Papers
- Back
Unmixing Diffusion for Self-Supervised Hyperspectral Image Denoising-
[pdf]
[supp]
[bibtex]@InProceedings{Zeng_2024_CVPR, author = {Zeng, Haijin and Cao, Jiezhang and Zhang, Kai and Chen, Yongyong and Luong, Hiep and Philips, Wilfried}, title = {Unmixing Diffusion for Self-Supervised Hyperspectral Image Denoising}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {27820-27830} }
Test-Time Linear Out-of-Distribution Detection-
[pdf]
[supp]
[bibtex]@InProceedings{Fan_2024_CVPR, author = {Fan, Ke and Liu, Tong and Qiu, Xingyu and Wang, Yikai and Huai, Lian and Shangguan, Zeyu and Gou, Shuang and Liu, Fengjian and Fu, Yuqian and Fu, Yanwei and Jiang, Xingqun}, title = {Test-Time Linear Out-of-Distribution Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {23752-23761} }
Unsupervised Blind Image Deblurring Based on Self-Enhancement-
[pdf]
[supp]
[bibtex]@InProceedings{Chen_2024_CVPR, author = {Chen, Lufei and Tian, Xiangpeng and Xiong, Shuhua and Lei, Yinjie and Ren, Chao}, title = {Unsupervised Blind Image Deblurring Based on Self-Enhancement}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {25691-25700} }
UFineBench: Towards Text-based Person Retrieval with Ultra-fine Granularity-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Zuo_2024_CVPR, author = {Zuo, Jialong and Zhou, Hanyu and Nie, Ying and Zhang, Feng and Guo, Tianyu and Sang, Nong and Wang, Yunhe and Gao, Changxin}, title = {UFineBench: Towards Text-based Person Retrieval with Ultra-fine Granularity}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {22010-22019} }
Efficient Hyperparameter Optimization with Adaptive Fidelity Identification-
[pdf]
[supp]
[bibtex]@InProceedings{Jiang_2024_CVPR, author = {Jiang, Jiantong and Wen, Zeyi and Mansoor, Atif and Mian, Ajmal}, title = {Efficient Hyperparameter Optimization with Adaptive Fidelity Identification}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {26181-26190} }
Focus on Hiders: Exploring Hidden Threats for Enhancing Adversarial Training-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Li_2024_CVPR, author = {Li, Qian and Hu, Yuxiao and Dong, Yinpeng and Zhang, Dongxiao and Chen, Yuntian}, title = {Focus on Hiders: Exploring Hidden Threats for Enhancing Adversarial Training}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {24442-24451} }
GoodSAM: Bridging Domain and Capacity Gaps via Segment Anything Model for Distortion-aware Panoramic Semantic Segmentation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Zhang_2024_CVPR, author = {Zhang, Weiming and Liu, Yexin and Zheng, Xu and Wang, Lin}, title = {GoodSAM: Bridging Domain and Capacity Gaps via Segment Anything Model for Distortion-aware Panoramic Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {28264-28273} }
DYSON: Dynamic Feature Space Self-Organization for Online Task-Free Class Incremental Learning-
[pdf]
[supp]
[bibtex]@InProceedings{He_2024_CVPR, author = {He, Yuhang and Chen, Yingjie and Jin, Yuhan and Dong, Songlin and Wei, Xing and Gong, Yihong}, title = {DYSON: Dynamic Feature Space Self-Organization for Online Task-Free Class Incremental Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {23741-23751} }
Event-based Structure-from-Orbit-
[pdf]
[arXiv]
[bibtex]@InProceedings{Elms_2024_CVPR, author = {Elms, Ethan and Latif, Yasir and Park, Tae Ha and Chin, Tat-Jun}, title = {Event-based Structure-from-Orbit}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {19541-19550} }
LED: A Large-scale Real-world Paired Dataset for Event Camera Denoising-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Duan_2024_CVPR, author = {Duan, Yuxing}, title = {LED: A Large-scale Real-world Paired Dataset for Event Camera Denoising}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {25637-25647} }
SVDinsTN: A Tensor Network Paradigm for Efficient Structure Search from Regularized Modeling Perspective-
[pdf]
[arXiv]
[bibtex]@InProceedings{Zheng_2024_CVPR, author = {Zheng, Yu-Bang and Zhao, Xi-Le and Zeng, Junhua and Li, Chao and Zhao, Qibin and Li, Heng-Chao and Huang, Ting-Zhu}, title = {SVDinsTN: A Tensor Network Paradigm for Efficient Structure Search from Regularized Modeling Perspective}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {26254-26263} }
Inverse Rendering of Glossy Objects via the Neural Plenoptic Function and Radiance Fields-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Wang_2024_CVPR, author = {Wang, Haoyuan and Hu, Wenbo and Zhu, Lei and Lau, Rynson W.H.}, title = {Inverse Rendering of Glossy Objects via the Neural Plenoptic Function and Radiance Fields}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {19999-20008} }
Split to Merge: Unifying Separated Modalities for Unsupervised Domain Adaptation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Li_2024_CVPR, author = {Li, Xinyao and Li, Yuke and Du, Zhekai and Li, Fengling and Lu, Ke and Li, Jingjing}, title = {Split to Merge: Unifying Separated Modalities for Unsupervised Domain Adaptation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {23364-23374} }
Overcoming Generic Knowledge Loss with Selective Parameter Update-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Zhang_2024_CVPR, author = {Zhang, Wenxuan and Janson, Paul and Aljundi, Rahaf and Elhoseiny, Mohamed}, title = {Overcoming Generic Knowledge Loss with Selective Parameter Update}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {24046-24056} }
Diff-BGM: A Diffusion Model for Video Background Music Generation-
[pdf]
[supp]
[bibtex]@InProceedings{Li_2024_CVPR, author = {Li, Sizhe and Qin, Yiming and Zheng, Minghang and Jin, Xin and Liu, Yang}, title = {Diff-BGM: A Diffusion Model for Video Background Music Generation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {27348-27357} }
Looking Similar Sounding Different: Leveraging Counterfactual Cross-Modal Pairs for Audiovisual Representation Learning-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Singh_2024_CVPR, author = {Singh, Nikhil and Wu, Chih-Wei and Orife, Iroro and Kalayeh, Mahdi}, title = {Looking Similar Sounding Different: Leveraging Counterfactual Cross-Modal Pairs for Audiovisual Representation Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {26907-26918} }
Towards HDR and HFR Video from Rolling-Mixed-Bit Spikings-
[pdf]
[supp]
[bibtex]@InProceedings{Chang_2024_CVPR, author = {Chang, Yakun and Xiaokaiti, Yeliduosi and Liu, Yujia and Fan, Bin and Huang, Zhaojun and Huang, Tiejun and Shi, Boxin}, title = {Towards HDR and HFR Video from Rolling-Mixed-Bit Spikings}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {25117-25127} }
Bridging the Synthetic-to-Authentic Gap: Distortion-Guided Unsupervised Domain Adaptation for Blind Image Quality Assessment-
[pdf]
[arXiv]
[bibtex]@InProceedings{Li_2024_CVPR, author = {Li, Aobo and Wu, Jinjian and Liu, Yongxu and Li, Leida}, title = {Bridging the Synthetic-to-Authentic Gap: Distortion-Guided Unsupervised Domain Adaptation for Blind Image Quality Assessment}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {28422-28431} }
Coherent Temporal Synthesis for Incremental Action Segmentation-
[pdf]
[arXiv]
[bibtex]@InProceedings{Ding_2024_CVPR, author = {Ding, Guodong and Golong, Hans and Yao, Angela}, title = {Coherent Temporal Synthesis for Incremental Action Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {28485-28494} }
HiFi4G: High-Fidelity Human Performance Rendering via Compact Gaussian Splatting-
[pdf]
[arXiv]
[bibtex]@InProceedings{Jiang_2024_CVPR, author = {Jiang, Yuheng and Shen, Zhehao and Wang, Penghao and Su, Zhuo and Hong, Yu and Zhang, Yingliang and Yu, Jingyi and Xu, Lan}, title = {HiFi4G: High-Fidelity Human Performance Rendering via Compact Gaussian Splatting}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {19734-19745} }
G-FARS: Gradient-Field-based Auto-Regressive Sampling for 3D Part Grouping-
[pdf]
[supp]
[bibtex]@InProceedings{Cheng_2024_CVPR, author = {Cheng, Junfeng and Stathaki, Tania}, title = {G-FARS: Gradient-Field-based Auto-Regressive Sampling for 3D Part Grouping}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {27652-27661} }
DMR: Decomposed Multi-Modality Representations for Frames and Events Fusion in Visual Reinforcement Learning-
[pdf]
[supp]
[bibtex]@InProceedings{Xu_2024_CVPR, author = {Xu, Haoran and Peng, Peixi and Tan, Guang and Li, Yuan and Xu, Xinhai and Tian, Yonghong}, title = {DMR: Decomposed Multi-Modality Representations for Frames and Events Fusion in Visual Reinforcement Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {26508-26518} }
DiffuseMix: Label-Preserving Data Augmentation with Diffusion Models-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Islam_2024_CVPR, author = {Islam, Khawar and Zaheer, Muhammad Zaigham and Mahmood, Arif and Nandakumar, Karthik}, title = {DiffuseMix: Label-Preserving Data Augmentation with Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {27621-27630} }
FREE: Faster and Better Data-Free Meta-Learning-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Wei_2024_CVPR, author = {Wei, Yongxian and Hu, Zixuan and Wang, Zhenyi and Shen, Li and Yuan, Chun and Tao, Dacheng}, title = {FREE: Faster and Better Data-Free Meta-Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {23273-23282} }
Bi-SSC: Geometric-Semantic Bidirectional Fusion for Camera-based 3D Semantic Scene Completion-
[pdf]
[supp]
[bibtex]@InProceedings{Xue_2024_CVPR, author = {Xue, Yujie and Li, Ruihui and Wu, Fan and Tang, Zhuo and Li, Kenli and Duan, Mingxing}, title = {Bi-SSC: Geometric-Semantic Bidirectional Fusion for Camera-based 3D Semantic Scene Completion}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {20124-20134} }
Parameter Efficient Self-Supervised Geospatial Domain Adaptation-
[pdf]
[supp]
[bibtex]@InProceedings{Scheibenreif_2024_CVPR, author = {Scheibenreif, Linus and Mommert, Michael and Borth, Damian}, title = {Parameter Efficient Self-Supervised Geospatial Domain Adaptation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {27841-27851} }
Defense without Forgetting: Continual Adversarial Defense with Anisotropic & Isotropic Pseudo Replay-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Zhou_2024_CVPR, author = {Zhou, Yuhang and Hua, Zhongyun}, title = {Defense without Forgetting: Continual Adversarial Defense with Anisotropic \& Isotropic Pseudo Replay}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {24263-24272} }
Transferable Structural Sparse Adversarial Attack Via Exact Group Sparsity Training-
[pdf]
[supp]
[bibtex]@InProceedings{Ming_2024_CVPR, author = {Ming, Di and Ren, Peng and Wang, Yunlong and Feng, Xin}, title = {Transferable Structural Sparse Adversarial Attack Via Exact Group Sparsity Training}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {24696-24705} }
Unsupervised Occupancy Learning from Sparse Point Cloud-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Ouasfi_2024_CVPR, author = {Ouasfi, Amine and Boukhayma, Adnane}, title = {Unsupervised Occupancy Learning from Sparse Point Cloud}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {21729-21739} }
3DInAction: Understanding Human Actions in 3D Point Clouds-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Ben-Shabat_2024_CVPR, author = {Ben-Shabat, Yizhak and Shrout, Oren and Gould, Stephen}, title = {3DInAction: Understanding Human Actions in 3D Point Clouds}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {19978-19987} }
SDDGR: Stable Diffusion-based Deep Generative Replay for Class Incremental Object Detection-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Kim_2024_CVPR, author = {Kim, Junsu and Cho, Hoseong and Kim, Jihyeon and Tiruneh, Yihalem Yimolal and Baek, Seungryul}, title = {SDDGR: Stable Diffusion-based Deep Generative Replay for Class Incremental Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {28772-28781} }
Physical 3D Adversarial Attacks against Monocular Depth Estimation in Autonomous Driving-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Zheng_2024_CVPR, author = {Zheng, Junhao and Lin, Chenhao and Sun, Jiahao and Zhao, Zhengyu and Li, Qian and Shen, Chao}, title = {Physical 3D Adversarial Attacks against Monocular Depth Estimation in Autonomous Driving}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {24452-24461} }
Adaptive Random Feature Regularization on Fine-tuning Deep Neural Networks-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Yamaguchi_2024_CVPR, author = {Yamaguchi, Shin'ya and Kanai, Sekitoshi and Adachi, Kazuki and Chijiwa, Daiki}, title = {Adaptive Random Feature Regularization on Fine-tuning Deep Neural Networks}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {23481-23490} }
Multimodal Prompt Perceiver: Empower Adaptiveness Generalizability and Fidelity for All-in-One Image Restoration-
[pdf]
[arXiv]
[bibtex]@InProceedings{Ai_2024_CVPR, author = {Ai, Yuang and Huang, Huaibo and Zhou, Xiaoqiang and Wang, Jiexiang and He, Ran}, title = {Multimodal Prompt Perceiver: Empower Adaptiveness Generalizability and Fidelity for All-in-One Image Restoration}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {25432-25444} }
Color Shift Estimation-and-Correction for Image Enhancement-
[pdf]
[arXiv]
[bibtex]@InProceedings{Li_2024_CVPR, author = {Li, Yiyu and Xu, Ke and Hancke, Gerhard Petrus and Lau, Rynson W.H.}, title = {Color Shift Estimation-and-Correction for Image Enhancement}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {25389-25398} }
Towards Scalable 3D Anomaly Detection and Localization: A Benchmark via 3D Anomaly Synthesis and A Self-Supervised Learning Network-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Li_2024_CVPR, author = {Li, Wenqiao and Xu, Xiaohao and Gu, Yao and Zheng, Bozhong and Gao, Shenghua and Wu, Yingna}, title = {Towards Scalable 3D Anomaly Detection and Localization: A Benchmark via 3D Anomaly Synthesis and A Self-Supervised Learning Network}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {22207-22216} }
Cam4DOcc: Benchmark for Camera-Only 4D Occupancy Forecasting in Autonomous Driving Applications-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Ma_2024_CVPR, author = {Ma, Junyi and Chen, Xieyuanli and Huang, Jiawei and Xu, Jingyi and Luo, Zhen and Xu, Jintao and Gu, Weihao and Ai, Rui and Wang, Hesheng}, title = {Cam4DOcc: Benchmark for Camera-Only 4D Occupancy Forecasting in Autonomous Driving Applications}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {21486-21495} }
DIEM: Decomposition-Integration Enhancing Multimodal Insights-
[pdf]
[bibtex]@InProceedings{Jiang_2024_CVPR, author = {Jiang, Xinyi and Wang, Guoming and Guo, Junhao and Li, Juncheng and Zhang, Wenqiao and Lu, Rongxing and Tang, Siliang}, title = {DIEM: Decomposition-Integration Enhancing Multimodal Insights}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {27304-27313} }
Contrastive Pre-Training with Multi-View Fusion for No-Reference Point Cloud Quality Assessment-
[pdf]
[arXiv]
[bibtex]@InProceedings{Shan_2024_CVPR, author = {Shan, Ziyu and Zhang, Yujie and Yang, Qi and Yang, Haichen and Xu, Yiling and Hwang, Jenq-Neng and Xu, Xiaozhong and Liu, Shan}, title = {Contrastive Pre-Training with Multi-View Fusion for No-Reference Point Cloud Quality Assessment}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {25942-25951} }
Revisiting Spatial-Frequency Information Integration from a Hierarchical Perspective for Panchromatic and Multi-Spectral Image Fusion-
[pdf]
[supp]
[bibtex]@InProceedings{Tan_2024_CVPR, author = {Tan, Jiangtong and Huang, Jie and Zheng, Naishan and Zhou, Man and Yan, Keyu and Hong, Danfeng and Zhao, Feng}, title = {Revisiting Spatial-Frequency Information Integration from a Hierarchical Perspective for Panchromatic and Multi-Spectral Image Fusion}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {25922-25931} }
BSNet: Box-Supervised Simulation-assisted Mean Teacher for 3D Instance Segmentation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Lu_2024_CVPR, author = {Lu, Jiahao and Deng, Jiacheng and Zhang, Tianzhu}, title = {BSNet: Box-Supervised Simulation-assisted Mean Teacher for 3D Instance Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {20374-20384} }
Adaptive Slot Attention: Object Discovery with Dynamic Slot Number-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Fan_2024_CVPR, author = {Fan, Ke and Bai, Zechen and Xiao, Tianjun and He, Tong and Horn, Max and Fu, Yanwei and Locatello, Francesco and Zhang, Zheng}, title = {Adaptive Slot Attention: Object Discovery with Dynamic Slot Number}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {23062-23071} }
Task-Driven Wavelets using Constrained Empirical Risk Minimization-
[pdf]
[supp]
[bibtex]@InProceedings{Marcus_2024_CVPR, author = {Marcus, Eric and Sheombarsing, Ray and Sonke, Jan-Jakob and Teuwen, Jonas}, title = {Task-Driven Wavelets using Constrained Empirical Risk Minimization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {24098-24107} }
DeiT-LT: Distillation Strikes Back for Vision Transformer Training on Long-Tailed Datasets-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Rangwani_2024_CVPR, author = {Rangwani, Harsh and Mondal, Pradipto and Mishra, Mayank and Asokan, Ashish Ramayee and Babu, R. Venkatesh}, title = {DeiT-LT: Distillation Strikes Back for Vision Transformer Training on Long-Tailed Datasets}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {23396-23406} }
FCS: Feature Calibration and Separation for Non-Exemplar Class Incremental Learning-
[pdf]
[supp]
[bibtex]@InProceedings{Li_2024_CVPR, author = {Li, Qiwei and Peng, Yuxin and Zhou, Jiahuan}, title = {FCS: Feature Calibration and Separation for Non-Exemplar Class Incremental Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {28495-28504} }
Task2Box: Box Embeddings for Modeling Asymmetric Task Relationships-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Daroya_2024_CVPR, author = {Daroya, Rangel and Sun, Aaron and Maji, Subhransu}, title = {Task2Box: Box Embeddings for Modeling Asymmetric Task Relationships}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {28827-28837} }
LoS: Local Structure-Guided Stereo Matching-
[pdf]
[supp]
[bibtex]@InProceedings{Li_2024_CVPR, author = {Li, Kunhong and Wang, Longguang and Zhang, Ye and Xue, Kaiwen and Zhou, Shunbo and Guo, Yulan}, title = {LoS: Local Structure-Guided Stereo Matching}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {19746-19756} }
Probing the 3D Awareness of Visual Foundation Models-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{El_Banani_2024_CVPR, author = {El Banani, Mohamed and Raj, Amit and Maninis, Kevis-Kokitsi and Kar, Abhishek and Li, Yuanzhen and Rubinstein, Michael and Sun, Deqing and Guibas, Leonidas and Johnson, Justin and Jampani, Varun}, title = {Probing the 3D Awareness of Visual Foundation Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {21795-21806} }
When Visual Grounding Meets Gigapixel-level Large-scale Scenes: Benchmark and Approach-
[pdf]
[supp]
[bibtex]@InProceedings{Ma_2024_CVPR, author = {Ma, Tao and Bai, Bing and Lin, Haozhe and Wang, Heyuan and Wang, Yu and Luo, Lin and Fang, Lu}, title = {When Visual Grounding Meets Gigapixel-level Large-scale Scenes: Benchmark and Approach}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {22119-22128} }
Mind Artist: Creating Artistic Snapshots with Human Thought-
[pdf]
[supp]
[bibtex]@InProceedings{Chen_2024_CVPR, author = {Chen, Jiaxuan and Qi, Yu and Wang, Yueming and Pan, Gang}, title = {Mind Artist: Creating Artistic Snapshots with Human Thought}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {27207-27217} }
Accept the Modality Gap: An Exploration in the Hyperbolic Space-
[pdf]
[supp]
[bibtex]@InProceedings{Ramasinghe_2024_CVPR, author = {Ramasinghe, Sameera and Shevchenko, Violetta and Avraham, Gil and Thalaiyasingam, Ajanthan}, title = {Accept the Modality Gap: An Exploration in the Hyperbolic Space}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {27263-27272} }
Unraveling Instance Associations: A Closer Look for Audio-Visual Segmentation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Chen_2024_CVPR, author = {Chen, Yuanhong and Liu, Yuyuan and Wang, Hu and Liu, Fengbei and Wang, Chong and Frazer, Helen and Carneiro, Gustavo}, title = {Unraveling Instance Associations: A Closer Look for Audio-Visual Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {26497-26507} }
Few-Shot Object Detection with Foundation Models-
[pdf]
[supp]
[bibtex]@InProceedings{Han_2024_CVPR, author = {Han, Guangxing and Lim, Ser-Nam}, title = {Few-Shot Object Detection with Foundation Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {28608-28618} }
FedMef: Towards Memory-efficient Federated Dynamic Pruning-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Huang_2024_CVPR, author = {Huang, Hong and Zhuang, Weiming and Chen, Chen and Lyu, Lingjuan}, title = {FedMef: Towards Memory-efficient Federated Dynamic Pruning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {27548-27557} }
PracticalDG: Perturbation Distillation on Vision-Language Models for Hybrid Domain Generalization-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Chen_2024_CVPR, author = {Chen, Zining and Wang, Weiqiu and Zhao, Zhicheng and Su, Fei and Men, Aidong and Meng, Hongying}, title = {PracticalDG: Perturbation Distillation on Vision-Language Models for Hybrid Domain Generalization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {23501-23511} }
SODA: Bottleneck Diffusion Models for Representation Learning-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Hudson_2024_CVPR, author = {Hudson, Drew A. and Zoran, Daniel and Malinowski, Mateusz and Lampinen, Andrew K. and Jaegle, Andrew and McClelland, James L. and Matthey, Loic and Hill, Felix and Lerchner, Alexander}, title = {SODA: Bottleneck Diffusion Models for Representation Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {23115-23127} }
Zero-Reference Low-Light Enhancement via Physical Quadruple Priors-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Wang_2024_CVPR, author = {Wang, Wenjing and Yang, Huan and Fu, Jianlong and Liu, Jiaying}, title = {Zero-Reference Low-Light Enhancement via Physical Quadruple Priors}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {26057-26066} }
NeRFCodec: Neural Feature Compression Meets Neural Radiance Fields for Memory-Efficient Scene Representation-
[pdf]
[arXiv]
[bibtex]@InProceedings{Li_2024_CVPR, author = {Li, Sicheng and Li, Hao and Liao, Yiyi and Yu, Lu}, title = {NeRFCodec: Neural Feature Compression Meets Neural Radiance Fields for Memory-Efficient Scene Representation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {21274-21283} }
Rethinking Transformers Pre-training for Multi-Spectral Satellite Imagery-
[pdf]
[arXiv]
[bibtex]@InProceedings{Noman_2024_CVPR, author = {Noman, Mubashir and Naseer, Muzammal and Cholakkal, Hisham and Anwer, Rao Muhammad and Khan, Salman and Khan, Fahad Shahbaz}, title = {Rethinking Transformers Pre-training for Multi-Spectral Satellite Imagery}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {27811-27819} }
LLM4SGG: Large Language Models for Weakly Supervised Scene Graph Generation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Kim_2024_CVPR, author = {Kim, Kibum and Yoon, Kanghoon and Jeon, Jaehyeong and In, Yeonjun and Moon, Jinyoung and Kim, Donghyun and Park, Chanyoung}, title = {LLM4SGG: Large Language Models for Weakly Supervised Scene Graph Generation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {28306-28316} }
Neural Directional Encoding for Efficient and Accurate View-Dependent Appearance Modeling-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Wu_2024_CVPR, author = {Wu, Liwen and Bi, Sai and Xu, Zexiang and Luan, Fujun and Zhang, Kai and Georgiev, Iliyan and Sunkavalli, Kalyan and Ramamoorthi, Ravi}, title = {Neural Directional Encoding for Efficient and Accurate View-Dependent Appearance Modeling}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {21157-21166} }
Label Propagation for Zero-shot Classification with Vision-Language Models-
[pdf]
[supp]
[bibtex]@InProceedings{Stojni?_2024_CVPR, author = {Stojni?, Vladan and Kalantidis, Yannis and Tolias, Giorgos}, title = {Label Propagation for Zero-shot Classification with Vision-Language Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {23209-23218} }
Revisiting Global Translation Estimation with Feature Tracks-
[pdf]
[supp]
[bibtex]@InProceedings{Tao_2024_CVPR, author = {Tao, Peilin and Cui, Hainan and Rong, Mengqi and Shen, Shuhan}, title = {Revisiting Global Translation Estimation with Feature Tracks}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {20686-20696} }
Open-Set Domain Adaptation for Semantic Segmentation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Choe_2024_CVPR, author = {Choe, Seun-An and Shin, Ah-Hyung and Park, Keon-Hee and Choi, Jinwoo and Park, Gyeong-Moon}, title = {Open-Set Domain Adaptation for Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {23943-23953} }
Sculpting Holistic 3D Representation in Contrastive Language-Image-3D Pre-training-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Gao_2024_CVPR, author = {Gao, Yipeng and Wang, Zeyu and Zheng, Wei-Shi and Xie, Cihang and Zhou, Yuyin}, title = {Sculpting Holistic 3D Representation in Contrastive Language-Image-3D Pre-training}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {22998-23008} }
Probing Synergistic High-Order Interaction in Infrared and Visible Image Fusion-
[pdf]
[bibtex]@InProceedings{Zheng_2024_CVPR, author = {Zheng, Naishan and Zhou, Man and Huang, Jie and Hou, Junming and Li, Haoying and Xu, Yuan and Zhao, Feng}, title = {Probing Synergistic High-Order Interaction in Infrared and Visible Image Fusion}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {26384-26395} }
ESCAPE: Encoding Super-keypoints for Category-Agnostic Pose Estimation-
[pdf]
[supp]
[bibtex]@InProceedings{Nguyen_2024_CVPR, author = {Nguyen, Khoi Duc and Li, Chen and Lee, Gim Hee}, title = {ESCAPE: Encoding Super-keypoints for Category-Agnostic Pose Estimation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {23491-23500} }
TULIP: Multi-camera 3D Precision Assessment of Parkinson's Disease-
[pdf]
[supp]
[bibtex]@InProceedings{Kim_2024_CVPR, author = {Kim, Kyungdo and Lyu, Sihan and Mantri, Sneha and Dunn, Timothy W.}, title = {TULIP: Multi-camera 3D Precision Assessment of Parkinson's Disease}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {22551-22562} }
HybridNeRF: Efficient Neural Rendering via Adaptive Volumetric Surfaces-
[pdf]
[supp]
[bibtex]@InProceedings{Turki_2024_CVPR, author = {Turki, Haithem and Agrawal, Vasu and Bul\`o, Samuel Rota and Porzi, Lorenzo and Kontschieder, Peter and Ramanan, Deva and Zollh\"ofer, Michael and Richardt, Christian}, title = {HybridNeRF: Efficient Neural Rendering via Adaptive Volumetric Surfaces}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {19647-19656} }
Motion-adaptive Separable Collaborative Filters for Blind Motion Deblurring-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Liu_2024_CVPR, author = {Liu, Chengxu and Wang, Xuan and Xu, Xiangyu and Tian, Ruhao and Li, Shuai and Qian, Xueming and Yang, Ming-Hsuan}, title = {Motion-adaptive Separable Collaborative Filters for Blind Motion Deblurring}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {25595-25605} }
DART: Implicit Doppler Tomography for Radar Novel View Synthesis-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Huang_2024_CVPR, author = {Huang, Tianshu and Miller, John and Prabhakara, Akarsh and Jin, Tao and Laroia, Tarana and Kolter, Zico and Rowe, Anthony}, title = {DART: Implicit Doppler Tomography for Radar Novel View Synthesis}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {24118-24129} }
Genuine Knowledge from Practice: Diffusion Test-Time Adaptation for Video Adverse Weather Removal-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Yang_2024_CVPR, author = {Yang, Yijun and Wu, Hongtao and Aviles-Rivero, Angelica I. and Zhang, Yulun and Qin, Jing and Zhu, Lei}, title = {Genuine Knowledge from Practice: Diffusion Test-Time Adaptation for Video Adverse Weather Removal}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {25606-25616} }
Gradient-based Parameter Selection for Efficient Fine-Tuning-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Zhang_2024_CVPR, author = {Zhang, Zhi and Zhang, Qizhe and Gao, Zijun and Zhang, Renrui and Shutova, Ekaterina and Zhou, Shiji and Zhang, Shanghang}, title = {Gradient-based Parameter Selection for Efficient Fine-Tuning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {28566-28577} }
Domain Prompt Learning with Quaternion Networks-
[pdf]
[arXiv]
[bibtex]@InProceedings{Cao_2024_CVPR, author = {Cao, Qinglong and Xu, Zhengqin and Chen, Yuntian and Ma, Chao and Yang, Xiaokang}, title = {Domain Prompt Learning with Quaternion Networks}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {26637-26646} }
BEHAVIOR Vision Suite: Customizable Dataset Generation via Simulation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Ge_2024_CVPR, author = {Ge, Yunhao and Tang, Yihe and Xu, Jiashu and Gokmen, Cem and Li, Chengshu and Ai, Wensi and Martinez, Benjamin Jose and Aydin, Arman and Anvari, Mona and Chakravarthy, Ayush K and Yu, Hong-Xing and Wong, Josiah and Srivastava, Sanjana and Lee, Sharon and Zha, Shengxin and Itti, Laurent and Li, Yunzhu and Mart{\'\i}n-Mart{\'\i}n, Roberto and Liu, Miao and Zhang, Pengchuan and Zhang, Ruohan and Fei-Fei, Li and Wu, Jiajun}, title = {BEHAVIOR Vision Suite: Customizable Dataset Generation via Simulation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {22401-22412} }
Gaussian-Flow: 4D Reconstruction with Dynamic 3D Gaussian Particle-
[pdf]
[supp]
[bibtex]@InProceedings{Lin_2024_CVPR, author = {Lin, Youtian and Dai, Zuozhuo and Zhu, Siyu and Yao, Yao}, title = {Gaussian-Flow: 4D Reconstruction with Dynamic 3D Gaussian Particle}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {21136-21145} }
DiVAS: Video and Audio Synchronization with Dynamic Frame Rates-
[pdf]
[bibtex]@InProceedings{Fernandez-Labrador_2024_CVPR, author = {Fernandez-Labrador, Clara and Ak\c{c}ay, Mertcan and Abecassis, Eitan and Massich, Joan and Schroers, Christopher}, title = {DiVAS: Video and Audio Synchronization with Dynamic Frame Rates}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {26846-26854} }
HDRFlow: Real-Time HDR Video Reconstruction with Large Motions-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Xu_2024_CVPR, author = {Xu, Gangwei and Wang, Yujin and Gu, Jinwei and Xue, Tianfan and Yang, Xin}, title = {HDRFlow: Real-Time HDR Video Reconstruction with Large Motions}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {24851-24860} }
SPIDeRS: Structured Polarization for Invisible Depth and Reflectance Sensing-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Ichikawa_2024_CVPR, author = {Ichikawa, Tomoki and Nobuhara, Shohei and Nishino, Ko}, title = {SPIDeRS: Structured Polarization for Invisible Depth and Reflectance Sensing}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {25077-25085} }
SuperNormal: Neural Surface Reconstruction via Multi-View Normal Integration-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Cao_2024_CVPR, author = {Cao, Xu and Taketomi, Takafumi}, title = {SuperNormal: Neural Surface Reconstruction via Multi-View Normal Integration}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {20581-20590} }
ADFactory: An Effective Framework for Generalizing Optical Flow with NeRF-
[pdf]
[supp]
[bibtex]@InProceedings{Ling_2024_CVPR, author = {Ling, Han and Sun, Quansen and Sun, Yinghui and Xu, Xian and Li, Xinfeng}, title = {ADFactory: An Effective Framework for Generalizing Optical Flow with NeRF}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {20591-20600} }
How Far Can We Compress Instant-NGP-Based NeRF?-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Chen_2024_CVPR, author = {Chen, Yihang and Wu, Qianyi and Harandi, Mehrtash and Cai, Jianfei}, title = {How Far Can We Compress Instant-NGP-Based NeRF?}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {20321-20330} }
GPT4Point: A Unified Framework for Point-Language Understanding and Generation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Qi_2024_CVPR, author = {Qi, Zhangyang and Fang, Ye and Sun, Zeyi and Wu, Xiaoyang and Wu, Tong and Wang, Jiaqi and Lin, Dahua and Zhao, Hengshuang}, title = {GPT4Point: A Unified Framework for Point-Language Understanding and Generation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {26417-26427} }
SemCity: Semantic Scene Generation with Triplane Diffusion-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Lee_2024_CVPR, author = {Lee, Jumin and Lee, Sebin and Jo, Changho and Im, Woobin and Seon, Juhyeong and Yoon, Sung-Eui}, title = {SemCity: Semantic Scene Generation with Triplane Diffusion}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {28337-28347} }
Improving Semantic Correspondence with Viewpoint-Guided Spherical Maps-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Mariotti_2024_CVPR, author = {Mariotti, Octave and Mac Aodha, Oisin and Bilen, Hakan}, title = {Improving Semantic Correspondence with Viewpoint-Guided Spherical Maps}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {19521-19530} }
Dual Memory Networks: A Versatile Adaptation Approach for Vision-Language Models-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Zhang_2024_CVPR, author = {Zhang, Yabin and Zhu, Wenjie and Tang, Hui and Ma, Zhiyuan and Zhou, Kaiyang and Zhang, Lei}, title = {Dual Memory Networks: A Versatile Adaptation Approach for Vision-Language Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {28718-28728} }
LION: Empowering Multimodal Large Language Model with Dual-Level Visual Knowledge-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Chen_2024_CVPR, author = {Chen, Gongwei and Shen, Leyang and Shao, Rui and Deng, Xiang and Nie, Liqiang}, title = {LION: Empowering Multimodal Large Language Model with Dual-Level Visual Knowledge}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {26540-26550} }
Learning to Select Views for Efficient Multi-View Understanding-
[pdf]
[supp]
[bibtex]@InProceedings{Hou_2024_CVPR, author = {Hou, Yunzhong and Gould, Stephen and Zheng, Liang}, title = {Learning to Select Views for Efficient Multi-View Understanding}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {20135-20144} }
Unified Entropy Optimization for Open-Set Test-Time Adaptation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Gao_2024_CVPR, author = {Gao, Zhengqing and Zhang, Xu-Yao and Liu, Cheng-Lin}, title = {Unified Entropy Optimization for Open-Set Test-Time Adaptation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {23975-23984} }
Expandable Subspace Ensemble for Pre-Trained Model-Based Class-Incremental Learning-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Zhou_2024_CVPR, author = {Zhou, Da-Wei and Sun, Hai-Long and Ye, Han-Jia and Zhan, De-Chuan}, title = {Expandable Subspace Ensemble for Pre-Trained Model-Based Class-Incremental Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {23554-23564} }
L4D-Track: Language-to-4D Modeling Towards 6-DoF Tracking and Shape Reconstruction in 3D Point Cloud Stream-
[pdf]
[supp]
[bibtex]@InProceedings{Sun_2024_CVPR, author = {Sun, Jingtao and Wang, Yaonan and Feng, Mingtao and Guo, Yulan and Mian, Ajmal and Shou, Mike Zheng}, title = {L4D-Track: Language-to-4D Modeling Towards 6-DoF Tracking and Shape Reconstruction in 3D Point Cloud Stream}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {21146-21156} }
General Point Model Pretraining with Autoencoding and Autoregressive-
[pdf]
[supp]
[bibtex]@InProceedings{Li_2024_CVPR, author = {Li, Zhe and Gao, Zhangyang and Tan, Cheng and Ren, Bocheng and Yang, Laurence T. and Li, Stan Z.}, title = {General Point Model Pretraining with Autoencoding and Autoregressive}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {20954-20964} }
MVHumanNet: A Large-scale Dataset of Multi-view Daily Dressing Human Captures-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Xiong_2024_CVPR, author = {Xiong, Zhangyang and Li, Chenghong and Liu, Kenkun and Liao, Hongjie and Hu, Jianqiao and Zhu, Junyi and Ning, Shuliang and Qiu, Lingteng and Wang, Chongjie and Wang, Shijie and Cui, Shuguang and Han, Xiaoguang}, title = {MVHumanNet: A Large-scale Dataset of Multi-view Daily Dressing Human Captures}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {19801-19811} }
NoiseCLR: A Contrastive Learning Approach for Unsupervised Discovery of Interpretable Directions in Diffusion Models-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Dalva_2024_CVPR, author = {Dalva, Yusuf and Yanardag, Pinar}, title = {NoiseCLR: A Contrastive Learning Approach for Unsupervised Discovery of Interpretable Directions in Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {24209-24218} }
SpecNeRF: Gaussian Directional Encoding for Specular Reflections-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Ma_2024_CVPR, author = {Ma, Li and Agrawal, Vasu and Turki, Haithem and Kim, Changil and Gao, Chen and Sander, Pedro and Zollh\"ofer, Michael and Richardt, Christian}, title = {SpecNeRF: Gaussian Directional Encoding for Specular Reflections}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {21188-21198} }
Snapshot Lidar: Fourier Embedding of Amplitude and Phase for Single-Image Depth Reconstruction-
[pdf]
[supp]
[bibtex]@InProceedings{Friday_2024_CVPR, author = {Friday, Sarah and Shi, Yunzi and Cherivirala, Yaswanth and Saragadam, Vishwanath and Pediredla, Adithya}, title = {Snapshot Lidar: Fourier Embedding of Amplitude and Phase for Single-Image Depth Reconstruction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {25203-25212} }
Convolutional Prompting meets Language Models for Continual Learning-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Roy_2024_CVPR, author = {Roy, Anurag and Moulick, Riddhiman and Verma, Vinay K. and Ghosh, Saptarshi and Das, Abir}, title = {Convolutional Prompting meets Language Models for Continual Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {23616-23626} }
Distilling Semantic Priors from SAM to Efficient Image Restoration Models-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Zhang_2024_CVPR, author = {Zhang, Quan and Liu, Xiaoyu and Li, Wei and Chen, Hanting and Liu, Junchao and Hu, Jie and Xiong, Zhiwei and Yuan, Chun and Wang, Yunhe}, title = {Distilling Semantic Priors from SAM to Efficient Image Restoration Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {25409-25419} }
Learning Intra-view and Cross-view Geometric Knowledge for Stereo Matching-
[pdf]
[arXiv]
[bibtex]@InProceedings{Gong_2024_CVPR, author = {Gong, Rui and Liu, Weide and Gu, Zaiwang and Yang, Xulei and Cheng, Jun}, title = {Learning Intra-view and Cross-view Geometric Knowledge for Stereo Matching}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {20752-20762} }
Rethinking the Evaluation Protocol of Domain Generalization-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Yu_2024_CVPR, author = {Yu, Han and Zhang, Xingxuan and Xu, Renzhe and Liu, Jiashuo and He, Yue and Cui, Peng}, title = {Rethinking the Evaluation Protocol of Domain Generalization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {21897-21908} }
Aligning Logits Generatively for Principled Black-Box Knowledge Distillation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Ma_2024_CVPR, author = {Ma, Jing and Xiang, Xiang and Wang, Ke and Wu, Yuchuan and Li, Yongbin}, title = {Aligning Logits Generatively for Principled Black-Box Knowledge Distillation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {23148-23157} }
HoloVIC: Large-scale Dataset and Benchmark for Multi-Sensor Holographic Intersection and Vehicle-Infrastructure Cooperative-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Ma_2024_CVPR, author = {Ma, Cong and Qiao, Lei and Zhu, Chengkai and Liu, Kai and Kong, Zelong and Li, Qing and Zhou, Xueqi and Kan, Yuheng and Wu, Wei}, title = {HoloVIC: Large-scale Dataset and Benchmark for Multi-Sensor Holographic Intersection and Vehicle-Infrastructure Cooperative}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {22129-22138} }
LOTUS: Evasive and Resilient Backdoor Attacks through Sub-Partitioning-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Cheng_2024_CVPR, author = {Cheng, Siyuan and Tao, Guanhong and Liu, Yingqi and Shen, Guangyu and An, Shengwei and Feng, Shiwei and Xu, Xiangzhe and Zhang, Kaiyuan and Ma, Shiqing and Zhang, Xiangyu}, title = {LOTUS: Evasive and Resilient Backdoor Attacks through Sub-Partitioning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {24798-24809} }
LAN: Learning to Adapt Noise for Image Denoising-
[pdf]
[supp]
[bibtex]@InProceedings{Kim_2024_CVPR, author = {Kim, Changjin and Kim, Tae Hyun and Baik, Sungyong}, title = {LAN: Learning to Adapt Noise for Image Denoising}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {25193-25202} }
HUNTER: Unsupervised Human-centric 3D Detection via Transferring Knowledge from Synthetic Instances to Real Scenes-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Yao_2024_CVPR, author = {Yao, Yichen and Jiang, Zimo and Sun, Yujing and Zhu, Zhencai and Zhu, Xinge and Chen, Runnan and Ma, Yuexin}, title = {HUNTER: Unsupervised Human-centric 3D Detection via Transferring Knowledge from Synthetic Instances to Real Scenes}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {28120-28129} }
Improving Transferable Targeted Adversarial Attacks with Model Self-Enhancement-
[pdf]
[bibtex]@InProceedings{Wu_2024_CVPR, author = {Wu, Han and Ou, Guanyan and Wu, Weibin and Zheng, Zibin}, title = {Improving Transferable Targeted Adversarial Attacks with Model Self-Enhancement}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {24615-24624} }
Unsupervised Learning of Category-Level 3D Pose from Object-Centric Videos-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Sommer_2024_CVPR, author = {Sommer, Leonhard and Jesslen, Artur and Ilg, Eddy and Kortylewski, Adam}, title = {Unsupervised Learning of Category-Level 3D Pose from Object-Centric Videos}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {22787-22796} }
FutureHuman3D: Forecasting Complex Long-Term 3D Human Behavior from Video Observations-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Diller_2024_CVPR, author = {Diller, Christian and Funkhouser, Thomas and Dai, Angela}, title = {FutureHuman3D: Forecasting Complex Long-Term 3D Human Behavior from Video Observations}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {19902-19914} }
NightCC: Nighttime Color Constancy via Adaptive Channel Masking-
[pdf]
[bibtex]@InProceedings{Li_2024_CVPR, author = {Li, Shuwei and Tan, Robby T.}, title = {NightCC: Nighttime Color Constancy via Adaptive Channel Masking}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {25522-25531} }
UnScene3D: Unsupervised 3D Instance Segmentation for Indoor Scenes-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Rozenberszki_2024_CVPR, author = {Rozenberszki, David and Litany, Or and Dai, Angela}, title = {UnScene3D: Unsupervised 3D Instance Segmentation for Indoor Scenes}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {19957-19967} }
Nearest is Not Dearest: Towards Practical Defense against Quantization-conditioned Backdoor Attacks-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Li_2024_CVPR, author = {Li, Boheng and Cai, Yishuo and Li, Haowei and Xue, Feng and Li, Zhifeng and Li, Yiming}, title = {Nearest is Not Dearest: Towards Practical Defense against Quantization-conditioned Backdoor Attacks}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {24523-24533} }
A Simple Recipe for Language-guided Domain Generalized Segmentation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Fahes_2024_CVPR, author = {Fahes, Mohammad and Vu, Tuan-Hung and Bursuc, Andrei and P\'erez, Patrick and de Charette, Raoul}, title = {A Simple Recipe for Language-guided Domain Generalized Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {23428-23437} }
Multiagent Multitraversal Multimodal Self-Driving: Open MARS Dataset-
[pdf]
[bibtex]@InProceedings{Li_2024_CVPR, author = {Li, Yiming and Li, Zhiheng and Chen, Nuo and Gong, Moonjun and Lyu, Zonglin and Wang, Zehong and Jiang, Peili and Feng, Chen}, title = {Multiagent Multitraversal Multimodal Self-Driving: Open MARS Dataset}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {22041-22051} }
From Variance to Veracity: Unbundling and Mitigating Gradient Variance in Differentiable Bundle Adjustment Layers-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Gurumurthy_2024_CVPR, author = {Gurumurthy, Swaminathan and Ram, Karnik and Chen, Bingqing and Manchester, Zachary and Kolter, Zico}, title = {From Variance to Veracity: Unbundling and Mitigating Gradient Variance in Differentiable Bundle Adjustment Layers}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {27507-27516} }
Image-Text Co-Decomposition for Text-Supervised Semantic Segmentation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Wu_2024_CVPR, author = {Wu, Ji-Jia and Chang, Andy Chia-Hao and Chuang, Chieh-Yu and Chen, Chun-Pei and Liu, Yu-Lun and Chen, Min-Hung and Hu, Hou-Ning and Chuang, Yung-Yu and Lin, Yen-Yu}, title = {Image-Text Co-Decomposition for Text-Supervised Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {26794-26803} }
Orchestrate Latent Expertise: Advancing Online Continual Learning with Multi-Level Supervision and Reverse Self-Distillation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Yan_2024_CVPR, author = {Yan, Hongwei and Wang, Liyuan and Ma, Kaisheng and Zhong, Yi}, title = {Orchestrate Latent Expertise: Advancing Online Continual Learning with Multi-Level Supervision and Reverse Self-Distillation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {23670-23680} }
Mitigating Object Dependencies: Improving Point Cloud Self-Supervised Learning through Object Exchange-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Wu_2024_CVPR, author = {Wu, Yanhao and Zhang, Tong and Ke, Wei and Qiu, Congpei and S\"usstrunk, Sabine and Salzmann, Mathieu}, title = {Mitigating Object Dependencies: Improving Point Cloud Self-Supervised Learning through Object Exchange}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {23052-23061} }
Visual Anagrams: Generating Multi-View Optical Illusions with Diffusion Models-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Geng_2024_CVPR, author = {Geng, Daniel and Park, Inbum and Owens, Andrew}, title = {Visual Anagrams: Generating Multi-View Optical Illusions with Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {24154-24163} }
Leveraging Predicate and Triplet Learning for Scene Graph Generation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Li_2024_CVPR, author = {Li, Jiankai and Wang, Yunhong and Guo, Xiefan and Yang, Ruijie and Li, Weixin}, title = {Leveraging Predicate and Triplet Learning for Scene Graph Generation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {28369-28379} }
CoDi-2: In-Context Interleaved and Interactive Any-to-Any Generation-
[pdf]
[supp]
[bibtex]@InProceedings{Tang_2024_CVPR, author = {Tang, Zineng and Yang, Ziyi and Khademi, Mahmoud and Liu, Yang and Zhu, Chenguang and Bansal, Mohit}, title = {CoDi-2: In-Context Interleaved and Interactive Any-to-Any Generation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {27425-27434} }
Tuning Stable Rank Shrinkage: Aiming at the Overlooked Structural Risk in Fine-tuning-
[pdf]
[supp]
[bibtex]@InProceedings{Shen_2024_CVPR, author = {Shen, Sicong and Zhou, Yang and Wei, Bingzheng and Chang, Eric I-Chao and Xu, Yan}, title = {Tuning Stable Rank Shrinkage: Aiming at the Overlooked Structural Risk in Fine-tuning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {28474-28484} }
Towards Automatic Power Battery Detection: New Challenge Benchmark Dataset and Baseline-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Zhao_2024_CVPR, author = {Zhao, Xiaoqi and Pang, Youwei and Chen, Zhenyu and Yu, Qian and Zhang, Lihe and Liu, Hanqi and Zuo, Jiaming and Lu, Huchuan}, title = {Towards Automatic Power Battery Detection: New Challenge Benchmark Dataset and Baseline}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {22020-22029} }
AVFF: Audio-Visual Feature Fusion for Video Deepfake Detection-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Oorloff_2024_CVPR, author = {Oorloff, Trevine and Koppisetti, Surya and Bonettini, Nicol\`o and Solanki, Divyaraj and Colman, Ben and Yacoob, Yaser and Shahriyari, Ali and Bharaj, Gaurav}, title = {AVFF: Audio-Visual Feature Fusion for Video Deepfake Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {27102-27112} }
X-MIC: Cross-Modal Instance Conditioning for Egocentric Action Generalization-
[pdf]
[supp]
[bibtex]@InProceedings{Kukleva_2024_CVPR, author = {Kukleva, Anna and Sener, Fadime and Remelli, Edoardo and Tekin, Bugra and Sauser, Eric and Schiele, Bernt and Ma, Shugao}, title = {X-MIC: Cross-Modal Instance Conditioning for Egocentric Action Generalization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {26364-26373} }
AV-RIR: Audio-Visual Room Impulse Response Estimation-
[pdf]
[supp]
[bibtex]@InProceedings{Ratnarajah_2024_CVPR, author = {Ratnarajah, Anton and Ghosh, Sreyan and Kumar, Sonal and Chiniya, Purva and Manocha, Dinesh}, title = {AV-RIR: Audio-Visual Room Impulse Response Estimation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {27164-27175} }
Dual-Consistency Model Inversion for Non-Exemplar Class Incremental Learning-
[pdf]
[supp]
[bibtex]@InProceedings{Qiu_2024_CVPR, author = {Qiu, Zihuan and Xu, Yi and Meng, Fanman and Li, Hongliang and Xu, Linfeng and Wu, Qingbo}, title = {Dual-Consistency Model Inversion for Non-Exemplar Class Incremental Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {24025-24035} }
Not All Prompts Are Secure: A Switchable Backdoor Attack Against Pre-trained Vision Transfomers-
[pdf]
[supp]
[bibtex]@InProceedings{Yang_2024_CVPR, author = {Yang, Sheng and Bai, Jiawang and Gao, Kuofeng and Yang, Yong and Li, Yiming and Xia, Shu-Tao}, title = {Not All Prompts Are Secure: A Switchable Backdoor Attack Against Pre-trained Vision Transfomers}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {24431-24441} }
PortraitBooth: A Versatile Portrait Model for Fast Identity-preserved Personalization-
[pdf]
[arXiv]
[bibtex]@InProceedings{Peng_2024_CVPR, author = {Peng, Xu and Zhu, Junwei and Jiang, Boyuan and Tai, Ying and Luo, Donghao and Zhang, Jiangning and Lin, Wei and Jin, Taisong and Wang, Chengjie and Ji, Rongrong}, title = {PortraitBooth: A Versatile Portrait Model for Fast Identity-preserved Personalization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {27080-27090} }
Learn from View Correlation: An Anchor Enhancement Strategy for Multi-view Clustering-
[pdf]
[supp]
[bibtex]@InProceedings{Liu_2024_CVPR, author = {Liu, Suyuan and Liang, Ke and Dong, Zhibin and Wang, Siwei and Yang, Xihong and Zhou, Sihang and Zhu, En and Liu, Xinwang}, title = {Learn from View Correlation: An Anchor Enhancement Strategy for Multi-view Clustering}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {26151-26161} }
APSeg: Auto-Prompt Network for Cross-Domain Few-Shot Semantic Segmentation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{He_2024_CVPR, author = {He, Weizhao and Zhang, Yang and Zhuo, Wei and Shen, Linlin and Yang, Jiaqi and Deng, Songhe and Sun, Liang}, title = {APSeg: Auto-Prompt Network for Cross-Domain Few-Shot Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {23762-23772} }
Enhancing Visual Continual Learning with Language-Guided Supervision-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Ni_2024_CVPR, author = {Ni, Bolin and Zhao, Hongbo and Zhang, Chenghao and Hu, Ke and Meng, Gaofeng and Zhang, Zhaoxiang and Xiang, Shiming}, title = {Enhancing Visual Continual Learning with Language-Guided Supervision}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {24068-24077} }
Revamping Federated Learning Security from a Defender's Perspective: A Unified Defense with Homomorphic Encrypted Data Space-
[pdf]
[supp]
[bibtex]@InProceedings{Kumar_2024_CVPR, author = {Kumar, K Naveen and Mitra, Reshmi and Mohan, C Krishna}, title = {Revamping Federated Learning Security from a Defender's Perspective: A Unified Defense with Homomorphic Encrypted Data Space}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {24387-24397} }
A Dynamic Kernel Prior Model for Unsupervised Blind Image Super-Resolution-
[pdf]
[arXiv]
[bibtex]@InProceedings{Yang_2024_CVPR, author = {Yang, Zhixiong and Xia, Jingyuan and Li, Shengxi and Huang, Xinghua and Zhang, Shuanghui and Liu, Zhen and Fu, Yaowen and Liu, Yongxiang}, title = {A Dynamic Kernel Prior Model for Unsupervised Blind Image Super-Resolution}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {26046-26056} }
Mitigating Noisy Correspondence by Geometrical Structure Consistency Learning-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Zhao_2024_CVPR, author = {Zhao, Zihua and Chen, Mengxi and Dai, Tianjie and Yao, Jiangchao and Han, Bo and Zhang, Ya and Wang, Yanfeng}, title = {Mitigating Noisy Correspondence by Geometrical Structure Consistency Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {27381-27390} }
DVMNet: Computing Relative Pose for Unseen Objects Beyond Hypotheses-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Zhao_2024_CVPR, author = {Zhao, Chen and Zhang, Tong and Dang, Zheng and Salzmann, Mathieu}, title = {DVMNet: Computing Relative Pose for Unseen Objects Beyond Hypotheses}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {20485-20495} }
MuRF: Multi-Baseline Radiance Fields-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Xu_2024_CVPR, author = {Xu, Haofei and Chen, Anpei and Chen, Yuedong and Sakaridis, Christos and Zhang, Yulun and Pollefeys, Marc and Geiger, Andreas and Yu, Fisher}, title = {MuRF: Multi-Baseline Radiance Fields}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {20041-20050} }
Flattening the Parent Bias: Hierarchical Semantic Segmentation in the Poincare Ball-
[pdf]
[supp]
[bibtex]@InProceedings{Weber_2024_CVPR, author = {Weber, Simon and Z\"ong\"ur, Bar?? and Araslanov, Nikita and Cremers, Daniel}, title = {Flattening the Parent Bias: Hierarchical Semantic Segmentation in the Poincare Ball}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {28223-28232} }
MVBench: A Comprehensive Multi-modal Video Understanding Benchmark-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Li_2024_CVPR, author = {Li, Kunchang and Wang, Yali and He, Yinan and Li, Yizhuo and Wang, Yi and Liu, Yi and Wang, Zun and Xu, Jilan and Chen, Guo and Luo, Ping and Wang, Limin and Qiao, Yu}, title = {MVBench: A Comprehensive Multi-modal Video Understanding Benchmark}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {22195-22206} }
An Aggregation-Free Federated Learning for Tackling Data Heterogeneity-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Wang_2024_CVPR, author = {Wang, Yuan and Fu, Huazhu and Kanagavelu, Renuga and Wei, Qingsong and Liu, Yong and Goh, Rick Siow Mong}, title = {An Aggregation-Free Federated Learning for Tackling Data Heterogeneity}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {26233-26242} }
Hierarchical Intra-modal Correlation Learning for Label-free 3D Semantic Segmentation-
[pdf]
[supp]
[bibtex]@InProceedings{Kang_2024_CVPR, author = {Kang, Xin and Chu, Lei and Li, Jiahao and Chen, Xuejin and Lu, Yan}, title = {Hierarchical Intra-modal Correlation Learning for Label-free 3D Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {28244-28253} }
DiffSal: Joint Audio and Video Learning for Diffusion Saliency Prediction-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Xiong_2024_CVPR, author = {Xiong, Junwen and Zhang, Peng and You, Tao and Li, Chuanyue and Huang, Wei and Zha, Yufei}, title = {DiffSal: Joint Audio and Video Learning for Diffusion Saliency Prediction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {27273-27283} }
Revisiting Single Image Reflection Removal In the Wild-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Zhu_2024_CVPR, author = {Zhu, Yurui and Fu, Xueyang and Jiang, Peng-Tao and Zhang, Hao and Sun, Qibin and Chen, Jinwei and Zha, Zheng-Jun and Li, Bo}, title = {Revisiting Single Image Reflection Removal In the Wild}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {25468-25478} }
SinSR: Diffusion-Based Image Super-Resolution in a Single Step-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Wang_2024_CVPR, author = {Wang, Yufei and Yang, Wenhan and Chen, Xinyuan and Wang, Yaohui and Guo, Lanqing and Chau, Lap-Pui and Liu, Ziwei and Qiao, Yu and Kot, Alex C. and Wen, Bihan}, title = {SinSR: Diffusion-Based Image Super-Resolution in a Single Step}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {25796-25805} }
Systematic Comparison of Semi-supervised and Self-supervised Learning for Medical Image Classification-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Huang_2024_CVPR, author = {Huang, Zhe and Jiang, Ruijie and Aeron, Shuchin and Hughes, Michael C.}, title = {Systematic Comparison of Semi-supervised and Self-supervised Learning for Medical Image Classification}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {22282-22293} }
MSU-4S - The Michigan State University Four Seasons Dataset-
[pdf]
[bibtex]@InProceedings{Kent_2024_CVPR, author = {Kent, Daniel and Alyaqoub, Mohammed and Lu, Xiaohu and Khatounabadi, Hamed and Sung, Kookjin and Scheller, Cole and Dalat, Alexander and bin Thabit, Asma and Whitley, Roberto and Radha, Hayder}, title = {MSU-4S - The Michigan State University Four Seasons Dataset}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {22658-22667} }
Improving Plasticity in Online Continual Learning via Collaborative Learning-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Wang_2024_CVPR, author = {Wang, Maorong and Michel, Nicolas and Xiao, Ling and Yamasaki, Toshihiko}, title = {Improving Plasticity in Online Continual Learning via Collaborative Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {23460-23469} }
Spectral and Polarization Vision: Spectro-polarimetric Real-world Dataset-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Jeon_2024_CVPR, author = {Jeon, Yujin and Choi, Eunsue and Kim, Youngchan and Moon, Yunseong and Omer, Khalid and Heide, Felix and Baek, Seung-Hwan}, title = {Spectral and Polarization Vision: Spectro-polarimetric Real-world Dataset}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {22098-22108} }
Transfer CLIP for Generalizable Image Denoising-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Cheng_2024_CVPR, author = {Cheng, Jun and Liang, Dong and Tan, Shan}, title = {Transfer CLIP for Generalizable Image Denoising}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {25974-25984} }
Revisiting Adversarial Training at Scale-
[pdf]
[arXiv]
[bibtex]@InProceedings{Wang_2024_CVPR, author = {Wang, Zeyu and Li, Xianhang and Zhu, Hongru and Xie, Cihang}, title = {Revisiting Adversarial Training at Scale}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {24675-24685} }
Towards Fairness-Aware Adversarial Learning-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Zhang_2024_CVPR, author = {Zhang, Yanghao and Zhang, Tianle and Mu, Ronghui and Huang, Xiaowei and Ruan, Wenjie}, title = {Towards Fairness-Aware Adversarial Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {24746-24755} }
MirageRoom: 3D Scene Segmentation with 2D Pre-trained Models by Mirage Projection-
[pdf]
[supp]
[bibtex]@InProceedings{Sun_2024_CVPR, author = {Sun, Haowen and Duan, Yueqi and Yan, Juncheng and Liu, Yifan and Lu, Jiwen}, title = {MirageRoom: 3D Scene Segmentation with 2D Pre-trained Models by Mirage Projection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {20237-20246} }
In2SET: Intra-Inter Similarity Exploiting Transformer for Dual-Camera Compressive Hyperspectral Imaging-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Wang_2024_CVPR, author = {Wang, Xin and Wang, Lizhi and Ma, Xiangtian and Zhang, Maoqing and Zhu, Lin and Huang, Hua}, title = {In2SET: Intra-Inter Similarity Exploiting Transformer for Dual-Camera Compressive Hyperspectral Imaging}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {24881-24891} }
Look-Up Table Compression for Efficient Image Restoration-
[pdf]
[supp]
[bibtex]@InProceedings{Li_2024_CVPR, author = {Li, Yinglong and Li, Jiacheng and Xiong, Zhiwei}, title = {Look-Up Table Compression for Efficient Image Restoration}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {26016-26025} }
TextNeRF: A Novel Scene-Text Image Synthesis Method based on Neural Radiance Fields-
[pdf]
[supp]
[bibtex]@InProceedings{Cui_2024_CVPR, author = {Cui, Jialei and Du, Jianwei and Liu, Wenzhuo and Lian, Zhouhui}, title = {TextNeRF: A Novel Scene-Text Image Synthesis Method based on Neural Radiance Fields}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {22272-22281} }
Dr.Hair: Reconstructing Scalp-Connected Hair Strands without Pre-Training via Differentiable Rendering of Line Segments-
[pdf]
[supp]
[bibtex]@InProceedings{Takimoto_2024_CVPR, author = {Takimoto, Yusuke and Takehara, Hikari and Sato, Hiroyuki and Zhu, Zihao and Zheng, Bo}, title = {Dr.Hair: Reconstructing Scalp-Connected Hair Strands without Pre-Training via Differentiable Rendering of Line Segments}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {20601-20611} }
DiVa-360: The Dynamic Visual Dataset for Immersive Neural Fields-
[pdf]
[supp]
[bibtex]@InProceedings{Lu_2024_CVPR, author = {Lu, Cheng-You and Zhou, Peisen and Xing, Angela and Pokhariya, Chandradeep and Dey, Arnab and Shah, Ishaan Nikhil and Mavidipalli, Rugved and Hu, Dylan and Comport, Andrew I. and Chen, Kefan and Sridhar, Srinath}, title = {DiVa-360: The Dynamic Visual Dataset for Immersive Neural Fields}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {22466-22476} }
FSC: Few-point Shape Completion-
[pdf]
[arXiv]
[bibtex]@InProceedings{Wu_2024_CVPR, author = {Wu, Xianzu and Wu, Xianfeng and Luan, Tianyu and Bai, Yajing and Lai, Zhongyuan and Yuan, Junsong}, title = {FSC: Few-point Shape Completion}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {26077-26087} }
T-VSL: Text-Guided Visual Sound Source Localization in Mixtures-
[pdf]
[supp]
[bibtex]@InProceedings{Mahmud_2024_CVPR, author = {Mahmud, Tanvir and Tian, Yapeng and Marculescu, Diana}, title = {T-VSL: Text-Guided Visual Sound Source Localization in Mixtures}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {26742-26751} }
VCoder: Versatile Vision Encoders for Multimodal Large Language Models-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Jain_2024_CVPR, author = {Jain, Jitesh and Yang, Jianwei and Shi, Humphrey}, title = {VCoder: Versatile Vision Encoders for Multimodal Large Language Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {27992-28002} }
Event-based Visible and Infrared Fusion via Multi-task Collaboration-
[pdf]
[supp]
[bibtex]@InProceedings{Geng_2024_CVPR, author = {Geng, Mengyue and Zhu, Lin and Wang, Lizhi and Zhang, Wei and Xiong, Ruiqin and Tian, Yonghong}, title = {Event-based Visible and Infrared Fusion via Multi-task Collaboration}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {26929-26939} }
RegionPLC: Regional Point-Language Contrastive Learning for Open-World 3D Scene Understanding-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Yang_2024_CVPR, author = {Yang, Jihan and Ding, Runyu and Deng, Weipeng and Wang, Zhe and Qi, Xiaojuan}, title = {RegionPLC: Regional Point-Language Contrastive Learning for Open-World 3D Scene Understanding}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {19823-19832} }
Three Pillars Improving Vision Foundation Model Distillation for Lidar-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Puy_2024_CVPR, author = {Puy, Gilles and Gidaris, Spyros and Boulch, Alexandre and Sim\'eoni, Oriane and Sautier, Corentin and P\'erez, Patrick and Bursuc, Andrei and Marlet, Renaud}, title = {Three Pillars Improving Vision Foundation Model Distillation for Lidar}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {21519-21529} }
ShapeWalk: Compositional Shape Editing Through Language-Guided Chains-
[pdf]
[supp]
[bibtex]@InProceedings{Slim_2024_CVPR, author = {Slim, Habib and Elhoseiny, Mohamed}, title = {ShapeWalk: Compositional Shape Editing Through Language-Guided Chains}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {22574-22583} }
MESA: Matching Everything by Segmenting Anything-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Zhang_2024_CVPR, author = {Zhang, Yesheng and Zhao, Xu}, title = {MESA: Matching Everything by Segmenting Anything}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {20217-20226} }
Learning Degradation-Independent Representations for Camera ISP Pipelines-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Guo_2024_CVPR, author = {Guo, Yanhui and Luo, Fangzhou and Wu, Xiaolin}, title = {Learning Degradation-Independent Representations for Camera ISP Pipelines}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {25774-25783} }
OmniGlue: Generalizable Feature Matching with Foundation Model Guidance-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Jiang_2024_CVPR, author = {Jiang, Hanwen and Karpur, Arjun and Cao, Bingyi and Huang, Qixing and Araujo, Andr\'e}, title = {OmniGlue: Generalizable Feature Matching with Foundation Model Guidance}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {19865-19875} }
OmniSDF: Scene Reconstruction using Omnidirectional Signed Distance Functions and Adaptive Binoctrees-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Kim_2024_CVPR, author = {Kim, Hakyeong and Meuleman, Andreas and Jang, Hyeonjoong and Tompkin, James and Kim, Min H.}, title = {OmniSDF: Scene Reconstruction using Omnidirectional Signed Distance Functions and Adaptive Binoctrees}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {20227-20236} }
Generating Content for HDR Deghosting from Frequency View-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Hu_2024_CVPR, author = {Hu, Tao and Yan, Qingsen and Qi, Yuankai and Zhang, Yanning}, title = {Generating Content for HDR Deghosting from Frequency View}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {25732-25741} }
LiDAR-Net: A Real-scanned 3D Point Cloud Dataset for Indoor Scenes-
[pdf]
[supp]
[bibtex]@InProceedings{Guo_2024_CVPR, author = {Guo, Yanwen and Li, Yuanqi and Ren, Dayong and Zhang, Xiaohong and Li, Jiawei and Pu, Liang and Ma, Changfeng and Zhan, Xiaoyu and Guo, Jie and Wei, Mingqiang and Zhang, Yan and Yu, Piaopiao and Yang, Shuangyu and Ji, Donghao and Ye, Huisheng and Sun, Hao and Liu, Yansong and Chen, Yinuo and Zhu, Jiaqi and Liu, Hongyu}, title = {LiDAR-Net: A Real-scanned 3D Point Cloud Dataset for Indoor Scenes}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {21989-21999} }
Rich Human Feedback for Text-to-Image Generation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Liang_2024_CVPR, author = {Liang, Youwei and He, Junfeng and Li, Gang and Li, Peizhao and Klimovskiy, Arseniy and Carolan, Nicholas and Sun, Jiao and Pont-Tuset, Jordi and Young, Sarah and Yang, Feng and Ke, Junjie and Dvijotham, Krishnamurthy Dj and Collins, Katherine M. and Luo, Yiwen and Li, Yang and Kohlhoff, Kai J and Ramachandran, Deepak and Navalpakkam, Vidhya}, title = {Rich Human Feedback for Text-to-Image Generation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {19401-19411} }
Map-Relative Pose Regression for Visual Re-Localization-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Chen_2024_CVPR, author = {Chen, Shuai and Cavallari, Tommaso and Prisacariu, Victor Adrian and Brachmann, Eric}, title = {Map-Relative Pose Regression for Visual Re-Localization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {20665-20674} }
Implicit Event-RGBD Neural SLAM-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Qu_2024_CVPR, author = {Qu, Delin and Yan, Chi and Wang, Dong and Yin, Jie and Chen, Qizhi and Xu, Dan and Zhang, Yiting and Zhao, Bin and Li, Xuelong}, title = {Implicit Event-RGBD Neural SLAM}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {19584-19594} }
Domain-Specific Block Selection and Paired-View Pseudo-Labeling for Online Test-Time Adaptation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Yu_2024_CVPR, author = {Yu, Yeonguk and Shin, Sungho and Back, Seunghyeok and Ko, Mihwan and Noh, Sangjun and Lee, Kyoobin}, title = {Domain-Specific Block Selection and Paired-View Pseudo-Labeling for Online Test-Time Adaptation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {22723-22732} }
Aerial Lifting: Neural Urban Semantic and Building Instance Lifting from Aerial Imagery-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Zhang_2024_CVPR, author = {Zhang, Yuqi and Chen, Guanying and Chen, Jiaxing and Cui, Shuguang}, title = {Aerial Lifting: Neural Urban Semantic and Building Instance Lifting from Aerial Imagery}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {21092-21103} }
Learning with Structural Labels for Learning with Noisy Labels-
[pdf]
[supp]
[bibtex]@InProceedings{Kim_2024_CVPR, author = {Kim, Noo-ri and Lee, Jin-Seop and Lee, Jee-Hyong}, title = {Learning with Structural Labels for Learning with Noisy Labels}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {27610-27620} }
DeMatch: Deep Decomposition of Motion Field for Two-View Correspondence Learning-
[pdf]
[supp]
[bibtex]@InProceedings{Zhang_2024_CVPR, author = {Zhang, Shihua and Li, Zizhuo and Gao, Yuan and Ma, Jiayi}, title = {DeMatch: Deep Decomposition of Motion Field for Two-View Correspondence Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {20278-20287} }
Sherpa3D: Boosting High-Fidelity Text-to-3D Generation via Coarse 3D Prior-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Liu_2024_CVPR, author = {Liu, Fangfu and Wu, Diankun and Wei, Yi and Rao, Yongming and Duan, Yueqi}, title = {Sherpa3D: Boosting High-Fidelity Text-to-3D Generation via Coarse 3D Prior}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {20763-20774} }
A Unified Diffusion Framework for Scene-aware Human Motion Estimation from Sparse Signals-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Tang_2024_CVPR, author = {Tang, Jiangnan and Wang, Jingya and Ji, Kaiyang and Xu, Lan and Yu, Jingyi and Shi, Ye}, title = {A Unified Diffusion Framework for Scene-aware Human Motion Estimation from Sparse Signals}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {21251-21262} }
Single Domain Generalization for Crowd Counting-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Peng_2024_CVPR, author = {Peng, Zhuoxuan and Chan, S.-H. Gary}, title = {Single Domain Generalization for Crowd Counting}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {28025-28034} }
Task-Aware Encoder Control for Deep Video Compression-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Ge_2024_CVPR, author = {Ge, Xingtong and Luo, Jixiang and Zhang, Xinjie and Xu, Tongda and Lu, Guo and He, Dailan and Geng, Jing and Wang, Yan and Zhang, Jun and Qin, Hongwei}, title = {Task-Aware Encoder Control for Deep Video Compression}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {26036-26045} }
Long-Tail Class Incremental Learning via Independent Sub-prototype Construction-
[pdf]
[supp]
[bibtex]@InProceedings{Wang_2024_CVPR, author = {Wang, Xi and Yang, Xu and Yin, Jie and Wei, Kun and Deng, Cheng}, title = {Long-Tail Class Incremental Learning via Independent Sub-prototype Construction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {28598-28607} }
Learning with Unreliability: Fast Few-shot Voxel Radiance Fields with Relative Geometric Consistency-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Xu_2024_CVPR, author = {Xu, Yingjie and Liu, Bangzhen and Tang, Hao and Deng, Bailin and He, Shengfeng}, title = {Learning with Unreliability: Fast Few-shot Voxel Radiance Fields with Relative Geometric Consistency}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {20342-20351} }
Towards Understanding and Improving Adversarial Robustness of Vision Transformers-
[pdf]
[supp]
[bibtex]@InProceedings{Jain_2024_CVPR, author = {Jain, Samyak and Dutta, Tanima}, title = {Towards Understanding and Improving Adversarial Robustness of Vision Transformers}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {24736-24745} }
S-DyRF: Reference-Based Stylized Radiance Fields for Dynamic Scenes-
[pdf]
[supp]
[bibtex]@InProceedings{Li_2024_CVPR, author = {Li, Xingyi and Cao, Zhiguo and Wu, Yizheng and Wang, Kewei and Xian, Ke and Wang, Zhe and Lin, Guosheng}, title = {S-DyRF: Reference-Based Stylized Radiance Fields for Dynamic Scenes}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {20102-20112} }
What How and When Should Object Detectors Update in Continually Changing Test Domains?-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Yoo_2024_CVPR, author = {Yoo, Jayeon and Lee, Dongkwan and Chung, Inseop and Kim, Donghyun and Kwak, Nojun}, title = {What How and When Should Object Detectors Update in Continually Changing Test Domains?}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {23354-23363} }
Bayesian Exploration of Pre-trained Models for Low-shot Image Classification-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Miao_2024_CVPR, author = {Miao, Yibo and Lei, Yu and Zhou, Feng and Deng, Zhijie}, title = {Bayesian Exploration of Pre-trained Models for Low-shot Image Classification}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {23849-23859} }
RoMa: Robust Dense Feature Matching-
[pdf]
[supp]
[bibtex]@InProceedings{Edstedt_2024_CVPR, author = {Edstedt, Johan and Sun, Qiyu and B\"okman, Georg and Wadenb\"ack, M\r{a}rten and Felsberg, Michael}, title = {RoMa: Robust Dense Feature Matching}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {19790-19800} }
Insights from the Use of Previously Unseen Neural Architecture Search Datasets-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Geada_2024_CVPR, author = {Geada, Rob and Towers, David and Forshaw, Matthew and Atapour-Abarghouei, Amir and McGough, A. Stephen}, title = {Insights from the Use of Previously Unseen Neural Architecture Search Datasets}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {22541-22550} }
Adversarially Robust Few-shot Learning via Parameter Co-distillation of Similarity and Class Concept Learners-
[pdf]
[supp]
[bibtex]@InProceedings{Dong_2024_CVPR, author = {Dong, Junhao and Koniusz, Piotr and Chen, Junxi and Xie, Xiaohua and Ong, Yew-Soon}, title = {Adversarially Robust Few-shot Learning via Parameter Co-distillation of Similarity and Class Concept Learners}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {28535-28544} }
APISR: Anime Production Inspired Real-World Anime Super-Resolution-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Wang_2024_CVPR, author = {Wang, Boyang and Yang, Fengyu and Yu, Xihang and Zhang, Chao and Zhao, Hanbin}, title = {APISR: Anime Production Inspired Real-World Anime Super-Resolution}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {25574-25584} }
MVCPS-NeuS: Multi-view Constrained Photometric Stereo for Neural Surface Reconstruction-
[pdf]
[supp]
[bibtex]@InProceedings{Santo_2024_CVPR, author = {Santo, Hiroaki and Okura, Fumio and Matsushita, Yasuyuki}, title = {MVCPS-NeuS: Multi-view Constrained Photometric Stereo for Neural Surface Reconstruction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {20475-20484} }
ULIP-2: Towards Scalable Multimodal Pre-training for 3D Understanding-
[pdf]
[supp]
[bibtex]@InProceedings{Xue_2024_CVPR, author = {Xue, Le and Yu, Ning and Zhang, Shu and Panagopoulou, Artemis and Li, Junnan 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-2: Towards Scalable Multimodal Pre-training for 3D Understanding}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {27091-27101} }
WaveMo: Learning Wavefront Modulations to See Through Scattering-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Xie_2024_CVPR, author = {Xie, Mingyang and Guo, Haiyun and Feng, Brandon Y. and Jin, Lingbo and Veeraraghavan, Ashok and Metzler, Christopher A.}, title = {WaveMo: Learning Wavefront Modulations to See Through Scattering}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {25276-25285} }
Integrating Efficient Optimal Transport and Functional Maps For Unsupervised Shape Correspondence Learning-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Le_2024_CVPR, author = {Le, Tung and Nguyen, Khai and Sun, Shanlin and Ho, Nhat and Xie, Xiaohui}, title = {Integrating Efficient Optimal Transport and Functional Maps For Unsupervised Shape Correspondence Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {23188-23198} }
ODCR: Orthogonal Decoupling Contrastive Regularization for Unpaired Image Dehazing-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Wang_2024_CVPR, author = {Wang, Zhongze and Zhao, Haitao and Peng, Jingchao and Yao, Lujian and Zhao, Kaijie}, title = {ODCR: Orthogonal Decoupling Contrastive Regularization for Unpaired Image Dehazing}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {25479-25489} }
OmniSeg3D: Omniversal 3D Segmentation via Hierarchical Contrastive Learning-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Ying_2024_CVPR, author = {Ying, Haiyang and Yin, Yixuan and Zhang, Jinzhi and Wang, Fan and Yu, Tao and Huang, Ruqi and Fang, Lu}, title = {OmniSeg3D: Omniversal 3D Segmentation via Hierarchical Contrastive Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {20612-20622} }
Simple Semantic-Aided Few-Shot Learning-
[pdf]
[arXiv]
[bibtex]@InProceedings{Zhang_2024_CVPR, author = {Zhang, Hai and Xu, Junzhe and Jiang, Shanlin and He, Zhenan}, title = {Simple Semantic-Aided Few-Shot Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {28588-28597} }
Leveraging Cross-Modal Neighbor Representation for Improved CLIP Classification-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Yi_2024_CVPR, author = {Yi, Chao and Ren, Lu and Zhan, De-Chuan and Ye, Han-Jia}, title = {Leveraging Cross-Modal Neighbor Representation for Improved CLIP Classification}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {27402-27411} }
Revisiting Adversarial Training Under Long-Tailed Distributions-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Yue_2024_CVPR, author = {Yue, Xinli and Mou, Ningping and Wang, Qian and Zhao, Lingchen}, title = {Revisiting Adversarial Training Under Long-Tailed Distributions}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {24492-24501} }
Monkey: Image Resolution and Text Label Are Important Things for Large Multi-modal Models-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Li_2024_CVPR, author = {Li, Zhang and Yang, Biao and Liu, Qiang and Ma, Zhiyin and Zhang, Shuo and Yang, Jingxu and Sun, Yabo and Liu, Yuliang and Bai, Xiang}, title = {Monkey: Image Resolution and Text Label Are Important Things for Large Multi-modal Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {26763-26773} }
Decompose-and-Compose: A Compositional Approach to Mitigating Spurious Correlation-
[pdf]
[supp]
[bibtex]@InProceedings{Noohdani_2024_CVPR, author = {Noohdani, Fahimeh Hosseini and Hosseini, Parsa and Parast, Aryan Yazdan and Araghi, Hamidreza Yaghoubi and Baghshah, Mahdieh Soleymani}, title = {Decompose-and-Compose: A Compositional Approach to Mitigating Spurious Correlation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {27662-27671} }
BEM: Balanced and Entropy-based Mix for Long-Tailed Semi-Supervised Learning-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Zheng_2024_CVPR, author = {Zheng, Hongwei and Zhou, Linyuan and Li, Han and Su, Jinming and Wei, Xiaoming and Xu, Xiaoming}, title = {BEM: Balanced and Entropy-based Mix for Long-Tailed Semi-Supervised Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {22893-22903} }
HUGS: Holistic Urban 3D Scene Understanding via Gaussian Splatting-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Zhou_2024_CVPR, author = {Zhou, Hongyu and Shao, Jiahao and Xu, Lu and Bai, Dongfeng and Qiu, Weichao and Liu, Bingbing and Wang, Yue and Geiger, Andreas and Liao, Yiyi}, title = {HUGS: Holistic Urban 3D Scene Understanding via Gaussian Splatting}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {21336-21345} }
GeoAuxNet: Towards Universal 3D Representation Learning for Multi-sensor Point Clouds-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Zhang_2024_CVPR, author = {Zhang, Shengjun and Fei, Xin and Duan, Yueqi}, title = {GeoAuxNet: Towards Universal 3D Representation Learning for Multi-sensor Point Clouds}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {20019-20028} }
Unveiling the Power of Audio-Visual Early Fusion Transformers with Dense Interactions through Masked Modeling-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Mo_2024_CVPR, author = {Mo, Shentong and Morgado, Pedro}, title = {Unveiling the Power of Audio-Visual Early Fusion Transformers with Dense Interactions through Masked Modeling}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {27186-27196} }
RepKPU: Point Cloud Upsampling with Kernel Point Representation and Deformation-
[pdf]
[supp]
[bibtex]@InProceedings{Rong_2024_CVPR, author = {Rong, Yi and Zhou, Haoran and Xia, Kang and Mei, Cheng and Wang, Jiahao and Lu, Tong}, title = {RepKPU: Point Cloud Upsampling with Kernel Point Representation and Deformation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {21050-21060} }
ConCon-Chi: Concept-Context Chimera Benchmark for Personalized Vision-Language Tasks-
[pdf]
[supp]
[bibtex]@InProceedings{Rosasco_2024_CVPR, author = {Rosasco, Andrea and Berti, Stefano and Pasquale, Giulia and Malafronte, Damiano and Sato, Shogo and Segawa, Hiroyuki and Inada, Tetsugo and Natale, Lorenzo}, title = {ConCon-Chi: Concept-Context Chimera Benchmark for Personalized Vision-Language Tasks}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {22239-22248} }
MeshGPT: Generating Triangle Meshes with Decoder-Only Transformers-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Siddiqui_2024_CVPR, author = {Siddiqui, Yawar and Alliegro, Antonio and Artemov, Alexey and Tommasi, Tatiana and Sirigatti, Daniele and Rosov, Vladislav and Dai, Angela and Nie{\ss}ner, Matthias}, title = {MeshGPT: Generating Triangle Meshes with Decoder-Only Transformers}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {19615-19625} }
Image Restoration by Denoising Diffusion Models with Iteratively Preconditioned Guidance-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Garber_2024_CVPR, author = {Garber, Tomer and Tirer, Tom}, title = {Image Restoration by Denoising Diffusion Models with Iteratively Preconditioned Guidance}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {25245-25254} }
MTMMC: A Large-Scale Real-World Multi-Modal Camera Tracking Benchmark-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Woo_2024_CVPR, author = {Woo, Sanghyun and Park, Kwanyong and Shin, Inkyu and Kim, Myungchul and Kweon, In So}, title = {MTMMC: A Large-Scale Real-World Multi-Modal Camera Tracking Benchmark}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {22335-22346} }
DAP: A Dynamic Adversarial Patch for Evading Person Detectors-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Guesmi_2024_CVPR, author = {Guesmi, Amira and Ding, Ruitian and Hanif, Muhammad Abdullah and Alouani, Ihsen and Shafique, Muhammad}, title = {DAP: A Dynamic Adversarial Patch for Evading Person Detectors}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {24595-24604} }
Learned Lossless Image Compression based on Bit Plane Slicing-
[pdf]
[supp]
[bibtex]@InProceedings{Zhang_2024_CVPR, author = {Zhang, Zhe and Wang, Huairui and Chen, Zhenzhong and Liu, Shan}, title = {Learned Lossless Image Compression based on Bit Plane Slicing}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {27579-27588} }
Flexible Depth Completion for Sparse and Varying Point Densities-
[pdf]
[supp]
[bibtex]@InProceedings{Park_2024_CVPR, author = {Park, Jinhyung and Li, Yu-Jhe and Kitani, Kris}, title = {Flexible Depth Completion for Sparse and Varying Point Densities}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {21540-21550} }
Shadows Don't Lie and Lines Can't Bend! Generative Models don't know Projective Geometry...for now-
[pdf]
[supp]
[bibtex]@InProceedings{Sarkar_2024_CVPR, author = {Sarkar, Ayush and Mai, Hanlin and Mahapatra, Amitabh and Lazebnik, Svetlana and Forsyth, D.A. and Bhattad, Anand}, title = {Shadows Don't Lie and Lines Can't Bend! Generative Models don't know Projective Geometry...for now}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {28140-28149} }
GEARS: Local Geometry-aware Hand-object Interaction Synthesis-
[pdf]
[arXiv]
[bibtex]@InProceedings{Zhou_2024_CVPR, author = {Zhou, Keyang and Bhatnagar, Bharat Lal and Lenssen, Jan Eric and Pons-Moll, Gerard}, title = {GEARS: Local Geometry-aware Hand-object Interaction Synthesis}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {20634-20643} }
CodedEvents: Optimal Point-Spread-Function Engineering for 3D-Tracking with Event Cameras-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Shah_2024_CVPR, author = {Shah, Sachin and Chan, Matthew A. and Cai, Haoming and Chen, Jingxi and Kulshrestha, Sakshum and Singh, Chahat Deep and Aloimonos, Yiannis and Metzler, Christopher A.}, title = {CodedEvents: Optimal Point-Spread-Function Engineering for 3D-Tracking with Event Cameras}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {25265-25275} }
Learning Discriminative Dynamics with Label Corruption for Noisy Label Detection-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Kim_2024_CVPR, author = {Kim, Suyeon and Lee, Dongha and Kang, SeongKu and Chae, Sukang and Jang, Sanghwan and Yu, Hwanjo}, title = {Learning Discriminative Dynamics with Label Corruption for Noisy Label Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {22477-22487} }
DiPrompT: Disentangled Prompt Tuning for Multiple Latent Domain Generalization in Federated Learning-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Bai_2024_CVPR, author = {Bai, Sikai and Zhang, Jie and Guo, Song and Li, Shuaicheng and Guo, Jingcai and Hou, Jun and Han, Tao and Lu, Xiaocheng}, title = {DiPrompT: Disentangled Prompt Tuning for Multiple Latent Domain Generalization in Federated Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {27284-27293} }
Adversarial Distillation Based on Slack Matching and Attribution Region Alignment-
[pdf]
[supp]
[bibtex]@InProceedings{Yin_2024_CVPR, author = {Yin, Shenglin and Xiao, Zhen and Song, Mingxuan and Long, Jieyi}, title = {Adversarial Distillation Based on Slack Matching and Attribution Region Alignment}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {24605-24614} }
Boosting Spike Camera Image Reconstruction from a Perspective of Dealing with Spike Fluctuations-
[pdf]
[supp]
[bibtex]@InProceedings{Zhao_2024_CVPR, author = {Zhao, Rui and Xiong, Ruiqin and Zhao, Jing and Zhang, Jian and Fan, Xiaopeng and Yu, Zhaofei and Huang, Tiejun}, title = {Boosting Spike Camera Image Reconstruction from a Perspective of Dealing with Spike Fluctuations}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {24955-24965} }
Text-guided Explorable Image Super-resolution-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Gandikota_2024_CVPR, author = {Gandikota, Kanchana Vaishnavi and Chandramouli, Paramanand}, title = {Text-guided Explorable Image Super-resolution}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {25900-25911} }
Improving the Generalization of Segmentation Foundation Model under Distribution Shift via Weakly Supervised Adaptation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Zhang_2024_CVPR, author = {Zhang, Haojie and Su, Yongyi and Xu, Xun and Jia, Kui}, title = {Improving the Generalization of Segmentation Foundation Model under Distribution Shift via Weakly Supervised Adaptation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {23385-23395} }
Correspondence-Free Non-Rigid Point Set Registration Using Unsupervised Clustering Analysis-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Zhao_2024_CVPR, author = {Zhao, Mingyang and Jiang, Jingen and Ma, Lei and Xin, Shiqing and Meng, Gaofeng and Yan, Dong-Ming}, title = {Correspondence-Free Non-Rigid Point Set Registration Using Unsupervised Clustering Analysis}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {21199-21208} }
BadCLIP: Trigger-Aware Prompt Learning for Backdoor Attacks on CLIP-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Bai_2024_CVPR, author = {Bai, Jiawang and Gao, Kuofeng and Min, Shaobo and Xia, Shu-Tao and Li, Zhifeng and Liu, Wei}, title = {BadCLIP: Trigger-Aware Prompt Learning for Backdoor Attacks on CLIP}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {24239-24250} }
PixelRNN: In-pixel Recurrent Neural Networks for End-to-end-optimized Perception with Neural Sensors-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{So_2024_CVPR, author = {So, Haley M. and Bose, Laurie and Dudek, Piotr and Wetzstein, Gordon}, title = {PixelRNN: In-pixel Recurrent Neural Networks for End-to-end-optimized Perception with Neural Sensors}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {25233-25244} }
DUSt3R: Geometric 3D Vision Made Easy-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Wang_2024_CVPR, author = {Wang, Shuzhe and Leroy, Vincent and Cabon, Yohann and Chidlovskii, Boris and Revaud, Jerome}, title = {DUSt3R: Geometric 3D Vision Made Easy}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {20697-20709} }
Robust Distillation via Untargeted and Targeted Intermediate Adversarial Samples-
[pdf]
[supp]
[bibtex]@InProceedings{Dong_2024_CVPR, author = {Dong, Junhao and Koniusz, Piotr and Chen, Junxi and Wang, Z. Jane and Ong, Yew-Soon}, title = {Robust Distillation via Untargeted and Targeted Intermediate Adversarial Samples}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {28432-28442} }
Soften to Defend: Towards Adversarial Robustness via Self-Guided Label Refinement-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Li_2024_CVPR, author = {Li, Zhuorong and Yu, Daiwei and Wei, Lina and Jin, Canghong and Zhang, Yun and Chan, Sixian}, title = {Soften to Defend: Towards Adversarial Robustness via Self-Guided Label Refinement}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {24776-24785} }
Pose-Guided Self-Training with Two-Stage Clustering for Unsupervised Landmark Discovery-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Tourani_2024_CVPR, author = {Tourani, Siddharth and Alwheibi, Ahmed and Mahmood, Arif and Khan, Muhammad Haris}, title = {Pose-Guided Self-Training with Two-Stage Clustering for Unsupervised Landmark Discovery}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {23041-23051} }
Learning from Synthetic Human Group Activities-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Chang_2024_CVPR, author = {Chang, Che-Jui and Li, Danrui and Patel, Deep and Goel, Parth and Zhou, Honglu and Moon, Seonghyeon and Sohn, Samuel S. and Yoon, Sejong and Pavlovic, Vladimir and Kapadia, Mubbasir}, title = {Learning from Synthetic Human Group Activities}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {21922-21932} }
Text Grouping Adapter: Adapting Pre-trained Text Detector for Layout Analysis-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Bi_2024_CVPR, author = {Bi, Tianci and Zhang, Xiaoyi and Zhang, Zhizheng and Xie, Wenxuan and Lan, Cuiling and Lu, Yan and Zheng, Nanning}, title = {Text Grouping Adapter: Adapting Pre-trained Text Detector for Layout Analysis}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {28150-28159} }
THRONE: An Object-based Hallucination Benchmark for the Free-form Generations of Large Vision-Language Models-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Kaul_2024_CVPR, author = {Kaul, Prannay and Li, Zhizhong and Yang, Hao and Dukler, Yonatan and Swaminathan, Ashwin and Taylor, C. J. and Soatto, Stefano}, title = {THRONE: An Object-based Hallucination Benchmark for the Free-form Generations of Large Vision-Language Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {27228-27238} }
LUWA Dataset: Learning Lithic Use-Wear Analysis on Microscopic Images-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Zhang_2024_CVPR, author = {Zhang, Jing and Fang, Irving and Wu, Hao and Kaushik, Akshat and Rodriguez, Alice and Zhao, Hanwen and Zhang, Juexiao and Zheng, Zhuo and Iovita, Radu and Feng, Chen}, title = {LUWA Dataset: Learning Lithic Use-Wear Analysis on Microscopic Images}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {22563-22573} }
The Audio-Visual Conversational Graph: From an Egocentric-Exocentric Perspective-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Jia_2024_CVPR, author = {Jia, Wenqi and Liu, Miao and Jiang, Hao and Ananthabhotla, Ishwarya and Rehg, James M. and Ithapu, Vamsi Krishna and Gao, Ruohan}, title = {The Audio-Visual Conversational Graph: From an Egocentric-Exocentric Perspective}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {26396-26405} }
Byzantine-robust Decentralized Federated Learning via Dual-domain Clustering and Trust Bootstrapping-
[pdf]
[supp]
[bibtex]@InProceedings{Sun_2024_CVPR, author = {Sun, Peng and Liu, Xinyang and Wang, Zhibo and Liu, Bo}, title = {Byzantine-robust Decentralized Federated Learning via Dual-domain Clustering and Trust Bootstrapping}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {24756-24765} }
No More Ambiguity in 360deg Room Layout via Bi-Layout Estimation-
[pdf]
[supp]
[bibtex]@InProceedings{Tsai_2024_CVPR, author = {Tsai, Yu-Ju and Jhang, Jin-Cheng and Zheng, Jingjing and Wang, Wei and Chen, Albert Y. C. and Sun, Min and Kuo, Cheng-Hao and Yang, Ming-Hsuan}, title = {No More Ambiguity in 360deg Room Layout via Bi-Layout Estimation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {28056-28065} }
A Noisy Elephant in the Room: Is Your Out-of-Distribution Detector Robust to Label Noise?-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Humblot-Renaux_2024_CVPR, author = {Humblot-Renaux, Galadrielle and Escalera, Sergio and Moeslund, Thomas B.}, title = {A Noisy Elephant in the Room: Is Your Out-of-Distribution Detector Robust to Label Noise?}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {22626-22636} }
VideoMAC: Video Masked Autoencoders Meet ConvNets-
[pdf]
[arXiv]
[bibtex]@InProceedings{Pei_2024_CVPR, author = {Pei, Gensheng and Chen, Tao and Jiang, Xiruo and Liu, Huafeng and Sun, Zeren and Yao, Yazhou}, title = {VideoMAC: Video Masked Autoencoders Meet ConvNets}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {22733-22743} }
Unsigned Orthogonal Distance Fields: An Accurate Neural Implicit Representation for Diverse 3D Shapes-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Lu_2024_CVPR, author = {Lu, Yujie and Wan, Long and Ding, Nayu and Wang, Yulong and Shen, Shuhan and Cai, Shen and Gao, Lin}, title = {Unsigned Orthogonal Distance Fields: An Accurate Neural Implicit Representation for Diverse 3D Shapes}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {20551-20560} }
OA-CNNs: Omni-Adaptive Sparse CNNs for 3D Semantic Segmentation-
[pdf]
[supp]
[bibtex]@InProceedings{Peng_2024_CVPR, author = {Peng, Bohao and Wu, Xiaoyang and Jiang, Li and Chen, Yukang and Zhao, Hengshuang and Tian, Zhuotao and Jia, Jiaya}, title = {OA-CNNs: Omni-Adaptive Sparse CNNs for 3D Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {21305-21315} }
Generative Image Dynamics-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Li_2024_CVPR, author = {Li, Zhengqi and Tucker, Richard and Snavely, Noah and Holynski, Aleksander}, title = {Generative Image Dynamics}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {24142-24153} }
On the Test-Time Zero-Shot Generalization of Vision-Language Models: Do We Really Need Prompt Learning?-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Zanella_2024_CVPR, author = {Zanella, Maxime and Ben Ayed, Ismail}, title = {On the Test-Time Zero-Shot Generalization of Vision-Language Models: Do We Really Need Prompt Learning?}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {23783-23793} }
Beyond Text: Frozen Large Language Models in Visual Signal Comprehension-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Zhu_2024_CVPR, author = {Zhu, Lei and Wei, Fangyun and Lu, Yanye}, title = {Beyond Text: Frozen Large Language Models in Visual Signal Comprehension}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {27047-27057} }
Rotated Multi-Scale Interaction Network for Referring Remote Sensing Image Segmentation-
[pdf]
[arXiv]
[bibtex]@InProceedings{Liu_2024_CVPR, author = {Liu, Sihan and Ma, Yiwei and Zhang, Xiaoqing and Wang, Haowei and Ji, Jiayi and Sun, Xiaoshuai and Ji, Rongrong}, title = {Rotated Multi-Scale Interaction Network for Referring Remote Sensing Image Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {26658-26668} }
GLACE: Global Local Accelerated Coordinate Encoding-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Wang_2024_CVPR, author = {Wang, Fangjinhua and Jiang, Xudong and Galliani, Silvano and Vogel, Christoph and Pollefeys, Marc}, title = {GLACE: Global Local Accelerated Coordinate Encoding}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {21562-21571} }
Localization Is All You Evaluate: Data Leakage in Online Mapping Datasets and How to Fix It-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Lilja_2024_CVPR, author = {Lilja, Adam and Fu, Junsheng and Stenborg, Erik and Hammarstrand, Lars}, title = {Localization Is All You Evaluate: Data Leakage in Online Mapping Datasets and How to Fix It}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {22150-22159} }
Alchemist: Parametric Control of Material Properties with Diffusion Models-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Sharma_2024_CVPR, author = {Sharma, Prafull and Jampani, Varun and Li, Yuanzhen and Jia, Xuhui and Lagun, Dmitry and Durand, Fredo and Freeman, Bill and Matthews, Mark}, title = {Alchemist: Parametric Control of Material Properties with Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {24130-24141} }
MoDE: CLIP Data Experts via Clustering-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Ma_2024_CVPR, author = {Ma, Jiawei and Huang, Po-Yao and Xie, Saining and Li, Shang-Wen and Zettlemoyer, Luke and Chang, Shih-Fu and Yih, Wen-Tau and Xu, Hu}, title = {MoDE: CLIP Data Experts via Clustering}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {26354-26363} }
FineSports: A Multi-person Hierarchical Sports Video Dataset for Fine-grained Action Understanding-
[pdf]
[supp]
[bibtex]@InProceedings{Xu_2024_CVPR, author = {Xu, Jinglin and Zhao, Guohao and Yin, Sibo and Zhou, Wenhao and Peng, Yuxin}, title = {FineSports: A Multi-person Hierarchical Sports Video Dataset for Fine-grained Action Understanding}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {21773-21782} }
GARField: Group Anything with Radiance Fields-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Kim_2024_CVPR, author = {Kim, Chung Min and Wu, Mingxuan and Kerr, Justin and Goldberg, Ken and Tancik, Matthew and Kanazawa, Angjoo}, title = {GARField: Group Anything with Radiance Fields}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {21530-21539} }
Learning Equi-angular Representations for Online Continual Learning-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Seo_2024_CVPR, author = {Seo, Minhyuk and Koh, Hyunseo and Jeung, Wonje and Lee, Minjae and Kim, San and Lee, Hankook and Cho, Sungjun and Choi, Sungik and Kim, Hyunwoo and Choi, Jonghyun}, title = {Learning Equi-angular Representations for Online Continual Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {23933-23942} }
POCE: Primal Policy Optimization with Conservative Estimation for Multi-constraint Offline Reinforcement Learning-
[pdf]
[supp]
[bibtex]@InProceedings{Guan_2024_CVPR, author = {Guan, Jiayi and Shen, Li and Zhou, Ao and Li, Lusong and Hu, Han and He, Xiaodong and Chen, Guang and Jiang, Changjun}, title = {POCE: Primal Policy Optimization with Conservative Estimation for Multi-constraint Offline Reinforcement Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {26243-26253} }
Masked Spatial Propagation Network for Sparsity-Adaptive Depth Refinement-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Jun_2024_CVPR, author = {Jun, Jinyoung and Lee, Jae-Han and Kim, Chang-Su}, title = {Masked Spatial Propagation Network for Sparsity-Adaptive Depth Refinement}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {19768-19778} }
C3Net: Compound Conditioned ControlNet for Multimodal Content Generation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Zhang_2024_CVPR, author = {Zhang, Juntao and Liu, Yuehuai and Tai, Yu-Wing and Tang, Chi-Keung}, title = {C3Net: Compound Conditioned ControlNet for Multimodal Content Generation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {26886-26895} }
Adapt Before Comparison: A New Perspective on Cross-Domain Few-Shot Segmentation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Herzog_2024_CVPR, author = {Herzog, Jonas}, title = {Adapt Before Comparison: A New Perspective on Cross-Domain Few-Shot Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {23605-23615} }
Insect-Foundation: A Foundation Model and Large-scale 1M Dataset for Visual Insect Understanding-
[pdf]
[supp]
[bibtex]@InProceedings{Nguyen_2024_CVPR, author = {Nguyen, Hoang-Quan and Truong, Thanh-Dat and Nguyen, Xuan Bac and Dowling, Ashley and Li, Xin and Luu, Khoa}, title = {Insect-Foundation: A Foundation Model and Large-scale 1M Dataset for Visual Insect Understanding}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {21945-21955} }
Data-Efficient Multimodal Fusion on a Single GPU-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Vouitsis_2024_CVPR, author = {Vouitsis, No\"el and Liu, Zhaoyan and Gorti, Satya Krishna and Villecroze, Valentin and Cresswell, Jesse C. and Yu, Guangwei and Loaiza-Ganem, Gabriel and Volkovs, Maksims}, title = {Data-Efficient Multimodal Fusion on a Single GPU}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {27239-27251} }
FedSelect: Personalized Federated Learning with Customized Selection of Parameters for Fine-Tuning-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Tamirisa_2024_CVPR, author = {Tamirisa, Rishub and Xie, Chulin and Bao, Wenxuan and Zhou, Andy and Arel, Ron and Shamsian, Aviv}, title = {FedSelect: Personalized Federated Learning with Customized Selection of Parameters for Fine-Tuning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {23985-23994} }
Bidirectional Multi-Scale Implicit Neural Representations for Image Deraining-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Chen_2024_CVPR, author = {Chen, Xiang and Pan, Jinshan and Dong, Jiangxin}, title = {Bidirectional Multi-Scale Implicit Neural Representations for Image Deraining}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {25627-25636} }
Enhancing Quality of Compressed Images by Mitigating Enhancement Bias Towards Compression Domain-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Xing_2024_CVPR, author = {Xing, Qunliang and Xu, Mai and Li, Shengxi and Deng, Xin and Zheng, Meisong and Liu, Huaida and Chen, Ying}, title = {Enhancing Quality of Compressed Images by Mitigating Enhancement Bias Towards Compression Domain}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {25501-25511} }
LangSplat: 3D Language Gaussian Splatting-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Qin_2024_CVPR, author = {Qin, Minghan and Li, Wanhua and Zhou, Jiawei and Wang, Haoqian and Pfister, Hanspeter}, title = {LangSplat: 3D Language Gaussian Splatting}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {20051-20060} }
Improving Spectral Snapshot Reconstruction with Spectral-Spatial Rectification-
[pdf]
[bibtex]@InProceedings{Zhang_2024_CVPR, author = {Zhang, Jiancheng and Zeng, Haijin and Chen, Yongyong and Yu, Dengxiu and Zhao, Yin-Ping}, title = {Improving Spectral Snapshot Reconstruction with Spectral-Spatial Rectification}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {25817-25826} }
DNGaussian: Optimizing Sparse-View 3D Gaussian Radiance Fields with Global-Local Depth Normalization-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Li_2024_CVPR, author = {Li, Jiahe and Zhang, Jiawei and Bai, Xiao and Zheng, Jin and Ning, Xin and Zhou, Jun and Gu, Lin}, title = {DNGaussian: Optimizing Sparse-View 3D Gaussian Radiance Fields with Global-Local Depth Normalization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {20775-20785} }
ColorPCR: Color Point Cloud Registration with Multi-Stage Geometric-Color Fusion-
[pdf]
[supp]
[bibtex]@InProceedings{Mu_2024_CVPR, author = {Mu, Juncheng and Bie, Lin and Du, Shaoyi and Gao, Yue}, title = {ColorPCR: Color Point Cloud Registration with Multi-Stage Geometric-Color Fusion}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {21061-21070} }
HomoFormer: Homogenized Transformer for Image Shadow Removal-
[pdf]
[supp]
[bibtex]@InProceedings{Xiao_2024_CVPR, author = {Xiao, Jie and Fu, Xueyang and Zhu, Yurui and Li, Dong and Huang, Jie and Zhu, Kai and Zha, Zheng-Jun}, title = {HomoFormer: Homogenized Transformer for Image Shadow Removal}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {25617-25626} }
What If the TV Was Off? Examining Counterfactual Reasoning Abilities of Multi-modal Language Models-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Zhang_2024_CVPR, author = {Zhang, Letian and Zhai, Xiaotong and Zhao, Zhongkai and Zong, Yongshuo and Wen, Xin and Zhao, Bingchen}, title = {What If the TV Was Off? Examining Counterfactual Reasoning Abilities of Multi-modal Language Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {21853-21862} }
FAR: Flexible Accurate and Robust 6DoF Relative Camera Pose Estimation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Rockwell_2024_CVPR, author = {Rockwell, Chris and Kulkarni, Nilesh and Jin, Linyi and Park, Jeong Joon and Johnson, Justin and Fouhey, David F.}, title = {FAR: Flexible Accurate and Robust 6DoF Relative Camera Pose Estimation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {19854-19864} }
eTraM: Event-based Traffic Monitoring Dataset-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Verma_2024_CVPR, author = {Verma, Aayush Atul and Chakravarthi, Bharatesh and Vaghela, Arpitsinh and Wei, Hua and Yang, Yezhou}, title = {eTraM: Event-based Traffic Monitoring Dataset}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {22637-22646} }
MoCha-Stereo: Motif Channel Attention Network for Stereo Matching-
[pdf]
[supp]
[bibtex]@InProceedings{Chen_2024_CVPR, author = {Chen, Ziyang and Long, Wei and Yao, He and Zhang, Yongjun and Wang, Bingshu and Qin, Yongbin and Wu, Jia}, title = {MoCha-Stereo: Motif Channel Attention Network for Stereo Matching}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {27768-27777} }
Extend Your Own Correspondences: Unsupervised Distant Point Cloud Registration by Progressive Distance Extension-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Liu_2024_CVPR, author = {Liu, Quan and Zhu, Hongzi and Wang, Zhenxi and Zhou, Yunsong and Chang, Shan and Guo, Minyi}, title = {Extend Your Own Correspondences: Unsupervised Distant Point Cloud Registration by Progressive Distance Extension}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {20816-20826} }
Multi-modal Learning for Geospatial Vegetation Forecasting-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Benson_2024_CVPR, author = {Benson, Vitus and Robin, Claire and Requena-Mesa, Christian and Alonso, Lazaro and Carvalhais, Nuno and Cort\'es, Jos\'e and Gao, Zhihan and Linscheid, Nora and Weynants, M\'elanie and Reichstein, Markus}, title = {Multi-modal Learning for Geospatial Vegetation Forecasting}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {27788-27799} }
Bring Event into RGB and LiDAR: Hierarchical Visual-Motion Fusion for Scene Flow-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Zhou_2024_CVPR, author = {Zhou, Hanyu and Chang, Yi and Shi, Zhiwei}, title = {Bring Event into RGB and LiDAR: Hierarchical Visual-Motion Fusion for Scene Flow}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {26477-26486} }
MMVP: A Multimodal MoCap Dataset with Vision and Pressure Sensors-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Zhang_2024_CVPR, author = {Zhang, He and Ren, Shenghao and Yuan, Haolei and Zhao, Jianhui and Li, Fan and Sun, Shuangpeng and Liang, Zhenghao and Yu, Tao and Shen, Qiu and Cao, Xun}, title = {MMVP: A Multimodal MoCap Dataset with Vision and Pressure Sensors}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {21842-21852} }
JoAPR: Cleaning the Lens of Prompt Learning for Vision-Language Models-
[pdf]
[supp]
[bibtex]@InProceedings{Guo_2024_CVPR, author = {Guo, Yuncheng and Gu, Xiaodong}, title = {JoAPR: Cleaning the Lens of Prompt Learning for Vision-Language Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {28695-28705} }
Open-Vocabulary 3D Semantic Segmentation with Foundation Models-
[pdf]
[bibtex]@InProceedings{Jiang_2024_CVPR, author = {Jiang, Li and Shi, Shaoshuai and Schiele, Bernt}, title = {Open-Vocabulary 3D Semantic Segmentation with Foundation Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {21284-21294} }
1-Lipschitz Layers Compared: Memory Speed and Certifiable Robustness-
[pdf]
[supp]
[bibtex]@InProceedings{Prach_2024_CVPR, author = {Prach, Bernd and Brau, Fabio and Buttazzo, Giorgio and Lampert, Christoph H.}, title = {1-Lipschitz Layers Compared: Memory Speed and Certifiable Robustness}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {24574-24583} }
Construct to Associate: Cooperative Context Learning for Domain Adaptive Point Cloud Segmentation-
[pdf]
[supp]
[bibtex]@InProceedings{Li_2024_CVPR, author = {Li, Guangrui}, title = {Construct to Associate: Cooperative Context Learning for Domain Adaptive Point Cloud Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {27917-27926} }
GoMVS: Geometrically Consistent Cost Aggregation for Multi-View Stereo-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Wu_2024_CVPR, author = {Wu, Jiang and Li, Rui and Xu, Haofei and Zhao, Wenxun and Zhu, Yu and Sun, Jinqiu and Zhang, Yanning}, title = {GoMVS: Geometrically Consistent Cost Aggregation for Multi-View Stereo}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {20207-20216} }
Evaluating Transferability in Retrieval Tasks: An Approach Using MMD and Kernel Methods-
[pdf]
[supp]
[bibtex]@InProceedings{Dai_2024_CVPR, author = {Dai, Mengyu and Raffiee, Amir Hossein and Jain, Aashish and Correa, Joshua}, title = {Evaluating Transferability in Retrieval Tasks: An Approach Using MMD and Kernel Methods}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {22390-22400} }
OMG-Seg: Is One Model Good Enough For All Segmentation?-
[pdf]
[supp]
[bibtex]@InProceedings{Li_2024_CVPR, author = {Li, Xiangtai and Yuan, Haobo and Li, Wei and Ding, Henghui and Wu, Size and Zhang, Wenwei and Li, Yining and Chen, Kai and Loy, Chen Change}, title = {OMG-Seg: Is One Model Good Enough For All Segmentation?}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {27948-27959} }
DetCLIPv3: Towards Versatile Generative Open-vocabulary Object Detection-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Yao_2024_CVPR, author = {Yao, Lewei and Pi, Renjie and Han, Jianhua and Liang, Xiaodan and Xu, Hang and Zhang, Wei and Li, Zhenguo and Xu, Dan}, title = {DetCLIPv3: Towards Versatile Generative Open-vocabulary Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {27391-27401} }
UVEB: A Large-scale Benchmark and Baseline Towards Real-World Underwater Video Enhancement-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Xie_2024_CVPR, author = {Xie, Yaofeng and Kong, Lingwei and Chen, Kai and Zheng, Ziqiang and Yu, Xiao and Yu, Zhibin and Zheng, Bing}, title = {UVEB: A Large-scale Benchmark and Baseline Towards Real-World Underwater Video Enhancement}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {22358-22367} }
Discovering Syntactic Interaction Clues for Human-Object Interaction Detection-
[pdf]
[bibtex]@InProceedings{Luo_2024_CVPR, author = {Luo, Jinguo and Ren, Weihong and Jiang, Weibo and Chen, Xi'ai and Wang, Qiang and Han, Zhi and Liu, Honghai}, title = {Discovering Syntactic Interaction Clues for Human-Object Interaction Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {28212-28222} }
Inter-X: Towards Versatile Human-Human Interaction Analysis-
[pdf]
[supp]
[bibtex]@InProceedings{Xu_2024_CVPR, author = {Xu, Liang and Lv, Xintao and Yan, Yichao and Jin, Xin and Wu, Shuwen and Xu, Congsheng and Liu, Yifan and Zhou, Yizhou and Rao, Fengyun and Sheng, Xingdong and Liu, Yunhui and Zeng, Wenjun and Yang, Xiaokang}, title = {Inter-X: Towards Versatile Human-Human Interaction Analysis}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {22260-22271} }
MaskClustering: View Consensus based Mask Graph Clustering for Open-Vocabulary 3D Instance Segmentation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Yan_2024_CVPR, author = {Yan, Mi and Zhang, Jiazhao and Zhu, Yan and Wang, He}, title = {MaskClustering: View Consensus based Mask Graph Clustering for Open-Vocabulary 3D Instance Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {28274-28284} }
PeerAiD: Improving Adversarial Distillation from a Specialized Peer Tutor-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Jung_2024_CVPR, author = {Jung, Jaewon and Jang, Hongsun and Song, Jaeyong and Lee, Jinho}, title = {PeerAiD: Improving Adversarial Distillation from a Specialized Peer Tutor}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {24482-24491} }
Scaling Laws for Data Filtering-- Data Curation cannot be Compute Agnostic-
[pdf]
[supp]
[bibtex]@InProceedings{Goyal_2024_CVPR, author = {Goyal, Sachin and Maini, Pratyush and Lipton, Zachary C. and Raghunathan, Aditi and Kolter, J. Zico}, title = {Scaling Laws for Data Filtering-- Data Curation cannot be Compute Agnostic}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {22702-22711} }
Beyond Average: Individualized Visual Scanpath Prediction-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Chen_2024_CVPR, author = {Chen, Xianyu and Jiang, Ming and Zhao, Qi}, title = {Beyond Average: Individualized Visual Scanpath Prediction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {25420-25431} }
Seeing Motion at Nighttime with an Event Camera-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Liu_2024_CVPR, author = {Liu, Haoyue and Peng, Shihan and Zhu, Lin and Chang, Yi and Zhou, Hanyu and Yan, Luxin}, title = {Seeing Motion at Nighttime with an Event Camera}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {25648-25658} }
FISBe: A Real-World Benchmark Dataset for Instance Segmentation of Long-Range Thin Filamentous Structures-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Mais_2024_CVPR, author = {Mais, Lisa and Hirsch, Peter and Managan, Claire and Kandarpa, Ramya and Rumberger, Josef Lorenz and Reinke, Annika and Maier-Hein, Lena and Ihrke, Gudrun and Kainmueller, Dagmar}, title = {FISBe: A Real-World Benchmark Dataset for Instance Segmentation of Long-Range Thin Filamentous Structures}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {22249-22259} }
LL3DA: Visual Interactive Instruction Tuning for Omni-3D Understanding Reasoning and Planning-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Chen_2024_CVPR, author = {Chen, Sijin and Chen, Xin and Zhang, Chi and Li, Mingsheng and Yu, Gang and Fei, Hao and Zhu, Hongyuan and Fan, Jiayuan and Chen, Tao}, title = {LL3DA: Visual Interactive Instruction Tuning for Omni-3D Understanding Reasoning and Planning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {26428-26438} }
4D Gaussian Splatting for Real-Time Dynamic Scene Rendering-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Wu_2024_CVPR, author = {Wu, Guanjun and Yi, Taoran and Fang, Jiemin and Xie, Lingxi and Zhang, Xiaopeng and Wei, Wei and Liu, Wenyu and Tian, Qi and Wang, Xinggang}, title = {4D Gaussian Splatting for Real-Time Dynamic Scene Rendering}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {20310-20320} }
Selective-Stereo: Adaptive Frequency Information Selection for Stereo Matching-
[pdf]
[supp]
[bibtex]@InProceedings{Wang_2024_CVPR, author = {Wang, Xianqi and Xu, Gangwei and Jia, Hao and Yang, Xin}, title = {Selective-Stereo: Adaptive Frequency Information Selection for Stereo Matching}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {19701-19710} }
PerAda: Parameter-Efficient Federated Learning Personalization with Generalization Guarantees-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Xie_2024_CVPR, author = {Xie, Chulin and Huang, De-An and Chu, Wenda and Xu, Daguang and Xiao, Chaowei and Li, Bo and Anandkumar, Anima}, title = {PerAda: Parameter-Efficient Federated Learning Personalization with Generalization Guarantees}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {23838-23848} }
MAFA: Managing False Negatives for Vision-Language Pre-training-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Byun_2024_CVPR, author = {Byun, Jaeseok and Kim, Dohoon and Moon, Taesup}, title = {MAFA: Managing False Negatives for Vision-Language Pre-training}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {27314-27324} }
InfLoRA: Interference-Free Low-Rank Adaptation for Continual Learning-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Liang_2024_CVPR, author = {Liang, Yan-Shuo and Li, Wu-Jun}, title = {InfLoRA: Interference-Free Low-Rank Adaptation for Continual Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {23638-23647} }
PLGSLAM: Progressive Neural Scene Represenation with Local to Global Bundle Adjustment-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Deng_2024_CVPR, author = {Deng, Tianchen and Shen, Guole and Qin, Tong and Wang, Jianyu and Zhao, Wentao and Wang, Jingchuan and Wang, Danwei and Chen, Weidong}, title = {PLGSLAM: Progressive Neural Scene Represenation with Local to Global Bundle Adjustment}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {19657-19666} }
Multi-Task Dense Prediction via Mixture of Low-Rank Experts-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Yang_2024_CVPR, author = {Yang, Yuqi and Jiang, Peng-Tao and Hou, Qibin and Zhang, Hao and Chen, Jinwei and Li, Bo}, title = {Multi-Task Dense Prediction via Mixture of Low-Rank Experts}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {27927-27937} }
Binding Touch to Everything: Learning Unified Multimodal Tactile Representations-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Yang_2024_CVPR, author = {Yang, Fengyu and Feng, Chao and Chen, Ziyang and Park, Hyoungseob and Wang, Daniel and Dou, Yiming and Zeng, Ziyao and Chen, Xien and Gangopadhyay, Rit and Owens, Andrew and Wong, Alex}, title = {Binding Touch to Everything: Learning Unified Multimodal Tactile Representations}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {26340-26353} }
Your Transferability Barrier is Fragile: Free-Lunch for Transferring the Non-Transferable Learning-
[pdf]
[supp]
[bibtex]@InProceedings{Hong_2024_CVPR, author = {Hong, Ziming and Shen, Li and Liu, Tongliang}, title = {Your Transferability Barrier is Fragile: Free-Lunch for Transferring the Non-Transferable Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {28805-28815} }
Complementing Event Streams and RGB Frames for Hand Mesh Reconstruction-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Jiang_2024_CVPR, author = {Jiang, Jianping and Zhou, Xinyu and Wang, Bingxuan and Deng, Xiaoming and Xu, Chao and Shi, Boxin}, title = {Complementing Event Streams and RGB Frames for Hand Mesh Reconstruction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {24944-24954} }
Empowering Resampling Operation for Ultra-High-Definition Image Enhancement with Model-Aware Guidance-
[pdf]
[supp]
[bibtex]@InProceedings{Yu_2024_CVPR, author = {Yu, Wei and Huang, Jie and Li, Bing and Zheng, Kaiwen and Zhu, Qi and Zhou, Man and Zhao, Feng}, title = {Empowering Resampling Operation for Ultra-High-Definition Image Enhancement with Model-Aware Guidance}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {25722-25731} }
Hallucination Augmented Contrastive Learning for Multimodal Large Language Model-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Jiang_2024_CVPR, author = {Jiang, Chaoya and Xu, Haiyang and Dong, Mengfan and Chen, Jiaxing and Ye, Wei and Yan, Ming and Ye, Qinghao and Zhang, Ji and Huang, Fei and Zhang, Shikun}, title = {Hallucination Augmented Contrastive Learning for Multimodal Large Language Model}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {27036-27046} }
Cooperation Does Matter: Exploring Multi-Order Bilateral Relations for Audio-Visual Segmentation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Yang_2024_CVPR, author = {Yang, Qi and Nie, Xing and Li, Tong and Gao, Pengfei and Guo, Ying and Zhen, Cheng and Yan, Pengfei and Xiang, Shiming}, title = {Cooperation Does Matter: Exploring Multi-Order Bilateral Relations for Audio-Visual Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {27134-27143} }
Improved Self-Training for Test-Time Adaptation-
[pdf]
[supp]
[bibtex]@InProceedings{Ma_2024_CVPR, author = {Ma, Jing}, title = {Improved Self-Training for Test-Time Adaptation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {23701-23710} }
Unsupervised Feature Learning with Emergent Data-Driven Prototypicality-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Guo_2024_CVPR, author = {Guo, Yunhui and Zhang, Youren and Chen, Yubei and Yu, Stella X.}, title = {Unsupervised Feature Learning with Emergent Data-Driven Prototypicality}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {23199-23208} }
Improving Generalized Zero-Shot Learning by Exploring the Diverse Semantics from External Class Names-
[pdf]
[supp]
[bibtex]@InProceedings{Li_2024_CVPR, author = {Li, Yapeng and Luo, Yong and Wang, Zengmao and Du, Bo}, title = {Improving Generalized Zero-Shot Learning by Exploring the Diverse Semantics from External Class Names}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {23344-23353} }
TeMO: Towards Text-Driven 3D Stylization for Multi-Object Meshes-
[pdf]
[arXiv]
[bibtex]@InProceedings{Zhang_2024_CVPR, author = {Zhang, Xuying and Yin, Bo-Wen and Chen, Yuming and Lin, Zheng and Li, Yunheng and Hou, Qibin and Cheng, Ming-Ming}, title = {TeMO: Towards Text-Driven 3D Stylization for Multi-Object Meshes}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {19531-19540} }
GSNeRF: Generalizable Semantic Neural Radiance Fields with Enhanced 3D Scene Understanding-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Chou_2024_CVPR, author = {Chou, Zi-Ting and Huang, Sheng-Yu and Liu, I-Jieh and Wang, Yu-Chiang Frank}, title = {GSNeRF: Generalizable Semantic Neural Radiance Fields with Enhanced 3D Scene Understanding}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {20806-20815} }
Alpha Invariance: On Inverse Scaling Between Distance and Volume Density in Neural Radiance Fields-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Ahn_2024_CVPR, author = {Ahn, Joshua and Wang, Haochen and Yeh, Raymond A. and Shakhnarovich, Greg}, title = {Alpha Invariance: On Inverse Scaling Between Distance and Volume Density in Neural Radiance Fields}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {20396-20405} }
D3T: Distinctive Dual-Domain Teacher Zigzagging Across RGB-Thermal Gap for Domain-Adaptive Object Detection-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Do_2024_CVPR, author = {Do, Dinh Phat and Kim, Taehoon and Na, Jaemin and Kim, Jiwon and Lee, Keonho and Cho, Kyunghwan and Hwang, Wonjun}, title = {D3T: Distinctive Dual-Domain Teacher Zigzagging Across RGB-Thermal Gap for Domain-Adaptive Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {23313-23322} }
Positive-Unlabeled Learning by Latent Group-Aware Meta Disambiguation-
[pdf]
[supp]
[bibtex]@InProceedings{Long_2024_CVPR, author = {Long, Lin and Wang, Haobo and Jiang, Zhijie and Feng, Lei and Yao, Chang and Chen, Gang and Zhao, Junbo}, title = {Positive-Unlabeled Learning by Latent Group-Aware Meta Disambiguation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {23138-23147} }
Linguistic-Aware Patch Slimming Framework for Fine-grained Cross-Modal Alignment-
[pdf]
[bibtex]@InProceedings{Fu_2024_CVPR, author = {Fu, Zheren and Zhang, Lei and Xia, Hou and Mao, Zhendong}, title = {Linguistic-Aware Patch Slimming Framework for Fine-grained Cross-Modal Alignment}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {26307-26316} }
Domain-Rectifying Adapter for Cross-Domain Few-Shot Segmentation-
[pdf]
[arXiv]
[bibtex]@InProceedings{Su_2024_CVPR, author = {Su, Jiapeng and Fan, Qi and Pei, Wenjie and Lu, Guangming and Chen, Fanglin}, title = {Domain-Rectifying Adapter for Cross-Domain Few-Shot Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {24036-24045} }
CPP-Net: Embracing Multi-Scale Feature Fusion into Deep Unfolding CP-PPA Network for Compressive Sensing-
[pdf]
[supp]
[bibtex]@InProceedings{Guo_2024_CVPR, author = {Guo, Zhen and Gan, Hongping}, title = {CPP-Net: Embracing Multi-Scale Feature Fusion into Deep Unfolding CP-PPA Network for Compressive Sensing}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {25086-25095} }
3DGStream: On-the-Fly Training of 3D Gaussians for Efficient Streaming of Photo-Realistic Free-Viewpoint Videos-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Sun_2024_CVPR, author = {Sun, Jiakai and Jiao, Han and Li, Guangyuan and Zhang, Zhanjie and Zhao, Lei and Xing, Wei}, title = {3DGStream: On-the-Fly Training of 3D Gaussians for Efficient Streaming of Photo-Realistic Free-Viewpoint Videos}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {20675-20685} }
FaceTalk: Audio-Driven Motion Diffusion for Neural Parametric Head Models-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Aneja_2024_CVPR, author = {Aneja, Shivangi and Thies, Justus and Dai, Angela and Nie{\ss}ner, Matthias}, title = {FaceTalk: Audio-Driven Motion Diffusion for Neural Parametric Head Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {21263-21273} }
Mip-Splatting: Alias-free 3D Gaussian Splatting-
[pdf]
[supp]
[bibtex]@InProceedings{Yu_2024_CVPR, author = {Yu, Zehao and Chen, Anpei and Huang, Binbin and Sattler, Torsten and Geiger, Andreas}, title = {Mip-Splatting: Alias-free 3D Gaussian Splatting}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {19447-19456} }
Learning Coupled Dictionaries from Unpaired Data for Image Super-Resolution-
[pdf]
[bibtex]@InProceedings{Wang_2024_CVPR, author = {Wang, Longguang and Li, Juncheng and Wang, Yingqian and Hu, Qingyong and Guo, Yulan}, title = {Learning Coupled Dictionaries from Unpaired Data for Image Super-Resolution}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {25712-25721} }
Deep Video Inverse Tone Mapping Based on Temporal Clues-
[pdf]
[supp]
[bibtex]@InProceedings{Ye_2024_CVPR, author = {Ye, Yuyao and Zhang, Ning and Zhao, Yang and Cao, Hongbin and Wang, Ronggang}, title = {Deep Video Inverse Tone Mapping Based on Temporal Clues}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {25995-26004} }
NeRF-HuGS: Improved Neural Radiance Fields in Non-static Scenes Using Heuristics-Guided Segmentation-
[pdf]
[supp]
[bibtex]@InProceedings{Chen_2024_CVPR, author = {Chen, Jiahao and Qin, Yipeng and Liu, Lingjie and Lu, Jiangbo and Li, Guanbin}, title = {NeRF-HuGS: Improved Neural Radiance Fields in Non-static Scenes Using Heuristics-Guided Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {19436-19446} }
ImageNet-D: Benchmarking Neural Network Robustness on Diffusion Synthetic Object-
[pdf]
[supp]
[bibtex]@InProceedings{Zhang_2024_CVPR, author = {Zhang, Chenshuang and Pan, Fei and Kim, Junmo and Kweon, In So and Mao, Chengzhi}, title = {ImageNet-D: Benchmarking Neural Network Robustness on Diffusion Synthetic Object}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {21752-21762} }
Text-Enhanced Data-free Approach for Federated Class-Incremental Learning-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Tran_2024_CVPR, author = {Tran, Minh-Tuan and Le, Trung and Le, Xuan-May and Harandi, Mehrtash and Phung, Dinh}, title = {Text-Enhanced Data-free Approach for Federated Class-Incremental Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {23870-23880} }
UDiFF: Generating Conditional Unsigned Distance Fields with Optimal Wavelet Diffusion-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Zhou_2024_CVPR, author = {Zhou, Junsheng and Zhang, Weiqi and Ma, Baorui and Shi, Kanle and Liu, Yu-Shen and Han, Zhizhong}, title = {UDiFF: Generating Conditional Unsigned Distance Fields with Optimal Wavelet Diffusion}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {21496-21506} }
Towards Large-scale 3D Representation Learning with Multi-dataset Point Prompt Training-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Wu_2024_CVPR, author = {Wu, Xiaoyang and Tian, Zhuotao and Wen, Xin and Peng, Bohao and Liu, Xihui and Yu, Kaicheng and Zhao, Hengshuang}, title = {Towards Large-scale 3D Representation Learning with Multi-dataset Point Prompt Training}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {19551-19562} }
EmbodiedScan: A Holistic Multi-Modal 3D Perception Suite Towards Embodied AI-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Wang_2024_CVPR, author = {Wang, Tai and Mao, Xiaohan and Zhu, Chenming and Xu, Runsen and Lyu, Ruiyuan and Li, Peisen and Chen, Xiao and Zhang, Wenwei and Chen, Kai and Xue, Tianfan and Liu, Xihui and Lu, Cewu and Lin, Dahua and Pang, Jiangmiao}, title = {EmbodiedScan: A Holistic Multi-Modal 3D Perception Suite Towards Embodied AI}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {19757-19767} }
SHINOBI: Shape and Illumination using Neural Object Decomposition via BRDF Optimization In-the-wild-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Engelhardt_2024_CVPR, author = {Engelhardt, Andreas and Raj, Amit and Boss, Mark and Zhang, Yunzhi and Kar, Abhishek and Li, Yuanzhen and Sun, Deqing and Brualla, Ricardo Martin and Barron, Jonathan T. and Lensch, Hendrik P. A. and Jampani, Varun}, title = {SHINOBI: Shape and Illumination using Neural Object Decomposition via BRDF Optimization In-the-wild}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {19636-19646} }
ES3: Evolving Self-Supervised Learning of Robust Audio-Visual Speech Representations-
[pdf]
[supp]
[bibtex]@InProceedings{Zhang_2024_CVPR, author = {Zhang, Yuanhang and Yang, Shuang and Shan, Shiguang and Chen, Xilin}, title = {ES3: Evolving Self-Supervised Learning of Robust Audio-Visual Speech Representations}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {27069-27079} }
Motion2VecSets: 4D Latent Vector Set Diffusion for Non-rigid Shape Reconstruction and Tracking-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Cao_2024_CVPR, author = {Cao, Wei and Luo, Chang and Zhang, Biao and Nie{\ss}ner, Matthias and Tang, Jiapeng}, title = {Motion2VecSets: 4D Latent Vector Set Diffusion for Non-rigid Shape Reconstruction and Tracking}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {20496-20506} }
A2XP: Towards Private Domain Generalization-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Yu_2024_CVPR, author = {Yu, Geunhyeok and Hwang, Hyoseok}, title = {A2XP: Towards Private Domain Generalization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {23544-23553} }
Active Domain Adaptation with False Negative Prediction for Object Detection-
[pdf]
[supp]
[bibtex]@InProceedings{Nakamura_2024_CVPR, author = {Nakamura, Yuzuru and Ishii, Yasunori and Yamashita, Takayoshi}, title = {Active Domain Adaptation with False Negative Prediction for Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {28782-28792} }
Generative 3D Part Assembly via Part-Whole-Hierarchy Message Passing-
[pdf]
[arXiv]
[bibtex]@InProceedings{Du_2024_CVPR, author = {Du, Bi'an and Gao, Xiang and Hu, Wei and Liao, Renjie}, title = {Generative 3D Part Assembly via Part-Whole-Hierarchy Message Passing}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {20850-20859} }
Benchmarking Segmentation Models with Mask-Preserved Attribute Editing-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Yin_2024_CVPR, author = {Yin, Zijin and Liang, Kongming and Li, Bing and Ma, Zhanyu and Guo, Jun}, title = {Benchmarking Segmentation Models with Mask-Preserved Attribute Editing}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {22509-22519} }
Analyzing and Improving the Training Dynamics of Diffusion Models-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Karras_2024_CVPR, author = {Karras, Tero and Aittala, Miika and Lehtinen, Jaakko and Hellsten, Janne and Aila, Timo and Laine, Samuli}, title = {Analyzing and Improving the Training Dynamics of Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {24174-24184} }
Hierarchical Correlation Clustering and Tree Preserving Embedding-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Chehreghani_2024_CVPR, author = {Chehreghani, Morteza Haghir and Chehreghani, Mostafa Haghir}, title = {Hierarchical Correlation Clustering and Tree Preserving Embedding}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {23083-23093} }
Can Protective Perturbation Safeguard Personal Data from Being Exploited by Stable Diffusion?-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Zhao_2024_CVPR, author = {Zhao, Zhengyue and Duan, Jinhao and Xu, Kaidi and Wang, Chenan and Zhang, Rui and Du, Zidong and Guo, Qi and Hu, Xing}, title = {Can Protective Perturbation Safeguard Personal Data from Being Exploited by Stable Diffusion?}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {24398-24407} }
MultiPLY: A Multisensory Object-Centric Embodied Large Language Model in 3D World-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Hong_2024_CVPR, author = {Hong, Yining and Zheng, Zishuo and Chen, Peihao and Wang, Yian and Li, Junyan and Gan, Chuang}, title = {MultiPLY: A Multisensory Object-Centric Embodied Large Language Model in 3D World}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {26406-26416} }
Learning to Visually Localize Sound Sources from Mixtures without Prior Source Knowledge-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Kim_2024_CVPR, author = {Kim, Dongjin and Um, Sung Jin and Lee, Sangmin and Kim, Jung Uk}, title = {Learning to Visually Localize Sound Sources from Mixtures without Prior Source Knowledge}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {26467-26476} }
Regressor-Segmenter Mutual Prompt Learning for Crowd Counting-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Guo_2024_CVPR, author = {Guo, Mingyue and Yuan, Li and Yan, Zhaoyi and Chen, Binghui and Wang, Yaowei and Ye, Qixiang}, title = {Regressor-Segmenter Mutual Prompt Learning for Crowd Counting}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {28380-28389} }
Instantaneous Perception of Moving Objects in 3D-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Liu_2024_CVPR, author = {Liu, Di and Zhuang, Bingbing and Metaxas, Dimitris N. and Chandraker, Manmohan}, title = {Instantaneous Perception of Moving Objects in 3D}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {19573-19583} }
CORE-MPI: Consistency Object Removal with Embedding MultiPlane Image-
[pdf]
[supp]
[bibtex]@InProceedings{Yoon_2024_CVPR, author = {Yoon, Donggeun and Cho, Donghyeon}, title = {CORE-MPI: Consistency Object Removal with Embedding MultiPlane Image}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {20081-20090} }
Backpropagation-free Network for 3D Test-time Adaptation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Wang_2024_CVPR, author = {Wang, Yanshuo and Cheraghian, Ali and Hayder, Zeeshan and Hong, Jie and Ramasinghe, Sameera and Rahman, Shafin and Ahmedt-Aristizabal, David and Li, Xuesong and Petersson, Lars and Harandi, Mehrtash}, title = {Backpropagation-free Network for 3D Test-time Adaptation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {23231-23241} }
ParamISP: Learned Forward and Inverse ISPs using Camera Parameters-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Kim_2024_CVPR, author = {Kim, Woohyeok and Kim, Geonu and Lee, Junyong and Lee, Seungyong and Baek, Seung-Hwan and Cho, Sunghyun}, title = {ParamISP: Learned Forward and Inverse ISPs using Camera Parameters}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {26067-26076} }
Perturbing Attention Gives You More Bang for the Buck: Subtle Imaging Perturbations That Efficiently Fool Customized Diffusion Models-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Xu_2024_CVPR, author = {Xu, Jingyao and Lu, Yuetong and Li, Yandong and Lu, Siyang and Wang, Dongdong and Wei, Xiang}, title = {Perturbing Attention Gives You More Bang for the Buck: Subtle Imaging Perturbations That Efficiently Fool Customized Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {24534-24543} }
SeNM-VAE: Semi-Supervised Noise Modeling with Hierarchical Variational Autoencoder-
[pdf]
[supp]
[bibtex]@InProceedings{Zheng_2024_CVPR, author = {Zheng, Dihan and Zou, Yihang and Zhang, Xiaowen and Bao, Chenglong}, title = {SeNM-VAE: Semi-Supervised Noise Modeling with Hierarchical Variational Autoencoder}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {25889-25899} }
Anchor-based Robust Finetuning of Vision-Language Models-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Han_2024_CVPR, author = {Han, Jinwei and Lin, Zhiwen and Sun, Zhongyisun and Gao, Yingguo and Yan, Ke and Ding, Shouhong and Gao, Yuan and Xia, Gui-Song}, title = {Anchor-based Robust Finetuning of Vision-Language Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {26919-26928} }
DiSR-NeRF: Diffusion-Guided View-Consistent Super-Resolution NeRF-
[pdf]
[supp]
[bibtex]@InProceedings{Lee_2024_CVPR, author = {Lee, Jie Long and Li, Chen and Lee, Gim Hee}, title = {DiSR-NeRF: Diffusion-Guided View-Consistent Super-Resolution NeRF}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {20561-20570} }
Dispersed Structured Light for Hyperspectral 3D Imaging-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Shin_2024_CVPR, author = {Shin, Suhyun and Choi, Seokjun and Heide, Felix and Baek, Seung-Hwan}, title = {Dispersed Structured Light for Hyperspectral 3D Imaging}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {24997-25006} }
GLID: Pre-training a Generalist Encoder-Decoder Vision Model-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Liu_2024_CVPR, author = {Liu, Jihao and Zheng, Jinliang and Liu, Yu and Li, Hongsheng}, title = {GLID: Pre-training a Generalist Encoder-Decoder Vision Model}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {22851-22860} }
PKU-DyMVHumans: A Multi-View Video Benchmark for High-Fidelity Dynamic Human Modeling-
[pdf]
[supp]
[bibtex]@InProceedings{Zheng_2024_CVPR, author = {Zheng, Xiaoyun and Liao, Liwei and Li, Xufeng and Jiao, Jianbo and Wang, Rongjie and Gao, Feng and Wang, Shiqi and Wang, Ronggang}, title = {PKU-DyMVHumans: A Multi-View Video Benchmark for High-Fidelity Dynamic Human Modeling}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {22530-22540} }
CausalPC: Improving the Robustness of Point Cloud Classification by Causal Effect Identification-
[pdf]
[supp]
[bibtex]@InProceedings{Huang_2024_CVPR, author = {Huang, Yuanmin and Zhang, Mi and Ding, Daizong and Jiang, Erling and Wang, Zhaoxiang and Yang, Min}, title = {CausalPC: Improving the Robustness of Point Cloud Classification by Causal Effect Identification}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {19779-19789} }
LASA: Instance Reconstruction from Real Scans using A Large-scale Aligned Shape Annotation Dataset-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Liu_2024_CVPR, author = {Liu, Haolin and Ye, Chongjie and Nie, Yinyu and He, Yingfan and Han, Xiaoguang}, title = {LASA: Instance Reconstruction from Real Scans using A Large-scale Aligned Shape Annotation Dataset}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {20454-20464} }
DiffSCI: Zero-Shot Snapshot Compressive Imaging via Iterative Spectral Diffusion Model-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Pan_2024_CVPR, author = {Pan, Zhenghao and Zeng, Haijin and Cao, Jiezhang and Zhang, Kai and Chen, Yongyong}, title = {DiffSCI: Zero-Shot Snapshot Compressive Imaging via Iterative Spectral Diffusion Model}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {25297-25306} }
MeLFusion: Synthesizing Music from Image and Language Cues using Diffusion Models-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Chowdhury_2024_CVPR, author = {Chowdhury, Sanjoy and Nag, Sayan and Joseph, K J and Srinivasan, Balaji Vasan and Manocha, Dinesh}, title = {MeLFusion: Synthesizing Music from Image and Language Cues using Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {26826-26835} }
Noisy-Correspondence Learning for Text-to-Image Person Re-identification-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Qin_2024_CVPR, author = {Qin, Yang and Chen, Yingke and Peng, Dezhong and Peng, Xi and Zhou, Joey Tianyi and Hu, Peng}, title = {Noisy-Correspondence Learning for Text-to-Image Person Re-identification}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {27197-27206} }
PanoRecon: Real-Time Panoptic 3D Reconstruction from Monocular Video-
[pdf]
[supp]
[bibtex]@InProceedings{Wu_2024_CVPR, author = {Wu, Dong and Yan, Zike and Zha, Hongbin}, title = {PanoRecon: Real-Time Panoptic 3D Reconstruction from Monocular Video}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {21507-21518} }
Towards Transferable Targeted 3D Adversarial Attack in the Physical World-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Huang_2024_CVPR, author = {Huang, Yao and Dong, Yinpeng and Ruan, Shouwei and Yang, Xiao and Su, Hang and Wei, Xingxing}, title = {Towards Transferable Targeted 3D Adversarial Attack in the Physical World}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {24512-24522} }
SwitchLight: Co-design of Physics-driven Architecture and Pre-training Framework for Human Portrait Relighting-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Kim_2024_CVPR, author = {Kim, Hoon and Jang, Minje and Yoon, Wonjun and Lee, Jisoo and Na, Donghyun and Woo, Sanghyun}, title = {SwitchLight: Co-design of Physics-driven Architecture and Pre-training Framework for Human Portrait Relighting}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {25096-25106} }
Adapters Strike Back-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Steitz_2024_CVPR, author = {Steitz, Jan-Martin O. and Roth, Stefan}, title = {Adapters Strike Back}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {23449-23459} }
CLIP-Driven Open-Vocabulary 3D Scene Graph Generation via Cross-Modality Contrastive Learning-
[pdf]
[bibtex]@InProceedings{Chen_2024_CVPR, author = {Chen, Lianggangxu and Wang, Xuejiao and Lu, Jiale and Lin, Shaohui and Wang, Changbo and He, Gaoqi}, title = {CLIP-Driven Open-Vocabulary 3D Scene Graph Generation via Cross-Modality Contrastive Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {27863-27873} }
StraightPCF: Straight Point Cloud Filtering-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{de_Silva_Edirimuni_2024_CVPR, author = {de Silva Edirimuni, Dasith and Lu, Xuequan and Li, Gang and Wei, Lei and Robles-Kelly, Antonio and Li, Hongdong}, title = {StraightPCF: Straight Point Cloud Filtering}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {20721-20730} }
Mirasol3B: A Multimodal Autoregressive Model for Time-Aligned and Contextual Modalities-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Piergiovanni_2024_CVPR, author = {Piergiovanni, AJ and Noble, Isaac and Kim, Dahun and Ryoo, Michael S. and Gomes, Victor and Angelova, Anelia}, title = {Mirasol3B: A Multimodal Autoregressive Model for Time-Aligned and Contextual Modalities}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {26804-26814} }
Semantically-Shifted Incremental Adapter-Tuning is A Continual ViTransformer-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Tan_2024_CVPR, author = {Tan, Yuwen and Zhou, Qinhao and Xiang, Xiang and Wang, Ke and Wu, Yuchuan and Li, Yongbin}, title = {Semantically-Shifted Incremental Adapter-Tuning is A Continual ViTransformer}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {23252-23262} }
Random Entangled Tokens for Adversarially Robust Vision Transformer-
[pdf]
[supp]
[bibtex]@InProceedings{Gong_2024_CVPR, author = {Gong, Huihui and Dong, Minjing and Ma, Siqi and Camtepe, Seyit and Nepal, Surya and Xu, Chang}, title = {Random Entangled Tokens for Adversarially Robust Vision Transformer}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {24554-24563} }
L2B: Learning to Bootstrap Robust Models for Combating Label Noise-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Zhou_2024_CVPR, author = {Zhou, Yuyin and Li, Xianhang and Liu, Fengze and Wei, Qingyue and Chen, Xuxi and Yu, Lequan and Xie, Cihang and Lungren, Matthew P. and Xing, Lei}, title = {L2B: Learning to Bootstrap Robust Models for Combating Label Noise}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {23523-23533} }
Tactile-Augmented Radiance Fields-
[pdf]
[arXiv]
[bibtex]@InProceedings{Dou_2024_CVPR, author = {Dou, Yiming and Yang, Fengyu and Liu, Yi and Loquercio, Antonio and Owens, Andrew}, title = {Tactile-Augmented Radiance Fields}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {26529-26539} }
Intensity-Robust Autofocus for Spike Camera-
[pdf]
[supp]
[bibtex]@InProceedings{Su_2024_CVPR, author = {Su, Changqing and Ye, Zhiyuan and Xiao, Yongsheng and Zhou, You and Cheng, Zhen and Xiong, Bo and Yu, Zhaofei and Huang, Tiejun}, title = {Intensity-Robust Autofocus for Spike Camera}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {25018-25027} }
COTR: Compact Occupancy TRansformer for Vision-based 3D Occupancy Prediction-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Ma_2024_CVPR, author = {Ma, Qihang and Tan, Xin and Qu, Yanyun and Ma, Lizhuang and Zhang, Zhizhong and Xie, Yuan}, title = {COTR: Compact Occupancy TRansformer for Vision-based 3D Occupancy Prediction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {19936-19945} }
BANF: Band-Limited Neural Fields for Levels of Detail Reconstruction-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Shabanov_2024_CVPR, author = {Shabanov, Akhmedkhan and Govindarajan, Shrisudhan and Reading, Cody and Goli, Lily and Rebain, Daniel and Yi, Kwang Moo and Tagliasacchi, Andrea}, title = {BANF: Band-Limited Neural Fields for Levels of Detail Reconstruction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {20571-20580} }
Physical Property Understanding from Language-Embedded Feature Fields-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Zhai_2024_CVPR, author = {Zhai, Albert J. and Shen, Yuan and Chen, Emily Y. and Wang, Gloria X. and Wang, Xinlei and Wang, Sheng and Guan, Kaiyu and Wang, Shenlong}, title = {Physical Property Understanding from Language-Embedded Feature Fields}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {28296-28305} }
LEAD: Exploring Logit Space Evolution for Model Selection-
[pdf]
[supp]
[bibtex]@InProceedings{Hu_2024_CVPR, author = {Hu, Zixuan and Li, Xiaotong and Tang, Shixiang and Liu, Jun and Hu, Yichun and Duan, Ling-Yu}, title = {LEAD: Exploring Logit Space Evolution for Model Selection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {28664-28673} }
GaussianAvatars: Photorealistic Head Avatars with Rigged 3D Gaussians-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Qian_2024_CVPR, author = {Qian, Shenhan and Kirschstein, Tobias and Schoneveld, Liam and Davoli, Davide and Giebenhain, Simon and Nie{\ss}ner, Matthias}, title = {GaussianAvatars: Photorealistic Head Avatars with Rigged 3D Gaussians}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {20299-20309} }
GaussianEditor: Editing 3D Gaussians Delicately with Text Instructions-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Wang_2024_CVPR, author = {Wang, Junjie and Fang, Jiemin and Zhang, Xiaopeng and Xie, Lingxi and Tian, Qi}, title = {GaussianEditor: Editing 3D Gaussians Delicately with Text Instructions}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {20902-20911} }
HiKER-SGG: Hierarchical Knowledge Enhanced Robust Scene Graph Generation-
[pdf]
[supp]
[bibtex]@InProceedings{Zhang_2024_CVPR, author = {Zhang, Ce and Stepputtis, Simon and Campbell, Joseph and Sycara, Katia and Xie, Yaqi}, title = {HiKER-SGG: Hierarchical Knowledge Enhanced Robust Scene Graph Generation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {28233-28243} }
Watermark-embedded Adversarial Examples for Copyright Protection against Diffusion Models-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Zhu_2024_CVPR, author = {Zhu, Peifei and Takahashi, Tsubasa and Kataoka, Hirokatsu}, title = {Watermark-embedded Adversarial Examples for Copyright Protection against Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {24420-24430} }
TCP:Textual-based Class-aware Prompt tuning for Visual-Language Model-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Yao_2024_CVPR, author = {Yao, Hantao and Zhang, Rui and Xu, Changsheng}, title = {TCP:Textual-based Class-aware Prompt tuning for Visual-Language Model}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {23438-23448} }
DiffusionMTL: Learning Multi-Task Denoising Diffusion Model from Partially Annotated Data-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Ye_2024_CVPR, author = {Ye, Hanrong and Xu, Dan}, title = {DiffusionMTL: Learning Multi-Task Denoising Diffusion Model from Partially Annotated Data}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {27960-27969} }
Spike-guided Motion Deblurring with Unknown Modal Spatiotemporal Alignment-
[pdf]
[supp]
[bibtex]@InProceedings{Zhang_2024_CVPR, author = {Zhang, Jiyuan and Chen, Shiyan and Zheng, Yajing and Yu, Zhaofei and Huang, Tiejun}, title = {Spike-guided Motion Deblurring with Unknown Modal Spatiotemporal Alignment}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {25047-25057} }
VRP-SAM: SAM with Visual Reference Prompt-
[pdf]
[supp]
[bibtex]@InProceedings{Sun_2024_CVPR, author = {Sun, Yanpeng and Chen, Jiahui and Zhang, Shan and Zhang, Xinyu and Chen, Qiang and Zhang, Gang and Ding, Errui and Wang, Jingdong and Li, Zechao}, title = {VRP-SAM: SAM with Visual Reference Prompt}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {23565-23574} }
Discriminability-Driven Channel Selection for Out-of-Distribution Detection-
[pdf]
[bibtex]@InProceedings{Yuan_2024_CVPR, author = {Yuan, Yue and He, Rundong and Dong, Yicong and Han, Zhongyi and Yin, Yilong}, title = {Discriminability-Driven Channel Selection for Out-of-Distribution Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {26171-26180} }
Traffic Scene Parsing through the TSP6K Dataset-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Jiang_2024_CVPR, author = {Jiang, Peng-Tao and Yang, Yuqi and Cao, Yang and Hou, Qibin and Cheng, Ming-Ming and Shen, Chunhua}, title = {Traffic Scene Parsing through the TSP6K Dataset}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {21874-21885} }
Fourier Priors-Guided Diffusion for Zero-Shot Joint Low-Light Enhancement and Deblurring-
[pdf]
[bibtex]@InProceedings{Lv_2024_CVPR, author = {Lv, Xiaoqian and Zhang, Shengping and Wang, Chenyang and Zheng, Yichen and Zhong, Bineng and Li, Chongyi and Nie, Liqiang}, title = {Fourier Priors-Guided Diffusion for Zero-Shot Joint Low-Light Enhancement and Deblurring}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {25378-25388} }
Scaling Up to Excellence: Practicing Model Scaling for Photo-Realistic Image Restoration In the Wild-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Yu_2024_CVPR, author = {Yu, Fanghua and Gu, Jinjin and Li, Zheyuan and Hu, Jinfan and Kong, Xiangtao and Wang, Xintao and He, Jingwen and Qiao, Yu and Dong, Chao}, title = {Scaling Up to Excellence: Practicing Model Scaling for Photo-Realistic Image Restoration In the Wild}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {25669-25680} }
Q-Instruct: Improving Low-level Visual Abilities for Multi-modality Foundation Models-
[pdf]
[supp]
[bibtex]@InProceedings{Wu_2024_CVPR, author = {Wu, Haoning and Zhang, Zicheng and Zhang, Erli and Chen, Chaofeng and Liao, Liang and Wang, Annan and Xu, Kaixin and Li, Chunyi and Hou, Jingwen and Zhai, Guangtao and Xue, Geng and Sun, Wenxiu and Yan, Qiong and Lin, Weisi}, title = {Q-Instruct: Improving Low-level Visual Abilities for Multi-modality Foundation Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {25490-25500} }
Zero-Shot Structure-Preserving Diffusion Model for High Dynamic Range Tone Mapping-
[pdf]
[supp]
[bibtex]@InProceedings{Zhu_2024_CVPR, author = {Zhu, Ruoxi and Xu, Shusong and Liu, Peiye and Li, Sicheng and Lu, Yanheng and Niu, Dimin and Liu, Zihao and Meng, Zihao and Li, Zhiyong and Chen, Xinhua and Fan, Yibo}, title = {Zero-Shot Structure-Preserving Diffusion Model for High Dynamic Range Tone Mapping}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {26130-26139} }
VoCo: A Simple-yet-Effective Volume Contrastive Learning Framework for 3D Medical Image Analysis-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Wu_2024_CVPR, author = {Wu, Linshan and Zhuang, Jiaxin and Chen, Hao}, title = {VoCo: A Simple-yet-Effective Volume Contrastive Learning Framework for 3D Medical Image Analysis}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {22873-22882} }
IPoD: Implicit Field Learning with Point Diffusion for Generalizable 3D Object Reconstruction from Single RGB-D Images-
[pdf]
[supp]
[bibtex]@InProceedings{Wu_2024_CVPR, author = {Wu, Yushuang and Shi, Luyue and Cai, Junhao and Yuan, Weihao and Qiu, Lingteng and Dong, Zilong and Bo, Liefeng and Cui, Shuguang and Han, Xiaoguang}, title = {IPoD: Implicit Field Learning with Point Diffusion for Generalizable 3D Object Reconstruction from Single RGB-D Images}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {20432-20442} }
CurveCloudNet: Processing Point Clouds with 1D Structure-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Stearns_2024_CVPR, author = {Stearns, Colton and Fu, Alex and Liu, Jiateng and Park, Jeong Joon and Rempe, Davis and Paschalidou, Despoina and Guibas, Leonidas J.}, title = {CurveCloudNet: Processing Point Clouds with 1D Structure}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {27981-27991} }
OpenStreetView-5M: The Many Roads to Global Visual Geolocation-
[pdf]
[supp]
[bibtex]@InProceedings{Astruc_2024_CVPR, author = {Astruc, Guillaume and Dufour, Nicolas and Siglidis, Ioannis and Aronssohn, Constantin and Bouia, Nacim and Fu, Stephanie and Loiseau, Romain and Nguyen, Van Nguyen and Raude, Charles and Vincent, Elliot and Xu, Lintao and Zhou, Hongyu and Landrieu, Loic}, title = {OpenStreetView-5M: The Many Roads to Global Visual Geolocation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {21967-21977} }
Text-IF: Leveraging Semantic Text Guidance for Degradation-Aware and Interactive Image Fusion-
[pdf]
[supp]
[bibtex]@InProceedings{Yi_2024_CVPR, author = {Yi, Xunpeng and Xu, Han and Zhang, Hao and Tang, Linfeng and Ma, Jiayi}, title = {Text-IF: Leveraging Semantic Text Guidance for Degradation-Aware and Interactive Image Fusion}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {27026-27035} }
Learning to Produce Semi-dense Correspondences for Visual Localization-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Giang_2024_CVPR, author = {Giang, Khang Truong and Song, Soohwan and Jo, Sungho}, title = {Learning to Produce Semi-dense Correspondences for Visual Localization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {19468-19478} }
Amodal Ground Truth and Completion in the Wild-
[pdf]
[arXiv]
[bibtex]@InProceedings{Zhan_2024_CVPR, author = {Zhan, Guanqi and Zheng, Chuanxia and Xie, Weidi and Zisserman, Andrew}, title = {Amodal Ground Truth and Completion in the Wild}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {28003-28013} }
NECA: Neural Customizable Human Avatar-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Xiao_2024_CVPR, author = {Xiao, Junjin and Zhang, Qing and Xu, Zhan and Zheng, Wei-Shi}, title = {NECA: Neural Customizable Human Avatar}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {20091-20101} }
Real-IAD: A Real-World Multi-View Dataset for Benchmarking Versatile Industrial Anomaly Detection-
[pdf]
[supp]
[bibtex]@InProceedings{Wang_2024_CVPR, author = {Wang, Chengjie and Zhu, Wenbing and Gao, Bin-Bin and Gan, Zhenye and Zhang, Jiangning and Gu, Zhihao and Qian, Shuguang and Chen, Mingang and Ma, Lizhuang}, title = {Real-IAD: A Real-World Multi-View Dataset for Benchmarking Versatile Industrial Anomaly Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {22883-22892} }
Boosting Adversarial Transferability by Block Shuffle and Rotation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Wang_2024_CVPR, author = {Wang, Kunyu and He, Xuanran and Wang, Wenxuan and Wang, Xiaosen}, title = {Boosting Adversarial Transferability by Block Shuffle and Rotation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {24336-24346} }
LidaRF: Delving into Lidar for Neural Radiance Field on Street Scenes-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Sun_2024_CVPR, author = {Sun, Shanlin and Zhuang, Bingbing and Jiang, Ziyu and Liu, Buyu and Xie, Xiaohui and Chandraker, Manmohan}, title = {LidaRF: Delving into Lidar for Neural Radiance Field on Street Scenes}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {19563-19572} }
Video Recognition in Portrait Mode-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Han_2024_CVPR, author = {Han, Mingfei and Yang, Linjie and Jin, Xiaojie and Feng, Jiashi and Chang, Xiaojun and Wang, Heng}, title = {Video Recognition in Portrait Mode}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {21831-21841} }
Selective Hourglass Mapping for Universal Image Restoration Based on Diffusion Model-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Zheng_2024_CVPR, author = {Zheng, Dian and Wu, Xiao-Ming and Yang, Shuzhou and Zhang, Jian and Hu, Jian-Fang and Zheng, Wei-Shi}, title = {Selective Hourglass Mapping for Universal Image Restoration Based on Diffusion Model}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {25445-25455} }
Audio-Visual Segmentation via Unlabeled Frame Exploitation-
[pdf]
[arXiv]
[bibtex]@InProceedings{Liu_2024_CVPR, author = {Liu, Jinxiang and Liu, Yikun and Zhang, Fei and Ju, Chen and Zhang, Ya and Wang, Yanfeng}, title = {Audio-Visual Segmentation via Unlabeled Frame Exploitation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {26328-26339} }
DriveTrack: A Benchmark for Long-Range Point Tracking in Real-World Videos-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Balasingam_2024_CVPR, author = {Balasingam, Arjun and Chandler, Joseph and Li, Chenning and Zhang, Zhoutong and Balakrishnan, Hari}, title = {DriveTrack: A Benchmark for Long-Range Point Tracking in Real-World Videos}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {22488-22497} }
Infrared Adversarial Car Stickers-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Zhu_2024_CVPR, author = {Zhu, Xiaopei and Liu, Yuqiu and Hu, Zhanhao and Li, Jianmin and Hu, Xiaolin}, title = {Infrared Adversarial Car Stickers}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {24284-24293} }
FreeMan: Towards Benchmarking 3D Human Pose Estimation under Real-World Conditions-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Wang_2024_CVPR, author = {Wang, Jiong and Yang, Fengyu and Li, Bingliang and Gou, Wenbo and Yan, Danqi and Zeng, Ailing and Gao, Yijun and Wang, Junle and Jing, Yanqing and Zhang, Ruimao}, title = {FreeMan: Towards Benchmarking 3D Human Pose Estimation under Real-World Conditions}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {21978-21988} }
GP-NeRF: Generalized Perception NeRF for Context-Aware 3D Scene Understanding-
[pdf]
[supp]
[bibtex]@InProceedings{Li_2024_CVPR, author = {Li, Hao and Zhang, Dingwen and Dai, Yalun and Liu, Nian and Cheng, Lechao and Li, Jingfeng and Wang, Jingdong and Han, Junwei}, title = {GP-NeRF: Generalized Perception NeRF for Context-Aware 3D Scene Understanding}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {21708-21718} }
Polarization Wavefront Lidar: Learning Large Scene Reconstruction from Polarized Wavefronts-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Scheuble_2024_CVPR, author = {Scheuble, Dominik and Lei, Chenyang and Baek, Seung-Hwan and Bijelic, Mario and Heide, Felix}, title = {Polarization Wavefront Lidar: Learning Large Scene Reconstruction from Polarized Wavefronts}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {21241-21250} }
GDA: Generalized Diffusion for Robust Test-time Adaptation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Tsai_2024_CVPR, author = {Tsai, Yun-Yun and Chen, Fu-Chen and Chen, Albert Y. C. and Yang, Junfeng and Su, Che-Chun and Sun, Min and Kuo, Cheng-Hao}, title = {GDA: Generalized Diffusion for Robust Test-time Adaptation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {23242-23251} }
Continual-MAE: Adaptive Distribution Masked Autoencoders for Continual Test-Time Adaptation-
[pdf]
[supp]
[bibtex]@InProceedings{Liu_2024_CVPR, author = {Liu, Jiaming and Xu, Ran and Yang, Senqiao and Zhang, Renrui and Zhang, Qizhe and Chen, Zehui and Guo, Yandong and Zhang, Shanghang}, title = {Continual-MAE: Adaptive Distribution Masked Autoencoders for Continual Test-Time Adaptation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {28653-28663} }
Dual-Enhanced Coreset Selection with Class-wise Collaboration for Online Blurry Class Incremental Learning-
[pdf]
[supp]
[bibtex]@InProceedings{Luo_2024_CVPR, author = {Luo, Yutian and Zhao, Shiqi and Wu, Haoran and Lu, Zhiwu}, title = {Dual-Enhanced Coreset Selection with Class-wise Collaboration for Online Blurry Class Incremental Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {23995-24004} }
Cyclic Learning for Binaural Audio Generation and Localization-
[pdf]
[supp]
[bibtex]@InProceedings{Li_2024_CVPR, author = {Li, Zhaojian and Zhao, Bin and Yuan, Yuan}, title = {Cyclic Learning for Binaural Audio Generation and Localization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {26669-26678} }
Learning Instance-Aware Correspondences for Robust Multi-Instance Point Cloud Registration in Cluttered Scenes-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Yu_2024_CVPR, author = {Yu, Zhiyuan and Qin, Zheng and Zheng, Lintao and Xu, Kai}, title = {Learning Instance-Aware Correspondences for Robust Multi-Instance Point Cloud Registration in Cluttered Scenes}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {19605-19614} }
COCONut: Modernizing COCO Segmentation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Deng_2024_CVPR, author = {Deng, Xueqing and Yu, Qihang and Wang, Peng and Shen, Xiaohui and Chen, Liang-Chieh}, title = {COCONut: Modernizing COCO Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {21863-21873} }
Semantic Line Combination Detector-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Ko_2024_CVPR, author = {Ko, Jinwon and Jin, Dongkwon and Kim, Chang-Su}, title = {Semantic Line Combination Detector}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {28066-28075} }
ReconFusion: 3D Reconstruction with Diffusion Priors-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Wu_2024_CVPR, author = {Wu, Rundi and Mildenhall, Ben and Henzler, Philipp and Park, Keunhong and Gao, Ruiqi and Watson, Daniel and Srinivasan, Pratul P. and Verbin, Dor and Barron, Jonathan T. and Poole, Ben and Ho?y?ski, Aleksander}, title = {ReconFusion: 3D Reconstruction with Diffusion Priors}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {21551-21561} }
InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Chen_2024_CVPR, author = {Chen, Zhe and Wu, Jiannan and Wang, Wenhai and Su, Weijie and Chen, Guo and Xing, Sen and Zhong, Muyan and Zhang, Qinglong and Zhu, Xizhou and Lu, Lewei and Li, Bin and Luo, Ping and Lu, Tong and Qiao, Yu and Dai, Jifeng}, title = {InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {24185-24198} }
PI3D: Efficient Text-to-3D Generation with Pseudo-Image Diffusion-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Liu_2024_CVPR, author = {Liu, Ying-Tian and Guo, Yuan-Chen and Luo, Guan and Sun, Heyi and Yin, Wei and Zhang, Song-Hai}, title = {PI3D: Efficient Text-to-3D Generation with Pseudo-Image Diffusion}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {19915-19924} }
pixelSplat: 3D Gaussian Splats from Image Pairs for Scalable Generalizable 3D Reconstruction-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Charatan_2024_CVPR, author = {Charatan, David and Li, Sizhe Lester and Tagliasacchi, Andrea and Sitzmann, Vincent}, title = {pixelSplat: 3D Gaussian Splats from Image Pairs for Scalable Generalizable 3D Reconstruction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {19457-19467} }
VBench: Comprehensive Benchmark Suite for Video Generative Models-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Huang_2024_CVPR, author = {Huang, Ziqi and He, Yinan and Yu, Jiashuo and Zhang, Fan and Si, Chenyang and Jiang, Yuming and Zhang, Yuanhan and Wu, Tianxing and Jin, Qingyang and Chanpaisit, Nattapol and Wang, Yaohui and Chen, Xinyuan and Wang, Limin and Lin, Dahua and Qiao, Yu and Liu, Ziwei}, title = {VBench: Comprehensive Benchmark Suite for Video Generative Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {21807-21818} }
MAP: MAsk-Pruning for Source-Free Model Intellectual Property Protection-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Peng_2024_CVPR, author = {Peng, Boyang and Qu, Sanqing and Wu, Yong and Zou, Tianpei and He, Lianghua and Knoll, Alois and Chen, Guang and Jiang, Changjun}, title = {MAP: MAsk-Pruning for Source-Free Model Intellectual Property Protection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {23585-23594} }
Visual Prompting for Generalized Few-shot Segmentation: A Multi-scale Approach-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Hossain_2024_CVPR, author = {Hossain, Mir Rayat Imtiaz and Siam, Mennatullah and Sigal, Leonid and Little, James J.}, title = {Visual Prompting for Generalized Few-shot Segmentation: A Multi-scale Approach}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {23470-23480} }
Memory-based Adapters for Online 3D Scene Perception-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Xu_2024_CVPR, author = {Xu, Xiuwei and Xia, Chong and Wang, Ziwei and Zhao, Linqing and Duan, Yueqi and Zhou, Jie and Lu, Jiwen}, title = {Memory-based Adapters for Online 3D Scene Perception}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {21604-21613} }
A Study of Dropout-Induced Modality Bias on Robustness to Missing Video Frames for Audio-Visual Speech Recognition-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Dai_2024_CVPR, author = {Dai, Yusheng and Chen, Hang and Du, Jun and Wang, Ruoyu and Chen, Shihao and Wang, Haotian and Lee, Chin-Hui}, title = {A Study of Dropout-Induced Modality Bias on Robustness to Missing Video Frames for Audio-Visual Speech Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {27445-27455} }
A Conditional Denoising Diffusion Probabilistic Model for Point Cloud Upsampling-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Qu_2024_CVPR, author = {Qu, Wentao and Shao, Yuantian and Meng, Lingwu and Huang, Xiaoshui and Xiao, Liang}, title = {A Conditional Denoising Diffusion Probabilistic Model for Point Cloud Upsampling}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {20786-20795} }
GAFusion: Adaptive Fusing LiDAR and Camera with Multiple Guidance for 3D Object Detection-
[pdf]
[supp]
[bibtex]@InProceedings{Li_2024_CVPR, author = {Li, Xiaotian and Fan, Baojie and Tian, Jiandong and Fan, Huijie}, title = {GAFusion: Adaptive Fusing LiDAR and Camera with Multiple Guidance for 3D Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {21209-21218} }
Improving Graph Contrastive Learning via Adaptive Positive Sampling-
[pdf]
[supp]
[bibtex]@InProceedings{Zhuo_2024_CVPR, author = {Zhuo, Jiaming and Qin, Feiyang and Cui, Can and Fu, Kun and Niu, Bingxin and Wang, Mengzhu and Guo, Yuanfang and Wang, Chuan and Wang, Zhen and Cao, Xiaochun and Yang, Liang}, title = {Improving Graph Contrastive Learning via Adaptive Positive Sampling}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {23179-23187} }
UFC-Net: Unrolling Fixed-point Continuous Network for Deep Compressive Sensing-
[pdf]
[supp]
[bibtex]@InProceedings{Wang_2024_CVPR, author = {Wang, Xiaoyang and Gan, Hongping}, title = {UFC-Net: Unrolling Fixed-point Continuous Network for Deep Compressive Sensing}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {25149-25159} }
ECoDepth: Effective Conditioning of Diffusion Models for Monocular Depth Estimation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Patni_2024_CVPR, author = {Patni, Suraj and Agarwal, Aradhye and Arora, Chetan}, title = {ECoDepth: Effective Conditioning of Diffusion Models for Monocular Depth Estimation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {28285-28295} }
DL3DV-10K: A Large-Scale Scene Dataset for Deep Learning-based 3D Vision-
[pdf]
[supp]
[bibtex]@InProceedings{Ling_2024_CVPR, author = {Ling, Lu and Sheng, Yichen and Tu, Zhi and Zhao, Wentian and Xin, Cheng and Wan, Kun and Yu, Lantao and Guo, Qianyu and Yu, Zixun and Lu, Yawen and Li, Xuanmao and Sun, Xingpeng and Ashok, Rohan and Mukherjee, Aniruddha and Kang, Hao and Kong, Xiangrui and Hua, Gang and Zhang, Tianyi and Benes, Bedrich and Bera, Aniket}, title = {DL3DV-10K: A Large-Scale Scene Dataset for Deep Learning-based 3D Vision}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {22160-22169} }
Bilateral Adaptation for Human-Object Interaction Detection with Occlusion-Robustness-
[pdf]
[supp]
[bibtex]@InProceedings{Wang_2024_CVPR, author = {Wang, Guangzhi and Guo, Yangyang and Xu, Ziwei and Kankanhalli, Mohan}, title = {Bilateral Adaptation for Human-Object Interaction Detection with Occlusion-Robustness}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {27970-27980} }
Projecting Trackable Thermal Patterns for Dynamic Computer Vision-
[pdf]
[supp]
[bibtex]@InProceedings{Sheinin_2024_CVPR, author = {Sheinin, Mark and Sankaranarayanan, Aswin C. and Narasimhan, Srinivasa G.}, title = {Projecting Trackable Thermal Patterns for Dynamic Computer Vision}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {25223-25232} }
SG-PGM: Partial Graph Matching Network with Semantic Geometric Fusion for 3D Scene Graph Alignment and Its Downstream Tasks-
[pdf]
[supp]
[bibtex]@InProceedings{Xie_2024_CVPR, author = {Xie, Yaxu and Pagani, Alain and Stricker, Didier}, title = {SG-PGM: Partial Graph Matching Network with Semantic Geometric Fusion for 3D Scene Graph Alignment and Its Downstream Tasks}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {28401-28411} }
Advancing Saliency Ranking with Human Fixations: Dataset Models and Benchmarks-
[pdf]
[supp]
[bibtex]@InProceedings{Deng_2024_CVPR, author = {Deng, Bowen and Song, Siyang and French, Andrew P. and Schluppeck, Denis and Pound, Michael P.}, title = {Advancing Saliency Ranking with Human Fixations: Dataset Models and Benchmarks}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {28348-28357} }
Unsupervised Deep Unrolling Networks for Phase Unwrapping-
[pdf]
[supp]
[bibtex]@InProceedings{Chen_2024_CVPR, author = {Chen, Zhile and Quan, Yuhui and Ji, Hui}, title = {Unsupervised Deep Unrolling Networks for Phase Unwrapping}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {25182-25192} }
Federated Generalized Category Discovery-
[pdf]
[supp]
[bibtex]@InProceedings{Pu_2024_CVPR, author = {Pu, Nan and Li, Wenjing and Ji, Xingyuan and Qin, Yalan and Sebe, Nicu and Zhong, Zhun}, title = {Federated Generalized Category Discovery}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {28741-28750} }
Edge-Aware 3D Instance Segmentation Network with Intelligent Semantic Prior-
[pdf]
[supp]
[bibtex]@InProceedings{Roh_2024_CVPR, author = {Roh, Wonseok and Jung, Hwanhee and Nam, Giljoo and Yeom, Jinseop and Park, Hyunje and Yoon, Sang Ho and Kim, Sangpil}, title = {Edge-Aware 3D Instance Segmentation Network with Intelligent Semantic Prior}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {20644-20653} }
Coherence As Texture - Passive Textureless 3D Reconstruction by Self-interference-
[pdf]
[supp]
[bibtex]@InProceedings{Chen_2024_CVPR, author = {Chen, Wei-Yu and Sankaranarayanan, Aswin C. and Levin, Anat and O'Toole, Matthew}, title = {Coherence As Texture - Passive Textureless 3D Reconstruction by Self-interference}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {25058-25066} }
Generative Multi-modal Models are Good Class Incremental Learners-
[pdf]
[arXiv]
[bibtex]@InProceedings{Cao_2024_CVPR, author = {Cao, Xusheng and Lu, Haori and Huang, Linlan and Liu, Xialei and Cheng, Ming-Ming}, title = {Generative Multi-modal Models are Good Class Incremental Learners}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {28706-28717} }
Low-Resource Vision Challenges for Foundation Models-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Zhang_2024_CVPR, author = {Zhang, Yunhua and Doughty, Hazel and Snoek, Cees G. M.}, title = {Low-Resource Vision Challenges for Foundation Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {21956-21966} }
RGBD Objects in the Wild: Scaling Real-World 3D Object Learning from RGB-D Videos-
[pdf]
[supp]
[bibtex]@InProceedings{Xia_2024_CVPR, author = {Xia, Hongchi and Fu, Yang and Liu, Sifei and Wang, Xiaolong}, title = {RGBD Objects in the Wild: Scaling Real-World 3D Object Learning from RGB-D Videos}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {22378-22389} }
Low-Res Leads the Way: Improving Generalization for Super-Resolution by Self-Supervised Learning-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Chen_2024_CVPR, author = {Chen, Haoyu and Li, Wenbo and Gu, Jinjin and Ren, Jingjing and Sun, Haoze and Zou, Xueyi and Zhang, Zhensong and Yan, Youliang and Zhu, Lei}, title = {Low-Res Leads the Way: Improving Generalization for Super-Resolution by Self-Supervised Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {25857-25867} }
Learning Spatial Features from Audio-Visual Correspondence in Egocentric Videos-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Majumder_2024_CVPR, author = {Majumder, Sagnik and Al-Halah, Ziad and Grauman, Kristen}, title = {Learning Spatial Features from Audio-Visual Correspondence in Egocentric Videos}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {27058-27068} }
Brain Decodes Deep Nets-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Yang_2024_CVPR, author = {Yang, Huzheng and Gee, James and Shi, Jianbo}, title = {Brain Decodes Deep Nets}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {23030-23040} }
Semantics Distortion and Style Matter: Towards Source-free UDA for Panoramic Segmentation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Zheng_2024_CVPR, author = {Zheng, Xu and Zhou, Pengyuan and Vasilakos, Athanasios V. and Wang, Lin}, title = {Semantics Distortion and Style Matter: Towards Source-free UDA for Panoramic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {27885-27895} }
GOV-NeSF: Generalizable Open-Vocabulary Neural Semantic Fields-
[pdf]
[supp]
[bibtex]@InProceedings{Wang_2024_CVPR, author = {Wang, Yunsong and Chen, Hanlin and Lee, Gim Hee}, title = {GOV-NeSF: Generalizable Open-Vocabulary Neural Semantic Fields}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {20443-20453} }
Dual-Scale Transformer for Large-Scale Single-Pixel Imaging-
[pdf]
[arXiv]
[bibtex]@InProceedings{Qu_2024_CVPR, author = {Qu, Gang and Wang, Ping and Yuan, Xin}, title = {Dual-Scale Transformer for Large-Scale Single-Pixel Imaging}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {25327-25337} }
Bridging Remote Sensors with Multisensor Geospatial Foundation Models-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Han_2024_CVPR, author = {Han, Boran and Zhang, Shuai and Shi, Xingjian and Reichstein, Markus}, title = {Bridging Remote Sensors with Multisensor Geospatial Foundation Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {27852-27862} }
SeeSR: Towards Semantics-Aware Real-World Image Super-Resolution-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Wu_2024_CVPR, author = {Wu, Rongyuan and Yang, Tao and Sun, Lingchen and Zhang, Zhengqiang and Li, Shuai and Zhang, Lei}, title = {SeeSR: Towards Semantics-Aware Real-World Image Super-Resolution}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {25456-25467} }
DrivingGaussian: Composite Gaussian Splatting for Surrounding Dynamic Autonomous Driving Scenes-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Zhou_2024_CVPR, author = {Zhou, Xiaoyu and Lin, Zhiwei and Shan, Xiaojun and Wang, Yongtao and Sun, Deqing and Yang, Ming-Hsuan}, title = {DrivingGaussian: Composite Gaussian Splatting for Surrounding Dynamic Autonomous Driving Scenes}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {21634-21643} }
Unsupervised Keypoints from Pretrained Diffusion Models-
[pdf]
[arXiv]
[bibtex]@InProceedings{Hedlin_2024_CVPR, author = {Hedlin, Eric and Sharma, Gopal and Mahajan, Shweta and He, Xingzhe and Isack, Hossam and Kar, Abhishek and Rhodin, Helge and Tagliasacchi, Andrea and Yi, Kwang Moo}, title = {Unsupervised Keypoints from Pretrained Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {22820-22830} }
Resolution Limit of Single-Photon LiDAR-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Chan_2024_CVPR, author = {Chan, Stanley H. and Weerasooriya, Hashan K. and Zhang, Weijian and Abshire, Pamela and Gyongy, Istvan and Henderson, Robert K.}, title = {Resolution Limit of Single-Photon LiDAR}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {25307-25316} }
Flatten Long-Range Loss Landscapes for Cross-Domain Few-Shot Learning-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Zou_2024_CVPR, author = {Zou, Yixiong and Liu, Yicong and Hu, Yiman and Li, Yuhua and Li, Ruixuan}, title = {Flatten Long-Range Loss Landscapes for Cross-Domain Few-Shot Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {23575-23584} }
Diffusion-based Blind Text Image Super-Resolution-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Zhang_2024_CVPR, author = {Zhang, Yuzhe and Zhang, Jiawei and Li, Hao and Wang, Zhouxia and Hou, Luwei and Zou, Dongqing and Bian, Liheng}, title = {Diffusion-based Blind Text Image Super-Resolution}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {25827-25836} }
Consistent Prompting for Rehearsal-Free Continual Learning-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Gao_2024_CVPR, author = {Gao, Zhanxin and Cen, Jun and Chang, Xiaobin}, title = {Consistent Prompting for Rehearsal-Free Continual Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {28463-28473} }
SeD: Semantic-Aware Discriminator for Image Super-Resolution-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Li_2024_CVPR, author = {Li, Bingchen and Li, Xin and Zhu, Hanxin and Jin, Yeying and Feng, Ruoyu and Zhang, Zhizheng and Chen, Zhibo}, title = {SeD: Semantic-Aware Discriminator for Image Super-Resolution}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {25784-25795} }
ReCoRe: Regularized Contrastive Representation Learning of World Model-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Poudel_2024_CVPR, author = {Poudel, Rudra P.K. and Pandya, Harit and Liwicki, Stephan and Cipolla, Roberto}, title = {ReCoRe: Regularized Contrastive Representation Learning of World Model}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {22904-22913} }
JRDB-PanoTrack: An Open-world Panoptic Segmentation and Tracking Robotic Dataset in Crowded Human Environments-
[pdf]
[supp]
[bibtex]@InProceedings{Le_2024_CVPR, author = {Le, Duy Tho and Gou, Chenhui and Datta, Stavya and Shi, Hengcan and Reid, Ian and Cai, Jianfei and Rezatofighi, Hamid}, title = {JRDB-PanoTrack: An Open-world Panoptic Segmentation and Tracking Robotic Dataset in Crowded Human Environments}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {22325-22334} }
Embracing Unimodal Aleatoric Uncertainty for Robust Multimodal Fusion-
[pdf]
[bibtex]@InProceedings{Gao_2024_CVPR, author = {Gao, Zixian and Jiang, Xun and Xu, Xing and Shen, Fumin and Li, Yujie and Shen, Heng Tao}, title = {Embracing Unimodal Aleatoric Uncertainty for Robust Multimodal Fusion}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {26876-26885} }
Unifying Correspondence Pose and NeRF for Generalized Pose-Free Novel View Synthesis-
[pdf]
[supp]
[bibtex]@InProceedings{Hong_2024_CVPR, author = {Hong, Sunghwan and Jung, Jaewoo and Shin, Heeseong and Yang, Jiaolong and Kim, Seungryong and Luo, Chong}, title = {Unifying Correspondence Pose and NeRF for Generalized Pose-Free Novel View Synthesis}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {20196-20206} }
Draw Step by Step: Reconstructing CAD Construction Sequences from Point Clouds via Multimodal Diffusion.-
[pdf]
[supp]
[bibtex]@InProceedings{Ma_2024_CVPR, author = {Ma, Weijian and Chen, Shuaiqi and Lou, Yunzhong and Li, Xueyang and Zhou, Xiangdong}, title = {Draw Step by Step: Reconstructing CAD Construction Sequences from Point Clouds via Multimodal Diffusion.}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {27154-27163} }
Discriminative Pattern Calibration Mechanism for Source-Free Domain Adaptation-
[pdf]
[bibtex]@InProceedings{Xia_2024_CVPR, author = {Xia, Haifeng and Xia, Siyu and Ding, Zhengming}, title = {Discriminative Pattern Calibration Mechanism for Source-Free Domain Adaptation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {23648-23658} }
Deep Generative Model based Rate-Distortion for Image Downscaling Assessment-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Liang_2024_CVPR, author = {Liang, Yuanbang and Garg, Bhavesh and Rosin, Paul and Qin, Yipeng}, title = {Deep Generative Model based Rate-Distortion for Image Downscaling Assessment}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {19363-19372} }
EFHQ: Multi-purpose ExtremePose-Face-HQ dataset-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Dao_2024_CVPR, author = {Dao, Trung Tuan and Vu, Duc Hong and Pham, Cuong and Tran, Anh}, title = {EFHQ: Multi-purpose ExtremePose-Face-HQ dataset}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {22605-22615} }
Dynamic Cues-Assisted Transformer for Robust Point Cloud Registration-
[pdf]
[bibtex]@InProceedings{Chen_2024_CVPR, author = {Chen, Hong and Yan, Pei and Xiang, Sihe and Tan, Yihua}, title = {Dynamic Cues-Assisted Transformer for Robust Point Cloud Registration}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {21698-21707} }
Patch2Self2: Self-supervised Denoising on Coresets via Matrix Sketching-
[pdf]
[supp]
[bibtex]@InProceedings{Fadnavis_2024_CVPR, author = {Fadnavis, Shreyas and Chowdhury, Agniva and Batson, Joshua and Drineas, Petros and Garyfallidis, Eleftherios}, title = {Patch2Self2: Self-supervised Denoising on Coresets via Matrix Sketching}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {27641-27651} }
The Devil is in the Fine-Grained Details: Evaluating Open-Vocabulary Object Detectors for Fine-Grained Understanding-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Bianchi_2024_CVPR, author = {Bianchi, Lorenzo and Carrara, Fabio and Messina, Nicola and Gennaro, Claudio and Falchi, Fabrizio}, title = {The Devil is in the Fine-Grained Details: Evaluating Open-Vocabulary Object Detectors for Fine-Grained Understanding}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {22520-22529} }
Link-Context Learning for Multimodal LLMs-
[pdf]
[arXiv]
[bibtex]@InProceedings{Tai_2024_CVPR, author = {Tai, Yan and Fan, Weichen and Zhang, Zhao and Liu, Ziwei}, title = {Link-Context Learning for Multimodal LLMs}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {27176-27185} }
ConsistDreamer: 3D-Consistent 2D Diffusion for High-Fidelity Scene Editing-
[pdf]
[supp]
[bibtex]@InProceedings{Chen_2024_CVPR, author = {Chen, Jun-Kun and Bul\`o, Samuel Rota and M\"uller, Norman and Porzi, Lorenzo and Kontschieder, Peter and Wang, Yu-Xiong}, title = {ConsistDreamer: 3D-Consistent 2D Diffusion for High-Fidelity Scene Editing}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {21071-21080} }
On the Robustness of Large Multimodal Models Against Image Adversarial Attacks-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Cui_2024_CVPR, author = {Cui, Xuanming and Aparcedo, Alejandro and Jang, Young Kyun and Lim, Ser-Nam}, title = {On the Robustness of Large Multimodal Models Against Image Adversarial Attacks}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {24625-24634} }
SoundingActions: Learning How Actions Sound from Narrated Egocentric Videos-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Chen_2024_CVPR, author = {Chen, Changan and Ashutosh, Kumar and Girdhar, Rohit and Harwath, David and Grauman, Kristen}, title = {SoundingActions: Learning How Actions Sound from Narrated Egocentric Videos}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {27252-27262} }
MonoHair: High-Fidelity Hair Modeling from a Monocular Video-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Wu_2024_CVPR, author = {Wu, Keyu and Yang, Lingchen and Kuang, Zhiyi and Feng, Yao and Han, Xutao and Shen, Yuefan and Fu, Hongbo and Zhou, Kun and Zheng, Youyi}, title = {MonoHair: High-Fidelity Hair Modeling from a Monocular Video}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {24164-24173} }
One Prompt Word is Enough to Boost Adversarial Robustness for Pre-trained Vision-Language Models-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Li_2024_CVPR, author = {Li, Lin and Guan, Haoyan and Qiu, Jianing and Spratling, Michael}, title = {One Prompt Word is Enough to Boost Adversarial Robustness for Pre-trained Vision-Language Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {24408-24419} }
A Versatile Framework for Continual Test-Time Domain Adaptation: Balancing Discriminability and Generalizability-
[pdf]
[supp]
[bibtex]@InProceedings{Yang_2024_CVPR, author = {Yang, Xu and Chen, Xuan and Li, Moqi and Wei, Kun and Deng, Cheng}, title = {A Versatile Framework for Continual Test-Time Domain Adaptation: Balancing Discriminability and Generalizability}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {23731-23740} }
Sieve: Multimodal Dataset Pruning using Image Captioning Models-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Mahmoud_2024_CVPR, author = {Mahmoud, Anas and Elhoushi, Mostafa and Abbas, Amro and Yang, Yu and Ardalani, Newsha and Leather, Hugh and Morcos, Ari S.}, title = {Sieve: Multimodal Dataset Pruning using Image Captioning Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {22423-22432} }
Dynamic LiDAR Re-simulation using Compositional Neural Fields-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Wu_2024_CVPR, author = {Wu, Hanfeng and Zuo, Xingxing and Leutenegger, Stefan and Litany, Or and Schindler, Konrad and Huang, Shengyu}, title = {Dynamic LiDAR Re-simulation using Compositional Neural Fields}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {19988-19998} }
AETTA: Label-Free Accuracy Estimation for Test-Time Adaptation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Lee_2024_CVPR, author = {Lee, Taeckyung and Chottananurak, Sorn and Gong, Taesik and Lee, Sung-Ju}, title = {AETTA: Label-Free Accuracy Estimation for Test-Time Adaptation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {28643-28652} }
An Empirical Study of the Generalization Ability of Lidar 3D Object Detectors to Unseen Domains-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Eskandar_2024_CVPR, author = {Eskandar, George}, title = {An Empirical Study of the Generalization Ability of Lidar 3D Object Detectors to Unseen Domains}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {23815-23825} }
Unsupervised Universal Image Segmentation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Niu_2024_CVPR, author = {Niu, Dantong and Wang, Xudong and Han, Xinyang and Lian, Long and Herzig, Roei and Darrell, Trevor}, title = {Unsupervised Universal Image Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {22744-22754} }
A Closer Look at the Few-Shot Adaptation of Large Vision-Language Models-
[pdf]
[supp]
[bibtex]@InProceedings{Silva-Rodriguez_2024_CVPR, author = {Silva-Rodr{\'\i}guez, Julio and Hajimiri, Sina and Ben Ayed, Ismail and Dolz, Jose}, title = {A Closer Look at the Few-Shot Adaptation of Large Vision-Language Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {23681-23690} }
Global and Hierarchical Geometry Consistency Priors for Few-shot NeRFs in Indoor Scenes-
[pdf]
[supp]
[bibtex]@InProceedings{Sun_2024_CVPR, author = {Sun, Xiaotian and Xu, Qingshan and Yang, Xinjie and Zang, Yu and Wang, Cheng}, title = {Global and Hierarchical Geometry Consistency Priors for Few-shot NeRFs in Indoor Scenes}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {20530-20539} }
Mask Grounding for Referring Image Segmentation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Chng_2024_CVPR, author = {Chng, Yong Xien and Zheng, Henry and Han, Yizeng and Qiu, Xuchong and Huang, Gao}, title = {Mask Grounding for Referring Image Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {26573-26583} }
Time-Efficient Light-Field Acquisition Using Coded Aperture and Events-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Habuchi_2024_CVPR, author = {Habuchi, Shuji and Takahashi, Keita and Tsutake, Chihiro and Fujii, Toshiaki and Nagahara, Hajime}, title = {Time-Efficient Light-Field Acquisition Using Coded Aperture and Events}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {24923-24933} }
EVS-assisted Joint Deblurring Rolling-Shutter Correction and Video Frame Interpolation through Sensor Inverse Modeling-
[pdf]
[supp]
[bibtex]@InProceedings{Jiang_2024_CVPR, author = {Jiang, Rui and Tu, Fangwen and Long, Yixuan and Vaish, Aabhaas and Zhou, Bowen and Wang, Qinyi and Zhang, Wei and Fang, Yuntan and Capel, Luis Eduardo Garcia and Mu, Bo and Dai, Tiejun and Suess, Andreas}, title = {EVS-assisted Joint Deblurring Rolling-Shutter Correction and Video Frame Interpolation through Sensor Inverse Modeling}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {25172-25181} }
Active Prompt Learning in Vision Language Models-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Bang_2024_CVPR, author = {Bang, Jihwan and Ahn, Sumyeong and Lee, Jae-Gil}, title = {Active Prompt Learning in Vision Language Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {27004-27014} }
NICE: Neurogenesis Inspired Contextual Encoding for Replay-free Class Incremental Learning-
[pdf]
[supp]
[bibtex]@InProceedings{Gurbuz_2024_CVPR, author = {Gurbuz, Mustafa Burak and Moorman, Jean Michael and Dovrolis, Constantine}, title = {NICE: Neurogenesis Inspired Contextual Encoding for Replay-free Class Incremental Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {23659-23669} }
Backdoor Defense via Test-Time Detecting and Repairing-
[pdf]
[supp]
[bibtex]@InProceedings{Guan_2024_CVPR, author = {Guan, Jiyang and Liang, Jian and He, Ran}, title = {Backdoor Defense via Test-Time Detecting and Repairing}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {24564-24573} }
OneFormer3D: One Transformer for Unified Point Cloud Segmentation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Kolodiazhnyi_2024_CVPR, author = {Kolodiazhnyi, Maxim and Vorontsova, Anna and Konushin, Anton and Rukhovich, Danila}, title = {OneFormer3D: One Transformer for Unified Point Cloud Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {20943-20953} }
JRDB-Social: A Multifaceted Robotic Dataset for Understanding of Context and Dynamics of Human Interactions Within Social Groups-
[pdf]
[supp]
[bibtex]@InProceedings{Jahangard_2024_CVPR, author = {Jahangard, Simindokht and Cai, Zhixi and Wen, Shiki and Rezatofighi, Hamid}, title = {JRDB-Social: A Multifaceted Robotic Dataset for Understanding of Context and Dynamics of Human Interactions Within Social Groups}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {22087-22097} }
GPT-4V(ision) is a Human-Aligned Evaluator for Text-to-3D Generation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Wu_2024_CVPR, author = {Wu, Tong and Yang, Guandao and Li, Zhibing and Zhang, Kai and Liu, Ziwei and Guibas, Leonidas and Lin, Dahua and Wetzstein, Gordon}, title = {GPT-4V(ision) is a Human-Aligned Evaluator for Text-to-3D Generation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {22227-22238} }
NTO3D: Neural Target Object 3D Reconstruction with Segment Anything-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Wei_2024_CVPR, author = {Wei, Xiaobao and Zhang, Renrui and Wu, Jiarui and Liu, Jiaming and Lu, Ming and Guo, Yandong and Zhang, Shanghang}, title = {NTO3D: Neural Target Object 3D Reconstruction with Segment Anything}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {20352-20362} }
OmniMedVQA: A New Large-Scale Comprehensive Evaluation Benchmark for Medical LVLM-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Hu_2024_CVPR, author = {Hu, Yutao and Li, Tianbin and Lu, Quanfeng and Shao, Wenqi and He, Junjun and Qiao, Yu and Luo, Ping}, title = {OmniMedVQA: A New Large-Scale Comprehensive Evaluation Benchmark for Medical LVLM}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {22170-22183} }
Visual Programming for Zero-shot Open-Vocabulary 3D Visual Grounding-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Yuan_2024_CVPR, author = {Yuan, Zhihao and Ren, Jinke and Feng, Chun-Mei and Zhao, Hengshuang and Cui, Shuguang and Li, Zhen}, title = {Visual Programming for Zero-shot Open-Vocabulary 3D Visual Grounding}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {20623-20633} }
Class Incremental Learning with Multi-Teacher Distillation-
[pdf]
[supp]
[bibtex]@InProceedings{Wen_2024_CVPR, author = {Wen, Haitao and Pan, Lili and Dai, Yu and Qiu, Heqian and Wang, Lanxiao and Wu, Qingbo and Li, Hongliang}, title = {Class Incremental Learning with Multi-Teacher Distillation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {28443-28452} }
AMU-Tuning: Effective Logit Bias for CLIP-based Few-shot Learning-
[pdf]
[supp]
[bibtex]@InProceedings{Tang_2024_CVPR, author = {Tang, Yuwei and Lin, Zhenyi and Wang, Qilong and Zhu, Pengfei and Hu, Qinghua}, title = {AMU-Tuning: Effective Logit Bias for CLIP-based Few-shot Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {23323-23333} }
Real-World Mobile Image Denoising Dataset with Efficient Baselines-
[pdf]
[supp]
[bibtex]@InProceedings{Flepp_2024_CVPR, author = {Flepp, Roman and Ignatov, Andrey and Timofte, Radu and Van Gool, Luc}, title = {Real-World Mobile Image Denoising Dataset with Efficient Baselines}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {22368-22377} }
Fine-Grained Bipartite Concept Factorization for Clustering-
[pdf]
[bibtex]@InProceedings{Peng_2024_CVPR, author = {Peng, Chong and Zhang, Pengfei and Chen, Yongyong and Kang, Zhao and Chen, Chenglizhao and Cheng, Qiang}, title = {Fine-Grained Bipartite Concept Factorization for Clustering}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {26264-26274} }
Language-Driven Anchors for Zero-Shot Adversarial Robustness-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Li_2024_CVPR, author = {Li, Xiao and Zhang, Wei and Liu, Yining and Hu, Zhanhao and Zhang, Bo and Hu, Xiaolin}, title = {Language-Driven Anchors for Zero-Shot Adversarial Robustness}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {24686-24695} }
Fooling Polarization-Based Vision using Locally Controllable Polarizing Projection-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Li_2024_CVPR, author = {Li, Zhuoxiao and Zhong, Zhihang and Nobuhara, Shohei and Nishino, Ko and Zheng, Yinqiang}, title = {Fooling Polarization-Based Vision using Locally Controllable Polarizing Projection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {24706-24715} }
DiffAM: Diffusion-based Adversarial Makeup Transfer for Facial Privacy Protection-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Sun_2024_CVPR, author = {Sun, Yuhao and Yu, Lingyun and Xie, Hongtao and Li, Jiaming and Zhang, Yongdong}, title = {DiffAM: Diffusion-based Adversarial Makeup Transfer for Facial Privacy Protection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {24584-24594} }
SlowFormer: Adversarial Attack on Compute and Energy Consumption of Efficient Vision Transformers-
[pdf]
[supp]
[bibtex]@InProceedings{Navaneet_2024_CVPR, author = {Navaneet, K L and Koohpayegani, Soroush Abbasi and Sleiman, Essam and Pirsiavash, Hamed}, title = {SlowFormer: Adversarial Attack on Compute and Energy Consumption of Efficient Vision Transformers}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {24786-24797} }
How to Configure Good In-Context Sequence for Visual Question Answering-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Li_2024_CVPR, author = {Li, Li and Peng, Jiawei and Chen, Huiyi and Gao, Chongyang and Yang, Xu}, title = {How to Configure Good In-Context Sequence for Visual Question Answering}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {26710-26720} }
Defense Against Adversarial Attacks on No-Reference Image Quality Models with Gradient Norm Regularization-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Liu_2024_CVPR, author = {Liu, Yujia and Yang, Chenxi and Li, Dingquan and Ding, Jianhao and Jiang, Tingting}, title = {Defense Against Adversarial Attacks on No-Reference Image Quality Models with Gradient Norm Regularization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {25554-25563} }
TACO: Benchmarking Generalizable Bimanual Tool-ACtion-Object Understanding-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Liu_2024_CVPR, author = {Liu, Yun and Yang, Haolin and Si, Xu and Liu, Ling and Li, Zipeng and Zhang, Yuxiang and Liu, Yebin and Yi, Li}, title = {TACO: Benchmarking Generalizable Bimanual Tool-ACtion-Object Understanding}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {21740-21751} }
AlignMiF: Geometry-Aligned Multimodal Implicit Field for LiDAR-Camera Joint Synthesis-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Tao_2024_CVPR, author = {Tao, Tang and Wang, Guangrun and Lao, Yixing and Chen, Peng and Liu, Jie and Lin, Liang and Yu, Kaicheng and Liang, Xiaodan}, title = {AlignMiF: Geometry-Aligned Multimodal Implicit Field for LiDAR-Camera Joint Synthesis}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {21230-21240} }
Improving Unsupervised Hierarchical Representation with Reinforcement Learning-
[pdf]
[supp]
[bibtex]@InProceedings{An_2024_CVPR, author = {An, Ruyi and Li, Yewen and He, Xu and Gu, Pengjie and Zhao, Mengchen and Li, Dong and Hao, Jianye and Wang, Chaojie and An, Bo and Zhou, Mingyuan}, title = {Improving Unsupervised Hierarchical Representation with Reinforcement Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {22946-22956} }
HPL-ESS: Hybrid Pseudo-Labeling for Unsupervised Event-based Semantic Segmentation-
[pdf]
[supp]
[bibtex]@InProceedings{Jing_2024_CVPR, author = {Jing, Linglin and Ding, Yiming and Gao, Yunpeng and Wang, Zhigang and Yan, Xu and Wang, Dong and Schaefer, Gerald and Fang, Hui and Zhao, Bin and Li, Xuelong}, title = {HPL-ESS: Hybrid Pseudo-Labeling for Unsupervised Event-based Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {23128-23137} }
Towards General Robustness Verification of MaxPool-based Convolutional Neural Networks via Tightening Linear Approximation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Xiao_2024_CVPR, author = {Xiao, Yuan and Ma, Shiqing and Zhai, Juan and Fang, Chunrong and Jia, Jinyuan and Chen, Zhenyu}, title = {Towards General Robustness Verification of MaxPool-based Convolutional Neural Networks via Tightening Linear Approximation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {24766-24775} }
Learning to Rematch Mismatched Pairs for Robust Cross-Modal Retrieval-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Han_2024_CVPR, author = {Han, Haochen and Zheng, Qinghua and Dai, Guang and Luo, Minnan and Wang, Jingdong}, title = {Learning to Rematch Mismatched Pairs for Robust Cross-Modal Retrieval}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {26679-26688} }
CDMAD: Class-Distribution-Mismatch-Aware Debiasing for Class-Imbalanced Semi-Supervised Learning-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Lee_2024_CVPR, author = {Lee, Hyuck and Kim, Heeyoung}, title = {CDMAD: Class-Distribution-Mismatch-Aware Debiasing for Class-Imbalanced Semi-Supervised Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {23891-23900} }
PanoPose: Self-supervised Relative Pose Estimation for Panoramic Images-
[pdf]
[supp]
[bibtex]@InProceedings{Tu_2024_CVPR, author = {Tu, Diantao and Cui, Hainan and Zheng, Xianwei and Shen, Shuhan}, title = {PanoPose: Self-supervised Relative Pose Estimation for Panoramic Images}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {20009-20018} }
Describing Differences in Image Sets with Natural Language-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Dunlap_2024_CVPR, author = {Dunlap, Lisa and Zhang, Yuhui and Wang, Xiaohan and Zhong, Ruiqi and Darrell, Trevor and Steinhardt, Jacob and Gonzalez, Joseph E. and Yeung-Levy, Serena}, title = {Describing Differences in Image Sets with Natural Language}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {24199-24208} }
Fully Geometric Panoramic Localization-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Kim_2024_CVPR, author = {Kim, Junho and Jeong, Jiwon and Kim, Young Min}, title = {Fully Geometric Panoramic Localization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {20827-20837} }
NeRF Director: Revisiting View Selection in Neural Volume Rendering-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Xiao_2024_CVPR, author = {Xiao, Wenhui and Cruz, Rodrigo Santa and Ahmedt-Aristizabal, David and Salvado, Olivier and Fookes, Clinton and Lebrat, Leo}, title = {NeRF Director: Revisiting View Selection in Neural Volume Rendering}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {20742-20751} }
SonicVisionLM: Playing Sound with Vision Language Models-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Xie_2024_CVPR, author = {Xie, Zhifeng and Yu, Shengye and He, Qile and Li, Mengtian}, title = {SonicVisionLM: Playing Sound with Vision Language Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {26866-26875} }
DiffuScene: Denoising Diffusion Models for Generative Indoor Scene Synthesis-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Tang_2024_CVPR, author = {Tang, Jiapeng and Nie, Yinyu and Markhasin, Lev and Dai, Angela and Thies, Justus and Nie{\ss}ner, Matthias}, title = {DiffuScene: Denoising Diffusion Models for Generative Indoor Scene Synthesis}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {20507-20518} }
MCNet: Rethinking the Core Ingredients for Accurate and Efficient Homography Estimation-
[pdf]
[supp]
[bibtex]@InProceedings{Zhu_2024_CVPR, author = {Zhu, Haokai and Cao, Si-Yuan and Hu, Jianxin and Zuo, Sitong and Yu, Beinan and Ying, Jiacheng and Li, Junwei and Shen, Hui-Liang}, title = {MCNet: Rethinking the Core Ingredients for Accurate and Efficient Homography Estimation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {25932-25941} }
Boosting Continual Learning of Vision-Language Models via Mixture-of-Experts Adapters-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Yu_2024_CVPR, author = {Yu, Jiazuo and Zhuge, Yunzhi and Zhang, Lu and Hu, Ping and Wang, Dong and Lu, Huchuan and He, You}, title = {Boosting Continual Learning of Vision-Language Models via Mixture-of-Experts Adapters}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {23219-23230} }
Benchmarking Implicit Neural Representation and Geometric Rendering in Real-Time RGB-D SLAM-
[pdf]
[supp]
[bibtex]@InProceedings{Hua_2024_CVPR, author = {Hua, Tongyan and Wang, Lin}, title = {Benchmarking Implicit Neural Representation and Geometric Rendering in Real-Time RGB-D SLAM}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {21346-21356} }
SuperSVG: Superpixel-based Scalable Vector Graphics Synthesis-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Hu_2024_CVPR, author = {Hu, Teng and Yi, Ran and Qian, Baihong and Zhang, Jiangning and Rosin, Paul L. and Lai, Yu-Kun}, title = {SuperSVG: Superpixel-based Scalable Vector Graphics Synthesis}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {24892-24901} }
AV2AV: Direct Audio-Visual Speech to Audio-Visual Speech Translation with Unified Audio-Visual Speech Representation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Choi_2024_CVPR, author = {Choi, Jeongsoo and Park, Se Jin and Kim, Minsu and Ro, Yong Man}, title = {AV2AV: Direct Audio-Visual Speech to Audio-Visual Speech Translation with Unified Audio-Visual Speech Representation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {27325-27337} }
Contrastive Mean-Shift Learning for Generalized Category Discovery-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Choi_2024_CVPR, author = {Choi, Sua and Kang, Dahyun and Cho, Minsu}, title = {Contrastive Mean-Shift Learning for Generalized Category Discovery}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {23094-23104} }
Improving Depth Completion via Depth Feature Upsampling-
[pdf]
[supp]
[bibtex]@InProceedings{Wang_2024_CVPR, author = {Wang, Yufei and Zhang, Ge and Wang, Shaoqian and Li, Bo and Liu, Qi and Hui, Le and Dai, Yuchao}, title = {Improving Depth Completion via Depth Feature Upsampling}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {21104-21113} }
SNI-SLAM: Semantic Neural Implicit SLAM-
[pdf]
[supp]
[bibtex]@InProceedings{Zhu_2024_CVPR, author = {Zhu, Siting and Wang, Guangming and Blum, Hermann and Liu, Jiuming and Song, Liang and Pollefeys, Marc and Wang, Hesheng}, title = {SNI-SLAM: Semantic Neural Implicit SLAM}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {21167-21177} }
Building a Strong Pre-Training Baseline for Universal 3D Large-Scale Perception-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Chen_2024_CVPR, author = {Chen, Haoming and Zhang, Zhizhong and Qu, Yanyun and Zhang, Ruixin and Tan, Xin and Xie, Yuan}, title = {Building a Strong Pre-Training Baseline for Universal 3D Large-Scale Perception}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {19925-19935} }
DS-NeRV: Implicit Neural Video Representation with Decomposed Static and Dynamic Codes-
[pdf]
[supp]
[bibtex]@InProceedings{Yan_2024_CVPR, author = {Yan, Hao and Ke, Zhihui and Zhou, Xiaobo and Qiu, Tie and Shi, Xidong and Jiang, Dadong}, title = {DS-NeRV: Implicit Neural Video Representation with Decomposed Static and Dynamic Codes}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {23019-23029} }
SDSTrack: Self-Distillation Symmetric Adapter Learning for Multi-Modal Visual Object Tracking-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Hou_2024_CVPR, author = {Hou, Xiaojun and Xing, Jiazheng and Qian, Yijie and Guo, Yaowei and Xin, Shuo and Chen, Junhao and Tang, Kai and Wang, Mengmeng and Jiang, Zhengkai and Liu, Liang and Liu, Yong}, title = {SDSTrack: Self-Distillation Symmetric Adapter Learning for Multi-Modal Visual Object Tracking}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {26551-26561} }
Semantic Shield: Defending Vision-Language Models Against Backdooring and Poisoning via Fine-grained Knowledge Alignment-
[pdf]
[supp]
[bibtex]@InProceedings{Ishmam_2024_CVPR, author = {Ishmam, Alvi Md and Thomas, Christopher}, title = {Semantic Shield: Defending Vision-Language Models Against Backdooring and Poisoning via Fine-grained Knowledge Alignment}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {24820-24830} }
Rethinking the Up-Sampling Operations in CNN-based Generative Network for Generalizable Deepfake Detection-
[pdf]
[arXiv]
[bibtex]@InProceedings{Tan_2024_CVPR, author = {Tan, Chuangchuang and Zhao, Yao and Wei, Shikui and Gu, Guanghua and Liu, Ping and Wei, Yunchao}, title = {Rethinking the Up-Sampling Operations in CNN-based Generative Network for Generalizable Deepfake Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {28130-28139} }
GlitchBench: Can Large Multimodal Models Detect Video Game Glitches?-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Taesiri_2024_CVPR, author = {Taesiri, Mohammad Reza and Feng, Tianjun and Bezemer, Cor-Paul and Nguyen, Anh}, title = {GlitchBench: Can Large Multimodal Models Detect Video Game Glitches?}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {22444-22455} }
Density-guided Translator Boosts Synthetic-to-Real Unsupervised Domain Adaptive Segmentation of 3D Point Clouds-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Yuan_2024_CVPR, author = {Yuan, Zhimin and Zeng, Wankang and Su, Yanfei and Liu, Weiquan and Cheng, Ming and Guo, Yulan and Wang, Cheng}, title = {Density-guided Translator Boosts Synthetic-to-Real Unsupervised Domain Adaptive Segmentation of 3D Point Clouds}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {23303-23312} }
Neural Spline Fields for Burst Image Fusion and Layer Separation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Chugunov_2024_CVPR, author = {Chugunov, Ilya and Shustin, David and Yan, Ruyu and Lei, Chenyang and Heide, Felix}, title = {Neural Spline Fields for Burst Image Fusion and Layer Separation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {25763-25773} }
NAPGuard: Towards Detecting Naturalistic Adversarial Patches-
[pdf]
[supp]
[bibtex]@InProceedings{Wu_2024_CVPR, author = {Wu, Siyang and Wang, Jiakai and Zhao, Jiejie and Wang, Yazhe and Liu, Xianglong}, title = {NAPGuard: Towards Detecting Naturalistic Adversarial Patches}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {24367-24376} }
Unified Language-driven Zero-shot Domain Adaptation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Yang_2024_CVPR, author = {Yang, Senqiao and Tian, Zhuotao and Jiang, Li and Jia, Jiaya}, title = {Unified Language-driven Zero-shot Domain Adaptation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {23407-23415} }
Equivariant Multi-Modality Image Fusion-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Zhao_2024_CVPR, author = {Zhao, Zixiang and Bai, Haowen and Zhang, Jiangshe and Zhang, Yulun and Zhang, Kai and Xu, Shuang and Chen, Dongdong and Timofte, Radu and Van Gool, Luc}, title = {Equivariant Multi-Modality Image Fusion}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {25912-25921} }
NeLF-Pro: Neural Light Field Probes for Multi-Scale Novel View Synthesis-
[pdf]
[supp]
[bibtex]@InProceedings{You_2024_CVPR, author = {You, Zinuo and Geiger, Andreas and Chen, Anpei}, title = {NeLF-Pro: Neural Light Field Probes for Multi-Scale Novel View Synthesis}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {19833-19843} }
Solving Masked Jigsaw Puzzles with Diffusion Vision Transformers-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Liu_2024_CVPR, author = {Liu, Jinyang and Teshome, Wondmgezahu and Ghimire, Sandesh and Sznaier, Mario and Camps, Octavia}, title = {Solving Masked Jigsaw Puzzles with Diffusion Vision Transformers}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {23009-23018} }
Fully Exploiting Every Real Sample: SuperPixel Sample Gradient Model Stealing-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Zhao_2024_CVPR, author = {Zhao, Yunlong and Deng, Xiaoheng and Liu, Yijing and Pei, Xinjun and Xia, Jiazhi and Chen, Wei}, title = {Fully Exploiting Every Real Sample: SuperPixel Sample Gradient Model Stealing}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {24316-24325} }
Progressive Divide-and-Conquer via Subsampling Decomposition for Accelerated MRI-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Wang_2024_CVPR, author = {Wang, Chong and Guo, Lanqing and Wang, Yufei and Cheng, Hao and Yu, Yi and Wen, Bihan}, title = {Progressive Divide-and-Conquer via Subsampling Decomposition for Accelerated MRI}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {25128-25137} }
MV-Adapter: Multimodal Video Transfer Learning for Video Text Retrieval-
[pdf]
[supp]
[bibtex]@InProceedings{Jin_2024_CVPR, author = {Jin, Xiaojie and Zhang, Bowen and Gong, Weibo and Xu, Kai and Deng, Xueqing and Wang, Peng and Zhang, Zhao and Shen, Xiaohui and Feng, Jiashi}, title = {MV-Adapter: Multimodal Video Transfer Learning for Video Text Retrieval}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {27144-27153} }
Rethinking Multi-view Representation Learning via Distilled Disentangling-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Ke_2024_CVPR, author = {Ke, Guanzhou and Wang, Bo and Wang, Xiaoli and He, Shengfeng}, title = {Rethinking Multi-view Representation Learning via Distilled Disentangling}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {26774-26783} }
Targeted Representation Alignment for Open-World Semi-Supervised Learning-
[pdf]
[supp]
[bibtex]@InProceedings{Xiao_2024_CVPR, author = {Xiao, Ruixuan and Feng, Lei and Tang, Kai and Zhao, Junbo and Li, Yixuan and Chen, Gang and Wang, Haobo}, title = {Targeted Representation Alignment for Open-World Semi-Supervised Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {23072-23082} }
Efficient Solution of Point-Line Absolute Pose-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Hruby_2024_CVPR, author = {Hruby, Petr and Duff, Timothy and Pollefeys, Marc}, title = {Efficient Solution of Point-Line Absolute Pose}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {21316-21325} }
Text-to-3D using Gaussian Splatting-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Chen_2024_CVPR, author = {Chen, Zilong and Wang, Feng and Wang, Yikai and Liu, Huaping}, title = {Text-to-3D using Gaussian Splatting}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {21401-21412} }
POPDG: Popular 3D Dance Generation with PopDanceSet-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Luo_2024_CVPR, author = {Luo, Zhenye and Ren, Min and Hu, Xuecai and Huang, Yongzhen and Yao, Li}, title = {POPDG: Popular 3D Dance Generation with PopDanceSet}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {26984-26993} }
Learning without Exact Guidance: Updating Large-scale High-resolution Land Cover Maps from Low-resolution Historical Labels-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Li_2024_CVPR, author = {Li, Zhuohong and He, Wei and Li, Jiepan and Lu, Fangxiao and Zhang, Hongyan}, title = {Learning without Exact Guidance: Updating Large-scale High-resolution Land Cover Maps from Low-resolution Historical Labels}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {27717-27727} }
TTA-EVF: Test-Time Adaptation for Event-based Video Frame Interpolation via Reliable Pixel and Sample Estimation-
[pdf]
[supp]
[bibtex]@InProceedings{Cho_2024_CVPR, author = {Cho, Hoonhee and Kim, Taewoo and Jeong, Yuhwan and Yoon, Kuk-Jin}, title = {TTA-EVF: Test-Time Adaptation for Event-based Video Frame Interpolation via Reliable Pixel and Sample Estimation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {25701-25711} }
BEVNeXt: Reviving Dense BEV Frameworks for 3D Object Detection-
[pdf]
[arXiv]
[bibtex]@InProceedings{Li_2024_CVPR, author = {Li, Zhenxin and Lan, Shiyi and Alvarez, Jose M. and Wu, Zuxuan}, title = {BEVNeXt: Reviving Dense BEV Frameworks for 3D Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {20113-20123} }
LEAD: Learning Decomposition for Source-free Universal Domain Adaptation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Qu_2024_CVPR, author = {Qu, Sanqing and Zou, Tianpei and He, Lianghua and R\"ohrbein, Florian and Knoll, Alois and Chen, Guang and Jiang, Changjun}, title = {LEAD: Learning Decomposition for Source-free Universal Domain Adaptation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {23334-23343} }
OneLLM: One Framework to Align All Modalities with Language-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Han_2024_CVPR, author = {Han, Jiaming and Gong, Kaixiong and Zhang, Yiyuan and Wang, Jiaqi and Zhang, Kaipeng and Lin, Dahua and Qiao, Yu and Gao, Peng and Yue, Xiangyu}, title = {OneLLM: One Framework to Align All Modalities with Language}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {26584-26595} }
PAD: Patch-Agnostic Defense against Adversarial Patch Attacks-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Jing_2024_CVPR, author = {Jing, Lihua and Wang, Rui and Ren, Wenqi and Dong, Xin and Zou, Cong}, title = {PAD: Patch-Agnostic Defense against Adversarial Patch Attacks}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {24472-24481} }
MULAN: A Multi Layer Annotated Dataset for Controllable Text-to-Image Generation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Tudosiu_2024_CVPR, author = {Tudosiu, Petru-Daniel and Yang, Yongxin and Zhang, Shifeng and Chen, Fei and McDonagh, Steven and Lampouras, Gerasimos and Iacobacci, Ignacio and Parisot, Sarah}, title = {MULAN: A Multi Layer Annotated Dataset for Controllable Text-to-Image Generation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {22413-22422} }
Unbiased Faster R-CNN for Single-source Domain Generalized Object Detection-
[pdf]
[supp]
[bibtex]@InProceedings{Liu_2024_CVPR, author = {Liu, Yajing and Zhou, Shijun and Liu, Xiyao and Hao, Chunhui and Fan, Baojie and Tian, Jiandong}, title = {Unbiased Faster R-CNN for Single-source Domain Generalized Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {28838-28847} }
Super-Resolution Reconstruction from Bayer-Pattern Spike Streams-
[pdf]
[supp]
[bibtex]@InProceedings{Dong_2024_CVPR, author = {Dong, Yanchen and Xiong, Ruiqin and Zhang, Jian and Yu, Zhaofei and Fan, Xiaopeng and Zhu, Shuyuan and Huang, Tiejun}, title = {Super-Resolution Reconstruction from Bayer-Pattern Spike Streams}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {24871-24880} }
Stationary Representations: Optimally Approximating Compatibility and Implications for Improved Model Replacements-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Biondi_2024_CVPR, author = {Biondi, Niccol\`o and Pernici, Federico and Ricci, Simone and Del Bimbo, Alberto}, title = {Stationary Representations: Optimally Approximating Compatibility and Implications for Improved Model Replacements}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {28793-28804} }
Towards Calibrated Multi-label Deep Neural Networks-
[pdf]
[supp]
[bibtex]@InProceedings{Cheng_2024_CVPR, author = {Cheng, Jiacheng and Vasconcelos, Nuno}, title = {Towards Calibrated Multi-label Deep Neural Networks}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {27589-27599} }
SceneTex: High-Quality Texture Synthesis for Indoor Scenes via Diffusion Priors-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Chen_2024_CVPR, author = {Chen, Dave Zhenyu and Li, Haoxuan and Lee, Hsin-Ying and Tulyakov, Sergey and Nie{\ss}ner, Matthias}, title = {SceneTex: High-Quality Texture Synthesis for Indoor Scenes via Diffusion Priors}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {21081-21091} }
TUMTraf V2X Cooperative Perception Dataset-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Zimmer_2024_CVPR, author = {Zimmer, Walter and Wardana, Gerhard Arya and Sritharan, Suren and Zhou, Xingcheng and Song, Rui and Knoll, Alois C.}, title = {TUMTraf V2X Cooperative Perception Dataset}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {22668-22677} }
SPECAT: SPatial-spEctral Cumulative-Attention Transformer for High-Resolution Hyperspectral Image Reconstruction-
[pdf]
[bibtex]@InProceedings{Yao_2024_CVPR, author = {Yao, Zhiyang and Liu, Shuyang and Yuan, Xiaoyun and Fang, Lu}, title = {SPECAT: SPatial-spEctral Cumulative-Attention Transformer for High-Resolution Hyperspectral Image Reconstruction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {25368-25377} }
Attentive Illumination Decomposition Model for Multi-Illuminant White Balancing-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Kim_2024_CVPR, author = {Kim, Dongyoung and Kim, Jinwoo and Yu, Junsang and Kim, Seon Joo}, title = {Attentive Illumination Decomposition Model for Multi-Illuminant White Balancing}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {25512-25521} }
Efficient Stitchable Task Adaptation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{He_2024_CVPR, author = {He, Haoyu and Pan, Zizheng and Liu, Jing and Cai, Jianfei and Zhuang, Bohan}, title = {Efficient Stitchable Task Adaptation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {28555-28565} }
Image Processing GNN: Breaking Rigidity in Super-Resolution-
[pdf]
[supp]
[bibtex]@InProceedings{Tian_2024_CVPR, author = {Tian, Yuchuan and Chen, Hanting and Xu, Chao and Wang, Yunhe}, title = {Image Processing GNN: Breaking Rigidity in Super-Resolution}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {24108-24117} }
Towards Generalizing to Unseen Domains with Few Labels-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Galappaththige_2024_CVPR, author = {Galappaththige, Chamuditha Jayanga and Baliah, Sanoojan and Gunawardhana, Malitha and Khan, Muhammad Haris}, title = {Towards Generalizing to Unseen Domains with Few Labels}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {23691-23700} }
LTGC: Long-tail Recognition via Leveraging LLMs-driven Generated Content-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Zhao_2024_CVPR, author = {Zhao, Qihao and Dai, Yalun and Li, Hao and Hu, Wei and Zhang, Fan and Liu, Jun}, title = {LTGC: Long-tail Recognition via Leveraging LLMs-driven Generated Content}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {19510-19520} }
Neural Refinement for Absolute Pose Regression with Feature Synthesis-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Chen_2024_CVPR, author = {Chen, Shuai and Bhalgat, Yash and Li, Xinghui and Bian, Jia-Wang and Li, Kejie and Wang, Zirui and Prisacariu, Victor Adrian}, title = {Neural Refinement for Absolute Pose Regression with Feature Synthesis}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {20987-20996} }
DiffCast: A Unified Framework via Residual Diffusion for Precipitation Nowcasting-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Yu_2024_CVPR, author = {Yu, Demin and Li, Xutao and Ye, Yunming and Zhang, Baoquan and Luo, Chuyao and Dai, Kuai and Wang, Rui and Chen, Xunlai}, title = {DiffCast: A Unified Framework via Residual Diffusion for Precipitation Nowcasting}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {27758-27767} }
Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives-
[pdf]
[supp]
[bibtex]@InProceedings{Grauman_2024_CVPR, author = {Grauman, Kristen and Westbury, Andrew and Torresani, Lorenzo and Kitani, Kris and Malik, Jitendra and Afouras, Triantafyllos and Ashutosh, Kumar and Baiyya, Vijay and Bansal, Siddhant and Boote, Bikram and Byrne, Eugene and Chavis, Zach and Chen, Joya and Cheng, Feng and Chu, Fu-Jen and Crane, Sean and Dasgupta, Avijit and Dong, Jing and Escobar, Maria and Forigua, Cristhian and Gebreselasie, Abrham and Haresh, Sanjay and Huang, Jing and Islam, Md Mohaiminul and Jain, Suyog and Khirodkar, Rawal and Kukreja, Devansh and Liang, Kevin J and Liu, Jia-Wei and Majumder, Sagnik and Mao, Yongsen and Martin, Miguel and Mavroudi, Effrosyni and Nagarajan, Tushar and Ragusa, Francesco and Ramakrishnan, Santhosh Kumar and Seminara, Luigi and Somayazulu, Arjun and Song, Yale and Su, Shan and Xue, Zihui and Zhang, Edward and Zhang, Jinxu and Castillo, Angela and Chen, Changan and Fu, Xinzhu and Furuta, Ryosuke and Gonzalez, Cristina and Gupta, Prince and Hu, Jiabo and Huang, Yifei and Huang, Yiming and Khoo, Weslie and Kumar, Anush and Kuo, Robert and Lakhavani, Sach and Liu, Miao and Luo, Mi and Luo, Zhengyi and Meredith, Brighid and Miller, Austin and Oguntola, Oluwatumininu and Pan, Xiaqing and Peng, Penny and Pramanick, Shraman and Ramazanova, Merey and Ryan, Fiona and Shan, Wei and Somasundaram, Kiran and Song, Chenan and Southerland, Audrey and Tateno, Masatoshi and Wang, Huiyu and Wang, Yuchen and Yagi, Takuma and Yan, Mingfei and Yang, Xitong and Yu, Zecheng and Zha, Shengxin Cindy and Zhao, Chen and Zhao, Ziwei and Zhu, Zhifan and Zhuo, Jeff and Arbelaez, Pablo and Bertasius, Gedas and Damen, Dima and Engel, Jakob and Farinella, Giovanni Maria and Furnari, Antonino and Ghanem, Bernard and Hoffman, Judy and Jawahar, C.V. and Newcombe, Richard and Park, Hyun Soo and Rehg, James M. and Sato, Yoichi and Savva, Manolis and Shi, Jianbo and Shou, Mike Zheng and Wray, Michael}, title = {Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {19383-19400} }
Point Cloud Pre-training with Diffusion Models-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Zheng_2024_CVPR, author = {Zheng, Xiao and Huang, Xiaoshui and Mei, Guofeng and Hou, Yuenan and Lyu, Zhaoyang and Dai, Bo and Ouyang, Wanli and Gong, Yongshun}, title = {Point Cloud Pre-training with Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {22935-22945} }
CAMixerSR: Only Details Need More "Attention"-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Wang_2024_CVPR, author = {Wang, Yan and Liu, Yi and Zhao, Shijie and Li, Junlin and Zhang, Li}, title = {CAMixerSR: Only Details Need More ''Attention''}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {25837-25846} }
Towards Backward-Compatible Continual Learning of Image Compression-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Duan_2024_CVPR, author = {Duan, Zhihao and Lu, Ming and Yang, Justin and He, Jiangpeng and Ma, Zhan and Zhu, Fengqing}, title = {Towards Backward-Compatible Continual Learning of Image Compression}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {25564-25573} }
Latent Modulated Function for Computational Optimal Continuous Image Representation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{He_2024_CVPR, author = {He, Zongyao and Jin, Zhi}, title = {Latent Modulated Function for Computational Optimal Continuous Image Representation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {26026-26035} }
VideoCutLER: Surprisingly Simple Unsupervised Video Instance Segmentation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Wang_2024_CVPR, author = {Wang, Xudong and Misra, Ishan and Zeng, Ziyun and Girdhar, Rohit and Darrell, Trevor}, title = {VideoCutLER: Surprisingly Simple Unsupervised Video Instance Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {22755-22764} }
PAPR in Motion: Seamless Point-level 3D Scene Interpolation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Peng_2024_CVPR, author = {Peng, Shichong and Zhang, Yanshu and Li, Ke}, title = {PAPR in Motion: Seamless Point-level 3D Scene Interpolation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {21007-21016} }
Causal Mode Multiplexer: A Novel Framework for Unbiased Multispectral Pedestrian Detection-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Kim_2024_CVPR, author = {Kim, Taeheon and Shin, Sebin and Yu, Youngjoon and Kim, Hak Gu and Ro, Yong Man}, title = {Causal Mode Multiplexer: A Novel Framework for Unbiased Multispectral Pedestrian Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {26784-26793} }
LTA-PCS: Learnable Task-Agnostic Point Cloud Sampling-
[pdf]
[bibtex]@InProceedings{Liu_2024_CVPR, author = {Liu, Jiaheng and Li, Jianhao and Wang, Kaisiyuan and Guo, Hongcheng and Yang, Jian and Peng, Junran and Xu, Ke and Liu, Xianglong and Guo, Jinyang}, title = {LTA-PCS: Learnable Task-Agnostic Point Cloud Sampling}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {28035-28045} }
Non-Rigid Structure-from-Motion: Temporally-Smooth Procrustean Alignment and Spatially-Variant Deformation Modeling-
[pdf]
[supp]
[bibtex]@InProceedings{Shi_2024_CVPR, author = {Shi, Jiawei and Deng, Hui and Dai, Yuchao}, title = {Non-Rigid Structure-from-Motion: Temporally-Smooth Procrustean Alignment and Spatially-Variant Deformation Modeling}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {21446-21455} }
ShapeMatcher: Self-Supervised Joint Shape Canonicalization Segmentation Retrieval and Deformation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Di_2024_CVPR, author = {Di, Yan and Zhang, Chenyangguang and Wang, Chaowei and Zhang, Ruida and Zhai, Guangyao and Li, Yanyan and Fu, Bowen and Ji, Xiangyang and Gao, Shan}, title = {ShapeMatcher: Self-Supervised Joint Shape Canonicalization Segmentation Retrieval and Deformation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {21017-21028} }
Global Latent Neural Rendering-
[pdf]
[arXiv]
[bibtex]@InProceedings{Tanay_2024_CVPR, author = {Tanay, Thomas and Maggioni, Matteo}, title = {Global Latent Neural Rendering}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {19723-19733} }
Meta-Point Learning and Refining for Category-Agnostic Pose Estimation-
[pdf]
[arXiv]
[bibtex]@InProceedings{Chen_2024_CVPR, author = {Chen, Junjie and Yan, Jiebin and Fang, Yuming and Niu, Li}, title = {Meta-Point Learning and Refining for Category-Agnostic Pose Estimation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {23534-23543} }
Batch Normalization Alleviates the Spectral Bias in Coordinate Networks-
[pdf]
[supp]
[bibtex]@InProceedings{Cai_2024_CVPR, author = {Cai, Zhicheng and Zhu, Hao and Shen, Qiu and Wang, Xinran and Cao, Xun}, title = {Batch Normalization Alleviates the Spectral Bias in Coordinate Networks}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {25160-25171} }
SplaTAM: Splat Track & Map 3D Gaussians for Dense RGB-D SLAM-
[pdf]
[supp]
[bibtex]@InProceedings{Keetha_2024_CVPR, author = {Keetha, Nikhil and Karhade, Jay and Jatavallabhula, Krishna Murthy and Yang, Gengshan and Scherer, Sebastian and Ramanan, Deva and Luiten, Jonathon}, title = {SplaTAM: Splat Track \& Map 3D Gaussians for Dense RGB-D SLAM}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {21357-21366} }
Instance-based Max-margin for Practical Few-shot Recognition-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Fu_2024_CVPR, author = {Fu, Minghao and Zhu, Ke}, title = {Instance-based Max-margin for Practical Few-shot Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {28674-28683} }
ZeroRF: Fast Sparse View 360deg Reconstruction with Zero Pretraining-
[pdf]
[supp]
[bibtex]@InProceedings{Shi_2024_CVPR, author = {Shi, Ruoxi and Wei, Xinyue and Wang, Cheng and Su, Hao}, title = {ZeroRF: Fast Sparse View 360deg Reconstruction with Zero Pretraining}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {21114-21124} }
RCooper: A Real-world Large-scale Dataset for Roadside Cooperative Perception-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Hao_2024_CVPR, author = {Hao, Ruiyang and Fan, Siqi and Dai, Yingru and Zhang, Zhenlin and Li, Chenxi and Wang, Yuntian and Yu, Haibao and Yang, Wenxian and Yuan, Jirui and Nie, Zaiqing}, title = {RCooper: A Real-world Large-scale Dataset for Roadside Cooperative Perception}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {22347-22357} }
TutteNet: Injective 3D Deformations by Composition of 2D Mesh Deformations-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Sun_2024_CVPR, author = {Sun, Bo and Groueix, Thibault and Song, Chen and Huang, Qixing and Aigerman, Noam}, title = {TutteNet: Injective 3D Deformations by Composition of 2D Mesh Deformations}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {21378-21389} }
Estimating Noisy Class Posterior with Part-level Labels for Noisy Label Learning-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Zhao_2024_CVPR, author = {Zhao, Rui and Shi, Bin and Ruan, Jianfei and Pan, Tianze and Dong, Bo}, title = {Estimating Noisy Class Posterior with Part-level Labels for Noisy Label Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {22809-22819} }
Leveraging Vision-Language Models for Improving Domain Generalization in Image Classification-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Addepalli_2024_CVPR, author = {Addepalli, Sravanti and Asokan, Ashish Ramayee and Sharma, Lakshay and Babu, R. Venkatesh}, title = {Leveraging Vision-Language Models for Improving Domain Generalization in Image Classification}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {23922-23932} }
Prompt Learning via Meta-Regularization-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Park_2024_CVPR, author = {Park, Jinyoung and Ko, Juyeon and Kim, Hyunwoo J.}, title = {Prompt Learning via Meta-Regularization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {26940-26950} }
Embodied Multi-Modal Agent trained by an LLM from a Parallel TextWorld-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Yang_2024_CVPR, author = {Yang, Yijun and Zhou, Tianyi and Li, Kanxue and Tao, Dapeng and Li, Lusong and Shen, Li and He, Xiaodong and Jiang, Jing and Shi, Yuhui}, title = {Embodied Multi-Modal Agent trained by an LLM from a Parallel TextWorld}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {26275-26285} }
Point-VOS: Pointing Up Video Object Segmentation-
[pdf]
[supp]
[bibtex]@InProceedings{Mahadevan_2024_CVPR, author = {Mahadevan, Sabarinath and Zulfikar, Idil Esen and Voigtlaender, Paul and Leibe, Bastian}, title = {Point-VOS: Pointing Up Video Object Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {22217-22226} }
Intriguing Properties of Diffusion Models: An Empirical Study of the Natural Attack Capability in Text-to-Image Generative Models-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Sato_2024_CVPR, author = {Sato, Takami and Yue, Justin and Chen, Nanze and Wang, Ningfei and Chen, Qi Alfred}, title = {Intriguing Properties of Diffusion Models: An Empirical Study of the Natural Attack Capability in Text-to-Image Generative Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {24635-24644} }
HouseCat6D - A Large-Scale Multi-Modal Category Level 6D Object Perception Dataset with Household Objects in Realistic Scenarios-
[pdf]
[supp]
[bibtex]@InProceedings{Jung_2024_CVPR, author = {Jung, HyunJun and Wu, Shun-Cheng and Ruhkamp, Patrick and Zhai, Guangyao and Schieber, Hannah and Rizzoli, Giulia and Wang, Pengyuan and Zhao, Hongcheng and Garattoni, Lorenzo and Meier, Sven and Roth, Daniel and Navab, Nassir and Busam, Benjamin}, title = {HouseCat6D - A Large-Scale Multi-Modal Category Level 6D Object Perception Dataset with Household Objects in Realistic Scenarios}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {22498-22508} }
Towards Co-Evaluation of Cameras HDR and Algorithms for Industrial-Grade 6DoF Pose Estimation-
[pdf]
[supp]
[bibtex]@InProceedings{Kalra_2024_CVPR, author = {Kalra, Agastya and Stoppi, Guy and Marin, Dmitrii and Taamazyan, Vage and Shandilya, Aarrushi and Agarwal, Rishav and Boykov, Anton and Chong, Tze Hao and Stark, Michael}, title = {Towards Co-Evaluation of Cameras HDR and Algorithms for Industrial-Grade 6DoF Pose Estimation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {22691-22701} }
MLP Can Be A Good Transformer Learner-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Lin_2024_CVPR, author = {Lin, Sihao and Lyu, Pumeng and Liu, Dongrui and Tang, Tao and Liang, Xiaodan and Song, Andy and Chang, Xiaojun}, title = {MLP Can Be A Good Transformer Learner}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {19489-19498} }
GraphDreamer: Compositional 3D Scene Synthesis from Scene Graphs-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Gao_2024_CVPR, author = {Gao, Gege and Liu, Weiyang and Chen, Anpei and Geiger, Andreas and Sch\"olkopf, Bernhard}, title = {GraphDreamer: Compositional 3D Scene Synthesis from Scene Graphs}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {21295-21304} }
Visual-Augmented Dynamic Semantic Prototype for Generative Zero-Shot Learning-
[pdf]
[arXiv]
[bibtex]@InProceedings{Hou_2024_CVPR, author = {Hou, Wenjin and Chen, Shiming and Chen, Shuhuang and Hong, Ziming and Wang, Yan and Feng, Xuetao and Khan, Salman and Khan, Fahad Shahbaz and You, Xinge}, title = {Visual-Augmented Dynamic Semantic Prototype for Generative Zero-Shot Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {23627-23637} }
Dynamic Prompt Optimizing for Text-to-Image Generation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Mo_2024_CVPR, author = {Mo, Wenyi and Zhang, Tianyu and Bai, Yalong and Su, Bing and Wen, Ji-Rong and Yang, Qing}, title = {Dynamic Prompt Optimizing for Text-to-Image Generation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {26627-26636} }
360Loc: A Dataset and Benchmark for Omnidirectional Visual Localization with Cross-device Queries-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Huang_2024_CVPR, author = {Huang, Huajian and Liu, Changkun and Zhu, Yipeng and Cheng, Hui and Braud, Tristan and Yeung, Sai-Kit}, title = {360Loc: A Dataset and Benchmark for Omnidirectional Visual Localization with Cross-device Queries}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {22314-22324} }
Domain Gap Embeddings for Generative Dataset Augmentation-
[pdf]
[supp]
[bibtex]@InProceedings{Wang_2024_CVPR, author = {Wang, Yinong Oliver and Chung, Younjoon and Wu, Chen Henry and De la Torre, Fernando}, title = {Domain Gap Embeddings for Generative Dataset Augmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {28684-28694} }
Geometrically-driven Aggregation for Zero-shot 3D Point Cloud Understanding-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Mei_2024_CVPR, author = {Mei, Guofeng and Riz, Luigi and Wang, Yiming and Poiesi, Fabio}, title = {Geometrically-driven Aggregation for Zero-shot 3D Point Cloud Understanding}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {27896-27905} }
Learning to Rank Patches for Unbiased Image Redundancy Reduction-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Luo_2024_CVPR, author = {Luo, Yang and Chen, Zhineng and Zhou, Peng and Wu, Zuxuan and Gao, Xieping and Jiang, Yu-Gang}, title = {Learning to Rank Patches for Unbiased Image Redundancy Reduction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {22831-22840} }
Going Beyond Multi-Task Dense Prediction with Synergy Embedding Models-
[pdf]
[bibtex]@InProceedings{Huang_2024_CVPR, author = {Huang, Huimin and Huang, Yawen and Lin, Lanfen and Tong, Ruofeng and Chen, Yen-Wei and Zheng, Hao and Li, Yuexiang and Zheng, Yefeng}, title = {Going Beyond Multi-Task Dense Prediction with Synergy Embedding Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {28181-28190} }
Disentangled Pre-training for Human-Object Interaction Detection-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Li_2024_CVPR, author = {Li, Zhuolong and Li, Xingao and Ding, Changxing and Xu, Xiangmin}, title = {Disentangled Pre-training for Human-Object Interaction Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {28191-28201} }
MetaCloak: Preventing Unauthorized Subject-driven Text-to-image Diffusion-based Synthesis via Meta-learning-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Liu_2024_CVPR, author = {Liu, Yixin and Fan, Chenrui and Dai, Yutong and Chen, Xun and Zhou, Pan and Sun, Lichao}, title = {MetaCloak: Preventing Unauthorized Subject-driven Text-to-image Diffusion-based Synthesis via Meta-learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {24219-24228} }
Neural Modes: Self-supervised Learning of Nonlinear Modal Subspaces-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Wang_2024_CVPR, author = {Wang, Jiahong and Du, Yinwei and Coros, Stelian and Thomaszewski, Bernhard}, title = {Neural Modes: Self-supervised Learning of Nonlinear Modal Subspaces}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {23158-23167} }
How to Train Neural Field Representations: A Comprehensive Study and Benchmark-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Papa_2024_CVPR, author = {Papa, Samuele and Valperga, Riccardo and Knigge, David and Kofinas, Miltiadis and Lippe, Phillip and Sonke, Jan-Jakob and Gavves, Efstratios}, title = {How to Train Neural Field Representations: A Comprehensive Study and Benchmark}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {22616-22625} }
Strong Transferable Adversarial Attacks via Ensembled Asymptotically Normal Distribution Learning-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Fang_2024_CVPR, author = {Fang, Zhengwei and Wang, Rui and Huang, Tao and Jing, Liping}, title = {Strong Transferable Adversarial Attacks via Ensembled Asymptotically Normal Distribution Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {24841-24850} }
Spanning Training Progress: Temporal Dual-Depth Scoring (TDDS) for Enhanced Dataset Pruning-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Zhang_2024_CVPR, author = {Zhang, Xin and Du, Jiawei and Li, Yunsong and Xie, Weiying and Zhou, Joey Tianyi}, title = {Spanning Training Progress: Temporal Dual-Depth Scoring (TDDS) for Enhanced Dataset Pruning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {26223-26232} }
CoSeR: Bridging Image and Language for Cognitive Super-Resolution-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Sun_2024_CVPR, author = {Sun, Haoze and Li, Wenbo and Liu, Jianzhuang and Chen, Haoyu and Pei, Renjing and Zou, Xueyi and Yan, Youliang and Yang, Yujiu}, title = {CoSeR: Bridging Image and Language for Cognitive Super-Resolution}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {25868-25878} }
PromptKD: Unsupervised Prompt Distillation for Vision-Language Models-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Li_2024_CVPR, author = {Li, Zheng and Li, Xiang and Fu, Xinyi and Zhang, Xin and Wang, Weiqiang and Chen, Shuo and Yang, Jian}, title = {PromptKD: Unsupervised Prompt Distillation for Vision-Language Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {26617-26626} }
Robust Overfitting Does Matter: Test-Time Adversarial Purification With FGSM-
[pdf]
[arXiv]
[bibtex]@InProceedings{Tang_2024_CVPR, author = {Tang, Linyu and Zhang, Lei}, title = {Robust Overfitting Does Matter: Test-Time Adversarial Purification With FGSM}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {24347-24356} }
Modality-Collaborative Test-Time Adaptation for Action Recognition-
[pdf]
[bibtex]@InProceedings{Xiong_2024_CVPR, author = {Xiong, Baochen and Yang, Xiaoshan and Song, Yaguang and Wang, Yaowei and Xu, Changsheng}, title = {Modality-Collaborative Test-Time Adaptation for Action Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {26732-26741} }
Small Steps and Level Sets: Fitting Neural Surface Models with Point Guidance-
[pdf]
[supp]
[bibtex]@InProceedings{Koneputugodage_2024_CVPR, author = {Koneputugodage, Chamin Hewa and Ben-Shabat, Yizhak and Campbell, Dylan and Gould, Stephen}, title = {Small Steps and Level Sets: Fitting Neural Surface Models with Point Guidance}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {21456-21465} }
Domain-Agnostic Mutual Prompting for Unsupervised Domain Adaptation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Du_2024_CVPR, author = {Du, Zhekai and Li, Xinyao and Li, Fengling and Lu, Ke and Zhu, Lei and Li, Jingjing}, title = {Domain-Agnostic Mutual Prompting for Unsupervised Domain Adaptation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {23375-23384} }
Semantic-Aware Multi-Label Adversarial Attacks-
[pdf]
[supp]
[bibtex]@InProceedings{Mahmood_2024_CVPR, author = {Mahmood, Hassan and Elhamifar, Ehsan}, title = {Semantic-Aware Multi-Label Adversarial Attacks}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {24251-24262} }
MatSynth: A Modern PBR Materials Dataset-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Vecchio_2024_CVPR, author = {Vecchio, Giuseppe and Deschaintre, Valentin}, title = {MatSynth: A Modern PBR Materials Dataset}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {22109-22118} }
OTE: Exploring Accurate Scene Text Recognition Using One Token-
[pdf]
[supp]
[bibtex]@InProceedings{Xu_2024_CVPR, author = {Xu, Jianjun and Wang, Yuxin and Xie, Hongtao and Zhang, Yongdong}, title = {OTE: Exploring Accurate Scene Text Recognition Using One Token}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {28327-28336} }
Gaussian Shadow Casting for Neural Characters-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Bolanos_2024_CVPR, author = {Bolanos, Luis and Su, Shih-Yang and Rhodin, Helge}, title = {Gaussian Shadow Casting for Neural Characters}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {20997-21006} }
Federated Online Adaptation for Deep Stereo-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Poggi_2024_CVPR, author = {Poggi, Matteo and Tosi, Fabio}, title = {Federated Online Adaptation for Deep Stereo}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {20165-20175} }
Sequential Modeling Enables Scalable Learning for Large Vision Models-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Bai_2024_CVPR, author = {Bai, Yutong and Geng, Xinyang and Mangalam, Karttikeya and Bar, Amir and Yuille, Alan L. and Darrell, Trevor and Malik, Jitendra and Efros, Alexei A.}, title = {Sequential Modeling Enables Scalable Learning for Large Vision Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {22861-22872} }
Regularized Parameter Uncertainty for Improving Generalization in Reinforcement Learning-
[pdf]
[supp]
[bibtex]@InProceedings{Moure_2024_CVPR, author = {Moure, Pehuen and Cheng, Longbiao and Ott, Joachim and Wang, Zuowen and Liu, Shih-Chii}, title = {Regularized Parameter Uncertainty for Improving Generalization in Reinforcement Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {23805-23814} }
CoralSCOP: Segment any COral Image on this Planet-
[pdf]
[supp]
[bibtex]@InProceedings{Zheng_2024_CVPR, author = {Zheng, Ziqiang and Liang, Haixin and Hua, Binh-Son and Wong, Yue Him and Ang, Jr, Put and Chui, Apple Pui Yi and Yeung, Sai-Kit}, title = {CoralSCOP: Segment any COral Image on this Planet}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {28170-28180} }
Improved Baselines with Visual Instruction Tuning-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Liu_2024_CVPR, author = {Liu, Haotian and Li, Chunyuan and Li, Yuheng and Lee, Yong Jae}, title = {Improved Baselines with Visual Instruction Tuning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {26296-26306} }
Unexplored Faces of Robustness and Out-of-Distribution: Covariate Shifts in Environment and Sensor Domains-
[pdf]
[supp]
[bibtex]@InProceedings{Baek_2024_CVPR, author = {Baek, Eunsu and Park, Keondo and Kim, Jiyoon and Kim, Hyung-Sin}, title = {Unexplored Faces of Robustness and Out-of-Distribution: Covariate Shifts in Environment and Sensor Domains}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {22294-22303} }
GaussianEditor: Swift and Controllable 3D Editing with Gaussian Splatting-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Chen_2024_CVPR, author = {Chen, Yiwen and Chen, Zilong and Zhang, Chi and Wang, Feng and Yang, Xiaofeng and Wang, Yikai and Cai, Zhongang and Yang, Lei and Liu, Huaping and Lin, Guosheng}, title = {GaussianEditor: Swift and Controllable 3D Editing with Gaussian Splatting}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {21476-21485} }
Open-Vocabulary Semantic Segmentation with Image Embedding Balancing-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Shan_2024_CVPR, author = {Shan, Xiangheng and Wu, Dongyue and Zhu, Guilin and Shao, Yuanjie and Sang, Nong and Gao, Changxin}, title = {Open-Vocabulary Semantic Segmentation with Image Embedding Balancing}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {28412-28421} }
Stronger Fewer & Superior: Harnessing Vision Foundation Models for Domain Generalized Semantic Segmentation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Wei_2024_CVPR, author = {Wei, Zhixiang and Chen, Lin and Jin, Yi and Ma, Xiaoxiao and Liu, Tianle and Ling, Pengyang and Wang, Ben and Chen, Huaian and Zheng, Jinjin}, title = {Stronger Fewer \& Superior: Harnessing Vision Foundation Models for Domain Generalized Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {28619-28630} }
UniBind: LLM-Augmented Unified and Balanced Representation Space to Bind Them All-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Lyu_2024_CVPR, author = {Lyu, Yuanhuiyi and Zheng, Xu and Zhou, Jiazhou and Wang, Lin}, title = {UniBind: LLM-Augmented Unified and Balanced Representation Space to Bind Them All}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {26752-26762} }
Test-Time Adaptation for Depth Completion-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Park_2024_CVPR, author = {Park, Hyoungseob and Gupta, Anjali and Wong, Alex}, title = {Test-Time Adaptation for Depth Completion}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {20519-20529} }
Binarized Low-light Raw Video Enhancement-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Zhang_2024_CVPR, author = {Zhang, Gengchen and Zhang, Yulun and Yuan, Xin and Fu, Ying}, title = {Binarized Low-light Raw Video Enhancement}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {25753-25762} }
MorpheuS: Neural Dynamic 360deg Surface Reconstruction from Monocular RGB-D Video-
[pdf]
[supp]
[bibtex]@InProceedings{Wang_2024_CVPR, author = {Wang, Hengyi and Wang, Jingwen and Agapito, Lourdes}, title = {MorpheuS: Neural Dynamic 360deg Surface Reconstruction from Monocular RGB-D Video}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {20965-20976} }
Weakly Misalignment-free Adaptive Feature Alignment for UAVs-based Multimodal Object Detection-
[pdf]
[supp]
[bibtex]@InProceedings{Chen_2024_CVPR, author = {Chen, Chen and Qi, Jiahao and Liu, Xingyue and Bin, Kangcheng and Fu, Ruigang and Hu, Xikun and Zhong, Ping}, title = {Weakly Misalignment-free Adaptive Feature Alignment for UAVs-based Multimodal Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {26836-26845} }
Passive Snapshot Coded Aperture Dual-Pixel RGB-D Imaging-
[pdf]
[supp]
[bibtex]@InProceedings{Ghanekar_2024_CVPR, author = {Ghanekar, Bhargav and Khan, Salman Siddique and Sharma, Pranav and Singh, Shreyas and Boominathan, Vivek and Mitra, Kaushik and Veeraraghavan, Ashok}, title = {Passive Snapshot Coded Aperture Dual-Pixel RGB-D Imaging}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {25348-25357} }
Instance Tracking in 3D Scenes from Egocentric Videos-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Zhao_2024_CVPR, author = {Zhao, Yunhan and Ma, Haoyu and Kong, Shu and Fowlkes, Charless}, title = {Instance Tracking in 3D Scenes from Egocentric Videos}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {21933-21944} }
Learning to Transform Dynamically for Better Adversarial Transferability-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Zhu_2024_CVPR, author = {Zhu, Rongyi and Zhang, Zeliang and Liang, Susan and Liu, Zhuo and Xu, Chenliang}, title = {Learning to Transform Dynamically for Better Adversarial Transferability}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {24273-24283} }
PanoContext-Former: Panoramic Total Scene Understanding with a Transformer-
[pdf]
[supp]
[bibtex]@InProceedings{Dong_2024_CVPR, author = {Dong, Yuan and Fang, Chuan and Bo, Liefeng and Dong, Zilong and Tan, Ping}, title = {PanoContext-Former: Panoramic Total Scene Understanding with a Transformer}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {28087-28097} }
Prompt3D: Random Prompt Assisted Weakly-Supervised 3D Object Detection-
[pdf]
[supp]
[bibtex]@InProceedings{Zhang_2024_CVPR, author = {Zhang, Xiaohong and Ye, Huisheng and Li, Jingwen and Tang, Qinyu and Li, Yuanqi and Guo, Yanwen and Guo, Jie}, title = {Prompt3D: Random Prompt Assisted Weakly-Supervised 3D Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {28046-28055} }
Navigating Beyond Dropout: An Intriguing Solution towards Generalizable Image Super Resolution-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Wang_2024_CVPR, author = {Wang, Hongjun and Chen, Jiyuan and Zheng, Yinqiang and Zeng, Tieyong}, title = {Navigating Beyond Dropout: An Intriguing Solution towards Generalizable Image Super Resolution}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {25532-25543} }
FC-GNN: Recovering Reliable and Accurate Correspondences from Interferences-
[pdf]
[supp]
[bibtex]@InProceedings{Xu_2024_CVPR, author = {Xu, Haobo and Zhou, Jun and Yang, Hua and Pan, Renjie and Li, Cunyan}, title = {FC-GNN: Recovering Reliable and Accurate Correspondences from Interferences}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {25213-25222} }
Turb-Seg-Res: A Segment-then-Restore Pipeline for Dynamic Videos with Atmospheric Turbulence-
[pdf]
[supp]
[bibtex]@InProceedings{Saha_2024_CVPR, author = {Saha, Ripon Kumar and Qin, Dehao and Li, Nianyi and Ye, Jinwei and Jayasuriya, Suren}, title = {Turb-Seg-Res: A Segment-then-Restore Pipeline for Dynamic Videos with Atmospheric Turbulence}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {25286-25296} }
Real-time Acquisition and Reconstruction of Dynamic Volumes with Neural Structured Illumination-
[pdf]
[supp]
[bibtex]@InProceedings{Zeng_2024_CVPR, author = {Zeng, Yixin and Bi, Zoubin and Yin, Mingrui and Feng, Xiang and Zhou, Kun and Wu, Hongzhi}, title = {Real-time Acquisition and Reconstruction of Dynamic Volumes with Neural Structured Illumination}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {20186-20195} }
Probabilistic Sampling of Balanced K-Means using Adiabatic Quantum Computing-
[pdf]
[supp]
[bibtex]@InProceedings{Zaech_2024_CVPR, author = {Zaech, Jan-Nico and Danelljan, Martin and Birdal, Tolga and Van Gool, Luc}, title = {Probabilistic Sampling of Balanced K-Means using Adiabatic Quantum Computing}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {26191-26201} }
UniPT: Universal Parallel Tuning for Transfer Learning with Efficient Parameter and Memory-
[pdf]
[arXiv]
[bibtex]@InProceedings{Diao_2024_CVPR, author = {Diao, Haiwen and Wan, Bo and Zhang, Ying and Jia, Xu and Lu, Huchuan and Chen, Long}, title = {UniPT: Universal Parallel Tuning for Transfer Learning with Efficient Parameter and Memory}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {28729-28740} }
Composed Video Retrieval via Enriched Context and Discriminative Embeddings-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Thawakar_2024_CVPR, author = {Thawakar, Omkar and Naseer, Muzammal and Anwer, Rao Muhammad and Khan, Salman and Felsberg, Michael and Shah, Mubarak and Khan, Fahad Shahbaz}, title = {Composed Video Retrieval via Enriched Context and Discriminative Embeddings}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {26896-26906} }
Perceptual Assessment and Optimization of HDR Image Rendering-
[pdf]
[arXiv]
[bibtex]@InProceedings{Cao_2024_CVPR, author = {Cao, Peibei and Mantiuk, Rafal K. and Ma, Kede}, title = {Perceptual Assessment and Optimization of HDR Image Rendering}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {22433-22443} }
Multiview Aerial Visual RECognition (MAVREC): Can Multi-view Improve Aerial Visual Perception?-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Dutta_2024_CVPR, author = {Dutta, Aritra and Das, Srijan and Nielsen, Jacob and Chakraborty, Rajatsubhra and Shah, Mubarak}, title = {Multiview Aerial Visual RECognition (MAVREC): Can Multi-view Improve Aerial Visual Perception?}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {22678-22690} }
SaCo Loss: Sample-wise Affinity Consistency for Vision-Language Pre-training-
[pdf]
[supp]
[bibtex]@InProceedings{Wu_2024_CVPR, author = {Wu, Sitong and Tan, Haoru and Tian, Zhuotao and Chen, Yukang and Qi, Xiaojuan and Jia, Jiaya}, title = {SaCo Loss: Sample-wise Affinity Consistency for Vision-Language Pre-training}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {27358-27369} }
Stable Neighbor Denoising for Source-free Domain Adaptive Segmentation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Zhao_2024_CVPR, author = {Zhao, Dong and Wang, Shuang and Zang, Qi and Jiao, Licheng and Sebe, Nicu and Zhong, Zhun}, title = {Stable Neighbor Denoising for Source-free Domain Adaptive Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {23416-23427} }
Boosting Adversarial Training via Fisher-Rao Norm-based Regularization-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Yin_2024_CVPR, author = {Yin, Xiangyu and Ruan, Wenjie}, title = {Boosting Adversarial Training via Fisher-Rao Norm-based Regularization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {24544-24553} }
DAVE - A Detect-and-Verify Paradigm for Low-Shot Counting-
[pdf]
[bibtex]@InProceedings{Pelhan_2024_CVPR, author = {Pelhan, Jer and Luke\v{z}i?, Alan and Zavrtanik, Vitjan and Kristan, Matej}, title = {DAVE - A Detect-and-Verify Paradigm for Low-Shot Counting}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {23293-23302} }
Efficient LoFTR: Semi-Dense Local Feature Matching with Sparse-Like Speed-
[pdf]
[arXiv]
[bibtex]@InProceedings{Wang_2024_CVPR, author = {Wang, Yifan and He, Xingyi and Peng, Sida and Tan, Dongli and Zhou, Xiaowei}, title = {Efficient LoFTR: Semi-Dense Local Feature Matching with Sparse-Like Speed}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {21666-21675} }
Contextual Augmented Global Contrast for Multimodal Intent Recognition-
[pdf]
[bibtex]@InProceedings{Sun_2024_CVPR, author = {Sun, Kaili and Xie, Zhiwen and Ye, Mang and Zhang, Huyin}, title = {Contextual Augmented Global Contrast for Multimodal Intent Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {26963-26973} }
Pre-trained Model Guided Fine-Tuning for Zero-Shot Adversarial Robustness-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Wang_2024_CVPR, author = {Wang, Sibo and Zhang, Jie and Yuan, Zheng and Shan, Shiguang}, title = {Pre-trained Model Guided Fine-Tuning for Zero-Shot Adversarial Robustness}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {24502-24511} }
CoGS: Controllable Gaussian Splatting-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Yu_2024_CVPR, author = {Yu, Heng and Julin, Joel and Milacski, Zolt\'an A. and Niinuma, Koichiro and Jeni, L\'aszl\'o A.}, title = {CoGS: Controllable Gaussian Splatting}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {21624-21633} }
Partial-to-Partial Shape Matching with Geometric Consistency-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Ehm_2024_CVPR, author = {Ehm, Viktoria and Gao, Maolin and Roetzer, Paul and Eisenberger, Marvin and Cremers, Daniel and Bernard, Florian}, title = {Partial-to-Partial Shape Matching with Geometric Consistency}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {27488-27497} }
Descriptor and Word Soups: Overcoming the Parameter Efficiency Accuracy Tradeoff for Out-of-Distribution Few-shot Learning-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Liao_2024_CVPR, author = {Liao, Christopher and Tsiligkaridis, Theodoros and Kulis, Brian}, title = {Descriptor and Word Soups: Overcoming the Parameter Efficiency Accuracy Tradeoff for Out-of-Distribution Few-shot Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {27015-27025} }
360+x: A Panoptic Multi-modal Scene Understanding Dataset-
[pdf]
[supp]
[bibtex]@InProceedings{Chen_2024_CVPR, author = {Chen, Hao and Hou, Yuqi and Qu, Chenyuan and Testini, Irene and Hong, Xiaohan and Jiao, Jianbo}, title = {360+x: A Panoptic Multi-modal Scene Understanding Dataset}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {19373-19382} }
Generalized Event Cameras-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Sundar_2024_CVPR, author = {Sundar, Varun and Dutson, Matthew and Ardelean, Andrei and Bruschini, Claudio and Charbon, Edoardo and Gupta, Mohit}, title = {Generalized Event Cameras}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {25007-25017} }
3D Neural Edge Reconstruction-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Li_2024_CVPR, author = {Li, Lei and Peng, Songyou and Yu, Zehao and Liu, Shaohui and Pautrat, R\'emi and Yin, Xiaochuan and Pollefeys, Marc}, title = {3D Neural Edge Reconstruction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {21219-21229} }
DGC-GNN: Leveraging Geometry and Color Cues for Visual Descriptor-Free 2D-3D Matching-
[pdf]
[supp]
[bibtex]@InProceedings{Wang_2024_CVPR, author = {Wang, Shuzhe and Kannala, Juho and Barath, Daniel}, title = {DGC-GNN: Leveraging Geometry and Color Cues for Visual Descriptor-Free 2D-3D Matching}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {20881-20891} }
CuVLER: Enhanced Unsupervised Object Discoveries through Exhaustive Self-Supervised Transformers-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Arica_2024_CVPR, author = {Arica, Shahaf and Rubin, Or and Gershov, Sapir and Laufer, Shlomi}, title = {CuVLER: Enhanced Unsupervised Object Discoveries through Exhaustive Self-Supervised Transformers}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {23105-23114} }
Entity-NeRF: Detecting and Removing Moving Entities in Urban Scenes-
[pdf]
[supp]
[bibtex]@InProceedings{Otonari_2024_CVPR, author = {Otonari, Takashi and Ikehata, Satoshi and Aizawa, Kiyoharu}, title = {Entity-NeRF: Detecting and Removing Moving Entities in Urban Scenes}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {20892-20901} }
TAMM: TriAdapter Multi-Modal Learning for 3D Shape Understanding-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Zhang_2024_CVPR, author = {Zhang, Zhihao and Cao, Shengcao and Wang, Yu-Xiong}, title = {TAMM: TriAdapter Multi-Modal Learning for 3D Shape Understanding}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {21413-21423} }
GauHuman: Articulated Gaussian Splatting from Monocular Human Videos-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Hu_2024_CVPR, author = {Hu, Shoukang and Hu, Tao and Liu, Ziwei}, title = {GauHuman: Articulated Gaussian Splatting from Monocular Human Videos}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {20418-20431} }
EGTR: Extracting Graph from Transformer for Scene Graph Generation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Im_2024_CVPR, author = {Im, Jinbae and Nam, JeongYeon and Park, Nokyung and Lee, Hyungmin and Park, Seunghyun}, title = {EGTR: Extracting Graph from Transformer for Scene Graph Generation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {24229-24238} }
Rethinking Multi-domain Generalization with A General Learning Objective-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Tan_2024_CVPR, author = {Tan, Zhaorui and Yang, Xi and Huang, Kaizhu}, title = {Rethinking Multi-domain Generalization with A General Learning Objective}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {23512-23522} }
Universal Novelty Detection Through Adaptive Contrastive Learning-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Mirzaei_2024_CVPR, author = {Mirzaei, Hossein and Nafez, Mojtaba and Jafari, Mohammad and Soltani, Mohammad Bagher and Azizmalayeri, Mohammad and Habibi, Jafar and Sabokrou, Mohammad and Rohban, Mohammad Hossein}, title = {Universal Novelty Detection Through Adaptive Contrastive Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {22914-22923} }
Resurrecting Old Classes with New Data for Exemplar-Free Continual Learning-
[pdf]
[supp]
[bibtex]@InProceedings{Goswami_2024_CVPR, author = {Goswami, Dipam and Soutif-Cormerais, Albin and Liu, Yuyang and Kamath, Sandesh and Twardowski, Bart?omiej and van de Weijer, Joost}, title = {Resurrecting Old Classes with New Data for Exemplar-Free Continual Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {28525-28534} }
Poly Kernel Inception Network for Remote Sensing Detection-
[pdf]
[arXiv]
[bibtex]@InProceedings{Cai_2024_CVPR, author = {Cai, Xinhao and Lai, Qiuxia and Wang, Yuwei and Wang, Wenguan and Sun, Zeren and Yao, Yazhou}, title = {Poly Kernel Inception Network for Remote Sensing Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {27706-27716} }
Dual Prior Unfolding for Snapshot Compressive Imaging-
[pdf]
[supp]
[bibtex]@InProceedings{Zhang_2024_CVPR, author = {Zhang, Jiancheng and Zeng, Haijin and Cao, Jiezhang and Chen, Yongyong and Yu, Dengxiu and Zhao, Yin-Ping}, title = {Dual Prior Unfolding for Snapshot Compressive Imaging}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {25742-25752} }
COLMAP-Free 3D Gaussian Splatting-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Fu_2024_CVPR, author = {Fu, Yang and Liu, Sifei and Kulkarni, Amey and Kautz, Jan and Efros, Alexei A. and Wang, Xiaolong}, title = {COLMAP-Free 3D Gaussian Splatting}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {20796-20805} }
BadCLIP: Dual-Embedding Guided Backdoor Attack on Multimodal Contrastive Learning-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Liang_2024_CVPR, author = {Liang, Siyuan and Zhu, Mingli and Liu, Aishan and Wu, Baoyuan and Cao, Xiaochun and Chang, Ee-Chien}, title = {BadCLIP: Dual-Embedding Guided Backdoor Attack on Multimodal Contrastive Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {24645-24654} }
Efficient Vision-Language Pre-training by Cluster Masking-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Wei_2024_CVPR, author = {Wei, Zihao and Pan, Zixuan and Owens, Andrew}, title = {Efficient Vision-Language Pre-training by Cluster Masking}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {26815-26825} }
GPS-Gaussian: Generalizable Pixel-wise 3D Gaussian Splatting for Real-time Human Novel View Synthesis-
[pdf]
[supp]
[bibtex]@InProceedings{Zheng_2024_CVPR, author = {Zheng, Shunyuan and Zhou, Boyao and Shao, Ruizhi and Liu, Boning and Zhang, Shengping and Nie, Liqiang and Liu, Yebin}, title = {GPS-Gaussian: Generalizable Pixel-wise 3D Gaussian Splatting for Real-time Human Novel View Synthesis}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {19680-19690} }
MAGICK: A Large-scale Captioned Dataset from Matting Generated Images using Chroma Keying-
[pdf]
[supp]
[bibtex]@InProceedings{Burgert_2024_CVPR, author = {Burgert, Ryan D. and Price, Brian L. and Kuen, Jason and Li, Yijun and Ryoo, Michael S.}, title = {MAGICK: A Large-scale Captioned Dataset from Matting Generated Images using Chroma Keying}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {22595-22604} }
Video Super-Resolution Transformer with Masked Inter&Intra-Frame Attention-
[pdf]
[supp]
[bibtex]@InProceedings{Zhou_2024_CVPR, author = {Zhou, Xingyu and Zhang, Leheng and Zhao, Xiaorui and Wang, Keze and Li, Leida and Gu, Shuhang}, title = {Video Super-Resolution Transformer with Masked Inter\&Intra-Frame Attention}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {25399-25408} }
SurroundSDF: Implicit 3D Scene Understanding Based on Signed Distance Field-
[pdf]
[arXiv]
[bibtex]@InProceedings{Liu_2024_CVPR, author = {Liu, Lizhe and Wang, Bohua and Xie, Hongwei and Liu, Daqi and Liu, Li and Tian, Zhiqiang and Yang, Kuiyuan and Wang, Bing}, title = {SurroundSDF: Implicit 3D Scene Understanding Based on Signed Distance Field}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {21614-21623} }
Outdoor Scene Extrapolation with Hierarchical Generative Cellular Automata-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Zhang_2024_CVPR, author = {Zhang, Dongsu and Williams, Francis and Gojcic, Zan and Kreis, Karsten and Fidler, Sanja and Kim, Young Min and Kar, Amlan}, title = {Outdoor Scene Extrapolation with Hierarchical Generative Cellular Automata}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {20145-20154} }
Instruct 4D-to-4D: Editing 4D Scenes as Pseudo-3D Scenes Using 2D Diffusion-
[pdf]
[supp]
[bibtex]@InProceedings{Mou_2024_CVPR, author = {Mou, Linzhan and Chen, Jun-Kun and Wang, Yu-Xiong}, title = {Instruct 4D-to-4D: Editing 4D Scenes as Pseudo-3D Scenes Using 2D Diffusion}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {20176-20185} }
Photo-SLAM: Real-time Simultaneous Localization and Photorealistic Mapping for Monocular Stereo and RGB-D Cameras-
[pdf]
[supp]
[bibtex]@InProceedings{Huang_2024_CVPR, author = {Huang, Huajian and Li, Longwei and Cheng, Hui and Yeung, Sai-Kit}, title = {Photo-SLAM: Real-time Simultaneous Localization and Photorealistic Mapping for Monocular Stereo and RGB-D Cameras}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {21584-21593} }
ProMotion: Prototypes As Motion Learners-
[pdf]
[arXiv]
[bibtex]@InProceedings{Lu_2024_CVPR, author = {Lu, Yawen and Liu, Dongfang and Wang, Qifan and Han, Cheng and Cui, Yiming and Cao, Zhiwen and Zhang, Xueling and Chen, Yingjie Victor and Fan, Heng}, title = {ProMotion: Prototypes As Motion Learners}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {28109-28119} }
SpatialTracker: Tracking Any 2D Pixels in 3D Space-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Xiao_2024_CVPR, author = {Xiao, Yuxi and Wang, Qianqian and Zhang, Shangzhan and Xue, Nan and Peng, Sida and Shen, Yujun and Zhou, Xiaowei}, title = {SpatialTracker: Tracking Any 2D Pixels in 3D Space}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {20406-20417} }
CrossMAE: Cross-Modality Masked Autoencoders for Region-Aware Audio-Visual Pre-Training-
[pdf]
[supp]
[bibtex]@InProceedings{Guo_2024_CVPR, author = {Guo, Yuxin and Sun, Siyang and Ma, Shuailei and Zheng, Kecheng and Bao, Xiaoyi and Ma, Shijie and Zou, Wei and Zheng, Yun}, title = {CrossMAE: Cross-Modality Masked Autoencoders for Region-Aware Audio-Visual Pre-Training}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {26721-26731} }
Osprey: Pixel Understanding with Visual Instruction Tuning-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Yuan_2024_CVPR, author = {Yuan, Yuqian and Li, Wentong and Liu, Jian and Tang, Dongqi and Luo, Xinjie and Qin, Chi and Zhang, Lei and Zhu, Jianke}, title = {Osprey: Pixel Understanding with Visual Instruction Tuning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {28202-28211} }
Few-shot Learner Parameterization by Diffusion Time-steps-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Yue_2024_CVPR, author = {Yue, Zhongqi and Zhou, Pan and Hong, Richang and Zhang, Hanwang and Sun, Qianru}, title = {Few-shot Learner Parameterization by Diffusion Time-steps}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {23263-23272} }
OrCo: Towards Better Generalization via Orthogonality and Contrast for Few-Shot Class-Incremental Learning-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Ahmed_2024_CVPR, author = {Ahmed, Noor and Kukleva, Anna and Schiele, Bernt}, title = {OrCo: Towards Better Generalization via Orthogonality and Contrast for Few-Shot Class-Incremental Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {28762-28771} }
MuGE: Multiple Granularity Edge Detection-
[pdf]
[supp]
[bibtex]@InProceedings{Zhou_2024_CVPR, author = {Zhou, Caixia and Huang, Yaping and Pu, Mengyang and Guan, Qingji and Deng, Ruoxi and Ling, Haibin}, title = {MuGE: Multiple Granularity Edge Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {25952-25962} }
Real-World Efficient Blind Motion Deblurring via Blur Pixel Discretization-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Kim_2024_CVPR, author = {Kim, Insoo and Choi, Jae Seok and Seo, Geonseok and Kwon, Kinam and Shin, Jinwoo and Lee, Hyong-Euk}, title = {Real-World Efficient Blind Motion Deblurring via Blur Pixel Discretization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {25879-25888} }
EmoVIT: Revolutionizing Emotion Insights with Visual Instruction Tuning-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Xie_2024_CVPR, author = {Xie, Hongxia and Peng, Chu-Jun and Tseng, Yu-Wen and Chen, Hung-Jen and Hsu, Chan-Feng and Shuai, Hong-Han and Cheng, Wen-Huang}, title = {EmoVIT: Revolutionizing Emotion Insights with Visual Instruction Tuning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {26596-26605} }
Learning to Count without Annotations-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Knobel_2024_CVPR, author = {Knobel, Lukas and Han, Tengda and Asano, Yuki M.}, title = {Learning to Count without Annotations}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {22924-22934} }
NARUTO: Neural Active Reconstruction from Uncertain Target Observations-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Feng_2024_CVPR, author = {Feng, Ziyue and Zhan, Huangying and Chen, Zheng and Yan, Qingan and Xu, Xiangyu and Cai, Changjiang and Li, Bing and Zhu, Qilun and Xu, Yi}, title = {NARUTO: Neural Active Reconstruction from Uncertain Target Observations}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {21572-21583} }
Learnable Earth Parser: Discovering 3D Prototypes in Aerial Scans-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Loiseau_2024_CVPR, author = {Loiseau, Romain and Vincent, Elliot and Aubry, Mathieu and Landrieu, Loic}, title = {Learnable Earth Parser: Discovering 3D Prototypes in Aerial Scans}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {27874-27884} }
NeRFiller: Completing Scenes via Generative 3D Inpainting-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Weber_2024_CVPR, author = {Weber, Ethan and Holynski, Aleksander and Jampani, Varun and Saxena, Saurabh and Snavely, Noah and Kar, Abhishek and Kanazawa, Angjoo}, title = {NeRFiller: Completing Scenes via Generative 3D Inpainting}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {20731-20741} }
Absolute Pose from One or Two Scaled and Oriented Features-
[pdf]
[supp]
[bibtex]@InProceedings{Ventura_2024_CVPR, author = {Ventura, Jonathan and Kukelova, Zuzana and Sattler, Torsten and Bar\'ath, D\'aniel}, title = {Absolute Pose from One or Two Scaled and Oriented Features}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {20870-20880} }
Source-Free Domain Adaptation with Frozen Multimodal Foundation Model-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Tang_2024_CVPR, author = {Tang, Song and Su, Wenxin and Ye, Mao and Zhu, Xiatian}, title = {Source-Free Domain Adaptation with Frozen Multimodal Foundation Model}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {23711-23720} }
Benchmarking Audio Visual Segmentation for Long-Untrimmed Videos-
[pdf]
[supp]
[bibtex]@InProceedings{Liu_2024_CVPR, author = {Liu, Chen and Li, Peike Patrick and Yu, Qingtao and Sheng, Hongwei and Wang, Dadong and Li, Lincheng and Yu, Xin}, title = {Benchmarking Audio Visual Segmentation for Long-Untrimmed Videos}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {22712-22722} }
VTQA: Visual Text Question Answering via Entity Alignment and Cross-Media Reasoning-
[pdf]
[arXiv]
[bibtex]@InProceedings{Chen_2024_CVPR, author = {Chen, Kang and Wu, Xiangqian}, title = {VTQA: Visual Text Question Answering via Entity Alignment and Cross-Media Reasoning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {27218-27227} }
QN-Mixer: A Quasi-Newton MLP-Mixer Model for Sparse-View CT Reconstruction-
[pdf]
[supp]
[bibtex]@InProceedings{Ayad_2024_CVPR, author = {Ayad, Ishak and Larue, Nicolas and Nguyen, Mai K.}, title = {QN-Mixer: A Quasi-Newton MLP-Mixer Model for Sparse-View CT Reconstruction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {25317-25326} }
Learning CNN on ViT: A Hybrid Model to Explicitly Class-specific Boundaries for Domain Adaptation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Ngo_2024_CVPR, author = {Ngo, Ba Hung and Do-Tran, Nhat-Tuong and Nguyen, Tuan-Ngoc and Jeon, Hae-Gon and Choi, Tae Jong}, title = {Learning CNN on ViT: A Hybrid Model to Explicitly Class-specific Boundaries for Domain Adaptation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {28545-28554} }
A Picture is Worth More Than 77 Text Tokens: Evaluating CLIP-Style Models on Dense Captions-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Urbanek_2024_CVPR, author = {Urbanek, Jack and Bordes, Florian and Astolfi, Pietro and Williamson, Mary and Sharma, Vasu and Romero-Soriano, Adriana}, title = {A Picture is Worth More Than 77 Text Tokens: Evaluating CLIP-Style Models on Dense Captions}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {26700-26709} }
Infinigen Indoors: Photorealistic Indoor Scenes using Procedural Generation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Raistrick_2024_CVPR, author = {Raistrick, Alexander and Mei, Lingjie and Kayan, Karhan and Yan, David and Zuo, Yiming and Han, Beining and Wen, Hongyu and Parakh, Meenal and Alexandropoulos, Stamatis and Lipson, Lahav and Ma, Zeyu and Deng, Jia}, title = {Infinigen Indoors: Photorealistic Indoor Scenes using Procedural Generation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {21783-21794} }
MimicDiffusion: Purifying Adversarial Perturbation via Mimicking Clean Diffusion Model-
[pdf]
[supp]
[bibtex]@InProceedings{Song_2024_CVPR, author = {Song, Kaiyu and Lai, Hanjiang and Pan, Yan and Yin, Jian}, title = {MimicDiffusion: Purifying Adversarial Perturbation via Mimicking Clean Diffusion Model}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {24665-24674} }
Robust Synthetic-to-Real Transfer for Stereo Matching-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Zhang_2024_CVPR, author = {Zhang, Jiawei and Li, Jiahe and Huang, Lei and Yu, Xiaohan and Gu, Lin and Zheng, Jin and Bai, Xiao}, title = {Robust Synthetic-to-Real Transfer for Stereo Matching}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {20247-20257} }
GenZI: Zero-Shot 3D Human-Scene Interaction Generation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Li_2024_CVPR, author = {Li, Lei and Dai, Angela}, title = {GenZI: Zero-Shot 3D Human-Scene Interaction Generation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {20465-20474} }
DiffAssemble: A Unified Graph-Diffusion Model for 2D and 3D Reassembly-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Scarpellini_2024_CVPR, author = {Scarpellini, Gianluca and Fiorini, Stefano and Giuliari, Francesco and Moreiro, Pietro and Del Bue, Alessio}, title = {DiffAssemble: A Unified Graph-Diffusion Model for 2D and 3D Reassembly}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {28098-28108} }
NeISF: Neural Incident Stokes Field for Geometry and Material Estimation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Li_2024_CVPR, author = {Li, Chenhao and Ono, Taishi and Uemori, Takeshi and Mihara, Hajime and Gatto, Alexander and Nagahara, Hajime and Moriuchi, Yusuke}, title = {NeISF: Neural Incident Stokes Field for Geometry and Material Estimation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {21434-21445} }
ViT-Lens: Towards Omni-modal Representations-
[pdf]
[supp]
[bibtex]@InProceedings{Lei_2024_CVPR, author = {Lei, Weixian and Ge, Yixiao and Yi, Kun and Zhang, Jianfeng and Gao, Difei and Sun, Dylan and Ge, Yuying and Shan, Ying and Shou, Mike Zheng}, title = {ViT-Lens: Towards Omni-modal Representations}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {26647-26657} }
GeoChat: Grounded Large Vision-Language Model for Remote Sensing-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Kuckreja_2024_CVPR, author = {Kuckreja, Kartik and Danish, Muhammad Sohail and Naseer, Muzammal and Das, Abhijit and Khan, Salman and Khan, Fahad Shahbaz}, title = {GeoChat: Grounded Large Vision-Language Model for Remote Sensing}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {27831-27840} }
PerceptionGPT: Effectively Fusing Visual Perception into LLM-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Pi_2024_CVPR, author = {Pi, Renjie and Yao, Lewei and Gao, Jiahui and Zhang, Jipeng and Zhang, Tong}, title = {PerceptionGPT: Effectively Fusing Visual Perception into LLM}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {27124-27133} }
Probabilistic Speech-Driven 3D Facial Motion Synthesis: New Benchmarks Methods and Applications-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Yang_2024_CVPR, author = {Yang, Karren D. and Ranjan, Anurag and Chang, Jen-Hao Rick and Vemulapalli, Raviteja and Tuzel, Oncel}, title = {Probabilistic Speech-Driven 3D Facial Motion Synthesis: New Benchmarks Methods and Applications}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {27294-27303} }
FreGS: 3D Gaussian Splatting with Progressive Frequency Regularization-
[pdf]
[arXiv]
[bibtex]@InProceedings{Zhang_2024_CVPR, author = {Zhang, Jiahui and Zhan, Fangneng and Xu, Muyu and Lu, Shijian and Xing, Eric}, title = {FreGS: 3D Gaussian Splatting with Progressive Frequency Regularization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {21424-21433} }
Discriminative Sample-Guided and Parameter-Efficient Feature Space Adaptation for Cross-Domain Few-Shot Learning-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Perera_2024_CVPR, author = {Perera, Rashindrie and Halgamuge, Saman}, title = {Discriminative Sample-Guided and Parameter-Efficient Feature Space Adaptation for Cross-Domain Few-Shot Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {23794-23804} }
Detector-Free Structure from Motion-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{He_2024_CVPR, author = {He, Xingyi and Sun, Jiaming and Wang, Yifan and Peng, Sida and Huang, Qixing and Bao, Hujun and Zhou, Xiaowei}, title = {Detector-Free Structure from Motion}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {21594-21603} }
CG-HOI: Contact-Guided 3D Human-Object Interaction Generation-
[pdf]
[supp]
[bibtex]@InProceedings{Diller_2024_CVPR, author = {Diller, Christian and Dai, Angela}, title = {CG-HOI: Contact-Guided 3D Human-Object Interaction Generation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {19888-19901} }
Towards Surveillance Video-and-Language Understanding: New Dataset Baselines and Challenges-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Yuan_2024_CVPR, author = {Yuan, Tongtong and Zhang, Xuange and Liu, Kun and Liu, Bo and Chen, Chen and Jin, Jian and Jiao, Zhenzhen}, title = {Towards Surveillance Video-and-Language Understanding: New Dataset Baselines and Challenges}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {22052-22061} }
AdaRevD: Adaptive Patch Exiting Reversible Decoder Pushes the Limit of Image Deblurring-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Mao_2024_CVPR, author = {Mao, Xintian and Li, Qingli and Wang, Yan}, title = {AdaRevD: Adaptive Patch Exiting Reversible Decoder Pushes the Limit of Image Deblurring}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {25681-25690} }
Learning to Remove Wrinkled Transparent Film with Polarized Prior-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Tang_2024_CVPR, author = {Tang, Jiaqi and Wu, Ruizheng and Xu, Xiaogang and Hu, Sixing and Chen, Ying-Cong}, title = {Learning to Remove Wrinkled Transparent Film with Polarized Prior}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {24987-24996} }
Dispel Darkness for Better Fusion: A Controllable Visual Enhancer based on Cross-modal Conditional Adversarial Learning-
[pdf]
[supp]
[bibtex]@InProceedings{Zhang_2024_CVPR, author = {Zhang, Hao and Tang, Linfeng and Xiang, Xinyu and Zuo, Xuhui and Ma, Jiayi}, title = {Dispel Darkness for Better Fusion: A Controllable Visual Enhancer based on Cross-modal Conditional Adversarial Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {26487-26496} }
Querying as Prompt: Parameter-Efficient Learning for Multimodal Language Model-
[pdf]
[supp]
[bibtex]@InProceedings{Liang_2024_CVPR, author = {Liang, Tian and Huang, Jing and Kong, Ming and Chen, Luyuan and Zhu, Qiang}, title = {Querying as Prompt: Parameter-Efficient Learning for Multimodal Language Model}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {26855-26865} }
Deformable 3D Gaussians for High-Fidelity Monocular Dynamic Scene Reconstruction-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Yang_2024_CVPR, author = {Yang, Ziyi and Gao, Xinyu and Zhou, Wen and Jiao, Shaohui and Zhang, Yuqing and Jin, Xiaogang}, title = {Deformable 3D Gaussians for High-Fidelity Monocular Dynamic Scene Reconstruction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {20331-20341} }
Enhancing 3D Object Detection with 2D Detection-Guided Query Anchors-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Ji_2024_CVPR, author = {Ji, Haoxuanye and Liang, Pengpeng and Cheng, Erkang}, title = {Enhancing 3D Object Detection with 2D Detection-Guided Query Anchors}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {21178-21187} }
Continual Forgetting for Pre-trained Vision Models-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Zhao_2024_CVPR, author = {Zhao, Hongbo and Ni, Bolin and Fan, Junsong and Wang, Yuxi and Chen, Yuntao and Meng, Gaofeng and Zhang, Zhaoxiang}, title = {Continual Forgetting for Pre-trained Vision Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {28631-28642} }
Real Acoustic Fields: An Audio-Visual Room Acoustics Dataset and Benchmark-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Chen_2024_CVPR, author = {Chen, Ziyang and Gebru, Israel D. and Richardt, Christian and Kumar, Anurag and Laney, William and Owens, Andrew and Richard, Alexander}, title = {Real Acoustic Fields: An Audio-Visual Room Acoustics Dataset and Benchmark}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {21886-21896} }
A Physics-informed Low-rank Deep Neural Network for Blind and Universal Lens Aberration Correction-
[pdf]
[bibtex]@InProceedings{Gong_2024_CVPR, author = {Gong, Jin and Yang, Runzhao and Zhang, Weihang and Suo, Jinli and Dai, Qionghai}, title = {A Physics-informed Low-rank Deep Neural Network for Blind and Universal Lens Aberration Correction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {24861-24870} }
Calibrating Multi-modal Representations: A Pursuit of Group Robustness without Annotations-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{You_2024_CVPR, author = {You, Chenyu and Min, Yifei and Dai, Weicheng and Sekhon, Jasjeet S. and Staib, Lawrence and Duncan, James S.}, title = {Calibrating Multi-modal Representations: A Pursuit of Group Robustness without Annotations}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {26140-26150} }
MCD: Diverse Large-Scale Multi-Campus Dataset for Robot Perception-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Nguyen_2024_CVPR, author = {Nguyen, Thien-Minh and Yuan, Shenghai and Nguyen, Thien Hoang and Yin, Pengyu and Cao, Haozhi and Xie, Lihua and Wozniak, Maciej and Jensfelt, Patric and Thiel, Marko and Ziegenbein, Justin and Blunder, Noel}, title = {MCD: Diverse Large-Scale Multi-Campus Dataset for Robot Perception}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {22304-22313} }
ArGue: Attribute-Guided Prompt Tuning for Vision-Language Models-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Tian_2024_CVPR, author = {Tian, Xinyu and Zou, Shu and Yang, Zhaoyuan and Zhang, Jing}, title = {ArGue: Attribute-Guided Prompt Tuning for Vision-Language Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {28578-28587} }
Close Imitation of Expert Retouching for Black-and-White Photography-
[pdf]
[bibtex]@InProceedings{Shin_2024_CVPR, author = {Shin, Seunghyun and Shin, Jisu and Bae, Jihwan and Shim, Inwook and Jeon, Hae-Gon}, title = {Close Imitation of Expert Retouching for Black-and-White Photography}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {25037-25046} }
Understanding and Improving Source-free Domain Adaptation from a Theoretical Perspective-
[pdf]
[supp]
[bibtex]@InProceedings{Mitsuzumi_2024_CVPR, author = {Mitsuzumi, Yu and Kimura, Akisato and Kashima, Hisashi}, title = {Understanding and Improving Source-free Domain Adaptation from a Theoretical Perspective}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {28515-28524} }
Learning SO(3)-Invariant Semantic Correspondence via Local Shape Transform-
[pdf]
[supp]
[bibtex]@InProceedings{Park_2024_CVPR, author = {Park, Chunghyun and Kim, Seungwook and Park, Jaesik and Cho, Minsu}, title = {Learning SO(3)-Invariant Semantic Correspondence via Local Shape Transform}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {22978-22987} }
Deep-TROJ: An Inference Stage Trojan Insertion Algorithm through Efficient Weight Replacement Attack-
[pdf]
[bibtex]@InProceedings{Ahmed_2024_CVPR, author = {Ahmed, Sabbir and Zhou, Ranyang and Angizi, Shaahin and Rakin, Adnan Siraj}, title = {Deep-TROJ: An Inference Stage Trojan Insertion Algorithm through Efficient Weight Replacement Attack}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {24810-24819} }
Investigating and Mitigating the Side Effects of Noisy Views for Self-Supervised Clustering Algorithms in Practical Multi-View Scenarios-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Xu_2024_CVPR, author = {Xu, Jie and Ren, Yazhou and Wang, Xiaolong and Feng, Lei and Zhang, Zheng and Niu, Gang and Zhu, Xiaofeng}, title = {Investigating and Mitigating the Side Effects of Noisy Views for Self-Supervised Clustering Algorithms in Practical Multi-View Scenarios}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {22957-22966} }
EvalCrafter: Benchmarking and Evaluating Large Video Generation Models-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Liu_2024_CVPR, author = {Liu, Yaofang and Cun, Xiaodong and Liu, Xuebo and Wang, Xintao and Zhang, Yong and Chen, Haoxin and Liu, Yang and Zeng, Tieyong and Chan, Raymond and Shan, Ying}, title = {EvalCrafter: Benchmarking and Evaluating Large Video Generation Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {22139-22149} }
SelfOcc: Self-Supervised Vision-Based 3D Occupancy Prediction-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Huang_2024_CVPR, author = {Huang, Yuanhui and Zheng, Wenzhao and Zhang, Borui and Zhou, Jie and Lu, Jiwen}, title = {SelfOcc: Self-Supervised Vision-Based 3D Occupancy Prediction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {19946-19956} }
SubT-MRS Dataset: Pushing SLAM Towards All-weather Environments-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Zhao_2024_CVPR, author = {Zhao, Shibo and Gao, Yuanjun and Wu, Tianhao and Singh, Damanpreet and Jiang, Rushan and Sun, Haoxiang and Sarawata, Mansi and Qiu, Yuheng and Whittaker, Warren and Higgins, Ian and Du, Yi and Su, Shaoshu and Xu, Can and Keller, John and Karhade, Jay and Nogueira, Lucas and Saha, Sourojit and Zhang, Ji and Wang, Wenshan and Wang, Chen and Scherer, Sebastian}, title = {SubT-MRS Dataset: Pushing SLAM Towards All-weather Environments}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {22647-22657} }
Relational Matching for Weakly Semi-Supervised Oriented Object Detection-
[pdf]
[supp]
[bibtex]@InProceedings{Wu_2024_CVPR, author = {Wu, Wenhao and Wong, Hau-San and Wu, Si and Zhang, Tianyou}, title = {Relational Matching for Weakly Semi-Supervised Oriented Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {27800-27810} }
Rethinking the Representation in Federated Unsupervised Learning with Non-IID Data-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Liao_2024_CVPR, author = {Liao, Xinting and Liu, Weiming and Chen, Chaochao and Zhou, Pengyang and Yu, Fengyuan and Zhu, Huabin and Yao, Binhui and Wang, Tao and Zheng, Xiaolin and Tan, Yanchao}, title = {Rethinking the Representation in Federated Unsupervised Learning with Non-IID Data}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {22841-22850} }
Distraction is All You Need: Memory-Efficient Image Immunization against Diffusion-Based Image Editing-
[pdf]
[supp]
[bibtex]@InProceedings{Lo_2024_CVPR, author = {Lo, Ling and Yeo, Cheng Yu and Shuai, Hong-Han and Cheng, Wen-Huang}, title = {Distraction is All You Need: Memory-Efficient Image Immunization against Diffusion-Based Image Editing}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {24462-24471} }
Knowledge-Enhanced Dual-stream Zero-shot Composed Image Retrieval-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Suo_2024_CVPR, author = {Suo, Yucheng and Ma, Fan and Zhu, Linchao and Yang, Yi}, title = {Knowledge-Enhanced Dual-stream Zero-shot Composed Image Retrieval}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {26951-26962} }
Grounding and Enhancing Grid-based Models for Neural Fields-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Zhao_2024_CVPR, author = {Zhao, Zelin and Fan, Fenglei and Liao, Wenlong and Yan, Junchi}, title = {Grounding and Enhancing Grid-based Models for Neural Fields}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {19425-19435} }
GART: Gaussian Articulated Template Models-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Lei_2024_CVPR, author = {Lei, Jiahui and Wang, Yufu and Pavlakos, Georgios and Liu, Lingjie and Daniilidis, Kostas}, title = {GART: Gaussian Articulated Template Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {19876-19887} }
KP-RED: Exploiting Semantic Keypoints for Joint 3D Shape Retrieval and Deformation-
[pdf]
[supp]
[bibtex]@InProceedings{Zhang_2024_CVPR, author = {Zhang, Ruida and Zhang, Chenyangguang and Di, Yan and Manhardt, Fabian and Liu, Xingyu and Tombari, Federico and Ji, Xiangyang}, title = {KP-RED: Exploiting Semantic Keypoints for Joint 3D Shape Retrieval and Deformation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {20540-20550} }
Learning from One Continuous Video Stream-
[pdf]
[arXiv]
[bibtex]@InProceedings{Carreira_2024_CVPR, author = {Carreira, Jo\~ao and King, Michael and Patraucean, Viorica and Gokay, Dilara and Ionescu, Catalin and Yang, Yi and Zoran, Daniel and Heyward, Joseph and Doersch, Carl and Aytar, Yusuf and Damen, Dima and Zisserman, Andrew}, title = {Learning from One Continuous Video Stream}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {28751-28761} }
VGGSfM: Visual Geometry Grounded Deep Structure From Motion-
[pdf]
[supp]
[bibtex]@InProceedings{Wang_2024_CVPR, author = {Wang, Jianyuan and Karaev, Nikita and Rupprecht, Christian and Novotny, David}, title = {VGGSfM: Visual Geometry Grounded Deep Structure From Motion}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {21686-21697} }
PixelLM: Pixel Reasoning with Large Multimodal Model-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Ren_2024_CVPR, author = {Ren, Zhongwei and Huang, Zhicheng and Wei, Yunchao and Zhao, Yao and Fu, Dongmei and Feng, Jiashi and Jin, Xiaojie}, title = {PixelLM: Pixel Reasoning with Large Multimodal Model}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {26374-26383} }
MRFS: Mutually Reinforcing Image Fusion and Segmentation-
[pdf]
[supp]
[bibtex]@InProceedings{Zhang_2024_CVPR, author = {Zhang, Hao and Zuo, Xuhui and Jiang, Jie and Guo, Chunchao and Ma, Jiayi}, title = {MRFS: Mutually Reinforcing Image Fusion and Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {26974-26983} }
Robust Depth Enhancement via Polarization Prompt Fusion Tuning-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Ikemura_2024_CVPR, author = {Ikemura, Kei and Huang, Yiming and Heide, Felix and Zhang, Zhaoxiang and Chen, Qifeng and Lei, Chenyang}, title = {Robust Depth Enhancement via Polarization Prompt Fusion Tuning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {20710-20720} }
Compact 3D Gaussian Representation for Radiance Field-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Lee_2024_CVPR, author = {Lee, Joo Chan and Rho, Daniel and Sun, Xiangyu and Ko, Jong Hwan and Park, Eunbyung}, title = {Compact 3D Gaussian Representation for Radiance Field}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {21719-21728} }
3D Building Reconstruction from Monocular Remote Sensing Images with Multi-level Supervisions-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Li_2024_CVPR, author = {Li, Weijia and Yang, Haote and Hu, Zhenghao and Zheng, Juepeng and Xia, Gui-Song and He, Conghui}, title = {3D Building Reconstruction from Monocular Remote Sensing Images with Multi-level Supervisions}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {27728-27737} }
Generative Latent Coding for Ultra-Low Bitrate Image Compression-
[pdf]
[supp]
[bibtex]@InProceedings{Jia_2024_CVPR, author = {Jia, Zhaoyang and Li, Jiahao and Li, Bin and Li, Houqiang and Lu, Yan}, title = {Generative Latent Coding for Ultra-Low Bitrate Image Compression}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {26088-26098} }
Distributionally Generative Augmentation for Fair Facial Attribute Classification-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Zhang_2024_CVPR, author = {Zhang, Fengda and He, Qianpei and Kuang, Kun and Liu, Jiashuo and Chen, Long and Wu, Chao and Xiao, Jun and Zhang, Hanwang}, title = {Distributionally Generative Augmentation for Fair Facial Attribute Classification}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {22797-22808} }
From SAM to CAMs: Exploring Segment Anything Model for Weakly Supervised Semantic Segmentation-
[pdf]
[supp]
[bibtex]@InProceedings{Kweon_2024_CVPR, author = {Kweon, Hyeokjun and Yoon, Kuk-Jin}, title = {From SAM to CAMs: Exploring Segment Anything Model for Weakly Supervised Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {19499-19509} }
Boosting Flow-based Generative Super-Resolution Models via Learned Prior-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Tsao_2024_CVPR, author = {Tsao, Li-Yuan and Lo, Yi-Chen and Chang, Chia-Che and Chen, Hao-Wei and Tseng, Roy and Feng, Chien and Lee, Chun-Yi}, title = {Boosting Flow-based Generative Super-Resolution Models via Learned Prior}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {26005-26015} }
What You See is What You GAN: Rendering Every Pixel for High-Fidelity Geometry in 3D GANs-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Trevithick_2024_CVPR, author = {Trevithick, Alex and Chan, Matthew and Takikawa, Towaki and Iqbal, Umar and De Mello, Shalini and Chandraker, Manmohan and Ramamoorthi, Ravi and Nagano, Koki}, title = {What You See is What You GAN: Rendering Every Pixel for High-Fidelity Geometry in 3D GANs}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {22765-22775} }
Towards Robust Learning to Optimize with Theoretical Guarantees-
[pdf]
[supp]
[bibtex]@InProceedings{Song_2024_CVPR, author = {Song, Qingyu and Lin, Wei and Wang, Juncheng and Xu, Hong}, title = {Towards Robust Learning to Optimize with Theoretical Guarantees}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {27498-27506} }
Differentiable Neural Surface Refinement for Modeling Transparent Objects-
[pdf]
[supp]
[bibtex]@InProceedings{Deng_2024_CVPR, author = {Deng, Weijian and Campbell, Dylan and Sun, Chunyi and Kanitkar, Shubham and Shaffer, Matthew E. and Gould, Stephen}, title = {Differentiable Neural Surface Refinement for Modeling Transparent Objects}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {20268-20277} }
Improving Generalization via Meta-Learning on Hard Samples-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Jain_2024_CVPR, author = {Jain, Nishant and Suggala, Arun S. and Shenoy, Pradeep}, title = {Improving Generalization via Meta-Learning on Hard Samples}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {27600-27609} }
Differentiable Information Bottleneck for Deterministic Multi-view Clustering-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Yan_2024_CVPR, author = {Yan, Xiaoqiang and Jin, Zhixiang and Han, Fengshou and Ye, Yangdong}, title = {Differentiable Information Bottleneck for Deterministic Multi-view Clustering}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {27435-27444} }
Animatable Gaussians: Learning Pose-dependent Gaussian Maps for High-fidelity Human Avatar Modeling-
[pdf]
[supp]
[bibtex]@InProceedings{Li_2024_CVPR, author = {Li, Zhe and Zheng, Zerong and Wang, Lizhen and Liu, Yebin}, title = {Animatable Gaussians: Learning Pose-dependent Gaussian Maps for High-fidelity Human Avatar Modeling}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {19711-19722} }
Latency Correction for Event-guided Deblurring and Frame Interpolation-
[pdf]
[supp]
[bibtex]@InProceedings{Yang_2024_CVPR, author = {Yang, Yixin and Liang, Jinxiu and Yu, Bohan and Chen, Yan and Ren, Jimmy S. and Shi, Boxin}, title = {Latency Correction for Event-guided Deblurring and Frame Interpolation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {24977-24986} }
WinSyn: : A High Resolution Testbed for Synthetic Data-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Kelly_2024_CVPR, author = {Kelly, Tom and Femiani, John and Wonka, Peter}, title = {WinSyn: : A High Resolution Testbed for Synthetic Data}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {22456-22465} }
Language-aware Visual Semantic Distillation for Video Question Answering-
[pdf]
[supp]
[bibtex]@InProceedings{Zou_2024_CVPR, author = {Zou, Bo and Yang, Chao and Qiao, Yu and Quan, Chengbin and Zhao, Youjian}, title = {Language-aware Visual Semantic Distillation for Video Question Answering}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {27113-27123} }
Disentangled Prompt Representation for Domain Generalization-
[pdf]
[bibtex]@InProceedings{Cheng_2024_CVPR, author = {Cheng, De and Xu, Zhipeng and Jiang, Xinyang and Wang, Nannan and Li, Dongsheng and Gao, Xinbo}, title = {Disentangled Prompt Representation for Domain Generalization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {23595-23604} }
Abductive Ego-View Accident Video Understanding for Safe Driving Perception-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Fang_2024_CVPR, author = {Fang, Jianwu and Li, Lei-lei and Zhou, Junfei and Xiao, Junbin and Yu, Hongkai and Lv, Chen and Xue, Jianru and Chua, Tat-Seng}, title = {Abductive Ego-View Accident Video Understanding for Safe Driving Perception}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {22030-22040} }
Cross-spectral Gated-RGB Stereo Depth Estimation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Brucker_2024_CVPR, author = {Brucker, Samuel and Walz, Stefanie and Bijelic, Mario and Heide, Felix}, title = {Cross-spectral Gated-RGB Stereo Depth Estimation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {21654-21665} }
KVQ: Kwai Video Quality Assessment for Short-form Videos-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Lu_2024_CVPR, author = {Lu, Yiting and Li, Xin and Pei, Yajing and Yuan, Kun and Xie, Qizhi and Qu, Yunpeng and Sun, Ming and Zhou, Chao and Chen, Zhibo}, title = {KVQ: Kwai Video Quality Assessment for Short-form Videos}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {25963-25973} }
Exploring the Transferability of Visual Prompting for Multimodal Large Language Models-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Zhang_2024_CVPR, author = {Zhang, Yichi and Dong, Yinpeng and Zhang, Siyuan and Min, Tianzan and Su, Hang and Zhu, Jun}, title = {Exploring the Transferability of Visual Prompting for Multimodal Large Language Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {26562-26572} }
SHAP-EDITOR: Instruction-Guided Latent 3D Editing in Seconds-
[pdf]
[supp]
[bibtex]@InProceedings{Chen_2024_CVPR, author = {Chen, Minghao and Xie, Junyu and Laina, Iro and Vedaldi, Andrea}, title = {SHAP-EDITOR: Instruction-Guided Latent 3D Editing in Seconds}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {26456-26466} }
HyperSDFusion: Bridging Hierarchical Structures in Language and Geometry for Enhanced 3D Text2Shape Generation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Leng_2024_CVPR, author = {Leng, Zhiying and Birdal, Tolga and Liang, Xiaohui and Tombari, Federico}, title = {HyperSDFusion: Bridging Hierarchical Structures in Language and Geometry for Enhanced 3D Text2Shape Generation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {19691-19700} }
Are Conventional SNNs Really Efficient? A Perspective from Network Quantization-
[pdf]
[supp]
[bibtex]@InProceedings{Shen_2024_CVPR, author = {Shen, Guobin and Zhao, Dongcheng and Li, Tenglong and Li, Jindong and Zeng, Yi}, title = {Are Conventional SNNs Really Efficient? A Perspective from Network Quantization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {27538-27547} }
Initialization Matters for Adversarial Transfer Learning-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Hua_2024_CVPR, author = {Hua, Andong and Gu, Jindong and Xue, Zhiyu and Carlini, Nicholas and Wong, Eric and Qin, Yao}, title = {Initialization Matters for Adversarial Transfer Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {24831-24840} }
L0-Sampler: An L0 Model Guided Volume Sampling for NeRF-
[pdf]
[supp]
[bibtex]@InProceedings{Li_2024_CVPR, author = {Li, Liangchen and Zhang, Juyong}, title = {L0-Sampler: An L0 Model Guided Volume Sampling for NeRF}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {21390-21400} }
Practical Measurements of Translucent Materials with Inter-Pixel Translucency Prior-
[pdf]
[supp]
[bibtex]@InProceedings{Chen_2024_CVPR, author = {Chen, Zhenyu and Guo, Jie and Lai, Shuichang and Fu, Ruoyu and Kong, Mengxun and Wang, Chen and Sun, Hongyu and Zhang, Zhebin and Li, Chen and Guo, Yanwen}, title = {Practical Measurements of Translucent Materials with Inter-Pixel Translucency Prior}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {20932-20942} }
TurboSL: Dense Accurate and Fast 3D by Neural Inverse Structured Light-
[pdf]
[supp]
[bibtex]@InProceedings{Mirdehghan_2024_CVPR, author = {Mirdehghan, Parsa and Wu, Maxx and Chen, Wenzheng and Lindell, David B. and Kutulakos, Kiriakos N.}, title = {TurboSL: Dense Accurate and Fast 3D by Neural Inverse Structured Light}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {25067-25076} }
GS-IR: 3D Gaussian Splatting for Inverse Rendering-
[pdf]
[supp]
[bibtex]@InProceedings{Liang_2024_CVPR, author = {Liang, Zhihao and Zhang, Qi and Feng, Ying and Shan, Ying and Jia, Kui}, title = {GS-IR: 3D Gaussian Splatting for Inverse Rendering}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {21644-21653} }
SynFog: A Photo-realistic Synthetic Fog Dataset based on End-to-end Imaging Simulation for Advancing Real-World Defogging in Autonomous Driving-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Xie_2024_CVPR, author = {Xie, Yiming and Wei, Henglu and Liu, Zhenyi and Wang, Xiaoyu and Ji, Xiangyang}, title = {SynFog: A Photo-realistic Synthetic Fog Dataset based on End-to-end Imaging Simulation for Advancing Real-World Defogging in Autonomous Driving}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {21763-21772} }
TRINS: Towards Multimodal Language Models that Can Read-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Zhang_2024_CVPR, author = {Zhang, Ruiyi and Zhang, Yanzhe and Chen, Jian and Zhou, Yufan and Gu, Jiuxiang and Chen, Changyou and Sun, Tong}, title = {TRINS: Towards Multimodal Language Models that Can Read}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {22584-22594} }
Self-Supervised Representation Learning from Arbitrary Scenarios-
[pdf]
[supp]
[bibtex]@InProceedings{Li_2024_CVPR, author = {Li, Zhaowen and Zhu, Yousong and Chen, Zhiyang and Gao, Zongxin and Zhao, Rui and Zhao, Chaoyang and Tang, Ming and Wang, Jinqiao}, title = {Self-Supervised Representation Learning from Arbitrary Scenarios}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {22967-22977} }
Living Scenes: Multi-object Relocalization and Reconstruction in Changing 3D Environments-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Zhu_2024_CVPR, author = {Zhu, Liyuan and Huang, Shengyu and Schindler, Konrad and Armeni, Iro}, title = {Living Scenes: Multi-object Relocalization and Reconstruction in Changing 3D Environments}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {28014-28024} }
Task-Adaptive Saliency Guidance for Exemplar-free Class Incremental Learning-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Liu_2024_CVPR, author = {Liu, Xialei and Zhai, Jiang-Tian and Bagdanov, Andrew D. and Li, Ke and Cheng, Ming-Ming}, title = {Task-Adaptive Saliency Guidance for Exemplar-free Class Incremental Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {23954-23963} }
Language-driven All-in-one Adverse Weather Removal-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Yang_2024_CVPR, author = {Yang, Hao and Pan, Liyuan and Yang, Yan and Liang, Wei}, title = {Language-driven All-in-one Adverse Weather Removal}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {24902-24912} }
MAPLM: A Real-World Large-Scale Vision-Language Benchmark for Map and Traffic Scene Understanding-
[pdf]
[bibtex]@InProceedings{Cao_2024_CVPR, author = {Cao, Xu and Zhou, Tong and Ma, Yunsheng and Ye, Wenqian and Cui, Can and Tang, Kun and Cao, Zhipeng and Liang, Kaizhao and Wang, Ziran and Rehg, James M. and Zheng, Chao}, title = {MAPLM: A Real-World Large-Scale Vision-Language Benchmark for Map and Traffic Scene Understanding}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {21819-21830} }
EgoExoLearn: A Dataset for Bridging Asynchronous Ego- and Exo-centric View of Procedural Activities in Real World-
[pdf]
[supp]
[bibtex]@InProceedings{Huang_2024_CVPR, author = {Huang, Yifei and Chen, Guo and Xu, Jilan and Zhang, Mingfang and Yang, Lijin and Pei, Baoqi and Zhang, Hongjie and Dong, Lu and Wang, Yali and Wang, Limin and Qiao, Yu}, title = {EgoExoLearn: A Dataset for Bridging Asynchronous Ego- and Exo-centric View of Procedural Activities in Real World}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {22072-22086} }
Improved Implicit Neural Representation with Fourier Reparameterized Training-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Shi_2024_CVPR, author = {Shi, Kexuan and Zhou, Xingyu and Gu, Shuhang}, title = {Improved Implicit Neural Representation with Fourier Reparameterized Training}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {25985-25994} }
Groupwise Query Specialization and Quality-Aware Multi-Assignment for Transformer-based Visual Relationship Detection-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Kim_2024_CVPR, author = {Kim, Jongha and Park, Jihwan and Park, Jinyoung and Kim, Jinyoung and Kim, Sehyung and Kim, Hyunwoo J.}, title = {Groupwise Query Specialization and Quality-Aware Multi-Assignment for Transformer-based Visual Relationship Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {28160-28169} }
Purified and Unified Steganographic Network-
[pdf]
[arXiv]
[bibtex]@InProceedings{Li_2024_CVPR, author = {Li, Guobiao and Li, Sheng and Luo, Zicong and Qian, Zhenxing and Zhang, Xinpeng}, title = {Purified and Unified Steganographic Network}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {27569-27578} }
TEA: Test-time Energy Adaptation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Yuan_2024_CVPR, author = {Yuan, Yige and Xu, Bingbing and Hou, Liang and Sun, Fei and Shen, Huawei and Cheng, Xueqi}, title = {TEA: Test-time Energy Adaptation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {23901-23911} }
NEAT: Distilling 3D Wireframes from Neural Attraction Fields-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Xue_2024_CVPR, author = {Xue, Nan and Tan, Bin and Xiao, Yuxi and Dong, Liang and Xia, Gui-Song and Wu, Tianfu and Shen, Yujun}, title = {NEAT: Distilling 3D Wireframes from Neural Attraction Fields}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {19968-19977} }
LDP: Language-driven Dual-Pixel Image Defocus Deblurring Network-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Yang_2024_CVPR, author = {Yang, Hao and Pan, Liyuan and Yang, Yan and Hartley, Richard and Liu, Miaomiao}, title = {LDP: Language-driven Dual-Pixel Image Defocus Deblurring Network}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {24078-24087} }
MMSum: A Dataset for Multimodal Summarization and Thumbnail Generation of Videos-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Qiu_2024_CVPR, author = {Qiu, Jielin and Zhu, Jiacheng and Han, William and Kumar, Aditesh and Mittal, Karthik and Jin, Claire and Yang, Zhengyuan and Li, Linjie and Wang, Jianfeng and Zhao, Ding and Li, Bo and Wang, Lijuan}, title = {MMSum: A Dataset for Multimodal Summarization and Thumbnail Generation of Videos}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {21909-21921} }
Pre-trained Vision and Language Transformers Are Few-Shot Incremental Learners-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Park_2024_CVPR, author = {Park, Keon-Hee and Song, Kyungwoo and Park, Gyeong-Moon}, title = {Pre-trained Vision and Language Transformers Are Few-Shot Incremental Learners}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {23881-23890} }
Language-guided Image Reflection Separation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Zhong_2024_CVPR, author = {Zhong, Haofeng and Hong, Yuchen and Weng, Shuchen and Liang, Jinxiu and Shi, Boxin}, title = {Language-guided Image Reflection Separation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {24913-24922} }
View-Category Interactive Sharing Transformer for Incomplete Multi-View Multi-Label Learning-
[pdf]
[supp]
[bibtex]@InProceedings{Ou_2024_CVPR, author = {Ou, Shilong and Xue, Zhe and Li, Yawen and Liang, Meiyu and Cai, Yuanqiang and Wu, Junjiang}, title = {View-Category Interactive Sharing Transformer for Incomplete Multi-View Multi-Label Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {27467-27476} }
The More You See in 2D the More You Perceive in 3D-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Han_2024_CVPR, author = {Han, Xinyang and Gao, Zelin and Kanazawa, Angjoo and Goel, Shubham and Gandelsman, Yossi}, title = {The More You See in 2D the More You Perceive in 3D}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {20912-20922} }
Unifying Automatic and Interactive Matting with Pretrained ViTs-
[pdf]
[supp]
[bibtex]@InProceedings{Ye_2024_CVPR, author = {Ye, Zixuan and Liu, Wenze and Guo, He and Liang, Yujia and Hong, Chaoyi and Lu, Hao and Cao, Zhiguo}, title = {Unifying Automatic and Interactive Matting with Pretrained ViTs}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {25585-25594} }
MoPE-CLIP: Structured Pruning for Efficient Vision-Language Models with Module-wise Pruning Error Metric-
[pdf]
[supp]
[bibtex]@InProceedings{Lin_2024_CVPR, author = {Lin, Haokun and Bai, Haoli and Liu, Zhili and Hou, Lu and Sun, Muyi and Song, Linqi and Wei, Ying and Sun, Zhenan}, title = {MoPE-CLIP: Structured Pruning for Efficient Vision-Language Models with Module-wise Pruning Error Metric}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {27370-27380} }
Leveraging Frame Affinity for sRGB-to-RAW Video De-rendering-
[pdf]
[bibtex]@InProceedings{Zhang_2024_CVPR, author = {Zhang, Chen and Han, Wencheng and Zhou, Yang and Shen, Jianbing and Xu, Cheng-zhong and Liu, Wentao}, title = {Leveraging Frame Affinity for sRGB-to-RAW Video De-rendering}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {25659-25668} }
The Mirrored Influence Hypothesis: Efficient Data Influence Estimation by Harnessing Forward Passes-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Ko_2024_CVPR, author = {Ko, Myeongseob and Kang, Feiyang and Shi, Weiyan and Jin, Ming and Yu, Zhou and Jia, Ruoxi}, title = {The Mirrored Influence Hypothesis: Efficient Data Influence Estimation by Harnessing Forward Passes}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {26286-26295} }
Choose What You Need: Disentangled Representation Learning for Scene Text Recognition Removal and Editing-
[pdf]
[arXiv]
[bibtex]@InProceedings{Zhang_2024_CVPR, author = {Zhang, Boqiang and Xie, Hongtao and Gao, Zuan and Wang, Yuxin}, title = {Choose What You Need: Disentangled Representation Learning for Scene Text Recognition Removal and Editing}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {28358-28368} }
Symphonize 3D Semantic Scene Completion with Contextual Instance Queries-
[pdf]
[arXiv]
[bibtex]@InProceedings{Jiang_2024_CVPR, author = {Jiang, Haoyi and Cheng, Tianheng and Gao, Naiyu and Zhang, Haoyang and Lin, Tianwei and Liu, Wenyu and Wang, Xinggang}, title = {Symphonize 3D Semantic Scene Completion with Contextual Instance Queries}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {20258-20267} }
Loopy-SLAM: Dense Neural SLAM with Loop Closures-
[pdf]
[bibtex]@InProceedings{Liso_2024_CVPR, author = {Liso, Lorenzo and Sandstr\"om, Erik and Yugay, Vladimir and Van Gool, Luc and Oswald, Martin R.}, title = {Loopy-SLAM: Dense Neural SLAM with Loop Closures}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {20363-20373} }
Content-Adaptive Non-Local Convolution for Remote Sensing Pansharpening-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Duan_2024_CVPR, author = {Duan, Yule and Wu, Xiao and Deng, Haoyu and Deng, Liang-Jian}, title = {Content-Adaptive Non-Local Convolution for Remote Sensing Pansharpening}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {27738-27747} }
Learning Inclusion Matching for Animation Paint Bucket Colorization-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Dai_2024_CVPR, author = {Dai, Yuekun and Zhou, Shangchen and Li, Qinyue and Li, Chongyi and Loy, Chen Change}, title = {Learning Inclusion Matching for Animation Paint Bucket Colorization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {25544-25553} }
SAM-6D: Segment Anything Model Meets Zero-Shot 6D Object Pose Estimation-
[pdf]
[supp]
[bibtex]@InProceedings{Lin_2024_CVPR, author = {Lin, Jiehong and Liu, Lihua and Lu, Dekun and Jia, Kui}, title = {SAM-6D: Segment Anything Model Meets Zero-Shot 6D Object Pose Estimation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {27906-27916} }
SPOT: Self-Training with Patch-Order Permutation for Object-Centric Learning with Autoregressive Transformers-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Kakogeorgiou_2024_CVPR, author = {Kakogeorgiou, Ioannis and Gidaris, Spyros and Karantzalos, Konstantinos and Komodakis, Nikos}, title = {SPOT: Self-Training with Patch-Order Permutation for Object-Centric Learning with Autoregressive Transformers}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {22776-22786} }
CroSel: Cross Selection of Confident Pseudo Labels for Partial-Label Learning-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Tian_2024_CVPR, author = {Tian, Shiyu and Wei, Hongxin and Wang, Yiqun and Feng, Lei}, title = {CroSel: Cross Selection of Confident Pseudo Labels for Partial-Label Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {19479-19488} }
ModaVerse: Efficiently Transforming Modalities with LLMs-
[pdf]
[arXiv]
[bibtex]@InProceedings{Wang_2024_CVPR, author = {Wang, Xinyu and Zhuang, Bohan and Wu, Qi}, title = {ModaVerse: Efficiently Transforming Modalities with LLMs}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {26606-26616} }
Frequency-aware Event-based Video Deblurring for Real-World Motion Blur-
[pdf]
[supp]
[bibtex]@InProceedings{Kim_2024_CVPR, author = {Kim, Taewoo and Cho, Hoonhee and Yoon, Kuk-Jin}, title = {Frequency-aware Event-based Video Deblurring for Real-World Motion Blur}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {24966-24976} }
Unsegment Anything by Simulating Deformation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Lu_2024_CVPR, author = {Lu, Jiahao and Yang, Xingyi and Wang, Xinchao}, title = {Unsegment Anything by Simulating Deformation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {24294-24304} }
Transductive Zero-Shot and Few-Shot CLIP-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Martin_2024_CVPR, author = {Martin, S\'egol\`ene and Huang, Yunshi and Shakeri, Fereshteh and Pesquet, Jean-Christophe and Ben Ayed, Ismail}, title = {Transductive Zero-Shot and Few-Shot CLIP}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {28816-28826} }
ID-Blau: Image Deblurring by Implicit Diffusion-based reBLurring AUgmentation-
[pdf]
[supp]
[bibtex]@InProceedings{Wu_2024_CVPR, author = {Wu, Jia-Hao and Tsai, Fu-Jen and Peng, Yan-Tsung and Tsai, Chung-Chi and Lin, Chia-Wen and Lin, Yen-Yu}, title = {ID-Blau: Image Deblurring by Implicit Diffusion-based reBLurring AUgmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {25847-25856} }
Decentralized Directed Collaboration for Personalized Federated Learning-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Liu_2024_CVPR, author = {Liu, Yingqi and Shi, Yifan and Li, Qinglun and Wu, Baoyuan and Wang, Xueqian and Shen, Li}, title = {Decentralized Directed Collaboration for Personalized Federated Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {23168-23178} }
GES : Generalized Exponential Splatting for Efficient Radiance Field Rendering-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Hamdi_2024_CVPR, author = {Hamdi, Abdullah and Melas-Kyriazi, Luke and Mai, Jinjie and Qian, Guocheng and Liu, Ruoshi and Vondrick, Carl and Ghanem, Bernard and Vedaldi, Andrea}, title = {GES : Generalized Exponential Splatting for Efficient Radiance Field Rendering}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {19812-19822} }
MMCert: Provable Defense against Adversarial Attacks to Multi-modal Models-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Wang_2024_CVPR, author = {Wang, Yanting and Fu, Hongye and Zou, Wei and Jia, Jinyuan}, title = {MMCert: Provable Defense against Adversarial Attacks to Multi-modal Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {24655-24664} }
NAYER: Noisy Layer Data Generation for Efficient and Effective Data-free Knowledge Distillation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Tran_2024_CVPR, author = {Tran, Minh-Tuan and Le, Trung and Le, Xuan-May and Harandi, Mehrtash and Tran, Quan Hung and Phung, Dinh}, title = {NAYER: Noisy Layer Data Generation for Efficient and Effective Data-free Knowledge Distillation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {23860-23869} }
OmniVec2 - A Novel Transformer based Network for Large Scale Multimodal and Multitask Learning-
[pdf]
[supp]
[bibtex]@InProceedings{Srivastava_2024_CVPR, author = {Srivastava, Siddharth and Sharma, Gaurav}, title = {OmniVec2 - A Novel Transformer based Network for Large Scale Multimodal and Multitask Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {27412-27424} }
Efficient Model Stealing Defense with Noise Transition Matrix-
[pdf]
[supp]
[bibtex]@InProceedings{Wu_2024_CVPR, author = {Wu, Dong-Dong and Fu, Chilin and Wu, Weichang and Xia, Wenwen and Zhang, Xiaolu and Zhou, Jun and Zhang, Min-Ling}, title = {Efficient Model Stealing Defense with Noise Transition Matrix}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {24305-24315} }
GS-SLAM: Dense Visual SLAM with 3D Gaussian Splatting-
[pdf]
[supp]
[bibtex]@InProceedings{Yan_2024_CVPR, author = {Yan, Chi and Qu, Delin and Xu, Dan and Zhao, Bin and Wang, Zhigang and Wang, Dong and Li, Xuelong}, title = {GS-SLAM: Dense Visual SLAM with 3D Gaussian Splatting}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {19595-19604} }
Scaffold-GS: Structured 3D Gaussians for View-Adaptive Rendering-
[pdf]
[supp]
[bibtex]@InProceedings{Lu_2024_CVPR, author = {Lu, Tao and Yu, Mulin and Xu, Linning and Xiangli, Yuanbo and Wang, Limin and Lin, Dahua and Dai, Bo}, title = {Scaffold-GS: Structured 3D Gaussians for View-Adaptive Rendering}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {20654-20664} }
Classes Are Not Equal: An Empirical Study on Image Recognition Fairness-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Cui_2024_CVPR, author = {Cui, Jiequan and Zhu, Beier and Wen, Xin and Qi, Xiaojuan and Yu, Bei and Zhang, Hanwang}, title = {Classes Are Not Equal: An Empirical Study on Image Recognition Fairness}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {23283-23292} }
Multi-Scale 3D Gaussian Splatting for Anti-Aliased Rendering-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Yan_2024_CVPR, author = {Yan, Zhiwen and Low, Weng Fei and Chen, Yu and Lee, Gim Hee}, title = {Multi-Scale 3D Gaussian Splatting for Anti-Aliased Rendering}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {20923-20931} }
A Bayesian Approach to OOD Robustness in Image Classification-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Kaushik_2024_CVPR, author = {Kaushik, Prakhar and Kortylewski, Adam and Yuille, Alan}, title = {A Bayesian Approach to OOD Robustness in Image Classification}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {22988-22997} }
Unified-IO 2: Scaling Autoregressive Multimodal Models with Vision Language Audio and Action-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Lu_2024_CVPR, author = {Lu, Jiasen and Clark, Christopher and Lee, Sangho and Zhang, Zichen and Khosla, Savya and Marten, Ryan and Hoiem, Derek and Kembhavi, Aniruddha}, title = {Unified-IO 2: Scaling Autoregressive Multimodal Models with Vision Language Audio and Action}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {26439-26455} }
Multi-Level Neural Scene Graphs for Dynamic Urban Environments-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Fischer_2024_CVPR, author = {Fischer, Tobias and Porzi, Lorenzo and Bulo, Samuel Rota and Pollefeys, Marc and Kontschieder, Peter}, title = {Multi-Level Neural Scene Graphs for Dynamic Urban Environments}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {21125-21135} }
Bayes' Rays: Uncertainty Quantification for Neural Radiance Fields-
[pdf]
[supp]
[bibtex]@InProceedings{Goli_2024_CVPR, author = {Goli, Lily and Reading, Cody and Sell\'an, Silvia and Jacobson, Alec and Tagliasacchi, Andrea}, title = {Bayes' Rays: Uncertainty Quantification for Neural Radiance Fields}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {20061-20070} }
Driving-Video Dehazing with Non-Aligned Regularization for Safety Assistance-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Fan_2024_CVPR, author = {Fan, Junkai and Weng, Jiangwei and Wang, Kun and Yang, Yijun and Qian, Jianjun and Li, Jun and Yang, Jian}, title = {Driving-Video Dehazing with Non-Aligned Regularization for Safety Assistance}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {26109-26119} }
Is Vanilla MLP in Neural Radiance Field Enough for Few-shot View Synthesis?-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Zhu_2024_CVPR, author = {Zhu, Hanxin and He, Tianyu and Li, Xin and Li, Bingchen and Chen, Zhibo}, title = {Is Vanilla MLP in Neural Radiance Field Enough for Few-shot View Synthesis?}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {20288-20298} }
CVT-xRF: Contrastive In-Voxel Transformer for 3D Consistent Radiance Fields from Sparse Inputs-
[pdf]
[bibtex]@InProceedings{Zhong_2024_CVPR, author = {Zhong, Yingji and Hong, Lanqing and Li, Zhenguo and Xu, Dan}, title = {CVT-xRF: Contrastive In-Voxel Transformer for 3D Consistent Radiance Fields from Sparse Inputs}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {21466-21475} }
Online Task-Free Continual Generative and Discriminative Learning via Dynamic Cluster Memory-
[pdf]
[supp]
[bibtex]@InProceedings{Ye_2024_CVPR, author = {Ye, Fei and Bors, Adrian G.}, title = {Online Task-Free Continual Generative and Discriminative Learning via Dynamic Cluster Memory}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {26202-26212} }
DSGG: Dense Relation Transformer for an End-to-end Scene Graph Generation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Hayder_2024_CVPR, author = {Hayder, Zeeshan and He, Xuming}, title = {DSGG: Dense Relation Transformer for an End-to-end Scene Graph Generation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {28317-28326} }
Object Dynamics Modeling with Hierarchical Point Cloud-based Representations-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Kim_2024_CVPR, author = {Kim, Chanho and Fuxin, Li}, title = {Object Dynamics Modeling with Hierarchical Point Cloud-based Representations}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {20977-20986} }
SkySense: A Multi-Modal Remote Sensing Foundation Model Towards Universal Interpretation for Earth Observation Imagery-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Guo_2024_CVPR, author = {Guo, Xin and Lao, Jiangwei and Dang, Bo and Zhang, Yingying and Yu, Lei and Ru, Lixiang and Zhong, Liheng and Huang, Ziyuan and Wu, Kang and Hu, Dingxiang and He, Huimei and Wang, Jian and Chen, Jingdong and Yang, Ming and Zhang, Yongjun and Li, Yansheng}, title = {SkySense: A Multi-Modal Remote Sensing Foundation Model Towards Universal Interpretation for Earth Observation Imagery}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {27672-27683} }
CFAT: Unleashing Triangular Windows for Image Super-resolution-
[pdf]
[supp]
[bibtex]@InProceedings{Ray_2024_CVPR, author = {Ray, Abhisek and Kumar, Gaurav and Kolekar, Maheshkumar H.}, title = {CFAT: Unleashing Triangular Windows for Image Super-resolution}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {26120-26129} }
Rolling Shutter Correction with Intermediate Distortion Flow Estimation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Cao_2024_CVPR, author = {Cao, Mingdeng and Yang, Sidi and Yang, Yujiu and Zheng, Yinqiang}, title = {Rolling Shutter Correction with Intermediate Distortion Flow Estimation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {25338-25347} }
Attack To Defend: Exploiting Adversarial Attacks for Detecting Poisoned Models-
[pdf]
[supp]
[bibtex]@InProceedings{Fares_2024_CVPR, author = {Fares, Samar and Nandakumar, Karthik}, title = {Attack To Defend: Exploiting Adversarial Attacks for Detecting Poisoned Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {24726-24735} }
Troika: Multi-Path Cross-Modal Traction for Compositional Zero-Shot Learning-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Huang_2024_CVPR, author = {Huang, Siteng and Gong, Biao and Feng, Yutong and Zhang, Min and Lv, Yiliang and Wang, Donglin}, title = {Troika: Multi-Path Cross-Modal Traction for Compositional Zero-Shot Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {24005-24014} }
Enhancing Multimodal Cooperation via Sample-level Modality Valuation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Wei_2024_CVPR, author = {Wei, Yake and Feng, Ruoxuan and Wang, Zihe and Hu, Di}, title = {Enhancing Multimodal Cooperation via Sample-level Modality Valuation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {27338-27347} }
SatSynth: Augmenting Image-Mask Pairs through Diffusion Models for Aerial Semantic Segmentation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Toker_2024_CVPR, author = {Toker, Aysim and Eisenberger, Marvin and Cremers, Daniel and Leal-Taix\'e, Laura}, title = {SatSynth: Augmenting Image-Mask Pairs through Diffusion Models for Aerial Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {27695-27705} }
XScale-NVS: Cross-Scale Novel View Synthesis with Hash Featurized Manifold-
[pdf]
[supp]
[bibtex]@InProceedings{Wang_2024_CVPR, author = {Wang, Guangyu and Zhang, Jinzhi and Wang, Fan and Huang, Ruqi and Fang, Lu}, title = {XScale-NVS: Cross-Scale Novel View Synthesis with Hash Featurized Manifold}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {21029-21039} }
Ink Dot-Oriented Differentiable Optimization for Neural Image Halftoning-
[pdf]
[supp]
[bibtex]@InProceedings{Jiang_2024_CVPR, author = {Jiang, Hao and Zhou, Bingfeng and Mu, Yadong}, title = {Ink Dot-Oriented Differentiable Optimization for Neural Image Halftoning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {27528-27537} }
Scalable 3D Registration via Truncated Entry-wise Absolute Residuals-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Huang_2024_CVPR, author = {Huang, Tianyu and Peng, Liangzu and Vidal, Rene and Liu, Yun-Hui}, title = {Scalable 3D Registration via Truncated Entry-wise Absolute Residuals}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {27477-27487} }
ExtraNeRF: Visibility-Aware View Extrapolation of Neural Radiance Fields with Diffusion Models-
[pdf]
[arXiv]
[bibtex]@InProceedings{Shih_2024_CVPR, author = {Shih, Meng-Li and Ma, Wei-Chiu and Boyice, Lorenzo and Holynski, Aleksander and Cole, Forrester and Curless, Brian and Kontkanen, Janne}, title = {ExtraNeRF: Visibility-Aware View Extrapolation of Neural Radiance Fields with Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {20385-20395} }
Equivariant Plug-and-Play Image Reconstruction-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Terris_2024_CVPR, author = {Terris, Matthieu and Moreau, Thomas and Pustelnik, Nelly and Tachella, Julian}, title = {Equivariant Plug-and-Play Image Reconstruction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {25255-25264} }
LP++: A Surprisingly Strong Linear Probe for Few-Shot CLIP-
[pdf]
[supp]
[bibtex]@InProceedings{Huang_2024_CVPR, author = {Huang, Yunshi and Shakeri, Fereshteh and Dolz, Jose and Boudiaf, Malik and Bahig, Houda and Ben Ayed, Ismail}, title = {LP++: A Surprisingly Strong Linear Probe for Few-Shot CLIP}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {23773-23782} }
FlowVQTalker: High-Quality Emotional Talking Face Generation through Normalizing Flow and Quantization-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Tan_2024_CVPR, author = {Tan, Shuai and Ji, Bin and Pan, Ye}, title = {FlowVQTalker: High-Quality Emotional Talking Face Generation through Normalizing Flow and Quantization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {26317-26327} }
Learning from Observer Gaze: Zero-Shot Attention Prediction Oriented by Human-Object Interaction Recognition-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Zhou_2024_CVPR, author = {Zhou, Yuchen and Liu, Linkai and Gou, Chao}, title = {Learning from Observer Gaze: Zero-Shot Attention Prediction Oriented by Human-Object Interaction Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {28390-28400} }
Lift3D: Zero-Shot Lifting of Any 2D Vision Model to 3D-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{T_2024_CVPR, author = {T, Mukund Varma and Wang, Peihao and Fan, Zhiwen and Wang, Zhangyang and Su, Hao and Ramamoorthi, Ravi}, title = {Lift3D: Zero-Shot Lifting of Any 2D Vision Model to 3D}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {21367-21377} }
Multiway Point Cloud Mosaicking with Diffusion and Global Optimization-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Jin_2024_CVPR, author = {Jin, Shengze and Armeni, Iro and Pollefeys, Marc and Barath, Daniel}, title = {Multiway Point Cloud Mosaicking with Diffusion and Global Optimization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {20838-20849} }
PBWR: Parametric-Building-Wireframe Reconstruction from Aerial LiDAR Point Clouds-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Huang_2024_CVPR, author = {Huang, Shangfeng and Wang, Ruisheng and Guo, Bo and Yang, Hongxin}, title = {PBWR: Parametric-Building-Wireframe Reconstruction from Aerial LiDAR Point Clouds}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {27778-27787} }
Spectrum AUC Difference (SAUCD): Human-aligned 3D Shape Evaluation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Luan_2024_CVPR, author = {Luan, Tianyu and Li, Zhong and Chen, Lele and Gong, Xuan and Chen, Lichang and Xu, Yi and Yuan, Junsong}, title = {Spectrum AUC Difference (SAUCD): Human-aligned 3D Shape Evaluation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {20155-20164} }
Multi-Session SLAM with Differentiable Wide-Baseline Pose Optimization-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Lipson_2024_CVPR, author = {Lipson, Lahav and Deng, Jia}, title = {Multi-Session SLAM with Differentiable Wide-Baseline Pose Optimization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {19626-19635} }
Improving Out-of-Distribution Generalization in Graphs via Hierarchical Semantic Environments-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Piao_2024_CVPR, author = {Piao, Yinhua and Lee, Sangseon and Lu, Yijingxiu and Kim, Sun}, title = {Improving Out-of-Distribution Generalization in Graphs via Hierarchical Semantic Environments}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {27631-27640} }
CN-RMA: Combined Network with Ray Marching Aggregation for 3D Indoor Object Detection from Multi-view Images-
[pdf]
[supp]
[bibtex]@InProceedings{Shen_2024_CVPR, author = {Shen, Guanlin and Huang, Jingwei and Hu, Zhihua and Wang, Bin}, title = {CN-RMA: Combined Network with Ray Marching Aggregation for 3D Indoor Object Detection from Multi-view Images}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {21326-21335} }
Hide in Thicket: Generating Imperceptible and Rational Adversarial Perturbations on 3D Point Clouds-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Lou_2024_CVPR, author = {Lou, Tianrui and Jia, Xiaojun and Gu, Jindong and Liu, Li and Liang, Siyuan and He, Bangyan and Cao, Xiaochun}, title = {Hide in Thicket: Generating Imperceptible and Rational Adversarial Perturbations on 3D Point Clouds}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {24326-24335} }
SG-BEV: Satellite-Guided BEV Fusion for Cross-View Semantic Segmentation-
[pdf]
[supp]
[bibtex]@InProceedings{Ye_2024_CVPR, author = {Ye, Junyan and Luo, Qiyan and Yu, Jinhua and Zhong, Huaping and Zheng, Zhimeng and He, Conghui and Li, Weijia}, title = {SG-BEV: Satellite-Guided BEV Fusion for Cross-View Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {27748-27757} }
LEAP-VO: Long-term Effective Any Point Tracking for Visual Odometry-
[pdf]
[supp]
[bibtex]@InProceedings{Chen_2024_CVPR, author = {Chen, Weirong and Chen, Le and Wang, Rui and Pollefeys, Marc}, title = {LEAP-VO: Long-term Effective Any Point Tracking for Visual Odometry}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {19844-19853} }
Unveiling the Unknown: Unleashing the Power of Unknown to Known in Open-Set Source-Free Domain Adaptation-
[pdf]
[supp]
[bibtex]@InProceedings{Wan_2024_CVPR, author = {Wan, Fuli and Zhao, Han and Yang, Xu and Deng, Cheng}, title = {Unveiling the Unknown: Unleashing the Power of Unknown to Known in Open-Set Source-Free Domain Adaptation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {24015-24024} }
Instance-Adaptive and Geometric-Aware Keypoint Learning for Category-Level 6D Object Pose Estimation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Lin_2024_CVPR, author = {Lin, Xiao and Yang, Wenfei and Gao, Yuan and Zhang, Tianzhu}, title = {Instance-Adaptive and Geometric-Aware Keypoint Learning for Category-Level 6D Object Pose Estimation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {21040-21049} }
Universal Semi-Supervised Domain Adaptation by Mitigating Common-Class Bias-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Zhang_2024_CVPR, author = {Zhang, Wenyu and Liu, Qingmu and Cong, Felix Ong Wei and Ragab, Mohamed and Foo, Chuan-Sheng}, title = {Universal Semi-Supervised Domain Adaptation by Mitigating Common-Class Bias}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {23912-23921} }
Feature 3DGS: Supercharging 3D Gaussian Splatting to Enable Distilled Feature Fields-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Zhou_2024_CVPR, author = {Zhou, Shijie and Chang, Haoran and Jiang, Sicheng and Fan, Zhiwen and Zhu, Zehao and Xu, Dejia and Chari, Pradyumna and You, Suya and Wang, Zhangyang and Kadambi, Achuta}, title = {Feature 3DGS: Supercharging 3D Gaussian Splatting to Enable Distilled Feature Fields}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {21676-21685} }
4K4D: Real-Time 4D View Synthesis at 4K Resolution-
[pdf]
[arXiv]
[bibtex]@InProceedings{Xu_2024_CVPR, author = {Xu, Zhen and Peng, Sida and Lin, Haotong and He, Guangzhao and Sun, Jiaming and Shen, Yujun and Bao, Hujun and Zhou, Xiaowei}, title = {4K4D: Real-Time 4D View Synthesis at 4K Resolution}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {20029-20040} }
View-decoupled Transformer for Person Re-identification under Aerial-ground Camera Network-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Zhang_2024_CVPR, author = {Zhang, Quan and Wang, Lei and Patel, Vishal M. and Xie, Xiaohua and Lai, Jianhaung}, title = {View-decoupled Transformer for Person Re-identification under Aerial-ground Camera Network}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {22000-22009} }
OED: Towards One-stage End-to-End Dynamic Scene Graph Generation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Wang_2024_CVPR, author = {Wang, Guan and Li, Zhimin and Chen, Qingchao and Liu, Yang}, title = {OED: Towards One-stage End-to-End Dynamic Scene Graph Generation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {27938-27947} }
DeIL: Direct-and-Inverse CLIP for Open-World Few-Shot Learning-
[pdf]
[supp]
[bibtex]@InProceedings{Shao_2024_CVPR, author = {Shao, Shuai and Bai, Yu and Wang, Yan and Liu, Baodi and Zhou, Yicong}, title = {DeIL: Direct-and-Inverse CLIP for Open-World Few-Shot Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {28505-28514} }
Large Language Models are Good Prompt Learners for Low-Shot Image Classification-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Zheng_2024_CVPR, author = {Zheng, Zhaoheng and Wei, Jingmin and Hu, Xuefeng and Zhu, Haidong and Nevatia, Ram}, title = {Large Language Models are Good Prompt Learners for Low-Shot Image Classification}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {28453-28462} }
VILA: On Pre-training for Visual Language Models-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Lin_2024_CVPR, author = {Lin, Ji and Yin, Hongxu and Ping, Wei and Molchanov, Pavlo and Shoeybi, Mohammad and Han, Song}, title = {VILA: On Pre-training for Visual Language Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {26689-26699} }
Text-Guided Variational Image Generation for Industrial Anomaly Detection and Segmentation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Lee_2024_CVPR, author = {Lee, Mingyu and Choi, Jongwon}, title = {Text-Guided Variational Image Generation for Industrial Anomaly Detection and Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {26519-26528} }
Self-Adaptive Reality-Guided Diffusion for Artifact-Free Super-Resolution-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Zheng_2024_CVPR, author = {Zheng, Qingping and Zheng, Ling and Guo, Yuanfan and Li, Ying and Xu, Songcen and Deng, Jiankang and Xu, Hang}, title = {Self-Adaptive Reality-Guided Diffusion for Artifact-Free Super-Resolution}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {25806-25816} }
Multimodal Representation Learning by Alternating Unimodal Adaptation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Zhang_2024_CVPR, author = {Zhang, Xiaohui and Yoon, Jaehong and Bansal, Mohit and Yao, Huaxiu}, title = {Multimodal Representation Learning by Alternating Unimodal Adaptation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {27456-27466} }
Pre-training Vision Models with Mandelbulb Variations-
[pdf]
[supp]
[bibtex]@InProceedings{Chiche_2024_CVPR, author = {Chiche, Benjamin Naoto and Horikawa, Yuto and Fujita, Ryo}, title = {Pre-training Vision Models with Mandelbulb Variations}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {22062-22071} }
S2MVTC: a Simple yet Efficient Scalable Multi-View Tensor Clustering-
[pdf]
[bibtex]@InProceedings{Long_2024_CVPR, author = {Long, Zhen and Wang, Qiyuan and Ren, Yazhou and Liu, Yipeng and Zhu, Ce}, title = {S2MVTC: a Simple yet Efficient Scalable Multi-View Tensor Clustering}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {26213-26222} }
S2MAE: A Spatial-Spectral Pretraining Foundation Model for Spectral Remote Sensing Data-
[pdf]
[bibtex]@InProceedings{Li_2024_CVPR, author = {Li, Xuyang and Hong, Danfeng and Chanussot, Jocelyn}, title = {S2MAE: A Spatial-Spectral Pretraining Foundation Model for Spectral Remote Sensing Data}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {24088-24097} }
DIMAT: Decentralized Iterative Merging-And-Training for Deep Learning Models-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Saadati_2024_CVPR, author = {Saadati, Nastaran and Pham, Minh and Saleem, Nasla and Waite, Joshua R. and Balu, Aditya and Jiang, Zhanong and Hegde, Chinmay and Sarkar, Soumik}, title = {DIMAT: Decentralized Iterative Merging-And-Training for Deep Learning Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {27517-27527} }
MMA: Multi-Modal Adapter for Vision-Language Models-
[pdf]
[bibtex]@InProceedings{Yang_2024_CVPR, author = {Yang, Lingxiao and Zhang, Ru-Yuan and Wang, Yanchen and Xie, Xiaohua}, title = {MMA: Multi-Modal Adapter for Vision-Language Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {23826-23837} }
BioCLIP: A Vision Foundation Model for the Tree of Life-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Stevens_2024_CVPR, author = {Stevens, Samuel and Wu, Jiaman and Thompson, Matthew J and Campolongo, Elizabeth G and Song, Chan Hee and Carlyn, David Edward and Dong, Li and Dahdul, Wasila M and Stewart, Charles and Berger-Wolf, Tanya and Chao, Wei-Lun and Su, Yu}, title = {BioCLIP: A Vision Foundation Model for the Tree of Life}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {19412-19424} }
From Pixels to Graphs: Open-Vocabulary Scene Graph Generation with Vision-Language Models-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Li_2024_CVPR, author = {Li, Rongjie and Zhang, Songyang and Lin, Dahua and Chen, Kai and He, Xuming}, title = {From Pixels to Graphs: Open-Vocabulary Scene Graph Generation with Vision-Language Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {28076-28086} }
Deep Imbalanced Regression via Hierarchical Classification Adjustment-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Xiong_2024_CVPR, author = {Xiong, Haipeng and Yao, Angela}, title = {Deep Imbalanced Regression via Hierarchical Classification Adjustment}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {23721-23730} }
Total-Decom: Decomposed 3D Scene Reconstruction with Minimal Interaction-
[pdf]
[supp]
[bibtex]@InProceedings{Lyu_2024_CVPR, author = {Lyu, Xiaoyang and Chang, Chirui and Dai, Peng and Sun, Yang-Tian and Qi, Xiaojuan}, title = {Total-Decom: Decomposed 3D Scene Reconstruction with Minimal Interaction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {20860-20869} }
Accelerating Neural Field Training via Soft Mining-
[pdf]
[arXiv]
[bibtex]@InProceedings{Kheradmand_2024_CVPR, author = {Kheradmand, Shakiba and Rebain, Daniel and Sharma, Gopal and Isack, Hossam and Kar, Abhishek and Tagliasacchi, Andrea and Yi, Kwang Moo}, title = {Accelerating Neural Field Training via Soft Mining}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {20071-20080} }
Ensemble Diversity Facilitates Adversarial Transferability-
[pdf]
[bibtex]@InProceedings{Tang_2024_CVPR, author = {Tang, Bowen and Wang, Zheng and Bin, Yi and Dou, Qi and Yang, Yang and Shen, Heng Tao}, title = {Ensemble Diversity Facilitates Adversarial Transferability}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {24377-24386} }
Gear-NeRF: Free-Viewpoint Rendering and Tracking with Motion-aware Spatio-Temporal Sampling-
[pdf]
[supp]
[bibtex]@InProceedings{Liu_2024_CVPR, author = {Liu, Xinhang and Tai, Yu-Wing and Tang, Chi-Keung and Miraldo, Pedro and Lohit, Suhas and Chatterjee, Moitreya}, title = {Gear-NeRF: Free-Viewpoint Rendering and Tracking with Motion-aware Spatio-Temporal Sampling}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {19667-19679} }
BrainWash: A Poisoning Attack to Forget in Continual Learning-
[pdf]
[arXiv]
[bibtex]@InProceedings{Abbasi_2024_CVPR, author = {Abbasi, Ali and Nooralinejad, Parsa and Pirsiavash, Hamed and Kolouri, Soheil}, title = {BrainWash: A Poisoning Attack to Forget in Continual Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {24057-24067} }
FreePoint: Unsupervised Point Cloud Instance Segmentation-
[pdf]
[arXiv]
[bibtex]@InProceedings{Zhang_2024_CVPR, author = {Zhang, Zhikai and Ding, Jian and Jiang, Li and Dai, Dengxin and Xia, Guisong}, title = {FreePoint: Unsupervised Point Cloud Instance Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {28254-28263} }
Circuit Design and Efficient Simulation of Quantum Inner Product and Empirical Studies of Its Effect on Near-Term Hybrid Quantum-Classic Machine Learning-
[pdf]
[supp]
[bibtex]@InProceedings{Xiong_2024_CVPR, author = {Xiong, Hao and Tang, Yehui and Ye, Xinyu and Yan, Junchi}, title = {Circuit Design and Efficient Simulation of Quantum Inner Product and Empirical Studies of Its Effect on Near-Term Hybrid Quantum-Classic Machine Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {26162-26170} }
How to Make Cross Encoder a Good Teacher for Efficient Image-Text Retrieval?-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Chen_2024_CVPR, author = {Chen, Yuxin and Ma, Zongyang and Zhang, Ziqi and Qi, Zhongang and Yuan, Chunfeng and Li, Bing and Pu, Junfu and Shan, Ying and Qi, Xiaojuan and Hu, Weiming}, title = {How to Make Cross Encoder a Good Teacher for Efficient Image-Text Retrieval?}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {26994-27003} }
Diffeomorphic Template Registration for Atmospheric Turbulence Mitigation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Lao_2024_CVPR, author = {Lao, Dong and Wang, Congli and Wong, Alex and Soatto, Stefano}, title = {Diffeomorphic Template Registration for Atmospheric Turbulence Mitigation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {25107-25116} }
Selective Nonlinearities Removal from Digital Signals-
[pdf]
[bibtex]@InProceedings{Maliszewski_2024_CVPR, author = {Maliszewski, Krzysztof A. and Urba?ska, Magdalena A. and Vetrova, Varvara and Kolenderska, Sylwia M.}, title = {Selective Nonlinearities Removal from Digital Signals}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {25028-25036} }
NB-GTR: Narrow-Band Guided Turbulence Removal-
[pdf]
[supp]
[bibtex]@InProceedings{Xia_2024_CVPR, author = {Xia, Yifei and Zhou, Chu and Zhu, Chengxuan and Teng, Minggui and Xu, Chao and Shi, Boxin}, title = {NB-GTR: Narrow-Band Guided Turbulence Removal}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {24934-24943} }
Can Biases in ImageNet Models Explain Generalization?-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Gavrikov_2024_CVPR, author = {Gavrikov, Paul and Keuper, Janis}, title = {Can Biases in ImageNet Models Explain Generalization?}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {22184-22194} }
Generative Quanta Color Imaging-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Purohit_2024_CVPR, author = {Purohit, Vishal and Luo, Junjie and Chi, Yiheng and Guo, Qi and Chan, Stanley H. and Qiu, Qiang}, title = {Generative Quanta Color Imaging}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {25138-25148} }
Overload: Latency Attacks on Object Detection for Edge Devices-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Chen_2024_CVPR, author = {Chen, Erh-Chung and Chen, Pin-Yu and Chung, I-Hsin and Lee, Che-Rung}, title = {Overload: Latency Attacks on Object Detection for Edge Devices}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {24716-24725} }
SD4Match: Learning to Prompt Stable Diffusion Model for Semantic Matching-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Li_2024_CVPR, author = {Li, Xinghui and Lu, Jingyi and Han, Kai and Prisacariu, Victor Adrian}, title = {SD4Match: Learning to Prompt Stable Diffusion Model for Semantic Matching}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {27558-27568} }
Neural Video Compression with Feature Modulation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Li_2024_CVPR, author = {Li, Jiahao and Li, Bin and Lu, Yan}, title = {Neural Video Compression with Feature Modulation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {26099-26108} }
Data Poisoning based Backdoor Attacks to Contrastive Learning-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Zhang_2024_CVPR, author = {Zhang, Jinghuai and Liu, Hongbin and Jia, Jinyuan and Gong, Neil Zhenqiang}, title = {Data Poisoning based Backdoor Attacks to Contrastive Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {24357-24366} }
Progressive Semantic-Guided Vision Transformer for Zero-Shot Learning-
[pdf]
[arXiv]
[bibtex]@InProceedings{Chen_2024_CVPR, author = {Chen, Shiming and Hou, Wenjin and Khan, Salman and Khan, Fahad Shahbaz}, title = {Progressive Semantic-Guided Vision Transformer for Zero-Shot Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {23964-23974} }
Building Bridges across Spatial and Temporal Resolutions: Reference-Based Super-Resolution via Change Priors and Conditional Diffusion Model-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Dong_2024_CVPR, author = {Dong, Runmin and Yuan, Shuai and Luo, Bin and Chen, Mengxuan and Zhang, Jinxiao and Zhang, Lixian and Li, Weijia and Zheng, Juepeng and Fu, Haohuan}, title = {Building Bridges across Spatial and Temporal Resolutions: Reference-Based Super-Resolution via Change Priors and Conditional Diffusion Model}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {27684-27694} }
Back