Papers
- Back
Deep Frequency Filtering for Domain Generalization-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Lin_2023_CVPR, author = {Lin, Shiqi and Zhang, Zhizheng and Huang, Zhipeng and Lu, Yan and Lan, Cuiling and Chu, Peng and You, Quanzeng and Wang, Jiang and Liu, Zicheng and Parulkar, Amey and Navkal, Viraj and Chen, Zhibo}, title = {Deep Frequency Filtering for Domain Generalization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11797-11807} }
Frame Flexible Network-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Zhang_2023_CVPR, author = {Zhang, Yitian and Bai, Yue and Liu, Chang and Wang, Huan and Li, Sheng and Fu, Yun}, title = {Frame Flexible Network}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10504-10513} }
Unsupervised Cumulative Domain Adaptation for Foggy Scene Optical Flow-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Zhou_2023_CVPR, author = {Zhou, Hanyu and Chang, Yi and Yan, Wending and Yan, Luxin}, title = {Unsupervised Cumulative Domain Adaptation for Foggy Scene Optical Flow}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9569-9578} }
MarS3D: A Plug-and-Play Motion-Aware Model for Semantic Segmentation on Multi-Scan 3D Point Clouds-
[pdf]
[supp]
[bibtex]@InProceedings{Liu_2023_CVPR, author = {Liu, Jiahui and Chang, Chirui and Liu, Jianhui and Wu, Xiaoyang and Ma, Lan and Qi, Xiaojuan}, title = {MarS3D: A Plug-and-Play Motion-Aware Model for Semantic Segmentation on Multi-Scan 3D Point Clouds}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9372-9381} }
An Image Quality Assessment Dataset for Portraits-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Chahine_2023_CVPR, author = {Chahine, Nicolas and Calarasanu, Stefania and Garcia-Civiero, Davide and Cayla, Th\'eo and Ferradans, Sira and Ponce, Jean}, title = {An Image Quality Assessment Dataset for Portraits}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9968-9978} }
Painting 3D Nature in 2D: View Synthesis of Natural Scenes From a Single Semantic Mask-
[pdf]
[arXiv]
[bibtex]@InProceedings{Zhang_2023_CVPR, author = {Zhang, Shangzhan and Peng, Sida and Chen, Tianrun and Mou, Linzhan and Lin, Haotong and Yu, Kaicheng and Liao, Yiyi and Zhou, Xiaowei}, title = {Painting 3D Nature in 2D: View Synthesis of Natural Scenes From a Single Semantic Mask}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8518-8528} }
Fast Point Cloud Generation With Straight Flows-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Wu_2023_CVPR, author = {Wu, Lemeng and Wang, Dilin and Gong, Chengyue and Liu, Xingchao and Xiong, Yunyang and Ranjan, Rakesh and Krishnamoorthi, Raghuraman and Chandra, Vikas and Liu, Qiang}, title = {Fast Point Cloud Generation With Straight Flows}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9445-9454} }
Achieving a Better Stability-Plasticity Trade-Off via Auxiliary Networks in Continual Learning-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Kim_2023_CVPR, author = {Kim, Sanghwan and Noci, Lorenzo and Orvieto, Antonio and Hofmann, Thomas}, title = {Achieving a Better Stability-Plasticity Trade-Off via Auxiliary Networks in Continual Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11930-11939} }
Video Event Restoration Based on Keyframes for Video Anomaly Detection-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Yang_2023_CVPR, author = {Yang, Zhiwei and Liu, Jing and Wu, Zhaoyang and Wu, Peng and Liu, Xiaotao}, title = {Video Event Restoration Based on Keyframes for Video Anomaly Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14592-14601} }
EcoTTA: Memory-Efficient Continual Test-Time Adaptation via Self-Distilled Regularization-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Song_2023_CVPR, author = {Song, Junha and Lee, Jungsoo and Kweon, In So and Choi, Sungha}, title = {EcoTTA: Memory-Efficient Continual Test-Time Adaptation via Self-Distilled Regularization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11920-11929} }
Tri-Perspective View for Vision-Based 3D Semantic Occupancy Prediction-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Huang_2023_CVPR, author = {Huang, Yuanhui and Zheng, Wenzhao and Zhang, Yunpeng and Zhou, Jie and Lu, Jiwen}, title = {Tri-Perspective View for Vision-Based 3D Semantic Occupancy Prediction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9223-9232} }
Castling-ViT: Compressing Self-Attention via Switching Towards Linear-Angular Attention at Vision Transformer Inference-
[pdf]
[supp]
[bibtex]@InProceedings{You_2023_CVPR, author = {You, Haoran and Xiong, Yunyang and Dai, Xiaoliang and Wu, Bichen and Zhang, Peizhao and Fan, Haoqi and Vajda, Peter and Lin, Yingyan (Celine)}, title = {Castling-ViT: Compressing Self-Attention via Switching Towards Linear-Angular Attention at Vision Transformer Inference}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14431-14442} }
Rethinking Federated Learning With Domain Shift: A Prototype View-
[pdf]
[bibtex]@InProceedings{Huang_2023_CVPR, author = {Huang, Wenke and Ye, Mang and Shi, Zekun and Li, He and Du, Bo}, title = {Rethinking Federated Learning With Domain Shift: A Prototype View}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16312-16322} }
HGFormer: Hierarchical Grouping Transformer for Domain Generalized Semantic Segmentation-
[pdf]
[bibtex]@InProceedings{Ding_2023_CVPR, author = {Ding, Jian and Xue, Nan and Xia, Gui-Song and Schiele, Bernt and Dai, Dengxin}, title = {HGFormer: Hierarchical Grouping Transformer for Domain Generalized Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15413-15423} }
Distilling Vision-Language Pre-Training To Collaborate With Weakly-Supervised Temporal Action Localization-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Ju_2023_CVPR, author = {Ju, Chen and Zheng, Kunhao and Liu, Jinxiang and Zhao, Peisen and Zhang, Ya and Chang, Jianlong and Tian, Qi and Wang, Yanfeng}, title = {Distilling Vision-Language Pre-Training To Collaborate With Weakly-Supervised Temporal Action Localization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14751-14762} }
Augmentation Matters: A Simple-Yet-Effective Approach to Semi-Supervised Semantic Segmentation-
[pdf]
[arXiv]
[bibtex]@InProceedings{Zhao_2023_CVPR, author = {Zhao, Zhen and Yang, Lihe and Long, Sifan and Pi, Jimin and Zhou, Luping and Wang, Jingdong}, title = {Augmentation Matters: A Simple-Yet-Effective Approach to Semi-Supervised Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11350-11359} }
Boosting Verified Training for Robust Image Classifications via Abstraction-
[pdf]
[arXiv]
[bibtex]@InProceedings{Zhang_2023_CVPR, author = {Zhang, Zhaodi and Xue, Zhiyi and Chen, Yang and Liu, Si and Zhang, Yueling and Liu, Jing and Zhang, Min}, title = {Boosting Verified Training for Robust Image Classifications via Abstraction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16251-16260} }
3D Shape Reconstruction of Semi-Transparent Worms-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Ilett_2023_CVPR, author = {Ilett, Thomas P. and Yuval, Omer and Ranner, Thomas and Cohen, Netta and Hogg, David C.}, title = {3D Shape Reconstruction of Semi-Transparent Worms}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12565-12575} }
Mapping Degeneration Meets Label Evolution: Learning Infrared Small Target Detection With Single Point Supervision-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Ying_2023_CVPR, author = {Ying, Xinyi and Liu, Li and Wang, Yingqian and Li, Ruojing and Chen, Nuo and Lin, Zaiping and Sheng, Weidong and Zhou, Shilin}, title = {Mapping Degeneration Meets Label Evolution: Learning Infrared Small Target Detection With Single Point Supervision}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15528-15538} }
Swept-Angle Synthetic Wavelength Interferometry-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Kotwal_2023_CVPR, author = {Kotwal, Alankar and Levin, Anat and Gkioulekas, Ioannis}, title = {Swept-Angle Synthetic Wavelength Interferometry}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8233-8243} }
Adaptive Global Decay Process for Event Cameras-
[pdf]
[supp]
[bibtex]@InProceedings{Nunes_2023_CVPR, author = {Nunes, Urbano Miguel and Benosman, Ryad and Ieng, Sio-Hoi}, title = {Adaptive Global Decay Process for Event Cameras}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9771-9780} }
Multi-Space Neural Radiance Fields-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Yin_2023_CVPR, author = {Yin, Ze-Xin and Qiu, Jiaxiong and Cheng, Ming-Ming and Ren, Bo}, title = {Multi-Space Neural Radiance Fields}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12407-12416} }
Bitstream-Corrupted JPEG Images Are Restorable: Two-Stage Compensation and Alignment Framework for Image Restoration-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Liu_2023_CVPR, author = {Liu, Wenyang and Wang, Yi and Yap, Kim-Hui and Chau, Lap-Pui}, title = {Bitstream-Corrupted JPEG Images Are Restorable: Two-Stage Compensation and Alignment Framework for Image Restoration}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9979-9988} }
Histopathology Whole Slide Image Analysis With Heterogeneous Graph Representation Learning-
[pdf]
[supp]
[bibtex]@InProceedings{Chan_2023_CVPR, author = {Chan, Tsai Hor and Cendra, Fernando Julio and Ma, Lan and Yin, Guosheng and Yu, Lequan}, title = {Histopathology Whole Slide Image Analysis With Heterogeneous Graph Representation Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15661-15670} }
Towards All-in-One Pre-Training via Maximizing Multi-Modal Mutual Information-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Su_2023_CVPR, author = {Su, Weijie and Zhu, Xizhou and Tao, Chenxin and Lu, Lewei and Li, Bin and Huang, Gao and Qiao, Yu and Wang, Xiaogang and Zhou, Jie and Dai, Jifeng}, title = {Towards All-in-One Pre-Training via Maximizing Multi-Modal Mutual Information}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15888-15899} }
Aligning Bag of Regions for Open-Vocabulary Object Detection-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Wu_2023_CVPR, author = {Wu, Size and Zhang, Wenwei and Jin, Sheng and Liu, Wentao and Loy, Chen Change}, title = {Aligning Bag of Regions for Open-Vocabulary Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15254-15264} }
Two-View Geometry Scoring Without Correspondences-
[pdf]
[supp]
[bibtex]@InProceedings{Barroso-Laguna_2023_CVPR, author = {Barroso-Laguna, Axel and Brachmann, Eric and Prisacariu, Victor Adrian and Brostow, Gabriel J. and Turmukhambetov, Daniyar}, title = {Two-View Geometry Scoring Without Correspondences}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8979-8989} }
Annealing-Based Label-Transfer Learning for Open World Object Detection-
[pdf]
[supp]
[bibtex]@InProceedings{Ma_2023_CVPR, author = {Ma, Yuqing and Li, Hainan and Zhang, Zhange and Guo, Jinyang and Zhang, Shanghang and Gong, Ruihao and Liu, Xianglong}, title = {Annealing-Based Label-Transfer Learning for Open World Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11454-11463} }
Self-Supervised Video Forensics by Audio-Visual Anomaly Detection-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Feng_2023_CVPR, author = {Feng, Chao and Chen, Ziyang and Owens, Andrew}, title = {Self-Supervised Video Forensics by Audio-Visual Anomaly Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10491-10503} }
Class Balanced Adaptive Pseudo Labeling for Federated Semi-Supervised Learning-
[pdf]
[supp]
[bibtex]@InProceedings{Li_2023_CVPR, author = {Li, Ming and Li, Qingli and Wang, Yan}, title = {Class Balanced Adaptive Pseudo Labeling for Federated Semi-Supervised Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16292-16301} }
Rethinking Out-of-Distribution (OOD) Detection: Masked Image Modeling Is All You Need-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Li_2023_CVPR, author = {Li, Jingyao and Chen, Pengguang and He, Zexin and Yu, Shaozuo and Liu, Shu and Jia, Jiaya}, title = {Rethinking Out-of-Distribution (OOD) Detection: Masked Image Modeling Is All You Need}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11578-11589} }
Masked Scene Contrast: A Scalable Framework for Unsupervised 3D Representation Learning-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Wu_2023_CVPR, author = {Wu, Xiaoyang and Wen, Xin and Liu, Xihui and Zhao, Hengshuang}, title = {Masked Scene Contrast: A Scalable Framework for Unsupervised 3D Representation Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9415-9424} }
Multi Domain Learning for Motion Magnification-
[pdf]
[supp]
[bibtex]@InProceedings{Singh_2023_CVPR, author = {Singh, Jasdeep and Murala, Subrahmanyam and Kosuru, G. Sankara Raju}, title = {Multi Domain Learning for Motion Magnification}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13914-13923} }
A Simple Baseline for Video Restoration With Grouped Spatial-Temporal Shift-
[pdf]
[supp]
[bibtex]@InProceedings{Li_2023_CVPR, author = {Li, Dasong and Shi, Xiaoyu and Zhang, Yi and Cheung, Ka Chun and See, Simon and Wang, Xiaogang and Qin, Hongwei and Li, Hongsheng}, title = {A Simple Baseline for Video Restoration With Grouped Spatial-Temporal Shift}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9822-9832} }
itKD: Interchange Transfer-Based Knowledge Distillation for 3D Object Detection-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Cho_2023_CVPR, author = {Cho, Hyeon and Choi, Junyong and Baek, Geonwoo and Hwang, Wonjun}, title = {itKD: Interchange Transfer-Based Knowledge Distillation for 3D Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13540-13549} }
2PCNet: Two-Phase Consistency Training for Day-to-Night Unsupervised Domain Adaptive Object Detection-
[pdf]
[arXiv]
[bibtex]@InProceedings{Kennerley_2023_CVPR, author = {Kennerley, Mikhail and Wang, Jian-Gang and Veeravalli, Bharadwaj and Tan, Robby T.}, title = {2PCNet: Two-Phase Consistency Training for Day-to-Night Unsupervised Domain Adaptive Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11484-11493} }
Panoptic Lifting for 3D Scene Understanding With Neural Fields-
[pdf]
[supp]
[bibtex]@InProceedings{Siddiqui_2023_CVPR, author = {Siddiqui, Yawar and Porzi, Lorenzo and Bul\`o, Samuel Rota and M\"uller, Norman and Nie{\ss}ner, Matthias and Dai, Angela and Kontschieder, Peter}, title = {Panoptic Lifting for 3D Scene Understanding With Neural Fields}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9043-9052} }
WeatherStream: Light Transport Automation of Single Image Deweathering-
[pdf]
[supp]
[bibtex]@InProceedings{Zhang_2023_CVPR, author = {Zhang, Howard and Ba, Yunhao and Yang, Ethan and Mehra, Varan and Gella, Blake and Suzuki, Akira and Pfahnl, Arnold and Chandrappa, Chethan Chinder and Wong, Alex and Kadambi, Achuta}, title = {WeatherStream: Light Transport Automation of Single Image Deweathering}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13499-13509} }
Learning To Detect Mirrors From Videos via Dual Correspondences-
[pdf]
[supp]
[bibtex]@InProceedings{Lin_2023_CVPR, author = {Lin, Jiaying and Tan, Xin and Lau, Rynson W.H.}, title = {Learning To Detect Mirrors From Videos via Dual Correspondences}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9109-9118} }
The Devil Is in the Points: Weakly Semi-Supervised Instance Segmentation via Point-Guided Mask Representation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Kim_2023_CVPR, author = {Kim, Beomyoung and Jeong, Joonhyun and Han, Dongyoon and Hwang, Sung Ju}, title = {The Devil Is in the Points: Weakly Semi-Supervised Instance Segmentation via Point-Guided Mask Representation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11360-11370} }
Language-Guided Audio-Visual Source Separation via Trimodal Consistency-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Tan_2023_CVPR, author = {Tan, Reuben and Ray, Arijit and Burns, Andrea and Plummer, Bryan A. and Salamon, Justin and Nieto, Oriol and Russell, Bryan and Saenko, Kate}, title = {Language-Guided Audio-Visual Source Separation via Trimodal Consistency}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10575-10584} }
DynaMask: Dynamic Mask Selection for Instance Segmentation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Li_2023_CVPR, author = {Li, Ruihuang and He, Chenhang and Li, Shuai and Zhang, Yabin and Zhang, Lei}, title = {DynaMask: Dynamic Mask Selection for Instance Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11279-11288} }
SAP-DETR: Bridging the Gap Between Salient Points and Queries-Based Transformer Detector for Fast Model Convergency-
[pdf]
[supp]
[bibtex]@InProceedings{Liu_2023_CVPR, author = {Liu, Yang and Zhang, Yao and Wang, Yixin and Zhang, Yang and Tian, Jiang and Shi, Zhongchao and Fan, Jianping and He, Zhiqiang}, title = {SAP-DETR: Bridging the Gap Between Salient Points and Queries-Based Transformer Detector for Fast Model Convergency}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15539-15547} }
GD-MAE: Generative Decoder for MAE Pre-Training on LiDAR Point Clouds-
[pdf]
[supp]
[bibtex]@InProceedings{Yang_2023_CVPR, author = {Yang, Honghui and He, Tong and Liu, Jiaheng and Chen, Hua and Wu, Boxi and Lin, Binbin and He, Xiaofei and Ouyang, Wanli}, title = {GD-MAE: Generative Decoder for MAE Pre-Training on LiDAR Point Clouds}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9403-9414} }
Re-Thinking Model Inversion Attacks Against Deep Neural Networks-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Nguyen_2023_CVPR, author = {Nguyen, Ngoc-Bao and Chandrasegaran, Keshigeyan and Abdollahzadeh, Milad and Cheung, Ngai-Man}, title = {Re-Thinking Model Inversion Attacks Against Deep Neural Networks}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16384-16393} }
You Need Multiple Exiting: Dynamic Early Exiting for Accelerating Unified Vision Language Model-
[pdf]
[arXiv]
[bibtex]@InProceedings{Tang_2023_CVPR, author = {Tang, Shengkun and Wang, Yaqing and Kong, Zhenglun and Zhang, Tianchi and Li, Yao and Ding, Caiwen and Wang, Yanzhi and Liang, Yi and Xu, Dongkuan}, title = {You Need Multiple Exiting: Dynamic Early Exiting for Accelerating Unified Vision Language Model}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10781-10791} }
PROB: Probabilistic Objectness for Open World Object Detection-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Zohar_2023_CVPR, author = {Zohar, Orr and Wang, Kuan-Chieh and Yeung, Serena}, title = {PROB: Probabilistic Objectness for Open World Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11444-11453} }
SparseFusion: Distilling View-Conditioned Diffusion for 3D Reconstruction-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Zhou_2023_CVPR, author = {Zhou, Zhizhuo and Tulsiani, Shubham}, title = {SparseFusion: Distilling View-Conditioned Diffusion for 3D Reconstruction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12588-12597} }
Dynamic Focus-Aware Positional Queries for Semantic Segmentation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{He_2023_CVPR, author = {He, Haoyu and Cai, Jianfei and Pan, Zizheng and Liu, Jing and Zhang, Jing and Tao, Dacheng and Zhuang, Bohan}, title = {Dynamic Focus-Aware Positional Queries for Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11299-11308} }
HARP: Personalized Hand Reconstruction From a Monocular RGB Video-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Karunratanakul_2023_CVPR, author = {Karunratanakul, Korrawe and Prokudin, Sergey and Hilliges, Otmar and Tang, Siyu}, title = {HARP: Personalized Hand Reconstruction From a Monocular RGB Video}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12802-12813} }
DART: Diversify-Aggregate-Repeat Training Improves Generalization of Neural Networks-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Jain_2023_CVPR, author = {Jain, Samyak and Addepalli, Sravanti and Sahu, Pawan Kumar and Dey, Priyam and Babu, R. Venkatesh}, title = {DART: Diversify-Aggregate-Repeat Training Improves Generalization of Neural Networks}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16048-16059} }
EvShutter: Transforming Events for Unconstrained Rolling Shutter Correction-
[pdf]
[supp]
[bibtex]@InProceedings{Erbach_2023_CVPR, author = {Erbach, Julius and Tulyakov, Stepan and Vitoria, Patricia and Bochicchio, Alfredo and Li, Yuanyou}, title = {EvShutter: Transforming Events for Unconstrained Rolling Shutter Correction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13904-13913} }
Ambiguity-Resistant Semi-Supervised Learning for Dense Object Detection-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Liu_2023_CVPR, author = {Liu, Chang and Zhang, Weiming and Lin, Xiangru and Zhang, Wei and Tan, Xiao and Han, Junyu and Li, Xiaomao and Ding, Errui and Wang, Jingdong}, title = {Ambiguity-Resistant Semi-Supervised Learning for Dense Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15579-15588} }
Scalable, Detailed and Mask-Free Universal Photometric Stereo-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Ikehata_2023_CVPR, author = {Ikehata, Satoshi}, title = {Scalable, Detailed and Mask-Free Universal Photometric Stereo}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13198-13207} }
Towards High-Quality and Efficient Video Super-Resolution via Spatial-Temporal Data Overfitting-
[pdf]
[arXiv]
[bibtex]@InProceedings{Li_2023_CVPR, author = {Li, Gen and Ji, Jie and Qin, Minghai and Niu, Wei and Ren, Bin and Afghah, Fatemeh and Guo, Linke and Ma, Xiaolong}, title = {Towards High-Quality and Efficient Video Super-Resolution via Spatial-Temporal Data Overfitting}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10259-10269} }
BiFormer: Vision Transformer With Bi-Level Routing Attention-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Zhu_2023_CVPR, author = {Zhu, Lei and Wang, Xinjiang and Ke, Zhanghan and Zhang, Wayne and Lau, Rynson W.H.}, title = {BiFormer: Vision Transformer With Bi-Level Routing Attention}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10323-10333} }
Class-Incremental Exemplar Compression for Class-Incremental Learning-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Luo_2023_CVPR, author = {Luo, Zilin and Liu, Yaoyao and Schiele, Bernt and Sun, Qianru}, title = {Class-Incremental Exemplar Compression for Class-Incremental Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11371-11380} }
Behind the Scenes: Density Fields for Single View Reconstruction-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Wimbauer_2023_CVPR, author = {Wimbauer, Felix and Yang, Nan and Rupprecht, Christian and Cremers, Daniel}, title = {Behind the Scenes: Density Fields for Single View Reconstruction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9076-9086} }
StyleGAN Salon: Multi-View Latent Optimization for Pose-Invariant Hairstyle Transfer-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Khwanmuang_2023_CVPR, author = {Khwanmuang, Sasikarn and Phongthawee, Pakkapon and Sangkloy, Patsorn and Suwajanakorn, Supasorn}, title = {StyleGAN Salon: Multi-View Latent Optimization for Pose-Invariant Hairstyle Transfer}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8609-8618} }
Resource-Efficient RGBD Aerial Tracking-
[pdf]
[supp]
[bibtex]@InProceedings{Yang_2023_CVPR, author = {Yang, Jinyu and Gao, Shang and Li, Zhe and Zheng, Feng and Leonardis, Ale\v{s}}, title = {Resource-Efficient RGBD Aerial Tracking}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13374-13383} }
Bilateral Memory Consolidation for Continual Learning-
[pdf]
[supp]
[bibtex]@InProceedings{Nie_2023_CVPR, author = {Nie, Xing and Xu, Shixiong and Liu, Xiyan and Meng, Gaofeng and Huo, Chunlei and Xiang, Shiming}, title = {Bilateral Memory Consolidation for Continual Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16026-16035} }
Search-Map-Search: A Frame Selection Paradigm for Action Recognition-
[pdf]
[supp]
[bibtex]@InProceedings{Zhao_2023_CVPR, author = {Zhao, Mingjun and Yu, Yakun and Wang, Xiaoli and Yang, Lei and Niu, Di}, title = {Search-Map-Search: A Frame Selection Paradigm for Action Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10627-10636} }
Uncovering the Missing Pattern: Unified Framework Towards Trajectory Imputation and Prediction-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Xu_2023_CVPR, author = {Xu, Yi and Bazarjani, Armin and Chi, Hyung-gun and Choi, Chiho and Fu, Yun}, title = {Uncovering the Missing Pattern: Unified Framework Towards Trajectory Imputation and Prediction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9632-9643} }
FlexiViT: One Model for All Patch Sizes-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Beyer_2023_CVPR, author = {Beyer, Lucas and Izmailov, Pavel and Kolesnikov, Alexander and Caron, Mathilde and Kornblith, Simon and Zhai, Xiaohua and Minderer, Matthias and Tschannen, Michael and Alabdulmohsin, Ibrahim and Pavetic, Filip}, title = {FlexiViT: One Model for All Patch Sizes}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14496-14506} }
Structured Kernel Estimation for Photon-Limited Deconvolution-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Sanghvi_2023_CVPR, author = {Sanghvi, Yash and Mao, Zhiyuan and Chan, Stanley H.}, title = {Structured Kernel Estimation for Photon-Limited Deconvolution}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9863-9872} }
Frame Interpolation Transformer and Uncertainty Guidance-
[pdf]
[supp]
[bibtex]@InProceedings{Plack_2023_CVPR, author = {Plack, Markus and Briedis, Karlis Martins and Djelouah, Abdelaziz and Hullin, Matthias B. and Gross, Markus and Schroers, Christopher}, title = {Frame Interpolation Transformer and Uncertainty Guidance}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9811-9821} }
Neural Preset for Color Style Transfer-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Ke_2023_CVPR, author = {Ke, Zhanghan and Liu, Yuhao and Zhu, Lei and Zhao, Nanxuan and Lau, Rynson W.H.}, title = {Neural Preset for Color Style Transfer}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14173-14182} }
Wavelet Diffusion Models Are Fast and Scalable Image Generators-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Phung_2023_CVPR, author = {Phung, Hao and Dao, Quan and Tran, Anh}, title = {Wavelet Diffusion Models Are Fast and Scalable Image Generators}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10199-10208} }
PA&DA: Jointly Sampling Path and Data for Consistent NAS-
[pdf]
[supp]
[bibtex]@InProceedings{Lu_2023_CVPR, author = {Lu, Shun and Hu, Yu and Yang, Longxing and Sun, Zihao and Mei, Jilin and Tan, Jianchao and Song, Chengru}, title = {PA\&DA: Jointly Sampling Path and Data for Consistent NAS}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11940-11949} }
3D Spatial Multimodal Knowledge Accumulation for Scene Graph Prediction in Point Cloud-
[pdf]
[supp]
[bibtex]@InProceedings{Feng_2023_CVPR, author = {Feng, Mingtao and Hou, Haoran and Zhang, Liang and Wu, Zijie and Guo, Yulan and Mian, Ajmal}, title = {3D Spatial Multimodal Knowledge Accumulation for Scene Graph Prediction in Point Cloud}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9182-9191} }
ViTs for SITS: Vision Transformers for Satellite Image Time Series-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Tarasiou_2023_CVPR, author = {Tarasiou, Michail and Chavez, Erik and Zafeiriou, Stefanos}, title = {ViTs for SITS: Vision Transformers for Satellite Image Time Series}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10418-10428} }
Prompt, Generate, Then Cache: Cascade of Foundation Models Makes Strong Few-Shot Learners-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Zhang_2023_CVPR, author = {Zhang, Renrui and Hu, Xiangfei and Li, Bohao and Huang, Siyuan and Deng, Hanqiu and Qiao, Yu and Gao, Peng and Li, Hongsheng}, title = {Prompt, Generate, Then Cache: Cascade of Foundation Models Makes Strong Few-Shot Learners}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15211-15222} }
VideoMAE V2: Scaling Video Masked Autoencoders With Dual Masking-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Wang_2023_CVPR, author = {Wang, Limin and Huang, Bingkun and Zhao, Zhiyu and Tong, Zhan and He, Yinan and Wang, Yi and Wang, Yali and Qiao, Yu}, title = {VideoMAE V2: Scaling Video Masked Autoencoders With Dual Masking}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14549-14560} }
Perception and Semantic Aware Regularization for Sequential Confidence Calibration-
[pdf]
[supp]
[bibtex]@InProceedings{Peng_2023_CVPR, author = {Peng, Zhenghua and Luo, Yu and Chen, Tianshui and Xu, Keke and Huang, Shuangping}, title = {Perception and Semantic Aware Regularization for Sequential Confidence Calibration}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10658-10668} }
Vid2Seq: Large-Scale Pretraining of a Visual Language Model for Dense Video Captioning-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Yang_2023_CVPR, author = {Yang, Antoine and Nagrani, Arsha and Seo, Paul Hongsuck and Miech, Antoine and Pont-Tuset, Jordi and Laptev, Ivan and Sivic, Josef and Schmid, Cordelia}, title = {Vid2Seq: Large-Scale Pretraining of a Visual Language Model for Dense Video Captioning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10714-10726} }
ERNIE-ViLG 2.0: Improving Text-to-Image Diffusion Model With Knowledge-Enhanced Mixture-of-Denoising-Experts-
[pdf]
[supp]
[bibtex]@InProceedings{Feng_2023_CVPR, author = {Feng, Zhida and Zhang, Zhenyu and Yu, Xintong and Fang, Yewei and Li, Lanxin and Chen, Xuyi and Lu, Yuxiang and Liu, Jiaxiang and Yin, Weichong and Feng, Shikun and Sun, Yu and Chen, Li and Tian, Hao and Wu, Hua and Wang, Haifeng}, title = {ERNIE-ViLG 2.0: Improving Text-to-Image Diffusion Model With Knowledge-Enhanced Mixture-of-Denoising-Experts}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10135-10145} }
Revisiting the Stack-Based Inverse Tone Mapping-
[pdf]
[supp]
[bibtex]@InProceedings{Zhang_2023_CVPR, author = {Zhang, Ning and Ye, Yuyao and Zhao, Yang and Wang, Ronggang}, title = {Revisiting the Stack-Based Inverse Tone Mapping}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9162-9171} }
Exploiting Completeness and Uncertainty of Pseudo Labels for Weakly Supervised Video Anomaly Detection-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Zhang_2023_CVPR, author = {Zhang, Chen and Li, Guorong and Qi, Yuankai and Wang, Shuhui and Qing, Laiyun and Huang, Qingming and Yang, Ming-Hsuan}, title = {Exploiting Completeness and Uncertainty of Pseudo Labels for Weakly Supervised Video Anomaly Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16271-16280} }
Full or Weak Annotations? An Adaptive Strategy for Budget-Constrained Annotation Campaigns-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Tejero_2023_CVPR, author = {Tejero, Javier Gamazo and Zinkernagel, Martin S. and Wolf, Sebastian and Sznitman, Raphael and M\'arquez-Neila, Pablo}, title = {Full or Weak Annotations? An Adaptive Strategy for Budget-Constrained Annotation Campaigns}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11381-11391} }
Backdoor Defense via Deconfounded Representation Learning-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Zhang_2023_CVPR, author = {Zhang, Zaixi and Liu, Qi and Wang, Zhicai and Lu, Zepu and Hu, Qingyong}, title = {Backdoor Defense via Deconfounded Representation Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12228-12238} }
HairStep: Transfer Synthetic to Real Using Strand and Depth Maps for Single-View 3D Hair Modeling-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Zheng_2023_CVPR, author = {Zheng, Yujian and Jin, Zirong and Li, Moran and Huang, Haibin and Ma, Chongyang and Cui, Shuguang and Han, Xiaoguang}, title = {HairStep: Transfer Synthetic to Real Using Strand and Depth Maps for Single-View 3D Hair Modeling}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12726-12735} }
MoDAR: Using Motion Forecasting for 3D Object Detection in Point Cloud Sequences-
[pdf]
[supp]
[bibtex]@InProceedings{Li_2023_CVPR, author = {Li, Yingwei and Qi, Charles R. and Zhou, Yin and Liu, Chenxi and Anguelov, Dragomir}, title = {MoDAR: Using Motion Forecasting for 3D Object Detection in Point Cloud Sequences}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9329-9339} }
ALSO: Automotive Lidar Self-Supervision by Occupancy Estimation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Boulch_2023_CVPR, author = {Boulch, Alexandre and Sautier, Corentin and Michele, Bj\"orn and Puy, Gilles and Marlet, Renaud}, title = {ALSO: Automotive Lidar Self-Supervision by Occupancy Estimation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13455-13465} }
Learning Dynamic Style Kernels for Artistic Style Transfer-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Xu_2023_CVPR, author = {Xu, Wenju and Long, Chengjiang and Nie, Yongwei}, title = {Learning Dynamic Style Kernels for Artistic Style Transfer}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10083-10092} }
Chat2Map: Efficient Scene Mapping From Multi-Ego Conversations-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Majumder_2023_CVPR, author = {Majumder, Sagnik and Jiang, Hao and Moulon, Pierre and Henderson, Ethan and Calamia, Paul and Grauman, Kristen and Ithapu, Vamsi Krishna}, title = {Chat2Map: Efficient Scene Mapping From Multi-Ego Conversations}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10554-10564} }
GeoMAE: Masked Geometric Target Prediction for Self-Supervised Point Cloud Pre-Training-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Tian_2023_CVPR, author = {Tian, Xiaoyu and Ran, Haoxi and Wang, Yue and Zhao, Hang}, title = {GeoMAE: Masked Geometric Target Prediction for Self-Supervised Point Cloud Pre-Training}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13570-13580} }
Learning Conditional Attributes for Compositional Zero-Shot Learning-
[pdf]
[bibtex]@InProceedings{Wang_2023_CVPR, author = {Wang, Qingsheng and Liu, Lingqiao and Jing, Chenchen and Chen, Hao and Liang, Guoqiang and Wang, Peng and Shen, Chunhua}, title = {Learning Conditional Attributes for Compositional Zero-Shot Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11197-11206} }
Complete 3D Human Reconstruction From a Single Incomplete Image-
[pdf]
[supp]
[bibtex]@InProceedings{Wang_2023_CVPR, author = {Wang, Junying and Yoon, Jae Shin and Wang, Tuanfeng Y. and Singh, Krishna Kumar and Neumann, Ulrich}, title = {Complete 3D Human Reconstruction From a Single Incomplete Image}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8748-8758} }
PVT-SSD: Single-Stage 3D Object Detector With Point-Voxel Transformer-
[pdf]
[supp]
[bibtex]@InProceedings{Yang_2023_CVPR, author = {Yang, Honghui and Wang, Wenxiao and Chen, Minghao and Lin, Binbin and He, Tong and Chen, Hua and He, Xiaofei and Ouyang, Wanli}, title = {PVT-SSD: Single-Stage 3D Object Detector With Point-Voxel Transformer}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13476-13487} }
Adaptive Human Matting for Dynamic Videos-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Lin_2023_CVPR, author = {Lin, Chung-Ching and Wang, Jiang and Luo, Kun and Lin, Kevin and Li, Linjie and Wang, Lijuan and Liu, Zicheng}, title = {Adaptive Human Matting for Dynamic Videos}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10229-10238} }
Learning Common Rationale To Improve Self-Supervised Representation for Fine-Grained Visual Recognition Problems-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Shu_2023_CVPR, author = {Shu, Yangyang and van den Hengel, Anton and Liu, Lingqiao}, title = {Learning Common Rationale To Improve Self-Supervised Representation for Fine-Grained Visual Recognition Problems}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11392-11401} }
High-Fidelity 3D Human Digitization From Single 2K Resolution Images-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Han_2023_CVPR, author = {Han, Sang-Hun and Park, Min-Gyu and Yoon, Ju Hong and Kang, Ju-Mi and Park, Young-Jae and Jeon, Hae-Gon}, title = {High-Fidelity 3D Human Digitization From Single 2K Resolution Images}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12869-12879} }
Fully Self-Supervised Depth Estimation From Defocus Clue-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Si_2023_CVPR, author = {Si, Haozhe and Zhao, Bin and Wang, Dong and Gao, Yunpeng and Chen, Mulin and Wang, Zhigang and Li, Xuelong}, title = {Fully Self-Supervised Depth Estimation From Defocus Clue}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9140-9149} }
Prompting Large Language Models With Answer Heuristics for Knowledge-Based Visual Question Answering-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Shao_2023_CVPR, author = {Shao, Zhenwei and Yu, Zhou and Wang, Meng and Yu, Jun}, title = {Prompting Large Language Models With Answer Heuristics for Knowledge-Based Visual Question Answering}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14974-14983} }
Improving Robustness of Semantic Segmentation to Motion-Blur Using Class-Centric Augmentation-
[pdf]
[supp]
[bibtex]@InProceedings{Aakanksha_2023_CVPR, author = {Aakanksha and Rajagopalan, A. N.}, title = {Improving Robustness of Semantic Segmentation to Motion-Blur Using Class-Centric Augmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10470-10479} }
Progressive Open Space Expansion for Open-Set Model Attribution-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Yang_2023_CVPR, author = {Yang, Tianyun and Wang, Danding and Tang, Fan and Zhao, Xinying and Cao, Juan and Tang, Sheng}, title = {Progressive Open Space Expansion for Open-Set Model Attribution}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15856-15865} }
Backdoor Cleansing With Unlabeled Data-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Pang_2023_CVPR, author = {Pang, Lu and Sun, Tao and Ling, Haibin and Chen, Chao}, title = {Backdoor Cleansing With Unlabeled Data}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12218-12227} }
Harmonious Feature Learning for Interactive Hand-Object Pose Estimation-
[pdf]
[supp]
[bibtex]@InProceedings{Lin_2023_CVPR, author = {Lin, Zhifeng and Ding, Changxing and Yao, Huan and Kuang, Zengsheng and Huang, Shaoli}, title = {Harmonious Feature Learning for Interactive Hand-Object Pose Estimation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12989-12998} }
CLOTH4D: A Dataset for Clothed Human Reconstruction-
[pdf]
[supp]
[bibtex]@InProceedings{Zou_2023_CVPR, author = {Zou, Xingxing and Han, Xintong and Wong, Waikeung}, title = {CLOTH4D: A Dataset for Clothed Human Reconstruction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12847-12857} }
Generative Bias for Robust Visual Question Answering-
[pdf]
[arXiv]
[bibtex]@InProceedings{Cho_2023_CVPR, author = {Cho, Jae Won and Kim, Dong-Jin and Ryu, Hyeonggon and Kweon, In So}, title = {Generative Bias for Robust Visual Question Answering}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11681-11690} }
Data-Free Sketch-Based Image Retrieval-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Chaudhuri_2023_CVPR, author = {Chaudhuri, Abhra and Bhunia, Ayan Kumar and Song, Yi-Zhe and Dutta, Anjan}, title = {Data-Free Sketch-Based Image Retrieval}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12084-12093} }
Multi-Object Manipulation via Object-Centric Neural Scattering Functions-
[pdf]
[supp]
[bibtex]@InProceedings{Tian_2023_CVPR, author = {Tian, Stephen and Cai, Yancheng and Yu, Hong-Xing and Zakharov, Sergey and Liu, Katherine and Gaidon, Adrien and Li, Yunzhu and Wu, Jiajun}, title = {Multi-Object Manipulation via Object-Centric Neural Scattering Functions}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9021-9031} }
The Wisdom of Crowds: Temporal Progressive Attention for Early Action Prediction-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Stergiou_2023_CVPR, author = {Stergiou, Alexandros and Damen, Dima}, title = {The Wisdom of Crowds: Temporal Progressive Attention for Early Action Prediction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14709-14719} }
Invertible Neural Skinning-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Kant_2023_CVPR, author = {Kant, Yash and Siarohin, Aliaksandr and Guler, Riza Alp and Chai, Menglei and Ren, Jian and Tulyakov, Sergey and Gilitschenski, Igor}, title = {Invertible Neural Skinning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8715-8725} }
Weakly Supervised Semantic Segmentation via Adversarial Learning of Classifier and Reconstructor-
[pdf]
[supp]
[bibtex]@InProceedings{Kweon_2023_CVPR, author = {Kweon, Hyeokjun and Yoon, Sung-Hoon and Yoon, Kuk-Jin}, title = {Weakly Supervised Semantic Segmentation via Adversarial Learning of Classifier and Reconstructor}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11329-11339} }
Distilling Cross-Temporal Contexts for Continuous Sign Language Recognition-
[pdf]
[supp]
[bibtex]@InProceedings{Guo_2023_CVPR, author = {Guo, Leming and Xue, Wanli and Guo, Qing and Liu, Bo and Zhang, Kaihua and Yuan, Tiantian and Chen, Shengyong}, title = {Distilling Cross-Temporal Contexts for Continuous Sign Language Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10771-10780} }
Unsupervised Deep Probabilistic Approach for Partial Point Cloud Registration-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Mei_2023_CVPR, author = {Mei, Guofeng and Tang, Hao and Huang, Xiaoshui and Wang, Weijie and Liu, Juan and Zhang, Jian and Van Gool, Luc and Wu, Qiang}, title = {Unsupervised Deep Probabilistic Approach for Partial Point Cloud Registration}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13611-13620} }
Similarity Metric Learning for RGB-Infrared Group Re-Identification-
[pdf]
[supp]
[bibtex]@InProceedings{Xiong_2023_CVPR, author = {Xiong, Jianghao and Lai, Jianhuang}, title = {Similarity Metric Learning for RGB-Infrared Group Re-Identification}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13662-13671} }
Train/Test-Time Adaptation With Retrieval-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Zancato_2023_CVPR, author = {Zancato, Luca and Achille, Alessandro and Liu, Tian Yu and Trager, Matthew and Perera, Pramuditha and Soatto, Stefano}, title = {Train/Test-Time Adaptation With Retrieval}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15911-15921} }
ProxyFormer: Proxy Alignment Assisted Point Cloud Completion With Missing Part Sensitive Transformer-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Li_2023_CVPR, author = {Li, Shanshan and Gao, Pan and Tan, Xiaoyang and Wei, Mingqiang}, title = {ProxyFormer: Proxy Alignment Assisted Point Cloud Completion With Missing Part Sensitive Transformer}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9466-9475} }
Mod-Squad: Designing Mixtures of Experts As Modular Multi-Task Learners-
[pdf]
[supp]
[bibtex]@InProceedings{Chen_2023_CVPR, author = {Chen, Zitian and Shen, Yikang and Ding, Mingyu and Chen, Zhenfang and Zhao, Hengshuang and Learned-Miller, Erik G. and Gan, Chuang}, title = {Mod-Squad: Designing Mixtures of Experts As Modular Multi-Task Learners}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11828-11837} }
Learning Customized Visual Models With Retrieval-Augmented Knowledge-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Liu_2023_CVPR, author = {Liu, Haotian and Son, Kilho and Yang, Jianwei and Liu, Ce and Gao, Jianfeng and Lee, Yong Jae and Li, Chunyuan}, title = {Learning Customized Visual Models With Retrieval-Augmented Knowledge}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15148-15158} }
Run, Don't Walk: Chasing Higher FLOPS for Faster Neural Networks-
[pdf]
[supp]
[bibtex]@InProceedings{Chen_2023_CVPR, author = {Chen, Jierun and Kao, Shiu-hong and He, Hao and Zhuo, Weipeng and Wen, Song and Lee, Chul-Ho and Chan, S.-H. Gary}, title = {Run, Don't Walk: Chasing Higher FLOPS for Faster Neural Networks}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12021-12031} }
Learning Procedure-Aware Video Representation From Instructional Videos and Their Narrations-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Zhong_2023_CVPR, author = {Zhong, Yiwu and Yu, Licheng and Bai, Yang and Li, Shangwen and Yan, Xueting and Li, Yin}, title = {Learning Procedure-Aware Video Representation From Instructional Videos and Their Narrations}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14825-14835} }
Co-Training 2L Submodels for Visual Recognition-
[pdf]
[supp]
[bibtex]@InProceedings{Touvron_2023_CVPR, author = {Touvron, Hugo and Cord, Matthieu and Oquab, Maxime and Bojanowski, Piotr and Verbeek, Jakob and J\'egou, Herv\'e}, title = {Co-Training 2L Submodels for Visual Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11701-11710} }
K-Planes: Explicit Radiance Fields in Space, Time, and Appearance-
[pdf]
[supp]
[bibtex]@InProceedings{Fridovich-Keil_2023_CVPR, author = {Fridovich-Keil, Sara and Meanti, Giacomo and Warburg, Frederik Rahb{\ae}k and Recht, Benjamin and Kanazawa, Angjoo}, title = {K-Planes: Explicit Radiance Fields in Space, Time, and Appearance}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12479-12488} }
Multi-Mode Online Knowledge Distillation for Self-Supervised Visual Representation Learning-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Song_2023_CVPR, author = {Song, Kaiyou and Xie, Jin and Zhang, Shan and Luo, Zimeng}, title = {Multi-Mode Online Knowledge Distillation for Self-Supervised Visual Representation Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11848-11857} }
Viewpoint Equivariance for Multi-View 3D Object Detection-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Chen_2023_CVPR, author = {Chen, Dian and Li, Jie and Guizilini, Vitor and Ambrus, Rares Andrei and Gaidon, Adrien}, title = {Viewpoint Equivariance for Multi-View 3D Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9213-9222} }
A Generalized Framework for Video Instance Segmentation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Heo_2023_CVPR, author = {Heo, Miran and Hwang, Sukjun and Hyun, Jeongseok and Kim, Hanjung and Oh, Seoung Wug and Lee, Joon-Young and Kim, Seon Joo}, title = {A Generalized Framework for Video Instance Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14623-14632} }
On Distillation of Guided Diffusion Models-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Meng_2023_CVPR, author = {Meng, Chenlin and Rombach, Robin and Gao, Ruiqi and Kingma, Diederik and Ermon, Stefano and Ho, Jonathan and Salimans, Tim}, title = {On Distillation of Guided Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14297-14306} }
Disentangled Representation Learning for Unsupervised Neural Quantization-
[pdf]
[bibtex]@InProceedings{Noh_2023_CVPR, author = {Noh, Haechan and Hyun, Sangeek and Jeong, Woojin and Lim, Hanshin and Heo, Jae-Pil}, title = {Disentangled Representation Learning for Unsupervised Neural Quantization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12001-12010} }
Zero-Shot Pose Transfer for Unrigged Stylized 3D Characters-
[pdf]
[supp]
[bibtex]@InProceedings{Wang_2023_CVPR, author = {Wang, Jiashun and Li, Xueting and Liu, Sifei and De Mello, Shalini and Gallo, Orazio and Wang, Xiaolong and Kautz, Jan}, title = {Zero-Shot Pose Transfer for Unrigged Stylized 3D Characters}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8704-8714} }
Listening Human Behavior: 3D Human Pose Estimation With Acoustic Signals-
[pdf]
[supp]
[bibtex]@InProceedings{Shibata_2023_CVPR, author = {Shibata, Yuto and Kawashima, Yutaka and Isogawa, Mariko and Irie, Go and Kimura, Akisato and Aoki, Yoshimitsu}, title = {Listening Human Behavior: 3D Human Pose Estimation With Acoustic Signals}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13323-13332} }
Meta-Learning With a Geometry-Adaptive Preconditioner-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Kang_2023_CVPR, author = {Kang, Suhyun and Hwang, Duhun and Eo, Moonjung and Kim, Taesup and Rhee, Wonjong}, title = {Meta-Learning With a Geometry-Adaptive Preconditioner}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16080-16090} }
NeuralDome: A Neural Modeling Pipeline on Multi-View Human-Object Interactions-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Zhang_2023_CVPR, author = {Zhang, Juze and Luo, Haimin and Yang, Hongdi and Xu, Xinru and Wu, Qianyang and Shi, Ye and Yu, Jingyi and Xu, Lan and Wang, Jingya}, title = {NeuralDome: A Neural Modeling Pipeline on Multi-View Human-Object Interactions}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8834-8845} }
No One Left Behind: Improving the Worst Categories in Long-Tailed Learning-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Du_2023_CVPR, author = {Du, Yingxiao and Wu, Jianxin}, title = {No One Left Behind: Improving the Worst Categories in Long-Tailed Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15804-15813} }
Target-Referenced Reactive Grasping for Dynamic Objects-
[pdf]
[supp]
[bibtex]@InProceedings{Liu_2023_CVPR, author = {Liu, Jirong and Zhang, Ruo and Fang, Hao-Shu and Gou, Minghao and Fang, Hongjie and Wang, Chenxi and Xu, Sheng and Yan, Hengxu and Lu, Cewu}, title = {Target-Referenced Reactive Grasping for Dynamic Objects}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8824-8833} }
Complexity-Guided Slimmable Decoder for Efficient Deep Video Compression-
[pdf]
[supp]
[bibtex]@InProceedings{Hu_2023_CVPR, author = {Hu, Zhihao and Xu, Dong}, title = {Complexity-Guided Slimmable Decoder for Efficient Deep Video Compression}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14358-14367} }
MarginMatch: Improving Semi-Supervised Learning with Pseudo-Margins-
[pdf]
[supp]
[bibtex]@InProceedings{Sosea_2023_CVPR, author = {Sosea, Tiberiu and Caragea, Cornelia}, title = {MarginMatch: Improving Semi-Supervised Learning with Pseudo-Margins}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15773-15782} }
Beyond Appearance: A Semantic Controllable Self-Supervised Learning Framework for Human-Centric Visual Tasks-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Chen_2023_CVPR, author = {Chen, Weihua and Xu, Xianzhe and Jia, Jian and Luo, Hao and Wang, Yaohua and Wang, Fan and Jin, Rong and Sun, Xiuyu}, title = {Beyond Appearance: A Semantic Controllable Self-Supervised Learning Framework for Human-Centric Visual Tasks}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15050-15061} }
Neural Fourier Filter Bank-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Wu_2023_CVPR, author = {Wu, Zhijie and Jin, Yuhe and Yi, Kwang Moo}, title = {Neural Fourier Filter Bank}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14153-14163} }
NeRFInvertor: High Fidelity NeRF-GAN Inversion for Single-Shot Real Image Animation-
[pdf]
[arXiv]
[bibtex]@InProceedings{Yin_2023_CVPR, author = {Yin, Yu and Ghasedi, Kamran and Wu, HsiangTao and Yang, Jiaolong and Tong, Xin and Fu, Yun}, title = {NeRFInvertor: High Fidelity NeRF-GAN Inversion for Single-Shot Real Image Animation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8539-8548} }
Trace and Pace: Controllable Pedestrian Animation via Guided Trajectory Diffusion-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Rempe_2023_CVPR, author = {Rempe, Davis and Luo, Zhengyi and Bin Peng, Xue and Yuan, Ye and Kitani, Kris and Kreis, Karsten and Fidler, Sanja and Litany, Or}, title = {Trace and Pace: Controllable Pedestrian Animation via Guided Trajectory Diffusion}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13756-13766} }
Overlooked Factors in Concept-Based Explanations: Dataset Choice, Concept Learnability, and Human Capability-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Ramaswamy_2023_CVPR, author = {Ramaswamy, Vikram V. and Kim, Sunnie S. Y. and Fong, Ruth and Russakovsky, Olga}, title = {Overlooked Factors in Concept-Based Explanations: Dataset Choice, Concept Learnability, and Human Capability}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10932-10941} }
Unsupervised 3D Shape Reconstruction by Part Retrieval and Assembly-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Xu_2023_CVPR, author = {Xu, Xianghao and Guerrero, Paul and Fisher, Matthew and Chaudhuri, Siddhartha and Ritchie, Daniel}, title = {Unsupervised 3D Shape Reconstruction by Part Retrieval and Assembly}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8559-8567} }
SeqTrack: Sequence to Sequence Learning for Visual Object Tracking-
[pdf]
[arXiv]
[bibtex]@InProceedings{Chen_2023_CVPR, author = {Chen, Xin and Peng, Houwen and Wang, Dong and Lu, Huchuan and Hu, Han}, title = {SeqTrack: Sequence to Sequence Learning for Visual Object Tracking}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14572-14581} }
AutoLabel: CLIP-Based Framework for Open-Set Video Domain Adaptation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Zara_2023_CVPR, author = {Zara, Giacomo and Roy, Subhankar and Rota, Paolo and Ricci, Elisa}, title = {AutoLabel: CLIP-Based Framework for Open-Set Video Domain Adaptation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11504-11513} }
DINER: Depth-Aware Image-Based NEural Radiance Fields-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Prinzler_2023_CVPR, author = {Prinzler, Malte and Hilliges, Otmar and Thies, Justus}, title = {DINER: Depth-Aware Image-Based NEural Radiance Fields}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12449-12459} }
Reconstructing Signing Avatars From Video Using Linguistic Priors-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Forte_2023_CVPR, author = {Forte, Maria-Paola and Kulits, Peter and Huang, Chun-Hao P. and Choutas, Vasileios and Tzionas, Dimitrios and Kuchenbecker, Katherine J. and Black, Michael J.}, title = {Reconstructing Signing Avatars From Video Using Linguistic Priors}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12791-12801} }
DeepMapping2: Self-Supervised Large-Scale LiDAR Map Optimization-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Chen_2023_CVPR, author = {Chen, Chao and Liu, Xinhao and Li, Yiming and Ding, Li and Feng, Chen}, title = {DeepMapping2: Self-Supervised Large-Scale LiDAR Map Optimization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9306-9316} }
DoNet: Deep De-Overlapping Network for Cytology Instance Segmentation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Jiang_2023_CVPR, author = {Jiang, Hao and Zhang, Rushan and Zhou, Yanning and Wang, Yumeng and Chen, Hao}, title = {DoNet: Deep De-Overlapping Network for Cytology Instance Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15641-15650} }
Instant Domain Augmentation for LiDAR Semantic Segmentation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Ryu_2023_CVPR, author = {Ryu, Kwonyoung and Hwang, Soonmin and Park, Jaesik}, title = {Instant Domain Augmentation for LiDAR Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9350-9360} }
A Characteristic Function-Based Method for Bottom-Up Human Pose Estimation-
[pdf]
[supp]
[bibtex]@InProceedings{Qu_2023_CVPR, author = {Qu, Haoxuan and Cai, Yujun and Foo, Lin Geng and Kumar, Ajay and Liu, Jun}, title = {A Characteristic Function-Based Method for Bottom-Up Human Pose Estimation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13009-13018} }
SceneTrilogy: On Human Scene-Sketch and Its Complementarity With Photo and Text-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Chowdhury_2023_CVPR, author = {Chowdhury, Pinaki Nath and Bhunia, Ayan Kumar and Sain, Aneeshan and Koley, Subhadeep and Xiang, Tao and Song, Yi-Zhe}, title = {SceneTrilogy: On Human Scene-Sketch and Its Complementarity With Photo and Text}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10972-10983} }
RefSR-NeRF: Towards High Fidelity and Super Resolution View Synthesis-
[pdf]
[supp]
[bibtex]@InProceedings{Huang_2023_CVPR, author = {Huang, Xudong and Li, Wei and Hu, Jie and Chen, Hanting and Wang, Yunhe}, title = {RefSR-NeRF: Towards High Fidelity and Super Resolution View Synthesis}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8244-8253} }
Polarimetric iToF: Measuring High-Fidelity Depth Through Scattering Media-
[pdf]
[supp]
[bibtex]@InProceedings{Jeon_2023_CVPR, author = {Jeon, Daniel S. and Meuleman, Andr\'eas and Baek, Seung-Hwan and Kim, Min H.}, title = {Polarimetric iToF: Measuring High-Fidelity Depth Through Scattering Media}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12353-12362} }
Mobile User Interface Element Detection via Adaptively Prompt Tuning-
[pdf]
[bibtex]@InProceedings{Gu_2023_CVPR, author = {Gu, Zhangxuan and Xu, Zhuoer and Chen, Haoxing and Lan, Jun and Meng, Changhua and Wang, Weiqiang}, title = {Mobile User Interface Element Detection via Adaptively Prompt Tuning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11155-11164} }
Sparse Multi-Modal Graph Transformer With Shared-Context Processing for Representation Learning of Giga-Pixel Images-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Nakhli_2023_CVPR, author = {Nakhli, Ramin and Moghadam, Puria Azadi and Mi, Haoyang and Farahani, Hossein and Baras, Alexander and Gilks, Blake and Bashashati, Ali}, title = {Sparse Multi-Modal Graph Transformer With Shared-Context Processing for Representation Learning of Giga-Pixel Images}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11547-11557} }
Generating Human Motion From Textual Descriptions With Discrete Representations-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Zhang_2023_CVPR, author = {Zhang, Jianrong and Zhang, Yangsong and Cun, Xiaodong and Zhang, Yong and Zhao, Hongwei and Lu, Hongtao and Shen, Xi and Shan, Ying}, title = {Generating Human Motion From Textual Descriptions With Discrete Representations}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14730-14740} }
Spatial-Temporal Concept Based Explanation of 3D ConvNets-
[pdf]
[arXiv]
[bibtex]@InProceedings{Ji_2023_CVPR, author = {Ji, Ying and Wang, Yu and Kato, Jien}, title = {Spatial-Temporal Concept Based Explanation of 3D ConvNets}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15444-15453} }
Robust Test-Time Adaptation in Dynamic Scenarios-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Yuan_2023_CVPR, author = {Yuan, Longhui and Xie, Binhui and Li, Shuang}, title = {Robust Test-Time Adaptation in Dynamic Scenarios}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15922-15932} }
Global and Local Mixture Consistency Cumulative Learning for Long-Tailed Visual Recognitions-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Du_2023_CVPR, author = {Du, Fei and Yang, Peng and Jia, Qi and Nan, Fengtao and Chen, Xiaoting and Yang, Yun}, title = {Global and Local Mixture Consistency Cumulative Learning for Long-Tailed Visual Recognitions}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15814-15823} }
NIRVANA: Neural Implicit Representations of Videos With Adaptive Networks and Autoregressive Patch-Wise Modeling-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Maiya_2023_CVPR, author = {Maiya, Shishira R. and Girish, Sharath and Ehrlich, Max and Wang, Hanyu and Lee, Kwot Sin and Poirson, Patrick and Wu, Pengxiang and Wang, Chen and Shrivastava, Abhinav}, title = {NIRVANA: Neural Implicit Representations of Videos With Adaptive Networks and Autoregressive Patch-Wise Modeling}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14378-14387} }
Collaboration Helps Camera Overtake LiDAR in 3D Detection-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Hu_2023_CVPR, author = {Hu, Yue and Lu, Yifan and Xu, Runsheng and Xie, Weidi and Chen, Siheng and Wang, Yanfeng}, title = {Collaboration Helps Camera Overtake LiDAR in 3D Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9243-9252} }
ReCo: Region-Controlled Text-to-Image Generation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Yang_2023_CVPR, author = {Yang, Zhengyuan and Wang, Jianfeng and Gan, Zhe and Li, Linjie and Lin, Kevin and Wu, Chenfei and Duan, Nan and Liu, Zicheng and Liu, Ce and Zeng, Michael and Wang, Lijuan}, title = {ReCo: Region-Controlled Text-to-Image Generation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14246-14255} }
Fix the Noise: Disentangling Source Feature for Controllable Domain Translation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Lee_2023_CVPR, author = {Lee, Dongyeun and Lee, Jae Young and Kim, Doyeon and Choi, Jaehyun and Yoo, Jaejun and Kim, Junmo}, title = {Fix the Noise: Disentangling Source Feature for Controllable Domain Translation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14224-14234} }
Sparsely Annotated Semantic Segmentation With Adaptive Gaussian Mixtures-
[pdf]
[supp]
[bibtex]@InProceedings{Wu_2023_CVPR, author = {Wu, Linshan and Zhong, Zhun and Fang, Leyuan and He, Xingxin and Liu, Qiang and Ma, Jiayi and Chen, Hao}, title = {Sparsely Annotated Semantic Segmentation With Adaptive Gaussian Mixtures}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15454-15464} }
Diversity-Aware Meta Visual Prompting-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Huang_2023_CVPR, author = {Huang, Qidong and Dong, Xiaoyi and Chen, Dongdong and Zhang, Weiming and Wang, Feifei and Hua, Gang and Yu, Nenghai}, title = {Diversity-Aware Meta Visual Prompting}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10878-10887} }
FaceLit: Neural 3D Relightable Faces-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Ranjan_2023_CVPR, author = {Ranjan, Anurag and Yi, Kwang Moo and Chang, Jen-Hao Rick and Tuzel, Oncel}, title = {FaceLit: Neural 3D Relightable Faces}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8619-8628} }
Visual Programming: Compositional Visual Reasoning Without Training-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Gupta_2023_CVPR, author = {Gupta, Tanmay and Kembhavi, Aniruddha}, title = {Visual Programming: Compositional Visual Reasoning Without Training}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14953-14962} }
Real-Time Evaluation in Online Continual Learning: A New Hope-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Ghunaim_2023_CVPR, author = {Ghunaim, Yasir and Bibi, Adel and Alhamoud, Kumail and Alfarra, Motasem and Al Kader Hammoud, Hasan Abed and Prabhu, Ameya and Torr, Philip H.S. and Ghanem, Bernard}, title = {Real-Time Evaluation in Online Continual Learning: A New Hope}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11888-11897} }
BAAM: Monocular 3D Pose and Shape Reconstruction With Bi-Contextual Attention Module and Attention-Guided Modeling-
[pdf]
[supp]
[bibtex]@InProceedings{Lee_2023_CVPR, author = {Lee, Hyo-Jun and Kim, Hanul and Choi, Su-Min and Jeong, Seong-Gyun and Koh, Yeong Jun}, title = {BAAM: Monocular 3D Pose and Shape Reconstruction With Bi-Contextual Attention Module and Attention-Guided Modeling}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9011-9020} }
Freestyle Layout-to-Image Synthesis-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Xue_2023_CVPR, author = {Xue, Han and Huang, Zhiwu and Sun, Qianru and Song, Li and Zhang, Wenjun}, title = {Freestyle Layout-to-Image Synthesis}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14256-14266} }
Visual Dependency Transformers: Dependency Tree Emerges From Reversed Attention-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Ding_2023_CVPR, author = {Ding, Mingyu and Shen, Yikang and Fan, Lijie and Chen, Zhenfang and Chen, Zitian and Luo, Ping and Tenenbaum, Joshua B. and Gan, Chuang}, title = {Visual Dependency Transformers: Dependency Tree Emerges From Reversed Attention}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14528-14539} }
Differentiable Architecture Search With Random Features-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Zhang_2023_CVPR, author = {Zhang, Xuanyang and Li, Yonggang and Zhang, Xiangyu and Wang, Yongtao and Sun, Jian}, title = {Differentiable Architecture Search With Random Features}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16060-16069} }
Enhanced Stable View Synthesis-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Jain_2023_CVPR, author = {Jain, Nishant and Kumar, Suryansh and Van Gool, Luc}, title = {Enhanced Stable View Synthesis}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13208-13217} }
Breaching FedMD: Image Recovery via Paired-Logits Inversion Attack-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Takahashi_2023_CVPR, author = {Takahashi, Hideaki and Liu, Jingjing and Liu, Yang}, title = {Breaching FedMD: Image Recovery via Paired-Logits Inversion Attack}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12198-12207} }
Biomechanics-Guided Facial Action Unit Detection Through Force Modeling-
[pdf]
[supp]
[bibtex]@InProceedings{Cui_2023_CVPR, author = {Cui, Zijun and Kuang, Chenyi and Gao, Tian and Talamadupula, Kartik and Ji, Qiang}, title = {Biomechanics-Guided Facial Action Unit Detection Through Force Modeling}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8694-8703} }
Equiangular Basis Vectors-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Shen_2023_CVPR, author = {Shen, Yang and Sun, Xuhao and Wei, Xiu-Shen}, title = {Equiangular Basis Vectors}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11755-11765} }
Cross-Guided Optimization of Radiance Fields With Multi-View Image Super-Resolution for High-Resolution Novel View Synthesis-
[pdf]
[supp]
[bibtex]@InProceedings{Yoon_2023_CVPR, author = {Yoon, Youngho and Yoon, Kuk-Jin}, title = {Cross-Guided Optimization of Radiance Fields With Multi-View Image Super-Resolution for High-Resolution Novel View Synthesis}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12428-12438} }
Unified Pose Sequence Modeling-
[pdf]
[bibtex]@InProceedings{Foo_2023_CVPR, author = {Foo, Lin Geng and Li, Tianjiao and Rahmani, Hossein and Ke, Qiuhong and Liu, Jun}, title = {Unified Pose Sequence Modeling}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13019-13030} }
Probability-Based Global Cross-Modal Upsampling for Pansharpening-
[pdf]
[arXiv]
[bibtex]@InProceedings{Zhu_2023_CVPR, author = {Zhu, Zeyu and Cao, Xiangyong and Zhou, Man and Huang, Junhao and Meng, Deyu}, title = {Probability-Based Global Cross-Modal Upsampling for Pansharpening}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14039-14048} }
FAC: 3D Representation Learning via Foreground Aware Feature Contrast-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Liu_2023_CVPR, author = {Liu, Kangcheng and Xiao, Aoran and Zhang, Xiaoqin and Lu, Shijian and Shao, Ling}, title = {FAC: 3D Representation Learning via Foreground Aware Feature Contrast}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9476-9485} }
Improving Visual Representation Learning Through Perceptual Understanding-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Tukra_2023_CVPR, author = {Tukra, Samyakh and Hoffman, Frederick and Chatfield, Ken}, title = {Improving Visual Representation Learning Through Perceptual Understanding}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14486-14495} }
Learning Bottleneck Concepts in Image Classification-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Wang_2023_CVPR, author = {Wang, Bowen and Li, Liangzhi and Nakashima, Yuta and Nagahara, Hajime}, title = {Learning Bottleneck Concepts in Image Classification}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10962-10971} }
Inversion-Based Style Transfer With Diffusion Models-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Zhang_2023_CVPR, author = {Zhang, Yuxin and Huang, Nisha and Tang, Fan and Huang, Haibin and Ma, Chongyang and Dong, Weiming and Xu, Changsheng}, title = {Inversion-Based Style Transfer With Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10146-10156} }
Learning Imbalanced Data With Vision Transformers-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Xu_2023_CVPR, author = {Xu, Zhengzhuo and Liu, Ruikang and Yang, Shuo and Chai, Zenghao and Yuan, Chun}, title = {Learning Imbalanced Data With Vision Transformers}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15793-15803} }
PHA: Patch-Wise High-Frequency Augmentation for Transformer-Based Person Re-Identification-
[pdf]
[bibtex]@InProceedings{Zhang_2023_CVPR, author = {Zhang, Guiwei and Zhang, Yongfei and Zhang, Tianyu and Li, Bo and Pu, Shiliang}, title = {PHA: Patch-Wise High-Frequency Augmentation for Transformer-Based Person Re-Identification}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14133-14142} }
Learning Instance-Level Representation for Large-Scale Multi-Modal Pretraining in E-Commerce-
[pdf]
[supp]
[bibtex]@InProceedings{Jin_2023_CVPR, author = {Jin, Yang and Li, Yongzhi and Yuan, Zehuan and Mu, Yadong}, title = {Learning Instance-Level Representation for Large-Scale Multi-Modal Pretraining in E-Commerce}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11060-11069} }
Conditional Text Image Generation With Diffusion Models-
[pdf]
[bibtex]@InProceedings{Zhu_2023_CVPR, author = {Zhu, Yuanzhi and Li, Zhaohai and Wang, Tianwei and He, Mengchao and Yao, Cong}, title = {Conditional Text Image Generation With Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14235-14245} }
AnchorFormer: Point Cloud Completion From Discriminative Nodes-
[pdf]
[bibtex]@InProceedings{Chen_2023_CVPR, author = {Chen, Zhikai and Long, Fuchen and Qiu, Zhaofan and Yao, Ting and Zhou, Wengang and Luo, Jiebo and Mei, Tao}, title = {AnchorFormer: Point Cloud Completion From Discriminative Nodes}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13581-13590} }
Co-SLAM: Joint Coordinate and Sparse Parametric Encodings for Neural Real-Time SLAM-
[pdf]
[supp]
[bibtex]@InProceedings{Wang_2023_CVPR, author = {Wang, Hengyi and Wang, Jingwen and Agapito, Lourdes}, title = {Co-SLAM: Joint Coordinate and Sparse Parametric Encodings for Neural Real-Time SLAM}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13293-13302} }
Regularization of Polynomial Networks for Image Recognition-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Chrysos_2023_CVPR, author = {Chrysos, Grigorios G. and Wang, Bohan and Deng, Jiankang and Cevher, Volkan}, title = {Regularization of Polynomial Networks for Image Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16123-16132} }
EfficientViT: Memory Efficient Vision Transformer With Cascaded Group Attention-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Liu_2023_CVPR, author = {Liu, Xinyu and Peng, Houwen and Zheng, Ningxin and Yang, Yuqing and Hu, Han and Yuan, Yixuan}, title = {EfficientViT: Memory Efficient Vision Transformer With Cascaded Group Attention}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14420-14430} }
DiffCollage: Parallel Generation of Large Content With Diffusion Models-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Zhang_2023_CVPR, author = {Zhang, Qinsheng and Song, Jiaming and Huang, Xun and Chen, Yongxin and Liu, Ming-Yu}, title = {DiffCollage: Parallel Generation of Large Content With Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10188-10198} }
Efficient Second-Order Plane Adjustment-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Zhou_2023_CVPR, author = {Zhou, Lipu}, title = {Efficient Second-Order Plane Adjustment}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13113-13121} }
Mofusion: A Framework for Denoising-Diffusion-Based Motion Synthesis-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Dabral_2023_CVPR, author = {Dabral, Rishabh and Mughal, Muhammad Hamza and Golyanik, Vladislav and Theobalt, Christian}, title = {Mofusion: A Framework for Denoising-Diffusion-Based Motion Synthesis}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9760-9770} }
PoseFormerV2: Exploring Frequency Domain for Efficient and Robust 3D Human Pose Estimation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Zhao_2023_CVPR, author = {Zhao, Qitao and Zheng, Ce and Liu, Mengyuan and Wang, Pichao and Chen, Chen}, title = {PoseFormerV2: Exploring Frequency Domain for Efficient and Robust 3D Human Pose Estimation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8877-8886} }
Mask3D: Pre-Training 2D Vision Transformers by Learning Masked 3D Priors-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Hou_2023_CVPR, author = {Hou, Ji and Dai, Xiaoliang and He, Zijian and Dai, Angela and Nie{\ss}ner, Matthias}, title = {Mask3D: Pre-Training 2D Vision Transformers by Learning Masked 3D Priors}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13510-13519} }
Physically Adversarial Infrared Patches With Learnable Shapes and Locations-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Wei_2023_CVPR, author = {Wei, Xingxing and Yu, Jie and Huang, Yao}, title = {Physically Adversarial Infrared Patches With Learnable Shapes and Locations}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12334-12342} }
Exemplar-FreeSOLO: Enhancing Unsupervised Instance Segmentation With Exemplars-
[pdf]
[supp]
[bibtex]@InProceedings{Ishtiak_2023_CVPR, author = {Ishtiak, Taoseef and En, Qing and Guo, Yuhong}, title = {Exemplar-FreeSOLO: Enhancing Unsupervised Instance Segmentation With Exemplars}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15424-15433} }
Multimodal Prompting With Missing Modalities for Visual Recognition-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Lee_2023_CVPR, author = {Lee, Yi-Lun and Tsai, Yi-Hsuan and Chiu, Wei-Chen and Lee, Chen-Yu}, title = {Multimodal Prompting With Missing Modalities for Visual Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14943-14952} }
Neural Koopman Pooling: Control-Inspired Temporal Dynamics Encoding for Skeleton-Based Action Recognition-
[pdf]
[supp]
[bibtex]@InProceedings{Wang_2023_CVPR, author = {Wang, Xinghan and Xu, Xin and Mu, Yadong}, title = {Neural Koopman Pooling: Control-Inspired Temporal Dynamics Encoding for Skeleton-Based Action Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10597-10607} }
Blind Image Quality Assessment via Vision-Language Correspondence: A Multitask Learning Perspective-
[pdf]
[arXiv]
[bibtex]@InProceedings{Zhang_2023_CVPR, author = {Zhang, Weixia and Zhai, Guangtao and Wei, Ying and Yang, Xiaokang and Ma, Kede}, title = {Blind Image Quality Assessment via Vision-Language Correspondence: A Multitask Learning Perspective}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14071-14081} }
Integral Neural Networks-
[pdf]
[supp]
[bibtex]@InProceedings{Solodskikh_2023_CVPR, author = {Solodskikh, Kirill and Kurbanov, Azim and Aydarkhanov, Ruslan and Zhelavskaya, Irina and Parfenov, Yury and Song, Dehua and Lefkimmiatis, Stamatios}, title = {Integral Neural Networks}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16113-16122} }
EXCALIBUR: Encouraging and Evaluating Embodied Exploration-
[pdf]
[supp]
[bibtex]@InProceedings{Zhu_2023_CVPR, author = {Zhu, Hao and Kapoor, Raghav and Min, So Yeon and Han, Winson and Li, Jiatai and Geng, Kaiwen and Neubig, Graham and Bisk, Yonatan and Kembhavi, Aniruddha and Weihs, Luca}, title = {EXCALIBUR: Encouraging and Evaluating Embodied Exploration}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14931-14942} }
Visual DNA: Representing and Comparing Images Using Distributions of Neuron Activations-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Ramtoula_2023_CVPR, author = {Ramtoula, Benjamin and Gadd, Matthew and Newman, Paul and De Martini, Daniele}, title = {Visual DNA: Representing and Comparing Images Using Distributions of Neuron Activations}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11113-11123} }
Recognizability Embedding Enhancement for Very Low-Resolution Face Recognition and Quality Estimation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Chai_2023_CVPR, author = {Chai, Jacky Chen Long and Ng, Tiong-Sik and Low, Cheng-Yaw and Park, Jaewoo and Teoh, Andrew Beng Jin}, title = {Recognizability Embedding Enhancement for Very Low-Resolution Face Recognition and Quality Estimation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9957-9967} }
Accelerating Dataset Distillation via Model Augmentation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Zhang_2023_CVPR, author = {Zhang, Lei and Zhang, Jie and Lei, Bowen and Mukherjee, Subhabrata and Pan, Xiang and Zhao, Bo and Ding, Caiwen and Li, Yao and Xu, Dongkuan}, title = {Accelerating Dataset Distillation via Model Augmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11950-11959} }
Frame-Event Alignment and Fusion Network for High Frame Rate Tracking-
[pdf]
[supp]
[bibtex]@InProceedings{Zhang_2023_CVPR, author = {Zhang, Jiqing and Wang, Yuanchen and Liu, Wenxi and Li, Meng and Bai, Jinpeng and Yin, Baocai and Yang, Xin}, title = {Frame-Event Alignment and Fusion Network for High Frame Rate Tracking}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9781-9790} }
Shape-Aware Text-Driven Layered Video Editing-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Lee_2023_CVPR, author = {Lee, Yao-Chih and Jang, Ji-Ze Genevieve and Chen, Yi-Ting and Qiu, Elizabeth and Huang, Jia-Bin}, title = {Shape-Aware Text-Driven Layered Video Editing}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14317-14326} }
Solving Relaxations of MAP-MRF Problems: Combinatorial In-Face Frank-Wolfe Directions-
[pdf]
[arXiv]
[bibtex]@InProceedings{Kolmogorov_2023_CVPR, author = {Kolmogorov, Vladimir}, title = {Solving Relaxations of MAP-MRF Problems: Combinatorial In-Face Frank-Wolfe Directions}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11980-11989} }
MEGANE: Morphable Eyeglass and Avatar Network-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Li_2023_CVPR, author = {Li, Junxuan and Saito, Shunsuke and Simon, Tomas and Lombardi, Stephen and Li, Hongdong and Saragih, Jason}, title = {MEGANE: Morphable Eyeglass and Avatar Network}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12769-12779} }
Enhancing Multiple Reliability Measures via Nuisance-Extended Information Bottleneck-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Jeong_2023_CVPR, author = {Jeong, Jongheon and Yu, Sihyun and Lee, Hankook and Shin, Jinwoo}, title = {Enhancing Multiple Reliability Measures via Nuisance-Extended Information Bottleneck}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16206-16218} }
Rethinking the Approximation Error in 3D Surface Fitting for Point Cloud Normal Estimation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Du_2023_CVPR, author = {Du, Hang and Yan, Xuejun and Wang, Jingjing and Xie, Di and Pu, Shiliang}, title = {Rethinking the Approximation Error in 3D Surface Fitting for Point Cloud Normal Estimation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9486-9495} }
Objaverse: A Universe of Annotated 3D Objects-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Deitke_2023_CVPR, author = {Deitke, Matt and Schwenk, Dustin and Salvador, Jordi and Weihs, Luca and Michel, Oscar and VanderBilt, Eli and Schmidt, Ludwig and Ehsani, Kiana and Kembhavi, Aniruddha and Farhadi, Ali}, title = {Objaverse: A Universe of Annotated 3D Objects}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13142-13153} }
A-Cap: Anticipation Captioning With Commonsense Knowledge-
[pdf]
[supp]
[bibtex]@InProceedings{Vo_2023_CVPR, author = {Vo, Duc Minh and Luong, Quoc-An and Sugimoto, Akihiro and Nakayama, Hideki}, title = {A-Cap: Anticipation Captioning With Commonsense Knowledge}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10824-10833} }
Domain Generalized Stereo Matching via Hierarchical Visual Transformation-
[pdf]
[supp]
[bibtex]@InProceedings{Chang_2023_CVPR, author = {Chang, Tianyu and Yang, Xun and Zhang, Tianzhu and Wang, Meng}, title = {Domain Generalized Stereo Matching via Hierarchical Visual Transformation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9559-9568} }
Adapting Shortcut With Normalizing Flow: An Efficient Tuning Framework for Visual Recognition-
[pdf]
[supp]
[bibtex]@InProceedings{Wang_2023_CVPR, author = {Wang, Yaoming and Shi, Bowen and Zhang, Xiaopeng and Li, Jin and Liu, Yuchen and Dai, Wenrui and Li, Chenglin and Xiong, Hongkai and Tian, Qi}, title = {Adapting Shortcut With Normalizing Flow: An Efficient Tuning Framework for Visual Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15965-15974} }
Unpaired Image-to-Image Translation With Shortest Path Regularization-
[pdf]
[bibtex]@InProceedings{Xie_2023_CVPR, author = {Xie, Shaoan and Xu, Yanwu and Gong, Mingming and Zhang, Kun}, title = {Unpaired Image-to-Image Translation With Shortest Path Regularization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10177-10187} }
MotionDiffuser: Controllable Multi-Agent Motion Prediction Using Diffusion-
[pdf]
[supp]
[bibtex]@InProceedings{Jiang_2023_CVPR, author = {Jiang, Chiyu {\textquotedblleft}Max{\textquotedblright} and Cornman, Andre and Park, Cheolho and Sapp, Benjamin and Zhou, Yin and Anguelov, Dragomir}, title = {MotionDiffuser: Controllable Multi-Agent Motion Prediction Using Diffusion}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9644-9653} }
ConvNeXt V2: Co-Designing and Scaling ConvNets With Masked Autoencoders-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Woo_2023_CVPR, author = {Woo, Sanghyun and Debnath, Shoubhik and Hu, Ronghang and Chen, Xinlei and Liu, Zhuang and Kweon, In So and Xie, Saining}, title = {ConvNeXt V2: Co-Designing and Scaling ConvNets With Masked Autoencoders}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16133-16142} }
Unsupervised Deep Asymmetric Stereo Matching With Spatially-Adaptive Self-Similarity-
[pdf]
[supp]
[bibtex]@InProceedings{Song_2023_CVPR, author = {Song, Taeyong and Kim, Sunok and Sohn, Kwanghoon}, title = {Unsupervised Deep Asymmetric Stereo Matching With Spatially-Adaptive Self-Similarity}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13672-13680} }
TWINS: A Fine-Tuning Framework for Improved Transferability of Adversarial Robustness and Generalization-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Liu_2023_CVPR, author = {Liu, Ziquan and Xu, Yi and Ji, Xiangyang and Chan, Antoni B.}, title = {TWINS: A Fine-Tuning Framework for Improved Transferability of Adversarial Robustness and Generalization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16436-16446} }
Object-Aware Distillation Pyramid for Open-Vocabulary Object Detection-
[pdf]
[arXiv]
[bibtex]@InProceedings{Wang_2023_CVPR, author = {Wang, Luting and Liu, Yi and Du, Penghui and Ding, Zihan and Liao, Yue and Qi, Qiaosong and Chen, Biaolong and Liu, Si}, title = {Object-Aware Distillation Pyramid for Open-Vocabulary Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11186-11196} }
Evolved Part Masking for Self-Supervised Learning-
[pdf]
[supp]
[bibtex]@InProceedings{Feng_2023_CVPR, author = {Feng, Zhanzhou and Zhang, Shiliang}, title = {Evolved Part Masking for Self-Supervised Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10386-10395} }
MV-JAR: Masked Voxel Jigsaw and Reconstruction for LiDAR-Based Self-Supervised Pre-Training-
[pdf]
[supp]
[bibtex]@InProceedings{Xu_2023_CVPR, author = {Xu, Runsen and Wang, Tai and Zhang, Wenwei and Chen, Runjian and Cao, Jinkun and Pang, Jiangmiao and Lin, Dahua}, title = {MV-JAR: Masked Voxel Jigsaw and Reconstruction for LiDAR-Based Self-Supervised Pre-Training}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13445-13454} }
Open-Set Semantic Segmentation for Point Clouds via Adversarial Prototype Framework-
[pdf]
[supp]
[bibtex]@InProceedings{Li_2023_CVPR, author = {Li, Jianan and Dong, Qiulei}, title = {Open-Set Semantic Segmentation for Point Clouds via Adversarial Prototype Framework}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9425-9434} }
Learning Attention As Disentangler for Compositional Zero-Shot Learning-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Hao_2023_CVPR, author = {Hao, Shaozhe and Han, Kai and Wong, Kwan-Yee K.}, title = {Learning Attention As Disentangler for Compositional Zero-Shot Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15315-15324} }
MetaViewer: Towards a Unified Multi-View Representation-
[pdf]
[arXiv]
[bibtex]@InProceedings{Wang_2023_CVPR, author = {Wang, Ren and Sun, Haoliang and Ma, Yuling and Xi, Xiaoming and Yin, Yilong}, title = {MetaViewer: Towards a Unified Multi-View Representation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11590-11599} }
Natural Language-Assisted Sign Language Recognition-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Zuo_2023_CVPR, author = {Zuo, Ronglai and Wei, Fangyun and Mak, Brian}, title = {Natural Language-Assisted Sign Language Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14890-14900} }
Learning Semantic Relationship Among Instances for Image-Text Matching-
[pdf]
[bibtex]@InProceedings{Fu_2023_CVPR, author = {Fu, Zheren and Mao, Zhendong and Song, Yan and Zhang, Yongdong}, title = {Learning Semantic Relationship Among Instances for Image-Text Matching}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15159-15168} }
Global-to-Local Modeling for Video-Based 3D Human Pose and Shape Estimation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Shen_2023_CVPR, author = {Shen, Xiaolong and Yang, Zongxin and Wang, Xiaohan and Ma, Jianxin and Zhou, Chang and Yang, Yi}, title = {Global-to-Local Modeling for Video-Based 3D Human Pose and Shape Estimation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8887-8896} }
BEDLAM: A Synthetic Dataset of Bodies Exhibiting Detailed Lifelike Animated Motion-
[pdf]
[supp]
[bibtex]@InProceedings{Black_2023_CVPR, author = {Black, Michael J. and Patel, Priyanka and Tesch, Joachim and Yang, Jinlong}, title = {BEDLAM: A Synthetic Dataset of Bodies Exhibiting Detailed Lifelike Animated Motion}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8726-8737} }
ProtoCon: Pseudo-Label Refinement via Online Clustering and Prototypical Consistency for Efficient Semi-Supervised Learning-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Nassar_2023_CVPR, author = {Nassar, Islam and Hayat, Munawar and Abbasnejad, Ehsan and Rezatofighi, Hamid and Haffari, Gholamreza}, title = {ProtoCon: Pseudo-Label Refinement via Online Clustering and Prototypical Consistency for Efficient Semi-Supervised Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11641-11650} }
Image Super-Resolution Using T-Tetromino Pixels-
[pdf]
[bibtex]@InProceedings{Grosche_2023_CVPR, author = {Grosche, Simon and Regensky, Andy and Seiler, J\"urgen and Kaup, Andr\'e}, title = {Image Super-Resolution Using T-Tetromino Pixels}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9989-9998} }
GFIE: A Dataset and Baseline for Gaze-Following From 2D to 3D in Indoor Environments-
[pdf]
[supp]
[bibtex]@InProceedings{Hu_2023_CVPR, author = {Hu, Zhengxi and Yang, Yuxue and Zhai, Xiaolin and Yang, Dingye and Zhou, Bohan and Liu, Jingtai}, title = {GFIE: A Dataset and Baseline for Gaze-Following From 2D to 3D in Indoor Environments}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8907-8916} }
BKinD-3D: Self-Supervised 3D Keypoint Discovery From Multi-View Videos-
[pdf]
[supp]
[bibtex]@InProceedings{Sun_2023_CVPR, author = {Sun, Jennifer J. and Karashchuk, Lili and Dravid, Amil and Ryou, Serim and Fereidooni, Sonia and Tuthill, John C. and Katsaggelos, Aggelos and Brunton, Bingni W. and Gkioxari, Georgia and Kennedy, Ann and Yue, Yisong and Perona, Pietro}, title = {BKinD-3D: Self-Supervised 3D Keypoint Discovery From Multi-View Videos}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9001-9010} }
StyleRF: Zero-Shot 3D Style Transfer of Neural Radiance Fields-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Liu_2023_CVPR, author = {Liu, Kunhao and Zhan, Fangneng and Chen, Yiwen and Zhang, Jiahui and Yu, Yingchen and El Saddik, Abdulmotaleb and Lu, Shijian and Xing, Eric P.}, title = {StyleRF: Zero-Shot 3D Style Transfer of Neural Radiance Fields}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8338-8348} }
Accidental Light Probes-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Yu_2023_CVPR, author = {Yu, Hong-Xing and Agarwala, Samir and Herrmann, Charles and Szeliski, Richard and Snavely, Noah and Wu, Jiajun and Sun, Deqing}, title = {Accidental Light Probes}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12521-12530} }
Iterative Vision-and-Language Navigation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Krantz_2023_CVPR, author = {Krantz, Jacob and Banerjee, Shurjo and Zhu, Wang and Corso, Jason and Anderson, Peter and Lee, Stefan and Thomason, Jesse}, title = {Iterative Vision-and-Language Navigation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14921-14930} }
Adversarial Counterfactual Visual Explanations-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Jeanneret_2023_CVPR, author = {Jeanneret, Guillaume and Simon, Lo{\"\i}c and Jurie, Fr\'ed\'eric}, title = {Adversarial Counterfactual Visual Explanations}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16425-16435} }
MaLP: Manipulation Localization Using a Proactive Scheme-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Asnani_2023_CVPR, author = {Asnani, Vishal and Yin, Xi and Hassner, Tal and Liu, Xiaoming}, title = {MaLP: Manipulation Localization Using a Proactive Scheme}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12343-12352} }
MM-Diffusion: Learning Multi-Modal Diffusion Models for Joint Audio and Video Generation-
[pdf]
[supp]
[bibtex]@InProceedings{Ruan_2023_CVPR, author = {Ruan, Ludan and Ma, Yiyang and Yang, Huan and He, Huiguo and Liu, Bei and Fu, Jianlong and Yuan, Nicholas Jing and Jin, Qin and Guo, Baining}, title = {MM-Diffusion: Learning Multi-Modal Diffusion Models for Joint Audio and Video Generation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10219-10228} }
Robust Generalization Against Photon-Limited Corruptions via Worst-Case Sharpness Minimization-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Huang_2023_CVPR, author = {Huang, Zhuo and Zhu, Miaoxi and Xia, Xiaobo and Shen, Li and Yu, Jun and Gong, Chen and Han, Bo and Du, Bo and Liu, Tongliang}, title = {Robust Generalization Against Photon-Limited Corruptions via Worst-Case Sharpness Minimization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16175-16185} }
Point2Pix: Photo-Realistic Point Cloud Rendering via Neural Radiance Fields-
[pdf]
[arXiv]
[bibtex]@InProceedings{Hu_2023_CVPR, author = {Hu, Tao and Xu, Xiaogang and Liu, Shu and Jia, Jiaya}, title = {Point2Pix: Photo-Realistic Point Cloud Rendering via Neural Radiance Fields}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8349-8358} }
NICO++: Towards Better Benchmarking for Domain Generalization-
[pdf]
[supp]
[bibtex]@InProceedings{Zhang_2023_CVPR, author = {Zhang, Xingxuan and He, Yue and Xu, Renzhe and Yu, Han and Shen, Zheyan and Cui, Peng}, title = {NICO++: Towards Better Benchmarking for Domain Generalization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16036-16047} }
CHMATCH: Contrastive Hierarchical Matching and Robust Adaptive Threshold Boosted Semi-Supervised Learning-
[pdf]
[supp]
[bibtex]@InProceedings{Wu_2023_CVPR, author = {Wu, Jianlong and Yang, Haozhe and Gan, Tian and Ding, Ning and Jiang, Feijun and Nie, Liqiang}, title = {CHMATCH: Contrastive Hierarchical Matching and Robust Adaptive Threshold Boosted Semi-Supervised Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15762-15772} }
Neural Dependencies Emerging From Learning Massive Categories-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Feng_2023_CVPR, author = {Feng, Ruili and Zheng, Kecheng and Zhu, Kai and Shen, Yujun and Zhao, Jian and Huang, Yukun and Zhao, Deli and Zhou, Jingren and Jordan, Michael and Zha, Zheng-Jun}, title = {Neural Dependencies Emerging From Learning Massive Categories}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11711-11720} }
ARCTIC: A Dataset for Dexterous Bimanual Hand-Object Manipulation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Fan_2023_CVPR, author = {Fan, Zicong and Taheri, Omid and Tzionas, Dimitrios and Kocabas, Muhammed and Kaufmann, Manuel and Black, Michael J. and Hilliges, Otmar}, title = {ARCTIC: A Dataset for Dexterous Bimanual Hand-Object Manipulation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12943-12954} }
MAGVIT: Masked Generative Video Transformer-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Yu_2023_CVPR, author = {Yu, Lijun and Cheng, Yong and Sohn, Kihyuk and Lezama, Jos\'e and Zhang, Han and Chang, Huiwen and Hauptmann, Alexander G. and Yang, Ming-Hsuan and Hao, Yuan and Essa, Irfan and Jiang, Lu}, title = {MAGVIT: Masked Generative Video Transformer}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10459-10469} }
Hidden Gems: 4D Radar Scene Flow Learning Using Cross-Modal Supervision-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Ding_2023_CVPR, author = {Ding, Fangqiang and Palffy, Andras and Gavrila, Dariu M. and Lu, Chris Xiaoxuan}, title = {Hidden Gems: 4D Radar Scene Flow Learning Using Cross-Modal Supervision}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9340-9349} }
OmniMAE: Single Model Masked Pretraining on Images and Videos-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Girdhar_2023_CVPR, author = {Girdhar, Rohit and El-Nouby, Alaaeldin and Singh, Mannat and Alwala, Kalyan Vasudev and Joulin, Armand and Misra, Ishan}, title = {OmniMAE: Single Model Masked Pretraining on Images and Videos}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10406-10417} }
Real-Time Neural Light Field on Mobile Devices-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Cao_2023_CVPR, author = {Cao, Junli and Wang, Huan and Chemerys, Pavlo and Shakhrai, Vladislav and Hu, Ju and Fu, Yun and Makoviichuk, Denys and Tulyakov, Sergey and Ren, Jian}, title = {Real-Time Neural Light Field on Mobile Devices}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8328-8337} }
End-to-End Video Matting With Trimap Propagation-
[pdf]
[supp]
[bibtex]@InProceedings{Huang_2023_CVPR, author = {Huang, Wei-Lun and Lee, Ming-Sui}, title = {End-to-End Video Matting With Trimap Propagation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14337-14347} }
DropMAE: Masked Autoencoders With Spatial-Attention Dropout for Tracking Tasks-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Wu_2023_CVPR, author = {Wu, Qiangqiang and Yang, Tianyu and Liu, Ziquan and Wu, Baoyuan and Shan, Ying and Chan, Antoni B.}, title = {DropMAE: Masked Autoencoders With Spatial-Attention Dropout for Tracking Tasks}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14561-14571} }
High-Fidelity Clothed Avatar Reconstruction From a Single Image-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Liao_2023_CVPR, author = {Liao, Tingting and Zhang, Xiaomei and Xiu, Yuliang and Yi, Hongwei and Liu, Xudong and Qi, Guo-Jun and Zhang, Yong and Wang, Xuan and Zhu, Xiangyu and Lei, Zhen}, title = {High-Fidelity Clothed Avatar Reconstruction From a Single Image}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8662-8672} }
Zero-Shot Object Counting-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Xu_2023_CVPR, author = {Xu, Jingyi and Le, Hieu and Nguyen, Vu and Ranjan, Viresh and Samaras, Dimitris}, title = {Zero-Shot Object Counting}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15548-15557} }
Implicit Diffusion Models for Continuous Super-Resolution-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Gao_2023_CVPR, author = {Gao, Sicheng and Liu, Xuhui and Zeng, Bohan and Xu, Sheng and Li, Yanjing and Luo, Xiaoyan and Liu, Jianzhuang and Zhen, Xiantong and Zhang, Baochang}, title = {Implicit Diffusion Models for Continuous Super-Resolution}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10021-10030} }
Phase-Shifting Coder: Predicting Accurate Orientation in Oriented Object Detection-
[pdf]
[arXiv]
[bibtex]@InProceedings{Yu_2023_CVPR, author = {Yu, Yi and Da, Feipeng}, title = {Phase-Shifting Coder: Predicting Accurate Orientation in Oriented Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13354-13363} }
Neural Lens Modeling-
[pdf]
[supp]
[bibtex]@InProceedings{Xian_2023_CVPR, author = {Xian, Wenqi and Bo\v{z}i\v{c}, Alja\v{z} and Snavely, Noah and Lassner, Christoph}, title = {Neural Lens Modeling}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8435-8445} }
CoralStyleCLIP: Co-Optimized Region and Layer Selection for Image Editing-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Revanur_2023_CVPR, author = {Revanur, Ambareesh and Basu, Debraj and Agrawal, Shradha and Agarwal, Dhwanit and Pai, Deepak}, title = {CoralStyleCLIP: Co-Optimized Region and Layer Selection for Image Editing}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12695-12704} }
GLeaD: Improving GANs With a Generator-Leading Task-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Bai_2023_CVPR, author = {Bai, Qingyan and Yang, Ceyuan and Xu, Yinghao and Liu, Xihui and Yang, Yujiu and Shen, Yujun}, title = {GLeaD: Improving GANs With a Generator-Leading Task}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12094-12104} }
GALIP: Generative Adversarial CLIPs for Text-to-Image Synthesis-
[pdf]
[arXiv]
[bibtex]@InProceedings{Tao_2023_CVPR, author = {Tao, Ming and Bao, Bing-Kun and Tang, Hao and Xu, Changsheng}, title = {GALIP: Generative Adversarial CLIPs for Text-to-Image Synthesis}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14214-14223} }
Indiscernible Object Counting in Underwater Scenes-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Sun_2023_CVPR, author = {Sun, Guolei and An, Zhaochong and Liu, Yun and Liu, Ce and Sakaridis, Christos and Fan, Deng-Ping and Van Gool, Luc}, title = {Indiscernible Object Counting in Underwater Scenes}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13791-13801} }
Low-Light Image Enhancement via Structure Modeling and Guidance-
[pdf]
[arXiv]
[bibtex]@InProceedings{Xu_2023_CVPR, author = {Xu, Xiaogang and Wang, Ruixing and Lu, Jiangbo}, title = {Low-Light Image Enhancement via Structure Modeling and Guidance}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9893-9903} }
Physics-Driven Diffusion Models for Impact Sound Synthesis From Videos-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Su_2023_CVPR, author = {Su, Kun and Qian, Kaizhi and Shlizerman, Eli and Torralba, Antonio and Gan, Chuang}, title = {Physics-Driven Diffusion Models for Impact Sound Synthesis From Videos}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9749-9759} }
Alias-Free Convnets: Fractional Shift Invariance via Polynomial Activations-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Michaeli_2023_CVPR, author = {Michaeli, Hagay and Michaeli, Tomer and Soudry, Daniel}, title = {Alias-Free Convnets: Fractional Shift Invariance via Polynomial Activations}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16333-16342} }
Shortcomings of Top-Down Randomization-Based Sanity Checks for Evaluations of Deep Neural Network Explanations-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Binder_2023_CVPR, author = {Binder, Alexander and Weber, Leander and Lapuschkin, Sebastian and Montavon, Gr\'egoire and M\"uller, Klaus-Robert and Samek, Wojciech}, title = {Shortcomings of Top-Down Randomization-Based Sanity Checks for Evaluations of Deep Neural Network Explanations}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16143-16152} }
Neural Part Priors: Learning To Optimize Part-Based Object Completion in RGB-D Scans-
[pdf]
[supp]
[bibtex]@InProceedings{Bokhovkin_2023_CVPR, author = {Bokhovkin, Aleksei and Dai, Angela}, title = {Neural Part Priors: Learning To Optimize Part-Based Object Completion in RGB-D Scans}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9032-9042} }
Towards Trustable Skin Cancer Diagnosis via Rewriting Model's Decision-
[pdf]
[supp]
[bibtex]@InProceedings{Yan_2023_CVPR, author = {Yan, Siyuan and Yu, Zhen and Zhang, Xuelin and Mahapatra, Dwarikanath and Chandra, Shekhar S. and Janda, Monika and Soyer, Peter and Ge, Zongyuan}, title = {Towards Trustable Skin Cancer Diagnosis via Rewriting Model's Decision}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11568-11577} }
FeatER: An Efficient Network for Human Reconstruction via Feature Map-Based TransformER-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Zheng_2023_CVPR, author = {Zheng, Ce and Mendieta, Matias and Yang, Taojiannan and Qi, Guo-Jun and Chen, Chen}, title = {FeatER: An Efficient Network for Human Reconstruction via Feature Map-Based TransformER}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13945-13954} }
Visibility Constrained Wide-Band Illumination Spectrum Design for Seeing-in-the-Dark-
[pdf]
[arXiv]
[bibtex]@InProceedings{Niu_2023_CVPR, author = {Niu, Muyao and Li, Zhuoxiao and Zhong, Zhihang and Zheng, Yinqiang}, title = {Visibility Constrained Wide-Band Illumination Spectrum Design for Seeing-in-the-Dark}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13976-13985} }
Learning With Noisy Labels via Self-Supervised Adversarial Noisy Masking-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Tu_2023_CVPR, author = {Tu, Yuanpeng and Zhang, Boshen and Li, Yuxi and Liu, Liang and Li, Jian and Zhang, Jiangning and Wang, Yabiao and Wang, Chengjie and Zhao, Cai Rong}, title = {Learning With Noisy Labels via Self-Supervised Adversarial Noisy Masking}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16186-16195} }
Towards Domain Generalization for Multi-View 3D Object Detection in Bird-Eye-View-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Wang_2023_CVPR, author = {Wang, Shuo and Zhao, Xinhai and Xu, Hai-Ming and Chen, Zehui and Yu, Dameng and Chang, Jiahao and Yang, Zhen and Zhao, Feng}, title = {Towards Domain Generalization for Multi-View 3D Object Detection in Bird-Eye-View}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13333-13342} }
Q: How To Specialize Large Vision-Language Models to Data-Scarce VQA Tasks? A: Self-Train on Unlabeled Images!-
[pdf]
[bibtex]@InProceedings{Khan_2023_CVPR, author = {Khan, Zaid and BG, Vijay Kumar and Schulter, Samuel and Yu, Xiang and Fu, Yun and Chandraker, Manmohan}, title = {Q: How To Specialize Large Vision-Language Models to Data-Scarce VQA Tasks? A: Self-Train on Unlabeled Images!}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15005-15015} }
Improving Robust Generalization by Direct PAC-Bayesian Bound Minimization-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Wang_2023_CVPR, author = {Wang, Zifan and Ding, Nan and Levinboim, Tomer and Chen, Xi and Soricut, Radu}, title = {Improving Robust Generalization by Direct PAC-Bayesian Bound Minimization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16458-16468} }
AssemblyHands: Towards Egocentric Activity Understanding via 3D Hand Pose Estimation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Ohkawa_2023_CVPR, author = {Ohkawa, Takehiko and He, Kun and Sener, Fadime and Hodan, Tomas and Tran, Luan and Keskin, Cem}, title = {AssemblyHands: Towards Egocentric Activity Understanding via 3D Hand Pose Estimation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12999-13008} }
Scene-Aware Egocentric 3D Human Pose Estimation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Wang_2023_CVPR, author = {Wang, Jian and Luvizon, Diogo and Xu, Weipeng and Liu, Lingjie and Sarkar, Kripasindhu and Theobalt, Christian}, title = {Scene-Aware Egocentric 3D Human Pose Estimation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13031-13040} }
NeuralField-LDM: Scene Generation With Hierarchical Latent Diffusion Models-
[pdf]
[supp]
[bibtex]@InProceedings{Kim_2023_CVPR, author = {Kim, Seung Wook and Brown, Bradley and Yin, Kangxue and Kreis, Karsten and Schwarz, Katja and Li, Daiqing and Rombach, Robin and Torralba, Antonio and Fidler, Sanja}, title = {NeuralField-LDM: Scene Generation With Hierarchical Latent Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8496-8506} }
DPF: Learning Dense Prediction Fields With Weak Supervision-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Chen_2023_CVPR, author = {Chen, Xiaoxue and Zheng, Yuhang and Zheng, Yupeng and Zhou, Qiang and Zhao, Hao and Zhou, Guyue and Zhang, Ya-Qin}, title = {DPF: Learning Dense Prediction Fields With Weak Supervision}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15347-15357} }
CNVid-3.5M: Build, Filter, and Pre-Train the Large-Scale Public Chinese Video-Text Dataset-
[pdf]
[supp]
[bibtex]@InProceedings{Gan_2023_CVPR, author = {Gan, Tian and Wang, Qing and Dong, Xingning and Ren, Xiangyuan and Nie, Liqiang and Guo, Qingpei}, title = {CNVid-3.5M: Build, Filter, and Pre-Train the Large-Scale Public Chinese Video-Text Dataset}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14815-14824} }
iQuery: Instruments As Queries for Audio-Visual Sound Separation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Chen_2023_CVPR, author = {Chen, Jiaben and Zhang, Renrui and Lian, Dongze and Yang, Jiaqi and Zeng, Ziyao and Shi, Jianbo}, title = {iQuery: Instruments As Queries for Audio-Visual Sound Separation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14675-14686} }
Sampling Is Matter: Point-Guided 3D Human Mesh Reconstruction-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Kim_2023_CVPR, author = {Kim, Jeonghwan and Gwon, Mi-Gyeong and Park, Hyunwoo and Kwon, Hyukmin and Um, Gi-Mun and Kim, Wonjun}, title = {Sampling Is Matter: Point-Guided 3D Human Mesh Reconstruction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12880-12889} }
Look Around for Anomalies: Weakly-Supervised Anomaly Detection via Context-Motion Relational Learning-
[pdf]
[supp]
[bibtex]@InProceedings{Cho_2023_CVPR, author = {Cho, MyeongAh and Kim, Minjung and Hwang, Sangwon and Park, Chaewon and Lee, Kyungjae and Lee, Sangyoun}, title = {Look Around for Anomalies: Weakly-Supervised Anomaly Detection via Context-Motion Relational Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12137-12146} }
Detecting Everything in the Open World: Towards Universal Object Detection-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Wang_2023_CVPR, author = {Wang, Zhenyu and Li, Yali and Chen, Xi and Lim, Ser-Nam and Torralba, Antonio and Zhao, Hengshuang and Wang, Shengjin}, title = {Detecting Everything in the Open World: Towards Universal Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11433-11443} }
NUWA-LIP: Language-Guided Image Inpainting With Defect-Free VQGAN-
[pdf]
[supp]
[bibtex]@InProceedings{Ni_2023_CVPR, author = {Ni, Minheng and Li, Xiaoming and Zuo, Wangmeng}, title = {NUWA-LIP: Language-Guided Image Inpainting With Defect-Free VQGAN}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14183-14192} }
Language Adaptive Weight Generation for Multi-Task Visual Grounding-
[pdf]
[supp]
[bibtex]@InProceedings{Su_2023_CVPR, author = {Su, Wei and Miao, Peihan and Dou, Huanzhang and Wang, Gaoang and Qiao, Liang and Li, Zheyang and Li, Xi}, title = {Language Adaptive Weight Generation for Multi-Task Visual Grounding}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10857-10866} }
Continuous Intermediate Token Learning With Implicit Motion Manifold for Keyframe Based Motion Interpolation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Mo_2023_CVPR, author = {Mo, Clinton A. and Hu, Kun and Long, Chengjiang and Wang, Zhiyong}, title = {Continuous Intermediate Token Learning With Implicit Motion Manifold for Keyframe Based Motion Interpolation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13894-13903} }
SGLoc: Scene Geometry Encoding for Outdoor LiDAR Localization-
[pdf]
[supp]
[bibtex]@InProceedings{Li_2023_CVPR, author = {Li, Wen and Yu, Shangshu and Wang, Cheng and Hu, Guosheng and Shen, Siqi and Wen, Chenglu}, title = {SGLoc: Scene Geometry Encoding for Outdoor LiDAR Localization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9286-9295} }
Bridging Search Region Interaction With Template for RGB-T Tracking-
[pdf]
[bibtex]@InProceedings{Hui_2023_CVPR, author = {Hui, Tianrui and Xun, Zizheng and Peng, Fengguang and Huang, Junshi and Wei, Xiaoming and Wei, Xiaolin and Dai, Jiao and Han, Jizhong and Liu, Si}, title = {Bridging Search Region Interaction With Template for RGB-T Tracking}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13630-13639} }
Indescribable Multi-Modal Spatial Evaluator-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Kong_2023_CVPR, author = {Kong, Lingke and Qi, X. Sharon and Shen, Qijin and Wang, Jiacheng and Zhang, Jingyi and Hu, Yanle and Zhou, Qichao}, title = {Indescribable Multi-Modal Spatial Evaluator}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9853-9862} }
ImageBind: One Embedding Space To Bind Them All-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Girdhar_2023_CVPR, author = {Girdhar, Rohit and El-Nouby, Alaaeldin and Liu, Zhuang and Singh, Mannat and Alwala, Kalyan Vasudev and Joulin, Armand and Misra, Ishan}, title = {ImageBind: One Embedding Space To Bind Them All}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15180-15190} }
Three Guidelines You Should Know for Universally Slimmable Self-Supervised Learning-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Cao_2023_CVPR, author = {Cao, Yun-Hao and Sun, Peiqin and Zhou, Shuchang}, title = {Three Guidelines You Should Know for Universally Slimmable Self-Supervised Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15742-15751} }
MetaFusion: Infrared and Visible Image Fusion via Meta-Feature Embedding From Object Detection-
[pdf]
[bibtex]@InProceedings{Zhao_2023_CVPR, author = {Zhao, Wenda and Xie, Shigeng and Zhao, Fan and He, You and Lu, Huchuan}, title = {MetaFusion: Infrared and Visible Image Fusion via Meta-Feature Embedding From Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13955-13965} }
End-to-End Vectorized HD-Map Construction With Piecewise Bezier Curve-
[pdf]
[supp]
[bibtex]@InProceedings{Qiao_2023_CVPR, author = {Qiao, Limeng and Ding, Wenjie and Qiu, Xi and Zhang, Chi}, title = {End-to-End Vectorized HD-Map Construction With Piecewise Bezier Curve}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13218-13228} }
On Data Scaling in Masked Image Modeling-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Xie_2023_CVPR, author = {Xie, Zhenda and Zhang, Zheng and Cao, Yue and Lin, Yutong and Wei, Yixuan and Dai, Qi and Hu, Han}, title = {On Data Scaling in Masked Image Modeling}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10365-10374} }
Balanced Energy Regularization Loss for Out-of-Distribution Detection-
[pdf]
[supp]
[bibtex]@InProceedings{Choi_2023_CVPR, author = {Choi, Hyunjun and Jeong, Hawook and Choi, Jin Young}, title = {Balanced Energy Regularization Loss for Out-of-Distribution Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15691-15700} }
3D-Aware Face Swapping-
[pdf]
[supp]
[bibtex]@InProceedings{Li_2023_CVPR, author = {Li, Yixuan and Ma, Chao and Yan, Yichao and Zhu, Wenhan and Yang, Xiaokang}, title = {3D-Aware Face Swapping}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12705-12714} }
Phone2Proc: Bringing Robust Robots Into Our Chaotic World-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Deitke_2023_CVPR, author = {Deitke, Matt and Hendrix, Rose and Farhadi, Ali and Ehsani, Kiana and Kembhavi, Aniruddha}, title = {Phone2Proc: Bringing Robust Robots Into Our Chaotic World}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9665-9675} }
Learning Articulated Shape With Keypoint Pseudo-Labels From Web Images-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Stathopoulos_2023_CVPR, author = {Stathopoulos, Anastasis and Pavlakos, Georgios and Han, Ligong and Metaxas, Dimitris N.}, title = {Learning Articulated Shape With Keypoint Pseudo-Labels From Web Images}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13092-13101} }
Rethinking Image Super Resolution From Long-Tailed Distribution Learning Perspective-
[pdf]
[supp]
[bibtex]@InProceedings{Gou_2023_CVPR, author = {Gou, Yuanbiao and Hu, Peng and Lv, Jiancheng and Zhu, Hongyuan and Peng, Xi}, title = {Rethinking Image Super Resolution From Long-Tailed Distribution Learning Perspective}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14327-14336} }
SCOTCH and SODA: A Transformer Video Shadow Detection Framework-
[pdf]
[arXiv]
[bibtex]@InProceedings{Liu_2023_CVPR, author = {Liu, Lihao and Prost, Jean and Zhu, Lei and Papadakis, Nicolas and Li\`o, Pietro and Sch\"onlieb, Carola-Bibiane and Aviles-Rivero, Angelica I.}, title = {SCOTCH and SODA: A Transformer Video Shadow Detection Framework}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10449-10458} }
CodeTalker: Speech-Driven 3D Facial Animation With Discrete Motion Prior-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Xing_2023_CVPR, author = {Xing, Jinbo and Xia, Menghan and Zhang, Yuechen and Cun, Xiaodong and Wang, Jue and Wong, Tien-Tsin}, title = {CodeTalker: Speech-Driven 3D Facial Animation With Discrete Motion Prior}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12780-12790} }
Improving Zero-Shot Generalization and Robustness of Multi-Modal Models-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Ge_2023_CVPR, author = {Ge, Yunhao and Ren, Jie and Gallagher, Andrew and Wang, Yuxiao and Yang, Ming-Hsuan and Adam, Hartwig and Itti, Laurent and Lakshminarayanan, Balaji and Zhao, Jiaping}, title = {Improving Zero-Shot Generalization and Robustness of Multi-Modal Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11093-11101} }
CODA-Prompt: COntinual Decomposed Attention-Based Prompting for Rehearsal-Free Continual Learning-
[pdf]
[supp]
[bibtex]@InProceedings{Smith_2023_CVPR, author = {Smith, James Seale and Karlinsky, Leonid and Gutta, Vyshnavi and Cascante-Bonilla, Paola and Kim, Donghyun and Arbelle, Assaf and Panda, Rameswar and Feris, Rogerio and Kira, Zsolt}, title = {CODA-Prompt: COntinual Decomposed Attention-Based Prompting for Rehearsal-Free Continual Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11909-11919} }
VideoFusion: Decomposed Diffusion Models for High-Quality Video Generation-
[pdf]
[arXiv]
[bibtex]@InProceedings{Luo_2023_CVPR, author = {Luo, Zhengxiong and Chen, Dayou and Zhang, Yingya and Huang, Yan and Wang, Liang and Shen, Yujun and Zhao, Deli and Zhou, Jingren and Tan, Tieniu}, title = {VideoFusion: Decomposed Diffusion Models for High-Quality Video Generation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10209-10218} }
Real-Time Multi-Person Eyeblink Detection in the Wild for Untrimmed Video-
[pdf]
[arXiv]
[bibtex]@InProceedings{Zeng_2023_CVPR, author = {Zeng, Wenzheng and Xiao, Yang and Wei, Sicheng and Gan, Jinfang and Zhang, Xintao and Cao, Zhiguo and Fang, Zhiwen and Zhou, Joey Tianyi}, title = {Real-Time Multi-Person Eyeblink Detection in the Wild for Untrimmed Video}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13854-13863} }
Category Query Learning for Human-Object Interaction Classification-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Xie_2023_CVPR, author = {Xie, Chi and Zeng, Fangao and Hu, Yue and Liang, Shuang and Wei, Yichen}, title = {Category Query Learning for Human-Object Interaction Classification}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15275-15284} }
MDQE: Mining Discriminative Query Embeddings To Segment Occluded Instances on Challenging Videos-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Li_2023_CVPR, author = {Li, Minghan and Li, Shuai and Xiang, Wangmeng and Zhang, Lei}, title = {MDQE: Mining Discriminative Query Embeddings To Segment Occluded Instances on Challenging Videos}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10524-10533} }
Are We Ready for Vision-Centric Driving Streaming Perception? The ASAP Benchmark-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Wang_2023_CVPR, author = {Wang, Xiaofeng and Zhu, Zheng and Zhang, Yunpeng and Huang, Guan and Ye, Yun and Xu, Wenbo and Chen, Ziwei and Wang, Xingang}, title = {Are We Ready for Vision-Centric Driving Streaming Perception? The ASAP Benchmark}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9600-9610} }
PDPP:Projected Diffusion for Procedure Planning in Instructional Videos-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Wang_2023_CVPR, author = {Wang, Hanlin and Wu, Yilu and Guo, Sheng and Wang, Limin}, title = {PDPP:Projected Diffusion for Procedure Planning in Instructional Videos}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14836-14845} }
Efficient Map Sparsification Based on 2D and 3D Discretized Grids-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Zhang_2023_CVPR, author = {Zhang, Xiaoyu and Liu, Yun-Hui}, title = {Efficient Map Sparsification Based on 2D and 3D Discretized Grids}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12470-12478} }
Class Attention Transfer Based Knowledge Distillation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Guo_2023_CVPR, author = {Guo, Ziyao and Yan, Haonan and Li, Hui and Lin, Xiaodong}, title = {Class Attention Transfer Based Knowledge Distillation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11868-11877} }
Temporally Consistent Online Depth Estimation Using Point-Based Fusion-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Khan_2023_CVPR, author = {Khan, Numair and Penner, Eric and Lanman, Douglas and Xiao, Lei}, title = {Temporally Consistent Online Depth Estimation Using Point-Based Fusion}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9119-9129} }
Generalizable Implicit Neural Representations via Instance Pattern Composers-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Kim_2023_CVPR, author = {Kim, Chiheon and Lee, Doyup and Kim, Saehoon and Cho, Minsu and Han, Wook-Shin}, title = {Generalizable Implicit Neural Representations via Instance Pattern Composers}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11808-11817} }
What Can Human Sketches Do for Object Detection?-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Chowdhury_2023_CVPR, author = {Chowdhury, Pinaki Nath and Bhunia, Ayan Kumar and Sain, Aneeshan and Koley, Subhadeep and Xiang, Tao and Song, Yi-Zhe}, title = {What Can Human Sketches Do for Object Detection?}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15083-15094} }
Identity-Preserving Talking Face Generation With Landmark and Appearance Priors-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Zhong_2023_CVPR, author = {Zhong, Weizhi and Fang, Chaowei and Cai, Yinqi and Wei, Pengxu and Zhao, Gangming and Lin, Liang and Li, Guanbin}, title = {Identity-Preserving Talking Face Generation With Landmark and Appearance Priors}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9729-9738} }
Weakly Supervised Segmentation With Point Annotations for Histopathology Images via Contrast-Based Variational Model-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Zhang_2023_CVPR, author = {Zhang, Hongrun and Burrows, Liam and Meng, Yanda and Sculthorpe, Declan and Mukherjee, Abhik and Coupland, Sarah E. and Chen, Ke and Zheng, Yalin}, title = {Weakly Supervised Segmentation With Point Annotations for Histopathology Images via Contrast-Based Variational Model}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15630-15640} }
Zero-Shot Generative Model Adaptation via Image-Specific Prompt Learning-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Guo_2023_CVPR, author = {Guo, Jiayi and Wang, Chaofei and Wu, You and Zhang, Eric and Wang, Kai and Xu, Xingqian and Shi, Humphrey and Huang, Gao and Song, Shiji}, title = {Zero-Shot Generative Model Adaptation via Image-Specific Prompt Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11494-11503} }
CelebV-Text: A Large-Scale Facial Text-Video Dataset-
[pdf]
[supp]
[bibtex]@InProceedings{Yu_2023_CVPR, author = {Yu, Jianhui and Zhu, Hao and Jiang, Liming and Loy, Chen Change and Cai, Weidong and Wu, Wayne}, title = {CelebV-Text: A Large-Scale Facial Text-Video Dataset}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14805-14814} }
Hard Patches Mining for Masked Image Modeling-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Wang_2023_CVPR, author = {Wang, Haochen and Song, Kaiyou and Fan, Junsong and Wang, Yuxi and Xie, Jin and Zhang, Zhaoxiang}, title = {Hard Patches Mining for Masked Image Modeling}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10375-10385} }
Diffusion-SDF: Text-To-Shape via Voxelized Diffusion-
[pdf]
[supp]
[bibtex]@InProceedings{Li_2023_CVPR, author = {Li, Muheng and Duan, Yueqi and Zhou, Jie and Lu, Jiwen}, title = {Diffusion-SDF: Text-To-Shape via Voxelized Diffusion}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12642-12651} }
Compositor: Bottom-Up Clustering and Compositing for Robust Part and Object Segmentation-
[pdf]
[bibtex]@InProceedings{He_2023_CVPR, author = {He, Ju and Chen, Jieneng and Lin, Ming-Xian and Yu, Qihang and Yuille, Alan L.}, title = {Compositor: Bottom-Up Clustering and Compositing for Robust Part and Object Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11259-11268} }
Boundary-Aware Backward-Compatible Representation via Adversarial Learning in Image Retrieval-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Pan_2023_CVPR, author = {Pan, Tan and Xu, Furong and Yang, Xudong and He, Sifeng and Jiang, Chen and Guo, Qingpei and Qian, Feng and Zhang, Xiaobo and Cheng, Yuan and Yang, Lei and Chu, Wei}, title = {Boundary-Aware Backward-Compatible Representation via Adversarial Learning in Image Retrieval}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15201-15210} }
Super-CLEVR: A Virtual Benchmark To Diagnose Domain Robustness in Visual Reasoning-
[pdf]
[supp]
[bibtex]@InProceedings{Li_2023_CVPR, author = {Li, Zhuowan and Wang, Xingrui and Stengel-Eskin, Elias and Kortylewski, Adam and Ma, Wufei and Van Durme, Benjamin and Yuille, Alan L.}, title = {Super-CLEVR: A Virtual Benchmark To Diagnose Domain Robustness in Visual Reasoning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14963-14973} }
Sliced Optimal Partial Transport-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Bai_2023_CVPR, author = {Bai, Yikun and Schmitzer, Bernhard and Thorpe, Matthew and Kolouri, Soheil}, title = {Sliced Optimal Partial Transport}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13681-13690} }
Siamese DETR-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Huang_2023_CVPR, author = {Huang, Gengshi and Li, Wei and Teng, Jianing and Wang, Kun and Chen, Zeren and Shao, Jing and Loy, Chen Change and Sheng, Lu}, title = {Siamese DETR}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15722-15731} }
Turning Strengths Into Weaknesses: A Certified Robustness Inspired Attack Framework Against Graph Neural Networks-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Wang_2023_CVPR, author = {Wang, Binghui and Pang, Meng and Dong, Yun}, title = {Turning Strengths Into Weaknesses: A Certified Robustness Inspired Attack Framework Against Graph Neural Networks}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16394-16403} }
Demystifying Causal Features on Adversarial Examples and Causal Inoculation for Robust Network by Adversarial Instrumental Variable Regression-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Kim_2023_CVPR, author = {Kim, Junho and Lee, Byung-Kwan and Ro, Yong Man}, title = {Demystifying Causal Features on Adversarial Examples and Causal Inoculation for Robust Network by Adversarial Instrumental Variable Regression}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12302-12312} }
B-Spline Texture Coefficients Estimator for Screen Content Image Super-Resolution-
[pdf]
[supp]
[bibtex]@InProceedings{Pak_2023_CVPR, author = {Pak, Byeonghyun and Lee, Jaewon and Jin, Kyong Hwan}, title = {B-Spline Texture Coefficients Estimator for Screen Content Image Super-Resolution}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10062-10071} }
Domain Expansion of Image Generators-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Nitzan_2023_CVPR, author = {Nitzan, Yotam and Gharbi, Micha\"el and Zhang, Richard and Park, Taesung and Zhu, Jun-Yan and Cohen-Or, Daniel and Shechtman, Eli}, title = {Domain Expansion of Image Generators}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15933-15942} }
LVQAC: Lattice Vector Quantization Coupled With Spatially Adaptive Companding for Efficient Learned Image Compression-
[pdf]
[arXiv]
[bibtex]@InProceedings{Zhang_2023_CVPR, author = {Zhang, Xi and Wu, Xiaolin}, title = {LVQAC: Lattice Vector Quantization Coupled With Spatially Adaptive Companding for Efficient Learned Image Compression}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10239-10248} }
Fine-Grained Face Swapping via Regional GAN Inversion-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Liu_2023_CVPR, author = {Liu, Zhian and Li, Maomao and Zhang, Yong and Wang, Cairong and Zhang, Qi and Wang, Jue and Nie, Yongwei}, title = {Fine-Grained Face Swapping via Regional GAN Inversion}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8578-8587} }
Taming Diffusion Models for Audio-Driven Co-Speech Gesture Generation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Zhu_2023_CVPR, author = {Zhu, Lingting and Liu, Xian and Liu, Xuanyu and Qian, Rui and Liu, Ziwei and Yu, Lequan}, title = {Taming Diffusion Models for Audio-Driven Co-Speech Gesture Generation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10544-10553} }
NeRFLix: High-Quality Neural View Synthesis by Learning a Degradation-Driven Inter-Viewpoint MiXer-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Zhou_2023_CVPR, author = {Zhou, Kun and Li, Wenbo and Wang, Yi and Hu, Tao and Jiang, Nianjuan and Han, Xiaoguang and Lu, Jiangbo}, title = {NeRFLix: High-Quality Neural View Synthesis by Learning a Degradation-Driven Inter-Viewpoint MiXer}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12363-12374} }
STMixer: A One-Stage Sparse Action Detector-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Wu_2023_CVPR, author = {Wu, Tao and Cao, Mengqi and Gao, Ziteng and Wu, Gangshan and Wang, Limin}, title = {STMixer: A One-Stage Sparse Action Detector}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14720-14729} }
Genie: Show Me the Data for Quantization-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Jeon_2023_CVPR, author = {Jeon, Yongkweon and Lee, Chungman and Kim, Ho-young}, title = {Genie: Show Me the Data for Quantization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12064-12073} }
Multi-Agent Automated Machine Learning-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Wang_2023_CVPR, author = {Wang, Zhaozhi and Su, Kefan and Zhang, Jian and Jia, Huizhu and Ye, Qixiang and Xie, Xiaodong and Lu, Zongqing}, title = {Multi-Agent Automated Machine Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11960-11969} }
Robot Structure Prior Guided Temporal Attention for Camera-to-Robot Pose Estimation From Image Sequence-
[pdf]
[bibtex]@InProceedings{Tian_2023_CVPR, author = {Tian, Yang and Zhang, Jiyao and Yin, Zekai and Dong, Hao}, title = {Robot Structure Prior Guided Temporal Attention for Camera-to-Robot Pose Estimation From Image Sequence}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8917-8926} }
HRDFuse: Monocular 360deg Depth Estimation by Collaboratively Learning Holistic-With-Regional Depth Distributions-
[pdf]
[supp]
[bibtex]@InProceedings{Ai_2023_CVPR, author = {Ai, Hao and Cao, Zidong and Cao, Yan-Pei and Shan, Ying and Wang, Lin}, title = {HRDFuse: Monocular 360deg Depth Estimation by Collaboratively Learning Holistic-With-Regional Depth Distributions}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13273-13282} }
StructVPR: Distill Structural Knowledge With Weighting Samples for Visual Place Recognition-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Shen_2023_CVPR, author = {Shen, Yanqing and Zhou, Sanping and Fu, Jingwen and Wang, Ruotong and Chen, Shitao and Zheng, Nanning}, title = {StructVPR: Distill Structural Knowledge With Weighting Samples for Visual Place Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11217-11226} }
Learning Human-to-Robot Handovers From Point Clouds-
[pdf]
[supp]
[bibtex]@InProceedings{Christen_2023_CVPR, author = {Christen, Sammy and Yang, Wei and P\'erez-D{\textquoteright}Arpino, Claudia and Hilliges, Otmar and Fox, Dieter and Chao, Yu-Wei}, title = {Learning Human-to-Robot Handovers From Point Clouds}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9654-9664} }
Score Jacobian Chaining: Lifting Pretrained 2D Diffusion Models for 3D Generation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Wang_2023_CVPR, author = {Wang, Haochen and Du, Xiaodan and Li, Jiahao and Yeh, Raymond A. and Shakhnarovich, Greg}, title = {Score Jacobian Chaining: Lifting Pretrained 2D Diffusion Models for 3D Generation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12619-12629} }
Role of Transients in Two-Bounce Non-Line-of-Sight Imaging-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Somasundaram_2023_CVPR, author = {Somasundaram, Siddharth and Dave, Akshat and Henley, Connor and Veeraraghavan, Ashok and Raskar, Ramesh}, title = {Role of Transients in Two-Bounce Non-Line-of-Sight Imaging}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9192-9201} }
Elastic Aggregation for Federated Optimization-
[pdf]
[supp]
[bibtex]@InProceedings{Chen_2023_CVPR, author = {Chen, Dengsheng and Hu, Jie and Tan, Vince Junkai and Wei, Xiaoming and Wu, Enhua}, title = {Elastic Aggregation for Federated Optimization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12187-12197} }
ObjectMatch: Robust Registration Using Canonical Object Correspondences-
[pdf]
[supp]
[bibtex]@InProceedings{Gumeli_2023_CVPR, author = {G\"umeli, Can and Dai, Angela and Nie{\ss}ner, Matthias}, title = {ObjectMatch: Robust Registration Using Canonical Object Correspondences}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13082-13091} }
Center Focusing Network for Real-Time LiDAR Panoptic Segmentation-
[pdf]
[supp]
[bibtex]@InProceedings{Li_2023_CVPR, author = {Li, Xiaoyan and Zhang, Gang and Wang, Boyue and Hu, Yongli and Yin, Baocai}, title = {Center Focusing Network for Real-Time LiDAR Panoptic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13425-13434} }
Restoration of Hand-Drawn Architectural Drawings Using Latent Space Mapping With Degradation Generator-
[pdf]
[supp]
[bibtex]@InProceedings{Choi_2023_CVPR, author = {Choi, Nakkwan and Lee, Seungjae and Lee, Yongsik and Yang, Seungjoon}, title = {Restoration of Hand-Drawn Architectural Drawings Using Latent Space Mapping With Degradation Generator}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14164-14172} }
Few-Shot Class-Incremental Learning via Class-Aware Bilateral Distillation-
[pdf]
[supp]
[bibtex]@InProceedings{Zhao_2023_CVPR, author = {Zhao, Linglan and Lu, Jing and Xu, Yunlu and Cheng, Zhanzhan and Guo, Dashan and Niu, Yi and Fang, Xiangzhong}, title = {Few-Shot Class-Incremental Learning via Class-Aware Bilateral Distillation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11838-11847} }
Learning To Dub Movies via Hierarchical Prosody Models-
[pdf]
[arXiv]
[bibtex]@InProceedings{Cong_2023_CVPR, author = {Cong, Gaoxiang and Li, Liang and Qi, Yuankai and Zha, Zheng-Jun and Wu, Qi and Wang, Wenyu and Jiang, Bin and Yang, Ming-Hsuan and Huang, Qingming}, title = {Learning To Dub Movies via Hierarchical Prosody Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14687-14697} }
DiffusionRig: Learning Personalized Priors for Facial Appearance Editing-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Ding_2023_CVPR, author = {Ding, Zheng and Zhang, Xuaner and Xia, Zhihao and Jebe, Lars and Tu, Zhuowen and Zhang, Xiuming}, title = {DiffusionRig: Learning Personalized Priors for Facial Appearance Editing}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12736-12746} }
Delving StyleGAN Inversion for Image Editing: A Foundation Latent Space Viewpoint-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Liu_2023_CVPR, author = {Liu, Hongyu and Song, Yibing and Chen, Qifeng}, title = {Delving StyleGAN Inversion for Image Editing: A Foundation Latent Space Viewpoint}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10072-10082} }
Enlarging Instance-Specific and Class-Specific Information for Open-Set Action Recognition-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Cen_2023_CVPR, author = {Cen, Jun and Zhang, Shiwei and Wang, Xiang and Pei, Yixuan and Qing, Zhiwu and Zhang, Yingya and Chen, Qifeng}, title = {Enlarging Instance-Specific and Class-Specific Information for Open-Set Action Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15295-15304} }
Decoupled Semantic Prototypes Enable Learning From Diverse Annotation Types for Semi-Weakly Segmentation in Expert-Driven Domains-
[pdf]
[supp]
[bibtex]@InProceedings{Reiss_2023_CVPR, author = {Rei{\ss}, Simon and Seibold, Constantin and Freytag, Alexander and Rodner, Erik and Stiefelhagen, Rainer}, title = {Decoupled Semantic Prototypes Enable Learning From Diverse Annotation Types for Semi-Weakly Segmentation in Expert-Driven Domains}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15495-15506} }
Iterative Next Boundary Detection for Instance Segmentation of Tree Rings in Microscopy Images of Shrub Cross Sections-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Gillert_2023_CVPR, author = {Gillert, Alexander and Resente, Giulia and Anadon-Rosell, Alba and Wilmking, Martin and von Lukas, Uwe Freiherr}, title = {Iterative Next Boundary Detection for Instance Segmentation of Tree Rings in Microscopy Images of Shrub Cross Sections}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14540-14548} }
Learning and Aggregating Lane Graphs for Urban Automated Driving-
[pdf]
[supp]
[bibtex]@InProceedings{Buchner_2023_CVPR, author = {B\"uchner, Martin and Z\"urn, Jannik and Todoran, Ion-George and Valada, Abhinav and Burgard, Wolfram}, title = {Learning and Aggregating Lane Graphs for Urban Automated Driving}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13415-13424} }
Universal Instance Perception As Object Discovery and Retrieval-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Yan_2023_CVPR, author = {Yan, Bin and Jiang, Yi and Wu, Jiannan and Wang, Dong and Luo, Ping and Yuan, Zehuan and Lu, Huchuan}, title = {Universal Instance Perception As Object Discovery and Retrieval}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15325-15336} }
Transferable Adversarial Attacks on Vision Transformers With Token Gradient Regularization-
[pdf]
[arXiv]
[bibtex]@InProceedings{Zhang_2023_CVPR, author = {Zhang, Jianping and Huang, Yizhan and Wu, Weibin and Lyu, Michael R.}, title = {Transferable Adversarial Attacks on Vision Transformers With Token Gradient Regularization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16415-16424} }
MCF: Mutual Correction Framework for Semi-Supervised Medical Image Segmentation-
[pdf]
[bibtex]@InProceedings{Wang_2023_CVPR, author = {Wang, Yongchao and Xiao, Bin and Bi, Xiuli and Li, Weisheng and Gao, Xinbo}, title = {MCF: Mutual Correction Framework for Semi-Supervised Medical Image Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15651-15660} }
Parametric Implicit Face Representation for Audio-Driven Facial Reenactment-
[pdf]
[supp]
[bibtex]@InProceedings{Huang_2023_CVPR, author = {Huang, Ricong and Lai, Peiwen and Qin, Yipeng and Li, Guanbin}, title = {Parametric Implicit Face Representation for Audio-Driven Facial Reenactment}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12759-12768} }
VILA: Learning Image Aesthetics From User Comments With Vision-Language Pretraining-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Ke_2023_CVPR, author = {Ke, Junjie and Ye, Keren and Yu, Jiahui and Wu, Yonghui and Milanfar, Peyman and Yang, Feng}, title = {VILA: Learning Image Aesthetics From User Comments With Vision-Language Pretraining}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10041-10051} }
Procedure-Aware Pretraining for Instructional Video Understanding-
[pdf]
[supp]
[bibtex]@InProceedings{Zhou_2023_CVPR, author = {Zhou, Honglu and Mart{\'\i}n-Mart{\'\i}n, Roberto and Kapadia, Mubbasir and Savarese, Silvio and Niebles, Juan Carlos}, title = {Procedure-Aware Pretraining for Instructional Video Understanding}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10727-10738} }
Fine-Grained Audible Video Description-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Shen_2023_CVPR, author = {Shen, Xuyang and Li, Dong and Zhou, Jinxing and Qin, Zhen and He, Bowen and Han, Xiaodong and Li, Aixuan and Dai, Yuchao and Kong, Lingpeng and Wang, Meng and Qiao, Yu and Zhong, Yiran}, title = {Fine-Grained Audible Video Description}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10585-10596} }
3D Semantic Segmentation in the Wild: Learning Generalized Models for Adverse-Condition Point Clouds-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Xiao_2023_CVPR, author = {Xiao, Aoran and Huang, Jiaxing and Xuan, Weihao and Ren, Ruijie and Liu, Kangcheng and Guan, Dayan and El Saddik, Abdulmotaleb and Lu, Shijian and Xing, Eric P.}, title = {3D Semantic Segmentation in the Wild: Learning Generalized Models for Adverse-Condition Point Clouds}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9382-9392} }
RaBit: Parametric Modeling of 3D Biped Cartoon Characters With a Topological-Consistent Dataset-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Luo_2023_CVPR, author = {Luo, Zhongjin and Cai, Shengcai and Dong, Jinguo and Ming, Ruibo and Qiu, Liangdong and Zhan, Xiaohang and Han, Xiaoguang}, title = {RaBit: Parametric Modeling of 3D Biped Cartoon Characters With a Topological-Consistent Dataset}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12825-12835} }
Uni3D: A Unified Baseline for Multi-Dataset 3D Object Detection-
[pdf]
[arXiv]
[bibtex]@InProceedings{Zhang_2023_CVPR, author = {Zhang, Bo and Yuan, Jiakang and Shi, Botian and Chen, Tao and Li, Yikang and Qiao, Yu}, title = {Uni3D: A Unified Baseline for Multi-Dataset 3D Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9253-9262} }
ACR: Attention Collaboration-Based Regressor for Arbitrary Two-Hand Reconstruction-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Yu_2023_CVPR, author = {Yu, Zhengdi and Huang, Shaoli and Fang, Chen and Breckon, Toby P. and Wang, Jue}, title = {ACR: Attention Collaboration-Based Regressor for Arbitrary Two-Hand Reconstruction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12955-12964} }
Improving Table Structure Recognition With Visual-Alignment Sequential Coordinate Modeling-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Huang_2023_CVPR, author = {Huang, Yongshuai and Lu, Ning and Chen, Dapeng and Li, Yibo and Xie, Zecheng and Zhu, Shenggao and Gao, Liangcai and Peng, Wei}, title = {Improving Table Structure Recognition With Visual-Alignment Sequential Coordinate Modeling}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11134-11143} }
HumanGen: Generating Human Radiance Fields With Explicit Priors-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Jiang_2023_CVPR, author = {Jiang, Suyi and Jiang, Haoran and Wang, Ziyu and Luo, Haimin and Chen, Wenzheng and Xu, Lan}, title = {HumanGen: Generating Human Radiance Fields With Explicit Priors}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {12543-12554} }
Local Connectivity-Based Density Estimation for Face Clustering-
[pdf]
[supp]
[bibtex]@InProceedings{Shin_2023_CVPR, author = {Shin, Junho and Lee, Hyo-Jun and Kim, Hyunseop and Baek, Jong-Hyeon and Kim, Daehyun and Koh, Yeong Jun}, title = {Local Connectivity-Based Density Estimation for Face Clustering}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13621-13629} }
Adaptive Zone-Aware Hierarchical Planner for Vision-Language Navigation-
[pdf]
[bibtex]@InProceedings{Gao_2023_CVPR, author = {Gao, Chen and Peng, Xingyu and Yan, Mi and Wang, He and Yang, Lirong and Ren, Haibing and Li, Hongsheng and Liu, Si}, title = {Adaptive Zone-Aware Hierarchical Planner for Vision-Language Navigation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14911-14920} }
Memory-Friendly Scalable Super-Resolution via Rewinding Lottery Ticket Hypothesis-
[pdf]
[supp]
[bibtex]@InProceedings{Lin_2023_CVPR, author = {Lin, Jin and Luo, Xiaotong and Hong, Ming and Qu, Yanyun and Xie, Yuan and Wu, Zongze}, title = {Memory-Friendly Scalable Super-Resolution via Rewinding Lottery Ticket Hypothesis}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {14398-14407} }
Therbligs in Action: Video Understanding Through Motion Primitives-
[pdf]
[bibtex]@InProceedings{Dessalene_2023_CVPR, author = {Dessalene, Eadom and Maynord, Michael and Ferm\"uller, Cornelia and Aloimonos, Yiannis}, title = {Therbligs in Action: Video Understanding Through Motion Primitives}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10618-10626} }
SadTalker: Learning Realistic 3D Motion Coefficients for Stylized Audio-Driven Single Image Talking Face Animation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Zhang_2023_CVPR, author = {Zhang, Wenxuan and Cun, Xiaodong and Wang, Xuan and Zhang, Yong and Shen, Xi and Guo, Yu and Shan, Ying and Wang, Fei}, title = {SadTalker: Learning Realistic 3D Motion Coefficients for Stylized Audio-Driven Single Image Talking Face Animation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8652-8661} }
HAAV: Hierarchical Aggregation of Augmented Views for Image Captioning-
[pdf]
[supp]
[bibtex]@InProceedings{Kuo_2023_CVPR, author = {Kuo, Chia-Wen and Kira, Zsolt}, title = {HAAV: Hierarchical Aggregation of Augmented Views for Image Captioning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11039-11049} }
Learning Sample Relationship for Exposure Correction-
[pdf]
[bibtex]@InProceedings{Huang_2023_CVPR, author = {Huang, Jie and Zhao, Feng and Zhou, Man and Xiao, Jie and Zheng, Naishan and Zheng, Kaiwen and Xiong, Zhiwei}, title = {Learning Sample Relationship for Exposure Correction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9904-9913} }
TRACE: 5D Temporal Regression of Avatars With Dynamic Cameras in 3D Environments-
[pdf]
[supp]
[bibtex]@InProceedings{Sun_2023_CVPR, author = {Sun, Yu and Bao, Qian and Liu, Wu and Mei, Tao and Black, Michael J.}, title = {TRACE: 5D Temporal Regression of Avatars With Dynamic Cameras in 3D Environments}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8856-8866} }
End-to-End 3D Dense Captioning With Vote2Cap-DETR-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Chen_2023_CVPR, author = {Chen, Sijin and Zhu, Hongyuan and Chen, Xin and Lei, Yinjie and Yu, Gang and Chen, Tao}, title = {End-to-End 3D Dense Captioning With Vote2Cap-DETR}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11124-11133} }
Learned Two-Plane Perspective Prior Based Image Resampling for Efficient Object Detection-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Ghosh_2023_CVPR, author = {Ghosh, Anurag and Reddy, N. Dinesh and Mertz, Christoph and Narasimhan, Srinivasa G.}, title = {Learned Two-Plane Perspective Prior Based Image Resampling for Efficient Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13364-13373} }
Tell Me What Happened: Unifying Text-Guided Video Completion via Multimodal Masked Video Generation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Fu_2023_CVPR, author = {Fu, Tsu-Jui and Yu, Licheng and Zhang, Ning and Fu, Cheng-Yang and Su, Jong-Chyi and Wang, William Yang and Bell, Sean}, title = {Tell Me What Happened: Unifying Text-Guided Video Completion via Multimodal Masked Video Generation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10681-10692} }
Tracking Through Containers and Occluders in the Wild-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Van_Hoorick_2023_CVPR, author = {Van Hoorick, Basile and Tokmakov, Pavel and Stent, Simon and Li, Jie and Vondrick, Carl}, title = {Tracking Through Containers and Occluders in the Wild}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13802-13812} }
Decompose, Adjust, Compose: Effective Normalization by Playing With Frequency for Domain Generalization-
[pdf]
[arXiv]
[bibtex]@InProceedings{Lee_2023_CVPR, author = {Lee, Sangrok and Bae, Jongseong and Kim, Ha Young}, title = {Decompose, Adjust, Compose: Effective Normalization by Playing With Frequency for Domain Generalization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11776-11785} }
Novel Class Discovery for 3D Point Cloud Semantic Segmentation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Riz_2023_CVPR, author = {Riz, Luigi and Saltori, Cristiano and Ricci, Elisa and Poiesi, Fabio}, title = {Novel Class Discovery for 3D Point Cloud Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9393-9402} }
Learning 3D-Aware Image Synthesis With Unknown Pose Distribution-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Shi_2023_CVPR, author = {Shi, Zifan and Shen, Yujun and Xu, Yinghao and Peng, Sida and Liao, Yiyi and Guo, Sheng and Chen, Qifeng and Yeung, Dit-Yan}, title = {Learning 3D-Aware Image Synthesis With Unknown Pose Distribution}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13062-13071} }
Train-Once-for-All Personalization-
[pdf]
[supp]
[bibtex]@InProceedings{Chen_2023_CVPR, author = {Chen, Hong-You and Li, Yandong and Cui, Yin and Zhang, Mingda and Chao, Wei-Lun and Zhang, Li}, title = {Train-Once-for-All Personalization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {11818-11827} }
DIFu: Depth-Guided Implicit Function for Clothed Human Reconstruction-
[pdf]
[supp]
[bibtex]@InProceedings{Song_2023_CVPR, author = {Song, Dae-Young and Lee, HeeKyung and Seo, Jeongil and Cho, Donghyeon}, title = {DIFu: Depth-Guided Implicit Function for Clothed Human Reconstruction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8738-8747} }
Bi-LRFusion: Bi-Directional LiDAR-Radar Fusion for 3D Dynamic Object Detection-
[pdf]
[supp]
[bibtex]@InProceedings{Wang_2023_CVPR, author = {Wang, Yingjie and Deng, Jiajun and Li, Yao and Hu, Jinshui and Liu, Cong and Zhang, Yu and Ji, Jianmin and Ouyang, Wanli and Zhang, Yanyong}, title = {Bi-LRFusion: Bi-Directional LiDAR-Radar Fusion for 3D Dynamic Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13394-13403} }
LOCATE: Localize and Transfer Object Parts for Weakly Supervised Affordance Grounding-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Li_2023_CVPR, author = {Li, Gen and Jampani, Varun and Sun, Deqing and Sevilla-Lara, Laura}, title = {LOCATE: Localize and Transfer Object Parts for Weakly Supervised Affordance Grounding}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10922-10931} }
TokenHPE: Learning Orientation Tokens for Efficient Head Pose Estimation via Transformers-
[pdf]
[supp]
[bibtex]@InProceedings{Zhang_2023_CVPR, author = {Zhang, Cheng and Liu, Hai and Deng, Yongjian and Xie, Bochen and Li, Youfu}, title = {TokenHPE: Learning Orientation Tokens for Efficient Head Pose Estimation via Transformers}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {8897-8906} }
BioNet: A Biologically-Inspired Network for Face Recognition-
[pdf]
[supp]
[bibtex]@InProceedings{Li_2023_CVPR, author = {Li, Pengyu}, title = {BioNet: A Biologically-Inspired Network for Face Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10344-10354} }
Scaling Up GANs for Text-to-Image Synthesis-
[pdf]
[arXiv]
[bibtex]@InProceedings{Kang_2023_CVPR, author = {Kang, Minguk and Zhu, Jun-Yan and Zhang, Richard and Park, Jaesik and Shechtman, Eli and Paris, Sylvain and Park, Taesung}, title = {Scaling Up GANs for Text-to-Image Synthesis}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {10124-10134} }
DepGraph: Towards Any Structural Pruning-
[pdf]
[arXiv]
[bibtex]@InProceedings{Fang_2023_CVPR, author = {Fang, Gongfan and Ma, Xinyin and Song, Mingli and Mi, Michael Bi and Wang, Xinchao}, title = {DepGraph: Towards Any Structural Pruning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {16091-16101} }
Exploring Discontinuity for Video Frame Interpolation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Lee_2023_CVPR, author = {Lee, Sangjin and Lee, Hyeongmin and Shin, Chajin and Son, Hanbin and Lee, Sangyoun}, title = {Exploring Discontinuity for Video Frame Interpolation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9791-9800} }
DynamicStereo: Consistent Dynamic Depth From Stereo Videos-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Karaev_2023_CVPR, author = {Karaev, Nikita and Rocco, Ignacio and Graham, Benjamin and Neverova, Natalia and Vedaldi, Andrea and Rupprecht, Christian}, title = {DynamicStereo: Consistent Dynamic Depth From Stereo Videos}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {13229-13239} }
Vid2Avatar: 3D Avatar Reconstruction From Videos in the Wild via Self-Supervised Scene Decomposition-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Guo_2023_CVPR, author = {Guo, Chen and Jiang, Tianjian and Chen, Xu and Song, Jie and Hilliges, Otmar}, title = {Vid2Avatar: 3D Avatar Reconstruction From Videos in the Wild via Self-Supervised Scene Decomposition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year