Action Recognition

Ishan Rajendrakumar Dave,

Mamshad Nayeem Rizve,

Chen Chen,

Mubarak Shah

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Dave_2023_CVPR, author = {Dave, Ishan Rajendrakumar and Rizve, Mamshad Nayeem and Chen, Chen and Shah, Mubarak}, title = {TimeBalance: Temporally-Invariant and Temporally-Distinctive Video Representations for Semi-Supervised Action Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2341-2352} }

Generating Aligned Pseudo-Supervision From Non-Aligned Data for Image Restoration in Under-Display Camera

Ruicheng Feng,

Chongyi Li,

Huaijin Chen,

Shuai Li,

Jinwei Gu,

Chen Change Loy

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Feng_2023_CVPR, author = {Feng, Ruicheng and Li, Chongyi and Chen, Huaijin and Li, Shuai and Gu, Jinwei and Loy, Chen Change}, title = {Generating Aligned Pseudo-Supervision From Non-Aligned Data for Image Restoration in Under-Display Camera}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5013-5022} }

Neural Pixel Composition for 3D-4D View Synthesis From Multi-Views

Aayush Bansal,

Michael Zollhöfer

[pdf] [supp]

[bibtex]

@InProceedings{Bansal_2023_CVPR, author = {Bansal, Aayush and Zollh\"ofer, Michael}, title = {Neural Pixel Composition for 3D-4D View Synthesis From Multi-Views}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {290-299} }

CRAFT: Concept Recursive Activation FacTorization for Explainability

Thomas Fel,

Agustin Picard,

Louis Béthune,

Thibaut Boissin,

David Vigouroux,

Julien Colin,

Rémi Cadène,

Thomas Serre

[pdf] [supp]

[bibtex]

@InProceedings{Fel_2023_CVPR, author = {Fel, Thomas and Picard, Agustin and B\'ethune, Louis and Boissin, Thibaut and Vigouroux, David and Colin, Julien and Cad\`ene, R\'emi and Serre, Thomas}, title = {CRAFT: Concept Recursive Activation FacTorization for Explainability}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2711-2721} }

Recognizing Rigid Patterns of Unlabeled Point Clouds by Complete and Continuous Isometry Invariants With No False Negatives and No False Positives

Daniel Widdowson,

Vitaliy Kurlin

[pdf] [arXiv]

[bibtex]

@InProceedings{Widdowson_2023_CVPR, author = {Widdowson, Daniel and Kurlin, Vitaliy}, title = {Recognizing Rigid Patterns of Unlabeled Point Clouds by Complete and Continuous Isometry Invariants With No False Negatives and No False Positives}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1275-1284} }

N-Gram in Swin Transformers for Efficient Lightweight Image Super-Resolution

Haram Choi,

Jeongmin Lee,

Jihoon Yang

[pdf] [supp]

[bibtex]

@InProceedings{Choi_2023_CVPR, author = {Choi, Haram and Lee, Jeongmin and Yang, Jihoon}, title = {N-Gram in Swin Transformers for Efficient Lightweight Image Super-Resolution}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2071-2081} }

Hybrid Neural Rendering for Large-Scale Scenes With Motion Blur

Peng Dai,

Yinda Zhang,

Xin Yu,

Xiaoyang Lyu,

Xiaojuan Qi

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Dai_2023_CVPR, author = {Dai, Peng and Zhang, Yinda and Yu, Xin and Lyu, Xiaoyang and Qi, Xiaojuan}, title = {Hybrid Neural Rendering for Large-Scale Scenes With Motion Blur}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {154-164} }

Perception-Oriented Single Image Super-Resolution Using Optimal Objective Estimation

Seung Ho Park,

Young Su Moon,

Nam Ik Cho

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Park_2023_CVPR, author = {Park, Seung Ho and Moon, Young Su and Cho, Nam Ik}, title = {Perception-Oriented Single Image Super-Resolution Using Optimal Objective Estimation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1725-1735} }

Learning 3D Scene Priors With 2D Supervision

Yinyu Nie,

Angela Dai,

Xiaoguang Han,

Matthias Nießner

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Nie_2023_CVPR, author = {Nie, Yinyu and Dai, Angela and Han, Xiaoguang and Nie{\ss}ner, Matthias}, title = {Learning 3D Scene Priors With 2D Supervision}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {792-802} }

Label-Free Liver Tumor Segmentation

Qixin Hu,

Yixiong Chen,

Junfei Xiao,

Shuwen Sun,

Jieneng Chen,

Alan L. Yuille,

Zongwei Zhou

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Hu_2023_CVPR, author = {Hu, Qixin and Chen, Yixiong and Xiao, Junfei and Sun, Shuwen and Chen, Jieneng and Yuille, Alan L. and Zhou, Zongwei}, title = {Label-Free Liver Tumor Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7422-7432} }

Uncurated Image-Text Datasets: Shedding Light on Demographic Bias

Noa Garcia,

Yusuke Hirota,

Yankun Wu,

Yuta Nakashima

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Garcia_2023_CVPR, author = {Garcia, Noa and Hirota, Yusuke and Wu, Yankun and Nakashima, Yuta}, title = {Uncurated Image-Text Datasets: Shedding Light on Demographic Bias}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6957-6966} }

Adversarial Robustness via Random Projection Filters

Minjing Dong,

Chang Xu

[pdf] [supp]

[bibtex]

@InProceedings{Dong_2023_CVPR, author = {Dong, Minjing and Xu, Chang}, title = {Adversarial Robustness via Random Projection Filters}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4077-4086} }

VNE: An Effective Method for Improving Deep Representation by Manipulating Eigenvalue Distribution

Jaeill Kim,

Suhyun Kang,

Duhun Hwang,

Jungwook Shin,

Wonjong Rhee

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Kim_2023_CVPR, author = {Kim, Jaeill and Kang, Suhyun and Hwang, Duhun and Shin, Jungwook and Rhee, Wonjong}, title = {VNE: An Effective Method for Improving Deep Representation by Manipulating Eigenvalue Distribution}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3799-3810} }

Local Implicit Ray Function for Generalizable Radiance Field Representation

Xin Huang,

Qi Zhang,

Ying Feng,

Xiaoyu Li,

Xuan Wang,

Qing Wang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Huang_2023_CVPR, author = {Huang, Xin and Zhang, Qi and Feng, Ying and Li, Xiaoyu and Wang, Xuan and Wang, Qing}, title = {Local Implicit Ray Function for Generalizable Radiance Field Representation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {97-107} }

Dense Distinct Query for End-to-End Object Detection

Shilong Zhang,

Xinjiang Wang,

Jiaqi Wang,

Jiangmiao Pang,

Chengqi Lyu,

Wenwei Zhang,

Ping Luo,

Kai Chen

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Zhang_2023_CVPR, author = {Zhang, Shilong and Wang, Xinjiang and Wang, Jiaqi and Pang, Jiangmiao and Lyu, Chengqi and Zhang, Wenwei and Luo, Ping and Chen, Kai}, title = {Dense Distinct Query for End-to-End Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7329-7338} }

Divide and Adapt: Active Domain Adaptation via Customized Learning

Duojun Huang,

Jichang Li,

Weikai Chen,

Junshi Huang,

Zhenhua Chai,

Guanbin Li

[pdf] [supp]

[bibtex]

@InProceedings{Huang_2023_CVPR, author = {Huang, Duojun and Li, Jichang and Chen, Weikai and Huang, Junshi and Chai, Zhenhua and Li, Guanbin}, title = {Divide and Adapt: Active Domain Adaptation via Customized Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7651-7660} }

Learning Spatial-Temporal Implicit Neural Representations for Event-Guided Video Super-Resolution

Yunfan Lu,

Zipeng Wang,

Minjie Liu,

Hongjian Wang,

Lin Wang

[pdf] [arXiv]

[bibtex]

@InProceedings{Lu_2023_CVPR, author = {Lu, Yunfan and Wang, Zipeng and Liu, Minjie and Wang, Hongjian and Wang, Lin}, title = {Learning Spatial-Temporal Implicit Neural Representations for Event-Guided Video Super-Resolution}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1557-1567} }

Both Style and Distortion Matter: Dual-Path Unsupervised Domain Adaptation for Panoramic Semantic Segmentation

Xu Zheng,

Jinjing Zhu,

Yexin Liu,

Zidong Cao,

Chong Fu,

Lin Wang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Zheng_2023_CVPR, author = {Zheng, Xu and Zhu, Jinjing and Liu, Yexin and Cao, Zidong and Fu, Chong and Wang, Lin}, title = {Both Style and Distortion Matter: Dual-Path Unsupervised Domain Adaptation for Panoramic Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1285-1295} }

ALTO: Alternating Latent Topologies for Implicit 3D Reconstruction

Zhen Wang,

Shijie Zhou,

Jeong Joon Park,

Despoina Paschalidou,

Suya You,

Gordon Wetzstein,

Leonidas Guibas,

Achuta Kadambi

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Zhen and Zhou, Shijie and Park, Jeong Joon and Paschalidou, Despoina and You, Suya and Wetzstein, Gordon and Guibas, Leonidas and Kadambi, Achuta}, title = {ALTO: Alternating Latent Topologies for Implicit 3D Reconstruction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {259-270} }

Learning Debiased Representations via Conditional Attribute Interpolation

Yi-Kai Zhang,

Qi-Wei Wang,

De-Chuan Zhan,

Han-Jia Ye

[pdf] [supp]

[bibtex]

@InProceedings{Zhang_2023_CVPR, author = {Zhang, Yi-Kai and Wang, Qi-Wei and Zhan, De-Chuan and Ye, Han-Jia}, title = {Learning Debiased Representations via Conditional Attribute Interpolation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7599-7608} }

Modeling Inter-Class and Intra-Class Constraints in Novel Class Discovery

Wenbin Li,

Zhichen Fan,

Jing Huo,

Yang Gao

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Li_2023_CVPR, author = {Li, Wenbin and Fan, Zhichen and Huo, Jing and Gao, Yang}, title = {Modeling Inter-Class and Intra-Class Constraints in Novel Class Discovery}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3449-3458} }

Multiple Instance Learning via Iterative Self-Paced Supervised Contrastive Learning

Kangning Liu,

Weicheng Zhu,

Yiqiu Shen,

Sheng Liu,

Narges Razavian,

Krzysztof J. Geras,

Carlos Fernandez-Granda

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Liu_2023_CVPR, author = {Liu, Kangning and Zhu, Weicheng and Shen, Yiqiu and Liu, Sheng and Razavian, Narges and Geras, Krzysztof J. and Fernandez-Granda, Carlos}, title = {Multiple Instance Learning via Iterative Self-Paced Supervised Contrastive Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3355-3365} }

CrowdCLIP: Unsupervised Crowd Counting via Vision-Language Model

Dingkang Liang,

Jiahao Xie,

Zhikang Zou,

Xiaoqing Ye,

Wei Xu,

Xiang Bai

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Liang_2023_CVPR, author = {Liang, Dingkang and Xie, Jiahao and Zou, Zhikang and Ye, Xiaoqing and Xu, Wei and Bai, Xiang}, title = {CrowdCLIP: Unsupervised Crowd Counting via Vision-Language Model}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2893-2903} }

iCLIP: Bridging Image Classification and Contrastive Language-Image Pre-Training for Visual Recognition

Yixuan Wei,

Yue Cao,

Zheng Zhang,

Houwen Peng,

Zhuliang Yao,

Zhenda Xie,

Han Hu,

Baining Guo

[pdf] [supp]

[bibtex]

@InProceedings{Wei_2023_CVPR, author = {Wei, Yixuan and Cao, Yue and Zhang, Zheng and Peng, Houwen and Yao, Zhuliang and Xie, Zhenda and Hu, Han and Guo, Baining}, title = {iCLIP: Bridging Image Classification and Contrastive Language-Image Pre-Training for Visual Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2776-2786} }

RepMode: Learning to Re-Parameterize Diverse Experts for Subcellular Structure Prediction

Donghao Zhou,

Chunbin Gu,

Junde Xu,

Furui Liu,

Qiong Wang,

Guangyong Chen,

Pheng-Ann Heng

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Zhou_2023_CVPR, author = {Zhou, Donghao and Gu, Chunbin and Xu, Junde and Liu, Furui and Wang, Qiong and Chen, Guangyong and Heng, Pheng-Ann}, title = {RepMode: Learning to Re-Parameterize Diverse Experts for Subcellular Structure Prediction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3312-3322} }

Masked Motion Encoding for Self-Supervised Video Representation Learning

Xinyu Sun,

Peihao Chen,

Liangwei Chen,

Changhao Li,

Thomas H. Li,

Mingkui Tan,

Chuang Gan

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Sun_2023_CVPR, author = {Sun, Xinyu and Chen, Peihao and Chen, Liangwei and Li, Changhao and Li, Thomas H. and Tan, Mingkui and Gan, Chuang}, title = {Masked Motion Encoding 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 = {2235-2245} }

FFHQ-UV: Normalized Facial UV-Texture Dataset for 3D Face Reconstruction

Haoran Bai,

Di Kang,

Haoxian Zhang,

Jinshan Pan,

Linchao Bao

[pdf] [supp]

[bibtex]

@InProceedings{Bai_2023_CVPR, author = {Bai, Haoran and Kang, Di and Zhang, Haoxian and Pan, Jinshan and Bao, Linchao}, title = {FFHQ-UV: Normalized Facial UV-Texture Dataset for 3D Face Reconstruction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {362-371} }

SurfelNeRF: Neural Surfel Radiance Fields for Online Photorealistic Reconstruction of Indoor Scenes

Yiming Gao,

Yan-Pei Cao,

Ying Shan

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Gao_2023_CVPR, author = {Gao, Yiming and Cao, Yan-Pei and Shan, Ying}, title = {SurfelNeRF: Neural Surfel Radiance Fields for Online Photorealistic Reconstruction of Indoor Scenes}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {108-118} }

Logical Implications for Visual Question Answering Consistency

Sergio Tascon-Morales,

Pablo Márquez-Neila,

Raphael Sznitman

[pdf] [supp]

[bibtex]

@InProceedings{Tascon-Morales_2023_CVPR, author = {Tascon-Morales, Sergio and M\'arquez-Neila, Pablo and Sznitman, Raphael}, title = {Logical Implications for Visual Question Answering Consistency}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6725-6735} }

NeUDF: Leaning Neural Unsigned Distance Fields With Volume Rendering

Yu-Tao Liu,

Li Wang,

Jie Yang,

Weikai Chen,

Xiaoxu Meng,

Bo Yang,

Lin Gao

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Liu_2023_CVPR, author = {Liu, Yu-Tao and Wang, Li and Yang, Jie and Chen, Weikai and Meng, Xiaoxu and Yang, Bo and Gao, Lin}, title = {NeUDF: Leaning Neural Unsigned Distance Fields With Volume Rendering}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {237-247} }

MM-3DScene: 3D Scene Understanding by Customizing Masked Modeling With Informative-Preserved Reconstruction and Self-Distilled Consistency

Mingye Xu,

Mutian Xu,

Tong He,

Wanli Ouyang,

Yali Wang,

Xiaoguang Han,

Yu Qiao

[pdf] [supp]

[bibtex]

@InProceedings{Xu_2023_CVPR, author = {Xu, Mingye and Xu, Mutian and He, Tong and Ouyang, Wanli and Wang, Yali and Han, Xiaoguang and Qiao, Yu}, title = {MM-3DScene: 3D Scene Understanding by Customizing Masked Modeling With Informative-Preserved Reconstruction and Self-Distilled Consistency}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4380-4390} }

Plug-and-Play Diffusion Features for Text-Driven Image-to-Image Translation

Narek Tumanyan,

Michal Geyer,

Shai Bagon,

Tali Dekel

[pdf] [arXiv]

[bibtex]

@InProceedings{Tumanyan_2023_CVPR, author = {Tumanyan, Narek and Geyer, Michal and Bagon, Shai and Dekel, Tali}, title = {Plug-and-Play Diffusion Features for Text-Driven Image-to-Image Translation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1921-1930} }

Fast Contextual Scene Graph Generation With Unbiased Context Augmentation

Tianlei Jin,

Fangtai Guo,

Qiwei Meng,

Shiqiang Zhu,

Xiangming Xi,

Wen Wang,

Zonghao Mu,

Wei Song

[pdf]

[bibtex]

@InProceedings{Jin_2023_CVPR, author = {Jin, Tianlei and Guo, Fangtai and Meng, Qiwei and Zhu, Shiqiang and Xi, Xiangming and Wang, Wen and Mu, Zonghao and Song, Wei}, title = {Fast Contextual Scene Graph Generation With Unbiased Context Augmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6302-6311} }

Re-Thinking Federated Active Learning Based on Inter-Class Diversity

SangMook Kim,

Sangmin Bae,

Hwanjun Song,

Se-Young Yun

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Kim_2023_CVPR, author = {Kim, SangMook and Bae, Sangmin and Song, Hwanjun and Yun, Se-Young}, title = {Re-Thinking Federated Active Learning Based on Inter-Class Diversity}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3944-3953} }

CiaoSR: Continuous Implicit Attention-in-Attention Network for Arbitrary-Scale Image Super-Resolution

Jiezhang Cao,

Qin Wang,

Yongqin Xian,

Yawei Li,

Bingbing Ni,

Zhiming Pi,

Kai Zhang,

Yulun Zhang,

Radu Timofte,

Luc Van Gool

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Cao_2023_CVPR, author = {Cao, Jiezhang and Wang, Qin and Xian, Yongqin and Li, Yawei and Ni, Bingbing and Pi, Zhiming and Zhang, Kai and Zhang, Yulun and Timofte, Radu and Van Gool, Luc}, title = {CiaoSR: Continuous Implicit Attention-in-Attention Network for Arbitrary-Scale Image Super-Resolution}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1796-1807} }

The Best Defense Is a Good Offense: Adversarial Augmentation Against Adversarial Attacks

Iuri Frosio,

Jan Kautz

[pdf] [supp]

[bibtex]

@InProceedings{Frosio_2023_CVPR, author = {Frosio, Iuri and Kautz, Jan}, title = {The Best Defense Is a Good Offense: Adversarial Augmentation Against Adversarial Attacks}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4067-4076} }

GaitGCI: Generative Counterfactual Intervention for Gait Recognition

Huanzhang Dou,

Pengyi Zhang,

Wei Su,

Yunlong Yu,

Yining Lin,

Xi Li

[pdf] [supp]

[bibtex]

@InProceedings{Dou_2023_CVPR, author = {Dou, Huanzhang and Zhang, Pengyi and Su, Wei and Yu, Yunlong and Lin, Yining and Li, Xi}, title = {GaitGCI: Generative Counterfactual Intervention for Gait Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5578-5588} }

Constructing Deep Spiking Neural Networks From Artificial Neural Networks With Knowledge Distillation

Qi Xu,

Yaxin Li,

Jiangrong Shen,

Jian K. Liu,

Huajin Tang,

Gang Pan

[pdf] [arXiv]

[bibtex]

@InProceedings{Xu_2023_CVPR, author = {Xu, Qi and Li, Yaxin and Shen, Jiangrong and Liu, Jian K. and Tang, Huajin and Pan, Gang}, title = {Constructing Deep Spiking Neural Networks From Artificial Neural Networks With Knowledge Distillation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7886-7895} }

KERM: Knowledge Enhanced Reasoning for Vision-and-Language Navigation

Xiangyang Li,

Zihan Wang,

Jiahao Yang,

Yaowei Wang,

Shuqiang Jiang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Li_2023_CVPR, author = {Li, Xiangyang and Wang, Zihan and Yang, Jiahao and Wang, Yaowei and Jiang, Shuqiang}, title = {KERM: Knowledge Enhanced Reasoning for Vision-and-Language Navigation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2583-2592} }

Abstract Visual Reasoning: An Algebraic Approach for Solving Raven's Progressive Matrices

Jingyi Xu,

Tushar Vaidya,

Yufei Wu,

Saket Chandra,

Zhangsheng Lai,

Kai Fong Ernest Chong

[pdf] [supp]

[bibtex]

@InProceedings{Xu_2023_CVPR, author = {Xu, Jingyi and Vaidya, Tushar and Wu, Yufei and Chandra, Saket and Lai, Zhangsheng and Chong, Kai Fong Ernest}, title = {Abstract Visual Reasoning: An Algebraic Approach for Solving Raven's Progressive Matrices}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6715-6724} }

3D-Aware Conditional Image Synthesis

Kangle Deng,

Gengshan Yang,

Deva Ramanan,

Jun-Yan Zhu

[pdf] [arXiv]

[bibtex]

@InProceedings{Deng_2023_CVPR, author = {Deng, Kangle and Yang, Gengshan and Ramanan, Deva and Zhu, Jun-Yan}, title = {3D-Aware Conditional Image Synthesis}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4434-4445} }

ABCD: Arbitrary Bitwise Coefficient for De-Quantization

Woo Kyoung Han,

Byeonghun Lee,

Sang Hyun Park,

Kyong Hwan Jin

[pdf] [supp]

[bibtex]

@InProceedings{Han_2023_CVPR, author = {Han, Woo Kyoung and Lee, Byeonghun and Park, Sang Hyun and Jin, Kyong Hwan}, title = {ABCD: Arbitrary Bitwise Coefficient for De-Quantization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5876-5885} }

Event-Based Blurry Frame Interpolation Under Blind Exposure

Wenming Weng,

Yueyi Zhang,

Zhiwei Xiong

[pdf] [supp]

[bibtex]

@InProceedings{Weng_2023_CVPR, author = {Weng, Wenming and Zhang, Yueyi and Xiong, Zhiwei}, title = {Event-Based Blurry Frame Interpolation Under Blind Exposure}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1588-1598} }

Spider GAN: Leveraging Friendly Neighbors To Accelerate GAN Training

Siddarth Asokan,

Chandra Sekhar Seelamantula

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Asokan_2023_CVPR, author = {Asokan, Siddarth and Seelamantula, Chandra Sekhar}, title = {Spider GAN: Leveraging Friendly Neighbors To Accelerate GAN Training}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3883-3893} }

ScaleDet: A Scalable Multi-Dataset Object Detector

Yanbei Chen,

Manchen Wang,

Abhay Mittal,

Zhenlin Xu,

Paolo Favaro,

Joseph Tighe,

Davide Modolo

[pdf] [supp]

[bibtex]

@InProceedings{Chen_2023_CVPR, author = {Chen, Yanbei and Wang, Manchen and Mittal, Abhay and Xu, Zhenlin and Favaro, Paolo and Tighe, Joseph and Modolo, Davide}, title = {ScaleDet: A Scalable Multi-Dataset Object Detector}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7288-7297} }

Unbiased Multiple Instance Learning for Weakly Supervised Video Anomaly Detection

Hui Lv,

Zhongqi Yue,

Qianru Sun,

Bin Luo,

Zhen Cui,

Hanwang Zhang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Lv_2023_CVPR, author = {Lv, Hui and Yue, Zhongqi and Sun, Qianru and Luo, Bin and Cui, Zhen and Zhang, Hanwang}, title = {Unbiased Multiple Instance Learning for Weakly Supervised Video Anomaly Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8022-8031} }

Towards Unbiased Volume Rendering of Neural Implicit Surfaces With Geometry Priors

Yongqiang Zhang,

Zhipeng Hu,

Haoqian Wu,

Minda Zhao,

Lincheng Li,

Zhengxia Zou,

Changjie Fan

[pdf] [supp]

[bibtex]

@InProceedings{Zhang_2023_CVPR, author = {Zhang, Yongqiang and Hu, Zhipeng and Wu, Haoqian and Zhao, Minda and Li, Lincheng and Zou, Zhengxia and Fan, Changjie}, title = {Towards Unbiased Volume Rendering of Neural Implicit Surfaces With Geometry Priors}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4359-4368} }

Neuro-Modulated Hebbian Learning for Fully Test-Time Adaptation

Yushun Tang,

Ce Zhang,

Heng Xu,

Shuoshuo Chen,

Jie Cheng,

Luziwei Leng,

Qinghai Guo,

Zhihai He

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Tang_2023_CVPR, author = {Tang, Yushun and Zhang, Ce and Xu, Heng and Chen, Shuoshuo and Cheng, Jie and Leng, Luziwei and Guo, Qinghai and He, Zhihai}, title = {Neuro-Modulated Hebbian Learning for Fully Test-Time Adaptation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3728-3738} }

Implicit Identity Leakage: The Stumbling Block to Improving Deepfake Detection Generalization

Shichao Dong,

Jin Wang,

Renhe Ji,

Jiajun Liang,

Haoqiang Fan,

Zheng Ge

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Dong_2023_CVPR, author = {Dong, Shichao and Wang, Jin and Ji, Renhe and Liang, Jiajun and Fan, Haoqiang and Ge, Zheng}, title = {Implicit Identity Leakage: The Stumbling Block to Improving Deepfake Detection Generalization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3994-4004} }

Learning Federated Visual Prompt in Null Space for MRI Reconstruction

Chun-Mei Feng,

Bangjun Li,

Xinxing Xu,

Yong Liu,

Huazhu Fu,

Wangmeng Zuo

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Feng_2023_CVPR, author = {Feng, Chun-Mei and Li, Bangjun and Xu, Xinxing and Liu, Yong and Fu, Huazhu and Zuo, Wangmeng}, title = {Learning Federated Visual Prompt in Null Space for MRI Reconstruction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8064-8073} }

Data-Driven Feature Tracking for Event Cameras

Nico Messikommer,

Carter Fang,

Mathias Gehrig,

Davide Scaramuzza

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Messikommer_2023_CVPR, author = {Messikommer, Nico and Fang, Carter and Gehrig, Mathias and Scaramuzza, Davide}, title = {Data-Driven Feature Tracking for Event Cameras}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5642-5651} }

Temporal Consistent 3D LiDAR Representation Learning for Semantic Perception in Autonomous Driving

Lucas Nunes,

Louis Wiesmann,

Rodrigo Marcuzzi,

Xieyuanli Chen,

Jens Behley,

Cyrill Stachniss

[pdf] [supp]

[bibtex]

@InProceedings{Nunes_2023_CVPR, author = {Nunes, Lucas and Wiesmann, Louis and Marcuzzi, Rodrigo and Chen, Xieyuanli and Behley, Jens and Stachniss, Cyrill}, title = {Temporal Consistent 3D LiDAR Representation Learning for Semantic Perception in Autonomous Driving}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5217-5228} }

DiffTalk: Crafting Diffusion Models for Generalized Audio-Driven Portraits Animation

Shuai Shen,

Wenliang Zhao,

Zibin Meng,

Wanhua Li,

Zheng Zhu,

Jie Zhou,

Jiwen Lu

[pdf] [arXiv]

[bibtex]

@InProceedings{Shen_2023_CVPR, author = {Shen, Shuai and Zhao, Wenliang and Meng, Zibin and Li, Wanhua and Zhu, Zheng and Zhou, Jie and Lu, Jiwen}, title = {DiffTalk: Crafting Diffusion Models for Generalized Audio-Driven Portraits Animation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1982-1991} }

Visual Query Tuning: Towards Effective Usage of Intermediate Representations for Parameter and Memory Efficient Transfer Learning

Cheng-Hao Tu,

Zheda Mai,

Wei-Lun Chao

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Tu_2023_CVPR, author = {Tu, Cheng-Hao and Mai, Zheda and Chao, Wei-Lun}, title = {Visual Query Tuning: Towards Effective Usage of Intermediate Representations for Parameter and Memory Efficient Transfer Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7725-7735} }

Compressing Volumetric Radiance Fields to 1 MB

Lingzhi Li,

Zhen Shen,

Zhongshu Wang,

Li Shen,

Liefeng Bo

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Li_2023_CVPR, author = {Li, Lingzhi and Shen, Zhen and Wang, Zhongshu and Shen, Li and Bo, Liefeng}, title = {Compressing Volumetric Radiance Fields to 1 MB}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4222-4231} }

Label Information Bottleneck for Label Enhancement

Qinghai Zheng,

Jihua Zhu,

Haoyu Tang

[pdf] [arXiv]

[bibtex]

@InProceedings{Zheng_2023_CVPR, author = {Zheng, Qinghai and Zhu, Jihua and Tang, Haoyu}, title = {Label Information Bottleneck for Label Enhancement}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7497-7506} }

Multi-Modal Representation Learning With Text-Driven Soft Masks

Jaeyoo Park,

Bohyung Han

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Park_2023_CVPR, author = {Park, Jaeyoo and Han, Bohyung}, title = {Multi-Modal Representation Learning With Text-Driven Soft Masks}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2798-2807} }

Gazeformer: Scalable, Effective and Fast Prediction of Goal-Directed Human Attention

Sounak Mondal,

Zhibo Yang,

Seoyoung Ahn,

Dimitris Samaras,

Gregory Zelinsky,

Minh Hoai

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Mondal_2023_CVPR, author = {Mondal, Sounak and Yang, Zhibo and Ahn, Seoyoung and Samaras, Dimitris and Zelinsky, Gregory and Hoai, Minh}, title = {Gazeformer: Scalable, Effective and Fast Prediction of Goal-Directed Human Attention}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1441-1450} }

Rethinking the Correlation in Few-Shot Segmentation: A Buoys View

Yuan Wang,

Rui Sun,

Tianzhu Zhang

[pdf] [supp]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Yuan and Sun, Rui and Zhang, Tianzhu}, title = {Rethinking the Correlation in Few-Shot Segmentation: A Buoys View}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7183-7192} }

DiffRF: Rendering-Guided 3D Radiance Field Diffusion

Norman Müller,

Yawar Siddiqui,

Lorenzo Porzi,

Samuel Rota Bulò,

Peter Kontschieder,

Matthias Nießner

[pdf] [supp]

[bibtex]

@InProceedings{Muller_2023_CVPR, author = {M\"uller, Norman and Siddiqui, Yawar and Porzi, Lorenzo and Bul\`o, Samuel Rota and Kontschieder, Peter and Nie{\ss}ner, Matthias}, title = {DiffRF: Rendering-Guided 3D Radiance Field Diffusion}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4328-4338} }

Parts2Words: Learning Joint Embedding of Point Clouds and Texts by Bidirectional Matching Between Parts and Words

Chuan Tang,

Xi Yang,

Bojian Wu,

Zhizhong Han,

Yi Chang

[pdf] [arXiv]

[bibtex]

@InProceedings{Tang_2023_CVPR, author = {Tang, Chuan and Yang, Xi and Wu, Bojian and Han, Zhizhong and Chang, Yi}, title = {Parts2Words: Learning Joint Embedding of Point Clouds and Texts by Bidirectional Matching Between Parts and Words}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6884-6893} }

Proposal-Based Multiple Instance Learning for Weakly-Supervised Temporal Action Localization

Huan Ren,

Wenfei Yang,

Tianzhu Zhang,

Yongdong Zhang

[pdf]

[bibtex]

@InProceedings{Ren_2023_CVPR, author = {Ren, Huan and Yang, Wenfei and Zhang, Tianzhu and Zhang, Yongdong}, title = {Proposal-Based Multiple Instance Learning for Weakly-Supervised Temporal Action Localization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2394-2404} }

ASPnet: Action Segmentation With Shared-Private Representation of Multiple Data Sources

Beatrice van Amsterdam,

Abdolrahim Kadkhodamohammadi,

Imanol Luengo,

Danail Stoyanov

[pdf]

[bibtex]

@InProceedings{van_Amsterdam_2023_CVPR, author = {van Amsterdam, Beatrice and Kadkhodamohammadi, Abdolrahim and Luengo, Imanol and Stoyanov, Danail}, title = {ASPnet: Action Segmentation With Shared-Private Representation of Multiple Data Sources}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2384-2393} }

Ingredient-Oriented Multi-Degradation Learning for Image Restoration

Jinghao Zhang,

Jie Huang,

Mingde Yao,

Zizheng Yang,

Hu Yu,

Man Zhou,

Feng Zhao

[pdf] [supp]

[bibtex]

@InProceedings{Zhang_2023_CVPR, author = {Zhang, Jinghao and Huang, Jie and Yao, Mingde and Yang, Zizheng and Yu, Hu and Zhou, Man and Zhao, Feng}, title = {Ingredient-Oriented Multi-Degradation Learning for Image Restoration}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5825-5835} }

How Can Objects Help Action Recognition?

Xingyi Zhou,

Anurag Arnab,

Chen Sun,

Cordelia Schmid

[pdf]

[bibtex]

@InProceedings{Zhou_2023_CVPR, author = {Zhou, Xingyi and Arnab, Anurag and Sun, Chen and Schmid, Cordelia}, title = {How Can Objects Help Action Recognition?}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2353-2362} }

Realistic Saliency Guided Image Enhancement

S. Mahdi H. Miangoleh,

Zoya Bylinskii,

Eric Kee,

Eli Shechtman,

Yağiz Aksoy

[pdf] [supp]

[bibtex]

@InProceedings{Miangoleh_2023_CVPR, author = {Miangoleh, S. Mahdi H. and Bylinskii, Zoya and Kee, Eric and Shechtman, Eli and Aksoy, Ya\u{g}iz}, title = {Realistic Saliency Guided Image Enhancement}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {186-194} }

SLOPER4D: A Scene-Aware Dataset for Global 4D Human Pose Estimation in Urban Environments

Yudi Dai,

Yitai Lin,

Xiping Lin,

Chenglu Wen,

Lan Xu,

Hongwei Yi,

Siqi Shen,

Yuexin Ma,

Cheng Wang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Dai_2023_CVPR, author = {Dai, Yudi and Lin, Yitai and Lin, Xiping and Wen, Chenglu and Xu, Lan and Yi, Hongwei and Shen, Siqi and Ma, Yuexin and Wang, Cheng}, title = {SLOPER4D: A Scene-Aware Dataset for Global 4D Human Pose Estimation in Urban Environments}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {682-692} }

Mask-Guided Matting in the Wild

Kwanyong Park,

Sanghyun Woo,

Seoung Wug Oh,

In So Kweon,

Joon-Young Lee

[pdf] [supp]

[bibtex]

@InProceedings{Park_2023_CVPR, author = {Park, Kwanyong and Woo, Sanghyun and Oh, Seoung Wug and Kweon, In So and Lee, Joon-Young}, title = {Mask-Guided Matting in the Wild}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1992-2001} }

Dynamic Conceptional Contrastive Learning for Generalized Category Discovery

Nan Pu,

Zhun Zhong,

Nicu Sebe

[pdf] [arXiv]

[bibtex]

@InProceedings{Pu_2023_CVPR, author = {Pu, Nan and Zhong, Zhun and Sebe, Nicu}, title = {Dynamic Conceptional Contrastive Learning for Generalized Category Discovery}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7579-7588} }

Neumann Network With Recursive Kernels for Single Image Defocus Deblurring

Yuhui Quan,

Zicong Wu,

Hui Ji

[pdf] [supp]

[bibtex]

@InProceedings{Quan_2023_CVPR, author = {Quan, Yuhui and Wu, Zicong and Ji, Hui}, title = {Neumann Network With Recursive Kernels for Single Image Defocus Deblurring}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5754-5763} }

Guided Recommendation for Model Fine-Tuning

Hao Li,

Charless Fowlkes,

Hao Yang,

Onkar Dabeer,

Zhuowen Tu,

Stefano Soatto

[pdf] [supp]

[bibtex]

@InProceedings{Li_2023_CVPR, author = {Li, Hao and Fowlkes, Charless and Yang, Hao and Dabeer, Onkar and Tu, Zhuowen and Soatto, Stefano}, title = {Guided Recommendation for Model Fine-Tuning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3633-3642} }

Masked Image Training for Generalizable Deep Image Denoising

Haoyu Chen,

Jinjin Gu,

Yihao Liu,

Salma Abdel Magid,

Chao Dong,

Qiong Wang,

Hanspeter Pfister,

Lei Zhu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Chen_2023_CVPR, author = {Chen, Haoyu and Gu, Jinjin and Liu, Yihao and Magid, Salma Abdel and Dong, Chao and Wang, Qiong and Pfister, Hanspeter and Zhu, Lei}, title = {Masked Image Training for Generalizable Deep Image Denoising}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1692-1703} }

DeAR: Debiasing Vision-Language Models With Additive Residuals

Ashish Seth,

Mayur Hemani,

Chirag Agarwal

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Seth_2023_CVPR, author = {Seth, Ashish and Hemani, Mayur and Agarwal, Chirag}, title = {DeAR: Debiasing Vision-Language Models With Additive Residuals}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6820-6829} }

E2PN: Efficient SE(3)-Equivariant Point Network

Minghan Zhu,

Maani Ghaffari,

William A. Clark,

Huei Peng

[pdf] [supp]

[bibtex]

@InProceedings{Zhu_2023_CVPR, author = {Zhu, Minghan and Ghaffari, Maani and Clark, William A. and Peng, Huei}, title = {E2PN: Efficient SE(3)-Equivariant Point Network}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1223-1232} }

Understanding Masked Image Modeling via Learning Occlusion Invariant Feature

Xiangwen Kong,

Xiangyu Zhang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Kong_2023_CVPR, author = {Kong, Xiangwen and Zhang, Xiangyu}, title = {Understanding Masked Image Modeling via Learning Occlusion Invariant Feature}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6241-6251} }

A Dynamic Multi-Scale Voxel Flow Network for Video Prediction

Xiaotao Hu,

Zhewei Huang,

Ailin Huang,

Jun Xu,

Shuchang Zhou

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Hu_2023_CVPR, author = {Hu, Xiaotao and Huang, Zhewei and Huang, Ailin and Xu, Jun and Zhou, Shuchang}, title = {A Dynamic Multi-Scale Voxel Flow Network for Video Prediction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6121-6131} }

UniDistill: A Universal Cross-Modality Knowledge Distillation Framework for 3D Object Detection in Bird's-Eye View

Shengchao Zhou,

Weizhou Liu,

Chen Hu,

Shuchang Zhou,

Chao Ma

[pdf] [supp]

[bibtex]

@InProceedings{Zhou_2023_CVPR, author = {Zhou, Shengchao and Liu, Weizhou and Hu, Chen and Zhou, Shuchang and Ma, Chao}, title = {UniDistill: A Universal Cross-Modality Knowledge Distillation Framework for 3D Object Detection in Bird's-Eye View}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5116-5125} }

Fine-Tuned CLIP Models Are Efficient Video Learners

Hanoona Rasheed,

Muhammad Uzair Khattak,

Muhammad Maaz,

Salman Khan,

Fahad Shahbaz Khan

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Rasheed_2023_CVPR, author = {Rasheed, Hanoona and Khattak, Muhammad Uzair and Maaz, Muhammad and Khan, Salman and Khan, Fahad Shahbaz}, title = {Fine-Tuned CLIP Models Are Efficient Video Learners}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6545-6554} }

Collaborative Diffusion for Multi-Modal Face Generation and Editing

Ziqi Huang,

Kelvin C.K. Chan,

Yuming Jiang,

Ziwei Liu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Huang_2023_CVPR, author = {Huang, Ziqi and Chan, Kelvin C.K. and Jiang, Yuming and Liu, Ziwei}, title = {Collaborative Diffusion for Multi-Modal Face Generation and Editing}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6080-6090} }

MACARONS: Mapping and Coverage Anticipation With RGB Online Self-Supervision

Antoine Guédon,

Tom Monnier,

Pascal Monasse,

Vincent Lepetit

[pdf] [supp]

[bibtex]

@InProceedings{Guedon_2023_CVPR, author = {Gu\'edon, Antoine and Monnier, Tom and Monasse, Pascal and Lepetit, Vincent}, title = {MACARONS: Mapping and Coverage Anticipation With RGB Online Self-Supervision}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {940-951} }

Tracking Multiple Deformable Objects in Egocentric Videos

Mingzhen Huang,

Xiaoxing Li,

Jun Hu,

Honghong Peng,

Siwei Lyu

[pdf]

[bibtex]

@InProceedings{Huang_2023_CVPR, author = {Huang, Mingzhen and Li, Xiaoxing and Hu, Jun and Peng, Honghong and Lyu, Siwei}, title = {Tracking Multiple Deformable Objects in Egocentric Videos}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1461-1471} }

REC-MV: REconstructing 3D Dynamic Cloth From Monocular Videos

Lingteng Qiu,

Guanying Chen,

Jiapeng Zhou,

Mutian Xu,

Junle Wang,

Xiaoguang Han

[pdf] [supp]

[bibtex]

@InProceedings{Qiu_2023_CVPR, author = {Qiu, Lingteng and Chen, Guanying and Zhou, Jiapeng and Xu, Mutian and Wang, Junle and Han, Xiaoguang}, title = {REC-MV: REconstructing 3D Dynamic Cloth From Monocular Videos}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4637-4646} }

JRDB-Pose: A Large-Scale Dataset for Multi-Person Pose Estimation and Tracking

Edward Vendrow,

Duy Tho Le,

Jianfei Cai,

Hamid Rezatofighi

[pdf] [supp]

[bibtex]

@InProceedings{Vendrow_2023_CVPR, author = {Vendrow, Edward and Le, Duy Tho and Cai, Jianfei and Rezatofighi, Hamid}, title = {JRDB-Pose: A Large-Scale Dataset for Multi-Person Pose Estimation and Tracking}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4811-4820} }

AsyFOD: An Asymmetric Adaptation Paradigm for Few-Shot Domain Adaptive Object Detection

Yipeng Gao,

Kun-Yu Lin,

Junkai Yan,

Yaowei Wang,

Wei-Shi Zheng

[pdf]

[bibtex]

@InProceedings{Gao_2023_CVPR, author = {Gao, Yipeng and Lin, Kun-Yu and Yan, Junkai and Wang, Yaowei and Zheng, Wei-Shi}, title = {AsyFOD: An Asymmetric Adaptation Paradigm for Few-Shot Domain Adaptive Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3261-3271} }

Federated Learning With Data-Agnostic Distribution Fusion

Jian-hui Duan,

Wenzhong Li,

Derun Zou,

Ruichen Li,

Sanglu Lu

[pdf] [supp]

[bibtex]

@InProceedings{Duan_2023_CVPR, author = {Duan, Jian-hui and Li, Wenzhong and Zou, Derun and Li, Ruichen and Lu, Sanglu}, title = {Federated Learning With Data-Agnostic Distribution Fusion}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8074-8083} }

Improving Commonsense in Vision-Language Models via Knowledge Graph Riddles

Shuquan Ye,

Yujia Xie,

Dongdong Chen,

Yichong Xu,

Lu Yuan,

Chenguang Zhu,

Jing Liao

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Ye_2023_CVPR, author = {Ye, Shuquan and Xie, Yujia and Chen, Dongdong and Xu, Yichong and Yuan, Lu and Zhu, Chenguang and Liao, Jing}, title = {Improving Commonsense in Vision-Language Models via Knowledge Graph Riddles}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2634-2645} }

S3C: Semi-Supervised VQA Natural Language Explanation via Self-Critical Learning

Wei Suo,

Mengyang Sun,

Weisong Liu,

Yiqi Gao,

Peng Wang,

Yanning Zhang,

Qi Wu

[pdf]

[bibtex]

@InProceedings{Suo_2023_CVPR, author = {Suo, Wei and Sun, Mengyang and Liu, Weisong and Gao, Yiqi and Wang, Peng and Zhang, Yanning and Wu, Qi}, title = {S3C: Semi-Supervised VQA Natural Language Explanation via Self-Critical Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2646-2656} }

Spatio-Focal Bidirectional Disparity Estimation From a Dual-Pixel Image

Donggun Kim,

Hyeonjoong Jang,

Inchul Kim,

Min H. Kim

[pdf] [supp]

[bibtex]

@InProceedings{Kim_2023_CVPR, author = {Kim, Donggun and Jang, Hyeonjoong and Kim, Inchul and Kim, Min H.}, title = {Spatio-Focal Bidirectional Disparity Estimation From a Dual-Pixel Image}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5023-5032} }

Rethinking Optical Flow From Geometric Matching Consistent Perspective

Qiaole Dong,

Chenjie Cao,

Yanwei Fu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Dong_2023_CVPR, author = {Dong, Qiaole and Cao, Chenjie and Fu, Yanwei}, title = {Rethinking Optical Flow From Geometric Matching Consistent Perspective}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1337-1347} }

Learning Optical Expansion From Scale Matching

Han Ling,

Yinghui Sun,

Quansen Sun,

Zhenwen Ren

[pdf] [supp]

[bibtex]

@InProceedings{Ling_2023_CVPR, author = {Ling, Han and Sun, Yinghui and Sun, Quansen and Ren, Zhenwen}, title = {Learning Optical Expansion From Scale Matching}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5445-5454} }

TopDiG: Class-Agnostic Topological Directional Graph Extraction From Remote Sensing Images

Bingnan Yang,

Mi Zhang,

Zhan Zhang,

Zhili Zhang,

Xiangyun Hu

[pdf] [supp]

[bibtex]

@InProceedings{Yang_2023_CVPR, author = {Yang, Bingnan and Zhang, Mi and Zhang, Zhan and Zhang, Zhili and Hu, Xiangyun}, title = {TopDiG: Class-Agnostic Topological Directional Graph Extraction From Remote Sensing Images}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1265-1274} }

StyleIPSB: Identity-Preserving Semantic Basis of StyleGAN for High Fidelity Face Swapping

Diqiong Jiang,

Dan Song,

Ruofeng Tong,

Min Tang

[pdf] [supp]

[bibtex]

@InProceedings{Jiang_2023_CVPR, author = {Jiang, Diqiong and Song, Dan and Tong, Ruofeng and Tang, Min}, title = {StyleIPSB: Identity-Preserving Semantic Basis of StyleGAN for High Fidelity Face Swapping}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {352-361} }

Unknown Sniffer for Object Detection: Don't Turn a Blind Eye to Unknown Objects

Wenteng Liang,

Feng Xue,

Yihao Liu,

Guofeng Zhong,

Anlong Ming

[pdf] [supp]

[bibtex]

@InProceedings{Liang_2023_CVPR, author = {Liang, Wenteng and Xue, Feng and Liu, Yihao and Zhong, Guofeng and Ming, Anlong}, title = {Unknown Sniffer for Object Detection: Don't Turn a Blind Eye to Unknown Objects}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3230-3239} }

Multi-Concept Customization of Text-to-Image Diffusion

Nupur Kumari,

Bingliang Zhang,

Richard Zhang,

Eli Shechtman,

Jun-Yan Zhu

[pdf] [arXiv]

[bibtex]

@InProceedings{Kumari_2023_CVPR, author = {Kumari, Nupur and Zhang, Bingliang and Zhang, Richard and Shechtman, Eli and Zhu, Jun-Yan}, title = {Multi-Concept Customization of Text-to-Image Diffusion}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1931-1941} }

LinK: Linear Kernel for LiDAR-Based 3D Perception

Tao Lu,

Xiang Ding,

Haisong Liu,

Gangshan Wu,

Limin Wang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Lu_2023_CVPR, author = {Lu, Tao and Ding, Xiang and Liu, Haisong and Wu, Gangshan and Wang, Limin}, title = {LinK: Linear Kernel for LiDAR-Based 3D Perception}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1105-1115} }

CP3: Channel Pruning Plug-In for Point-Based Networks

Yaomin Huang,

Ning Liu,

Zhengping Che,

Zhiyuan Xu,

Chaomin Shen,

Yaxin Peng,

Guixu Zhang,

Xinmei Liu,

Feifei Feng,

Jian Tang

[pdf] [supp]

[bibtex]

@InProceedings{Huang_2023_CVPR, author = {Huang, Yaomin and Liu, Ning and Che, Zhengping and Xu, Zhiyuan and Shen, Chaomin and Peng, Yaxin and Zhang, Guixu and Liu, Xinmei and Feng, Feifei and Tang, Jian}, title = {CP3: Channel Pruning Plug-In for Point-Based Networks}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5302-5312} }

Two-Way Multi-Label Loss

Takumi Kobayashi

[pdf] [supp]

[bibtex]

@InProceedings{Kobayashi_2023_CVPR, author = {Kobayashi, Takumi}, title = {Two-Way Multi-Label Loss}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7476-7485} }

Where Is My Wallet? Modeling Object Proposal Sets for Egocentric Visual Query Localization

Mengmeng Xu,

Yanghao Li,

Cheng-Yang Fu,

Bernard Ghanem,

Tao Xiang,

Juan-Manuel Pérez-Rúa

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Xu_2023_CVPR, author = {Xu, Mengmeng and Li, Yanghao and Fu, Cheng-Yang and Ghanem, Bernard and Xiang, Tao and P\'erez-R\'ua, Juan-Manuel}, title = {Where Is My Wallet? Modeling Object Proposal Sets for Egocentric Visual Query Localization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2593-2603} }

ReDirTrans: Latent-to-Latent Translation for Gaze and Head Redirection

Shiwei Jin,

Zhen Wang,

Lei Wang,

Ning Bi,

Truong Nguyen

[pdf] [supp]

[bibtex]

@InProceedings{Jin_2023_CVPR, author = {Jin, Shiwei and Wang, Zhen and Wang, Lei and Bi, Ning and Nguyen, Truong}, title = {ReDirTrans: Latent-to-Latent Translation for Gaze and Head Redirection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5547-5556} }

Noisy Correspondence Learning With Meta Similarity Correction

Haochen Han,

Kaiyao Miao,

Qinghua Zheng,

Minnan Luo

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Han_2023_CVPR, author = {Han, Haochen and Miao, Kaiyao and Zheng, Qinghua and Luo, Minnan}, title = {Noisy Correspondence Learning With Meta Similarity Correction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7517-7526} }

Rethinking Video ViTs: Sparse Video Tubes for Joint Image and Video Learning

AJ Piergiovanni,

Weicheng Kuo,

Anelia Angelova

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Piergiovanni_2023_CVPR, author = {Piergiovanni, AJ and Kuo, Weicheng and Angelova, Anelia}, title = {Rethinking Video ViTs: Sparse Video Tubes for Joint Image and Video Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2214-2224} }

Unsupervised Continual Semantic Adaptation Through Neural Rendering

Zhizheng Liu,

Francesco Milano,

Jonas Frey,

Roland Siegwart,

Hermann Blum,

Cesar Cadena

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Liu_2023_CVPR, author = {Liu, Zhizheng and Milano, Francesco and Frey, Jonas and Siegwart, Roland and Blum, Hermann and Cadena, Cesar}, title = {Unsupervised Continual Semantic Adaptation Through Neural Rendering}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3031-3040} }

Multi-View Adversarial Discriminator: Mine the Non-Causal Factors for Object Detection in Unseen Domains

Mingjun Xu,

Lingyun Qin,

Weijie Chen,

Shiliang Pu,

Lei Zhang

[pdf] [arXiv]

[bibtex]

@InProceedings{Xu_2023_CVPR, author = {Xu, Mingjun and Qin, Lingyun and Chen, Weijie and Pu, Shiliang and Zhang, Lei}, title = {Multi-View Adversarial Discriminator: Mine the Non-Causal Factors for Object Detection in Unseen Domains}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8103-8112} }

Instance Relation Graph Guided Source-Free Domain Adaptive Object Detection

Vibashan VS,

Poojan Oza,

Vishal M. Patel

[pdf] [arXiv]

[bibtex]

@InProceedings{VS_2023_CVPR, author = {VS, Vibashan and Oza, Poojan and Patel, Vishal M.}, title = {Instance Relation Graph Guided Source-Free Domain Adaptive Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3520-3530} }

Instant Multi-View Head Capture Through Learnable Registration

Timo Bolkart,

Tianye Li,

Michael J. Black

[pdf] [supp]

[bibtex]

@InProceedings{Bolkart_2023_CVPR, author = {Bolkart, Timo and Li, Tianye and Black, Michael J.}, title = {Instant Multi-View Head Capture Through Learnable Registration}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {768-779} }

GINA-3D: Learning To Generate Implicit Neural Assets in the Wild

Bokui Shen,

Xinchen Yan,

Charles R. Qi,

Mahyar Najibi,

Boyang Deng,

Leonidas Guibas,

Yin Zhou,

Dragomir Anguelov

[pdf] [supp]

[bibtex]

@InProceedings{Shen_2023_CVPR, author = {Shen, Bokui and Yan, Xinchen and Qi, Charles R. and Najibi, Mahyar and Deng, Boyang and Guibas, Leonidas and Zhou, Yin and Anguelov, Dragomir}, title = {GINA-3D: Learning To Generate Implicit Neural Assets in the Wild}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4913-4926} }

Consistent Direct Time-of-Flight Video Depth Super-Resolution

Zhanghao Sun,

Wei Ye,

Jinhui Xiong,

Gyeongmin Choe,

Jialiang Wang,

Shuochen Su,

Rakesh Ranjan

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Sun_2023_CVPR, author = {Sun, Zhanghao and Ye, Wei and Xiong, Jinhui and Choe, Gyeongmin and Wang, Jialiang and Su, Shuochen and Ranjan, Rakesh}, title = {Consistent Direct Time-of-Flight Video Depth Super-Resolution}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5075-5085} }

Crossing the Gap: Domain Generalization for Image Captioning

Yuchen Ren,

Zhendong Mao,

Shancheng Fang,

Yan Lu,

Tong He,

Hao Du,

Yongdong Zhang,

Wanli Ouyang

[pdf] [supp]

[bibtex]

@InProceedings{Ren_2023_CVPR, author = {Ren, Yuchen and Mao, Zhendong and Fang, Shancheng and Lu, Yan and He, Tong and Du, Hao and Zhang, Yongdong and Ouyang, Wanli}, title = {Crossing the Gap: Domain Generalization for Image Captioning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2871-2880} }

Probabilistic Prompt Learning for Dense Prediction

Hyeongjun Kwon,

Taeyong Song,

Somi Jeong,

Jin Kim,

Jinhyun Jang,

Kwanghoon Sohn

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Kwon_2023_CVPR, author = {Kwon, Hyeongjun and Song, Taeyong and Jeong, Somi and Kim, Jin and Jang, Jinhyun and Sohn, Kwanghoon}, title = {Probabilistic Prompt Learning for Dense Prediction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6768-6777} }

Exploring Intra-Class Variation Factors With Learnable Cluster Prompts for Semi-Supervised Image Synthesis

Yunfei Zhang,

Xiaoyang Huo,

Tianyi Chen,

Si Wu,

Hau San Wong

[pdf]

[bibtex]

@InProceedings{Zhang_2023_CVPR, author = {Zhang, Yunfei and Huo, Xiaoyang and Chen, Tianyi and Wu, Si and Wong, Hau San}, title = {Exploring Intra-Class Variation Factors With Learnable Cluster Prompts for Semi-Supervised Image Synthesis}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7392-7401} }

NeAT: Learning Neural Implicit Surfaces With Arbitrary Topologies From Multi-View Images

Xiaoxu Meng,

Weikai Chen,

Bo Yang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Meng_2023_CVPR, author = {Meng, Xiaoxu and Chen, Weikai and Yang, Bo}, title = {NeAT: Learning Neural Implicit Surfaces With Arbitrary Topologies From Multi-View Images}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {248-258} }

SPARF: Neural Radiance Fields From Sparse and Noisy Poses

Prune Truong,

Marie-Julie Rakotosaona,

Fabian Manhardt,

Federico Tombari

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Truong_2023_CVPR, author = {Truong, Prune and Rakotosaona, Marie-Julie and Manhardt, Fabian and Tombari, Federico}, title = {SPARF: Neural Radiance Fields From Sparse and Noisy Poses}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4190-4200} }

Local Implicit Normalizing Flow for Arbitrary-Scale Image Super-Resolution

Jie-En Yao,

Li-Yuan Tsao,

Yi-Chen Lo,

Roy Tseng,

Chia-Che Chang,

Chun-Yi Lee

[pdf] [arXiv]

[bibtex]

@InProceedings{Yao_2023_CVPR, author = {Yao, Jie-En and Tsao, Li-Yuan and Lo, Yi-Chen and Tseng, Roy and Chang, Chia-Che and Lee, Chun-Yi}, title = {Local Implicit Normalizing Flow for Arbitrary-Scale Image Super-Resolution}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1776-1785} }

Texts as Images in Prompt Tuning for Multi-Label Image Recognition

Zixian Guo,

Bowen Dong,

Zhilong Ji,

Jinfeng Bai,

Yiwen Guo,

Wangmeng Zuo

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Guo_2023_CVPR, author = {Guo, Zixian and Dong, Bowen and Ji, Zhilong and Bai, Jinfeng and Guo, Yiwen and Zuo, Wangmeng}, title = {Texts as Images in Prompt Tuning for Multi-Label Image Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2808-2817} }

Self-Correctable and Adaptable Inference for Generalizable Human Pose Estimation

Zhehan Kan,

Shuoshuo Chen,

Ce Zhang,

Yushun Tang,

Zhihai He

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Kan_2023_CVPR, author = {Kan, Zhehan and Chen, Shuoshuo and Zhang, Ce and Tang, Yushun and He, Zhihai}, title = {Self-Correctable and Adaptable Inference for Generalizable Human Pose Estimation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5537-5546} }

GradMA: A Gradient-Memory-Based Accelerated Federated Learning With Alleviated Catastrophic Forgetting

Kangyang Luo,

Xiang Li,

Yunshi Lan,

Ming Gao

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Luo_2023_CVPR, author = {Luo, Kangyang and Li, Xiang and Lan, Yunshi and Gao, Ming}, title = {GradMA: A Gradient-Memory-Based Accelerated Federated Learning With Alleviated Catastrophic Forgetting}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3708-3717} }

POTTER: Pooling Attention Transformer for Efficient Human Mesh Recovery

Ce Zheng,

Xianpeng Liu,

Guo-Jun Qi,

Chen Chen

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Zheng_2023_CVPR, author = {Zheng, Ce and Liu, Xianpeng and Qi, Guo-Jun and Chen, Chen}, title = {POTTER: Pooling Attention Transformer for Efficient Human Mesh Recovery}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1611-1620} }

Learning Detailed Radiance Manifolds for High-Fidelity and 3D-Consistent Portrait Synthesis From Monocular Image

Yu Deng,

Baoyuan Wang,

Heung-Yeung Shum

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Deng_2023_CVPR, author = {Deng, Yu and Wang, Baoyuan and Shum, Heung-Yeung}, title = {Learning Detailed Radiance Manifolds for High-Fidelity and 3D-Consistent Portrait Synthesis From Monocular Image}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4423-4433} }

Patch-Craft Self-Supervised Training for Correlated Image Denoising

Gregory Vaksman,

Michael Elad

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Vaksman_2023_CVPR, author = {Vaksman, Gregory and Elad, Michael}, title = {Patch-Craft Self-Supervised Training for Correlated Image Denoising}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5795-5804} }

DistilPose: Tokenized Pose Regression With Heatmap Distillation

Suhang Ye,

Yingyi Zhang,

Jie Hu,

Liujuan Cao,

Shengchuan Zhang,

Lei Shen,

Jun Wang,

Shouhong Ding,

Rongrong Ji

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Ye_2023_CVPR, author = {Ye, Suhang and Zhang, Yingyi and Hu, Jie and Cao, Liujuan and Zhang, Shengchuan and Shen, Lei and Wang, Jun and Ding, Shouhong and Ji, Rongrong}, title = {DistilPose: Tokenized Pose Regression With Heatmap Distillation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2163-2172} }

Neural Volumetric Memory for Visual Locomotion Control

Ruihan Yang,

Ge Yang,

Xiaolong Wang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Yang_2023_CVPR, author = {Yang, Ruihan and Yang, Ge and Wang, Xiaolong}, title = {Neural Volumetric Memory for Visual Locomotion Control}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1430-1440} }

Propagate and Calibrate: Real-Time Passive Non-Line-of-Sight Tracking

Yihao Wang,

Zhigang Wang,

Bin Zhao,

Dong Wang,

Mulin Chen,

Xuelong Li

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Yihao and Wang, Zhigang and Zhao, Bin and Wang, Dong and Chen, Mulin and Li, Xuelong}, title = {Propagate and Calibrate: Real-Time Passive Non-Line-of-Sight Tracking}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {972-981} }

Learning Decorrelated Representations Efficiently Using Fast Fourier Transform

Yutaro Shigeto,

Masashi Shimbo,

Yuya Yoshikawa,

Akikazu Takeuchi

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Shigeto_2023_CVPR, author = {Shigeto, Yutaro and Shimbo, Masashi and Yoshikawa, Yuya and Takeuchi, Akikazu}, title = {Learning Decorrelated Representations Efficiently Using Fast Fourier Transform}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2052-2060} }

Two-Shot Video Object Segmentation

Kun Yan,

Xiao Li,

Fangyun Wei,

Jinglu Wang,

Chenbin Zhang,

Ping Wang,

Yan Lu

[pdf] [arXiv]

[bibtex]

@InProceedings{Yan_2023_CVPR, author = {Yan, Kun and Li, Xiao and Wei, Fangyun and Wang, Jinglu and Zhang, Chenbin and Wang, Ping and Lu, Yan}, title = {Two-Shot Video Object Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2257-2267} }

PiMAE: Point Cloud and Image Interactive Masked Autoencoders for 3D Object Detection

Anthony Chen,

Kevin Zhang,

Renrui Zhang,

Zihan Wang,

Yuheng Lu,

Yandong Guo,

Shanghang Zhang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Chen_2023_CVPR, author = {Chen, Anthony and Zhang, Kevin and Zhang, Renrui and Wang, Zihan and Lu, Yuheng and Guo, Yandong and Zhang, Shanghang}, title = {PiMAE: Point Cloud and Image Interactive Masked Autoencoders for 3D Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5291-5301} }

High-Fidelity 3D GAN Inversion by Pseudo-Multi-View Optimization

Jiaxin Xie,

Hao Ouyang,

Jingtan Piao,

Chenyang Lei,

Qifeng Chen

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Xie_2023_CVPR, author = {Xie, Jiaxin and Ouyang, Hao and Piao, Jingtan and Lei, Chenyang and Chen, Qifeng}, title = {High-Fidelity 3D GAN Inversion by Pseudo-Multi-View Optimization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {321-331} }

Single Image Backdoor Inversion via Robust Smoothed Classifiers

Mingjie Sun,

Zico Kolter

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Sun_2023_CVPR, author = {Sun, Mingjie and Kolter, Zico}, title = {Single Image Backdoor Inversion via Robust Smoothed Classifiers}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8113-8122} }

A Hierarchical Representation Network for Accurate and Detailed Face Reconstruction From In-the-Wild Images

Biwen Lei,

Jianqiang Ren,

Mengyang Feng,

Miaomiao Cui,

Xuansong Xie

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Lei_2023_CVPR, author = {Lei, Biwen and Ren, Jianqiang and Feng, Mengyang and Cui, Miaomiao and Xie, Xuansong}, title = {A Hierarchical Representation Network for Accurate and Detailed Face Reconstruction From In-the-Wild Images}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {394-403} }

PersonNeRF: Personalized Reconstruction From Photo Collections

Chung-Yi Weng,

Pratul P. Srinivasan,

Brian Curless,

Ira Kemelmacher-Shlizerman

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Weng_2023_CVPR, author = {Weng, Chung-Yi and Srinivasan, Pratul P. and Curless, Brian and Kemelmacher-Shlizerman, Ira}, title = {PersonNeRF: Personalized Reconstruction From Photo Collections}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {524-533} }

NeuralLift-360: Lifting an In-the-Wild 2D Photo to a 3D Object With 360deg Views

Dejia Xu,

Yifan Jiang,

Peihao Wang,

Zhiwen Fan,

Yi Wang,

Zhangyang Wang

[pdf] [supp]

[bibtex]

@InProceedings{Xu_2023_CVPR, author = {Xu, Dejia and Jiang, Yifan and Wang, Peihao and Fan, Zhiwen and Wang, Yi and Wang, Zhangyang}, title = {NeuralLift-360: Lifting an In-the-Wild 2D Photo to a 3D Object With 360deg Views}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4479-4489} }

ViP3D: End-to-End Visual Trajectory Prediction via 3D Agent Queries

Junru Gu,

Chenxu Hu,

Tianyuan Zhang,

Xuanyao Chen,

Yilun Wang,

Yue Wang,

Hang Zhao

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Gu_2023_CVPR, author = {Gu, Junru and Hu, Chenxu and Zhang, Tianyuan and Chen, Xuanyao and Wang, Yilun and Wang, Yue and Zhao, Hang}, title = {ViP3D: End-to-End Visual Trajectory Prediction via 3D Agent Queries}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5496-5506} }

LidarGait: Benchmarking 3D Gait Recognition With Point Clouds

Chuanfu Shen,

Chao Fan,

Wei Wu,

Rui Wang,

George Q. Huang,

Shiqi Yu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Shen_2023_CVPR, author = {Shen, Chuanfu and Fan, Chao and Wu, Wei and Wang, Rui and Huang, George Q. and Yu, Shiqi}, title = {LidarGait: Benchmarking 3D Gait Recognition With Point Clouds}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1054-1063} }

D2Former: Jointly Learning Hierarchical Detectors and Contextual Descriptors via Agent-Based Transformers

Jianfeng He,

Yuan Gao,

Tianzhu Zhang,

Zhe Zhang,

Feng Wu

[pdf] [supp]

[bibtex]

@InProceedings{He_2023_CVPR, author = {He, Jianfeng and Gao, Yuan and Zhang, Tianzhu and Zhang, Zhe and Wu, Feng}, title = {D2Former: Jointly Learning Hierarchical Detectors and Contextual Descriptors via Agent-Based Transformers}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2904-2914} }

Joint Appearance and Motion Learning for Efficient Rolling Shutter Correction

Bin Fan,

Yuxin Mao,

Yuchao Dai,

Zhexiong Wan,

Qi Liu

[pdf] [supp]

[bibtex]

@InProceedings{Fan_2023_CVPR, author = {Fan, Bin and Mao, Yuxin and Dai, Yuchao and Wan, Zhexiong and Liu, Qi}, title = {Joint Appearance and Motion Learning for Efficient Rolling Shutter Correction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5671-5681} }

Federated Incremental Semantic Segmentation

Jiahua Dong,

Duzhen Zhang,

Yang Cong,

Wei Cong,

Henghui Ding,

Dengxin Dai

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Dong_2023_CVPR, author = {Dong, Jiahua and Zhang, Duzhen and Cong, Yang and Cong, Wei and Ding, Henghui and Dai, Dengxin}, title = {Federated Incremental Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3934-3943} }

Attention-Based Point Cloud Edge Sampling

Chengzhi Wu,

Junwei Zheng,

Julius Pfrommer,

Jürgen Beyerer

[pdf] [arXiv]

[bibtex]

@InProceedings{Wu_2023_CVPR, author = {Wu, Chengzhi and Zheng, Junwei and Pfrommer, Julius and Beyerer, J\"urgen}, title = {Attention-Based Point Cloud Edge Sampling}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5333-5343} }

Avatars Grow Legs: Generating Smooth Human Motion From Sparse Tracking Inputs With Diffusion Model

Yuming Du,

Robin Kips,

Albert Pumarola,

Sebastian Starke,

Ali Thabet,

Artsiom Sanakoyeu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Du_2023_CVPR, author = {Du, Yuming and Kips, Robin and Pumarola, Albert and Starke, Sebastian and Thabet, Ali and Sanakoyeu, Artsiom}, title = {Avatars Grow Legs: Generating Smooth Human Motion From Sparse Tracking Inputs With Diffusion Model}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {481-490} }

Learning Neural Proto-Face Field for Disentangled 3D Face Modeling in the Wild

Zhenyu Zhang,

Renwang Chen,

Weijian Cao,

Ying Tai,

Chengjie Wang

[pdf] [supp]

[bibtex]

@InProceedings{Zhang_2023_CVPR, author = {Zhang, Zhenyu and Chen, Renwang and Cao, Weijian and Tai, Ying and Wang, Chengjie}, title = {Learning Neural Proto-Face Field for Disentangled 3D Face Modeling in the Wild}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {382-393} }

BUFFER: Balancing Accuracy, Efficiency, and Generalizability in Point Cloud Registration

Sheng Ao,

Qingyong Hu,

Hanyun Wang,

Kai Xu,

Yulan Guo

[pdf] [supp]

[bibtex]

@InProceedings{Ao_2023_CVPR, author = {Ao, Sheng and Hu, Qingyong and Wang, Hanyun and Xu, Kai and Guo, Yulan}, title = {BUFFER: Balancing Accuracy, Efficiency, and Generalizability in Point Cloud Registration}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1255-1264} }

CrOC: Cross-View Online Clustering for Dense Visual Representation Learning

Thomas Stegmüller,

Tim Lebailly,

Behzad Bozorgtabar,

Tinne Tuytelaars,

Jean-Philippe Thiran

[pdf] [supp]

[bibtex]

@InProceedings{Stegmuller_2023_CVPR, author = {Stegm\"uller, Thomas and Lebailly, Tim and Bozorgtabar, Behzad and Tuytelaars, Tinne and Thiran, Jean-Philippe}, title = {CrOC: Cross-View Online Clustering for Dense Visual Representation Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7000-7009} }

DrapeNet: Garment Generation and Self-Supervised Draping

Luca De Luigi,

Ren Li,

Benoît Guillard,

Mathieu Salzmann,

Pascal Fua

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{De_Luigi_2023_CVPR, author = {De Luigi, Luca and Li, Ren and Guillard, Beno{\^\i}t and Salzmann, Mathieu and Fua, Pascal}, title = {DrapeNet: Garment Generation and Self-Supervised Draping}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1451-1460} }

FeatureBooster: Boosting Feature Descriptors With a Lightweight Neural Network

Xinjiang Wang,

Zeyu Liu,

Yu Hu,

Wei Xi,

Wenxian Yu,

Danping Zou

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Xinjiang and Liu, Zeyu and Hu, Yu and Xi, Wei and Yu, Wenxian and Zou, Danping}, title = {FeatureBooster: Boosting Feature Descriptors With a Lightweight Neural Network}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7630-7639} }

Towards Efficient Use of Multi-Scale Features in Transformer-Based Object Detectors

Gongjie Zhang,

Zhipeng Luo,

Zichen Tian,

Jingyi Zhang,

Xiaoqin Zhang,

Shijian Lu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Zhang_2023_CVPR, author = {Zhang, Gongjie and Luo, Zhipeng and Tian, Zichen and Zhang, Jingyi and Zhang, Xiaoqin and Lu, Shijian}, title = {Towards Efficient Use of Multi-Scale Features in Transformer-Based Object Detectors}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6206-6216} }

Delivering Arbitrary-Modal Semantic Segmentation

Jiaming Zhang,

Ruiping Liu,

Hao Shi,

Kailun Yang,

Simon Reiß,

Kunyu Peng,

Haodong Fu,

Kaiwei Wang,

Rainer Stiefelhagen

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Zhang_2023_CVPR, author = {Zhang, Jiaming and Liu, Ruiping and Shi, Hao and Yang, Kailun and Rei{\ss}, Simon and Peng, Kunyu and Fu, Haodong and Wang, Kaiwei and Stiefelhagen, Rainer}, title = {Delivering Arbitrary-Modal Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {1136-1147} }

Consistent-Teacher: Towards Reducing Inconsistent Pseudo-Targets in Semi-Supervised Object Detection

Xinjiang Wang,

Xingyi Yang,

Shilong Zhang,

Yijiang Li,

Litong Feng,

Shijie Fang,

Chengqi Lyu,

Kai Chen,

Wayne Zhang

[pdf] [supp]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Xinjiang and Yang, Xingyi and Zhang, Shilong and Li, Yijiang and Feng, Litong and Fang, Shijie and Lyu, Chengqi and Chen, Kai and Zhang, Wayne}, title = {Consistent-Teacher: Towards Reducing Inconsistent Pseudo-Targets in Semi-Supervised Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3240-3249} }

DNeRV: Modeling Inherent Dynamics via Difference Neural Representation for Videos

Qi Zhao,

M. Salman Asif,

Zhan Ma

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Zhao_2023_CVPR, author = {Zhao, Qi and Asif, M. Salman and Ma, Zhan}, title = {DNeRV: Modeling Inherent Dynamics via Difference Neural Representation for Videos}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2031-2040} }

Continuous Pseudo-Label Rectified Domain Adaptive Semantic Segmentation With Implicit Neural Representations

Rui Gong,

Qin Wang,

Martin Danelljan,

Dengxin Dai,

Luc Van Gool

[pdf] [supp]

[bibtex]

@InProceedings{Gong_2023_CVPR, author = {Gong, Rui and Wang, Qin and Danelljan, Martin and Dai, Dengxin and Van Gool, Luc}, title = {Continuous Pseudo-Label Rectified Domain Adaptive Semantic Segmentation With Implicit Neural Representations}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7225-7235} }

Hyperbolic Contrastive Learning for Visual Representations Beyond Objects

Songwei Ge,

Shlok Mishra,

Simon Kornblith,

Chun-Liang Li,

David Jacobs

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Ge_2023_CVPR, author = {Ge, Songwei and Mishra, Shlok and Kornblith, Simon and Li, Chun-Liang and Jacobs, David}, title = {Hyperbolic Contrastive Learning for Visual Representations Beyond Objects}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6840-6849} }

AligNeRF: High-Fidelity Neural Radiance Fields via Alignment-Aware Training

Yifan Jiang,

Peter Hedman,

Ben Mildenhall,

Dejia Xu,

Jonathan T. Barron,

Zhangyang Wang,

Tianfan Xue

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Jiang_2023_CVPR, author = {Jiang, Yifan and Hedman, Peter and Mildenhall, Ben and Xu, Dejia and Barron, Jonathan T. and Wang, Zhangyang and Xue, Tianfan}, title = {AligNeRF: High-Fidelity Neural Radiance Fields via Alignment-Aware Training}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {46-55} }

NAR-Former: Neural Architecture Representation Learning Towards Holistic Attributes Prediction

Yun Yi,

Haokui Zhang,

Wenze Hu,

Nannan Wang,

Xiaoyu Wang

[pdf] [supp]

[bibtex]

@InProceedings{Yi_2023_CVPR, author = {Yi, Yun and Zhang, Haokui and Hu, Wenze and Wang, Nannan and Wang, Xiaoyu}, title = {NAR-Former: Neural Architecture Representation Learning Towards Holistic Attributes Prediction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7715-7724} }

Teaching Structured Vision & Language Concepts to Vision & Language Models

Sivan Doveh,

Assaf Arbelle,

Sivan Harary,

Eli Schwartz,

Roei Herzig,

Raja Giryes,

Rogerio Feris,

Rameswar Panda,

Shimon Ullman,

Leonid Karlinsky

[pdf] [supp]

[bibtex]

@InProceedings{Doveh_2023_CVPR, author = {Doveh, Sivan and Arbelle, Assaf and Harary, Sivan and Schwartz, Eli and Herzig, Roei and Giryes, Raja and Feris, Rogerio and Panda, Rameswar and Ullman, Shimon and Karlinsky, Leonid}, title = {Teaching Structured Vision \& Language Concepts to Vision \& Language Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2657-2668} }

NULL-Text Inversion for Editing Real Images Using Guided Diffusion Models

Ron Mokady,

Amir Hertz,

Kfir Aberman,

Yael Pritch,

Daniel Cohen-Or

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Mokady_2023_CVPR, author = {Mokady, Ron and Hertz, Amir and Aberman, Kfir and Pritch, Yael and Cohen-Or, Daniel}, title = {NULL-Text Inversion for Editing Real Images Using Guided Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6038-6047} }

Selective Structured State-Spaces for Long-Form Video Understanding

Jue Wang,

Wentao Zhu,

Pichao Wang,

Xiang Yu,

Linda Liu,

Mohamed Omar,

Raffay Hamid

[pdf] [arXiv]

[bibtex]

@InProceedings{Wang_2023_CVPR, author = {Wang, Jue and Zhu, Wentao and Wang, Pichao and Yu, Xiang and Liu, Linda and Omar, Mohamed and Hamid, Raffay}, title = {Selective Structured State-Spaces for Long-Form Video Understanding}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6387-6397} }

Motion Information Propagation for Neural Video Compression

Linfeng Qi,

Jiahao Li,

Bin Li,

Houqiang Li,

Yan Lu

[pdf] [supp]

[bibtex]

@InProceedings{Qi_2023_CVPR, author = {Qi, Linfeng and Li, Jiahao and Li, Bin and Li, Houqiang and Lu, Yan}, title = {Motion Information Propagation for Neural Video Compression}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {6111-6120} }

Accelerated Coordinate Encoding: Learning to Relocalize in Minutes Using RGB and Poses

Eric Brachmann,

Tommaso Cavallari,

Victor Adrian Prisacariu

[pdf] [supp]

[bibtex]

@InProceedings{Brachmann_2023_CVPR, author = {Brachmann, Eric and Cavallari, Tommaso and Prisacariu, Victor Adrian}, title = {Accelerated Coordinate Encoding: Learning to Relocalize in Minutes Using RGB and Poses}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {5044-5053} }

Robust Dynamic Radiance Fields

Yu-Lun Liu,

Chen Gao,

Andréas Meuleman,

Hung-Yu Tseng,

Ayush Saraf,

Changil Kim,

Yung-Yu Chuang,

Johannes Kopf,

Jia-Bin Huang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Liu_2023_CVPR, author = {Liu, Yu-Lun and Gao, Chen and Meuleman, Andr\'eas and Tseng, Hung-Yu and Saraf, Ayush and Kim, Changil and Chuang, Yung-Yu and Kopf, Johannes and Huang, Jia-Bin}, title = {Robust Dynamic Radiance Fields}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13-23} }

PLIKS: A Pseudo-Linear Inverse Kinematic Solver for 3D Human Body Estimation

Karthik Shetty,

Annette Birkhold,

Srikrishna Jaganathan,

Norbert Strobel,

Markus Kowarschik,

Andreas Maier,

Bernhard Egger

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Shetty_2023_CVPR, author = {Shetty, Karthik and Birkhold, Annette and Jaganathan, Srikrishna and Strobel, Norbert and Kowarschik, Markus and Maier, Andreas and Egger, Bernhard}, title = {PLIKS: A Pseudo-Linear Inverse Kinematic Solver for 3D Human Body Estimation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {574-584} }

Promoting Semantic Connectivity: Dual Nearest Neighbors Contrastive Learning for Unsupervised Domain Generalization

Yuchen Liu,

Yaoming Wang,

Yabo Chen,

Wenrui Dai,

Chenglin Li,

Junni Zou,

Hongkai Xiong

[pdf] [supp]

[bibtex]

@InProceedings{Liu_2023_CVPR, author = {Liu, Yuchen and Wang, Yaoming and Chen, Yabo and Dai, Wenrui and Li, Chenglin and Zou, Junni and Xiong, Hongkai}, title = {Promoting Semantic Connectivity: Dual Nearest Neighbors Contrastive Learning for Unsupervised Domain Generalization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3510-3519} }

Interactive Segmentation of Radiance Fields

Rahul Goel,

Dhawal Sirikonda,

Saurabh Saini,

P. J. Narayanan

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Goel_2023_CVPR, author = {Goel, Rahul and Sirikonda, Dhawal and Saini, Saurabh and Narayanan, P. J.}, title = {Interactive Segmentation of Radiance Fields}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4201-4211} }

Exploring and Utilizing Pattern Imbalance

Shibin Mei,

Chenglong Zhao,

Shengchao Yuan,

Bingbing Ni

[pdf] [supp]

[bibtex]

@InProceedings{Mei_2023_CVPR, author = {Mei, Shibin and Zhao, Chenglong and Yuan, Shengchao and Ni, Bingbing}, title = {Exploring and Utilizing Pattern Imbalance}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {7569-7578} }

Are Data-Driven Explanations Robust Against Out-of-Distribution Data?

Tang Li,

Fengchun Qiao,

Mengmeng Ma,

Xi Peng

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Li_2023_CVPR, author = {Li, Tang and Qiao, Fengchun and Ma, Mengmeng and Peng, Xi}, title = {Are Data-Driven Explanations Robust Against Out-of-Distribution Data?}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3821-3831} }

Top-Down Visual Attention From Analysis by Synthesis

Baifeng Shi,

Trevor Darrell,

Xin Wang

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Shi_2023_CVPR, author = {Shi, Baifeng and Darrell, Trevor and Wang, Xin}, title = {Top-Down Visual Attention From Analysis by Synthesis}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {2102-2112} }

Hierarchical Fine-Grained Image Forgery Detection and Localization

Xiao Guo,

Xiaohong Liu,

Zhiyuan Ren,

Steven Grosz,

Iacopo Masi,

Xiaoming Liu

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Guo_2023_CVPR, author = {Guo, Xiao and Liu, Xiaohong and Ren, Zhiyuan and Grosz, Steven and Masi, Iacopo and Liu, Xiaoming}, title = {Hierarchical Fine-Grained Image Forgery Detection and Localization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {3155-3165} }

Fantastic Breaks: A Dataset of Paired 3D Scans of Real-World Broken Objects and Their Complete Counterparts

Nikolas Lamb,

Cameron Palmer,

Benjamin Molloy,

Sean Banerjee,

Natasha Kholgade Banerjee

[pdf] [supp] [arXiv]

[bibtex]

@InProceedings{Lamb_2023_CVPR, author = {Lamb, Nikolas and Palmer, Cameron and Molloy, Benjamin and Banerjee, Sean and Banerjee, Natasha Kholgade}, title = {Fantastic Breaks: A Dataset of Paired 3D Scans of Real-World Broken Objects and Their Complete Counterparts}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4681-4691} }

Back