个人简历

教育经历\r
1999年09月-2002年12月 清华大学计算机科学与技术系，人机交互及媒体集成研究所，博士\r
1997年03月-1999年07月 清华大学计算机科学与技术系，人机交互及媒体集成研究所，硕士\r
\r
工作经历\r
2015年01月-02月，美国西北大学EECS访问（Prof.Ying Wu）；\r
2014年07月-08月，美国卡耐基梅陇大学计算机学院访问(Prof.Eric Xing)；\r
2021年12月-今，清华大学深圳国际研究生院信息学部，教授；\r
2011年06月-今，清华大学深圳研究生院信息学部，博士生导师；\r
2006年12月-今，清华大学深圳研究生院信息学部，副研究员；\r
2005年05月-2006年11月，清华大学深圳研究生院信息学部，讲师；\r
2003年03月-2004年12月，法国国家信息和自动化研究所（Paris, INRIA）；\r
2002年02月-2002年09月，微软亚洲研究院互联网多媒体组实习；\r
\r
学术兼职\r
2013.4-2014，中国计算机学会CCF青年计算机科技论坛YOCSEF，深圳分论坛主席；\r
2021年09月-今，中国计算机学会CCF，杰出会员；\r
2019年06月-今，鹏城国家实验室，双聘副研究员；\r
2021年07月-今，中国计算机学会CCF 深圳分会，监事；\r
2005年06月-今，中国计算机学会多媒体专委会，执行委员；\r
2019年04月-今，IEEE国际电子电气工程师学会，高级会员；\r
2020年07月-今，CVPR2021/2022，程序委员；\r
2021年07月-今，AAAI2022，程序委员；\r
2020年10月-今，JCAI2021/2022，程序委员/特殊委员SPC；\r
2021年05月-今，BMVC2021，程序委员；\r
2020年08月-今，WACV2020/2021，程序委员；\r
2018年03月-2020，ACMMM2018/2019，程序委员；

研究领域

"机器学习：迁移学习，自监督学习，鲁棒学习，半监督学习，图网络\r
计算机视觉：图像和视频实例分割，目标检测和跟踪，视频内容预测及生成\r
图像和视频内容理解：视觉问答，图像和视频的自然语言描述\r
强化学习：稀疏奖励环境下的强化学习算法，非完美信息博弈\r
\r
"

近期论文

An Chi Huang, Chun Yuan, Sheng Hui Meng, Tian Jiun Huang: Design of Fatigue Driving Behavior Detection Based on Circle Hough Transform. Big Data 11(1): 1-17 (2023)\r
\r
Ke Zhang, Chun Yuan, Yiming Zhu, Yong Jiang, Lishu Luo: Weakly Supervised Instance Segmentation by Exploring Entire Object Regions. IEEE Trans. Multim. 25: 352-363 (2023)\r
\r
Yunpeng Bai, Zihan Zhong, Chao Dong, Weichen Zhang, Guowei Xu, Chun Yuan: Towards Arbitrary Text-driven Image Manipulation via Space Alignment. CoRR abs/2301.10670 (2023)\r
\r
Yunpeng Bai, Jiayue Liu, Chao Dong, Chun Yuan: ITstyler: Image-optimized Text-based Style Transfer. CoRR abs/2301.10916 (2023)\r
\r
Dachuan Shi, Chaofan Tao, Ying Jin, Zhendong Yang, Chun Yuan, Jiaqi Wang: UPop: Unified and Progressive Pruning for Compressing Vision-Language Transformers. CoRR abs/2301.13741 (2023)\r
\r
Zhengzhuo Xu, Shuo Yang, Xingjun Wang, Chun Yuan: Rethink Long-tailed Recognition with Vision Transforms. CoRR abs/2302.14284 (2023)\r
\r
Yunpeng Bai, Cairong Wang, Shuzhao Xie, Chao Dong, Chun Yuan, Zhi Wang: TextIR: A Simple Framework for Text-based Editable Image Restoration. CoRR abs/2302.14736 (2023)\r
\r
Haoyu Wang, Shaoli Huang, Fang Zhao, Chun Yuan, Ying Shan: HMC: Hierarchical Mesh Coarsening for Skeleton-free Motion Retargeting. CoRR abs/2303.10941 (2023)\r
\r
Zixuan Hu, Li Shen, Zhenyi Wang, Tongliang Liu, Chun Yuan, Dacheng Tao: Architecture, Dataset and Model-Scale Agnostic Data-free Meta-Learning. CoRR abs/2303.11183 (2023)\r
\r
Zenghao Chai, Tianke Zhang, Tianyu He, Xu Tan, Tadas Baltrusaitis, HsiangTao Wu, Runnan Li, Sheng Zhao, Chun Yuan, Jiang Bian: HiFace: High-Fidelity 3D Face Reconstruction by Learning Static and Dynamic Details. CoRR abs/2303.11225 (2023)\r
\r
Ziyang Yuan, Yiming Zhu, Yu Li, Hongyu Liu, Chun Yuan: Make Encoder Great Again in 3D GAN Inversion through Geometry and Occlusion-Aware Encoding. CoRR abs/2303.12326 (2023)\r
\r
Zhendong Yang, Ailing Zeng, Zhe Li, Tianke Zhang, Chun Yuan, Yu Li: From Knowledge Distillation to Self-Knowledge Distillation: A Unified Approach with Normalized Loss and Customized Soft Labels. CoRR abs/2303.13005 (2023)\r
\r
Metin Vural, Chun Yuan, Nicola Kleppmann, Peter Jung, Slawomir Stanczak: Illinois-Type Methods for Noisy Euclidean Distance Realization. IEEE Signal Process. Lett. 29: 2687-2691 (2022)\r
\r
Lei Li, Kai Fan, Hongjia Li, Chun Yuan: Structural Supervision for Word Alignment and Machine Translation. ACL (Findings) 2022: 4084-4094\r
\r
Zhihui Lin, Tianyu Yang, Maomao Li, Ziyu Wang, Chun Yuan, Wenhao Jiang, Wei Liu: SWEM: Towards Real-Time Video Object Segmentation with Sequential Weighted Expectation-Maximization. CVPR 2022: 1352-1362\r
\r
Zhendong Yang, Zhe Li, Xiaohu Jiang, Yuan Gong, Zehuan Yuan, Danpei Zhao, Chun Yuan: Focal and Global Knowledge Distillation for Detectors. CVPR 2022: 4633-4642\r
\r
Cairong Wang, Yiming Zhu, Chun Yuan: Diverse Image Inpainting with Normalizing Flow. ECCV (23) 2022: 53-69\r
\r
Zhendong Yang, Zhe Li, Mingqi Shao, Dachuan Shi, Zehuan Yuan, Chun Yuan: Masked Generative Distillation. ECCV (11) 2022: 53-69\r
\r
Zenghao Chai, Haoxian Zhang, Jing Ren, Di Kang, Zhengzhuo Xu, Xuefei Zhe, Chun Yuan, Linchao Bao: REALY: Rethinking the Evaluation of 3D Face Reconstruction. ECCV (8) 2022: 74-92\r
\r
Yunpeng Bai, Chao Dong, Zenghao Chai, Andong Wang, Zhengzhuo Xu, Chun Yuan: Semantic-Sparse Colorization Network for Deep Exemplar-Based Colorization. ECCV (6) 2022: 505-521\r
\r
Jinjin Gu, Haoming Cai, Chenyu Dong, Ruofan Zhang, Yulun Zhang, Wenming Yang, Chun Yuan: Super-Resolution by Predicting Offsets: An Ultra-Efficient Super-Resolution Network for Rasterized Images. ECCV (19) 2022: 583-598\r
\r
Dachuan Shi, Ruiyang Liu, Linmi Tao, Chun Yuan: Heuristic Dropout: An Efficient Regularization Method for Medical Image Segmentation Models. ICASSP 2022: 1101-1105\r
\r
Zenghao Chai, Zhengzhuo Xu, Chun Yuan: Modernn: Towards Fine-Grained Motion Details for Spatiotemporal Predictive Learning. ICASSP 2022: 4658-4662\r
\r
Binjie Zhang, Yixiao Ge, Yantao Shen, Yu Li, Chun Yuan, Xuyuan Xu, Yexin Wang, Ying Shan: Hot-Refresh Model Upgrades with Regression-Free Compatible Training in Image Retrieval. ICLR 2022\r
\r
Zenghao Chai, Zhengzhuo Xu, Yunpeng Bai, Zhihui Lin, Chun Yuan: CMS-LSTM: Context Embedding and Multi-Scale Spatiotemporal Expression LSTM for Predictive Learning. ICME 2022: 1-6\r
\r
Chun Yuan, Youxuan Zhong, Jiake Tian, Yi Zou: A Real-time Digit Gesture Recognition System Based on mmWave Radar. ICMLA 2022: 770-775\r
\r
Binjie Zhang, Yixiao Ge, Yantao Shen, Shupeng Su, Fanzi Wu, Chun Yuan, Xuyuan Xu, Yexin Wang, Ying Shan: Towards Universal Backward-Compatible Representation Learning. IJCAI 2022: 1615-1621\r
\r
Lei Li, Kai Fan, Chun Yuan: Cross-modal Representation Learning and Relation Reasoning for Bidirectional Adaptive Manipulation. IJCAI 2022: 3222-3228\r
\r
Yunpeng Bai, Chun Yuan: Contrastive Learning in Wavelet Domain for Image Dehazing. IJCNN 2022: 1-7\r
\r
Hongjia Li, Lingyu Yang, Lei Li, Chengyin Xu, Shu-Tao Xia, Chun Yuan: PTS: A Prompt-based Teacher-Student Network for Weakly Supervised Aspect Detection. IJCNN 2022: 1-8\r
\r
Lingyu Yang, Hongjia Li, Lei Li, Chun Yuan, Shu-Tao Xia: ACEs: Unsupervised Multi-label Aspect Detection with Aspect-category Experts. IJCNN 2022: 1-8\r
\r
Jiayin Cai, Changlin Li, Xin Tao, Chun Yuan, Yu-Wing Tai: DeViT: Deformed Vision Transformers in Video Inpainting. ACM Multimedia 2022: 779-789\r
\r
Chengyin Xu, Zenghao Chai, Zhengzhuo Xu, Chun Yuan, Yanbo Fan, Jue Wang: HyP2 Loss: Beyond Hypersphere Metric Space for Multi-label Image Retrieval. ACM Multimedia 2022: 3173-3184\r
\r
Manyi Zhang, Yuxin Ren, Zihao Wang, Chun Yuan: Tackling Instance-Dependent Label Noise with Dynamic Distribution Calibration. ACM Multimedia 2022: 4635-4644\r
\r
Wenzhe Li, Zirui Zhu, Tianchi Huang, Lifeng Sun, Chun Yuan: Federated Knowledge Transfer for Heterogeneous Visual Models. MMAsia 2022: 5:1-5:7\r
\r
Binjie Zhang, Yixiao Ge, Yantao Shen, Yu Li, Chun Yuan, Xuyuan Xu, Yexin Wang, Ying Shan: Hot-Refresh Model Upgrades with Regression-Alleviating Compatible Training in Image Retrieval. CoRR abs/2201.09724 (2022)\r
\r
Binjie Zhang, Yixiao Ge, Yantao Shen, Shupeng Su, Fanzi Wu, Chun Yuan, Xuyuan Xu, Yexin Wang, Ying Shan: Towards Universal Backward-Compatible Representation Learning. CoRR abs/2203.01583 (2022)\r
\r
Zenghao Chai, Haoxian Zhang, Jing Ren, Di Kang, Zhengzhuo Xu, Xuefei Zhe, Chun Yuan, Linchao Bao: REALY: Rethinking the Evaluation of 3D Face Reconstruction. CoRR abs/2203.09729 (2022)\r
\r
Shupeng Su, Binjie Zhang, Yixiao Ge, Xuyuan Xu, Yexin Wang, Chun Yuan, Ying Shan: Privacy-Preserving Model Upgrades with Bidirectional Compatible Training in Image Retrieval. CoRR abs/2204.13919 (2022)\r
\r
Zhendong Yang, Zhe Li, Mingqi Shao, Dachuan Shi, Zehuan Yuan, Chun Yuan: Masked Generative Distillation. CoRR abs/2205.01529 (2022)\r
\r
Yunpeng Bai, Cairong Wang, Chun Yuan, Yanbo Fan, Jue Wang: Improving the Latent Space of Image Style Transfer. CoRR abs/2205.12135 (2022)\r
\r
Chengyin Xu, Zenghao Chai, Zhengzhuo Xu, Chun Yuan, Yanbo Fan, Jue Wang: HyP2 Loss: Beyond Hypersphere Metric Space for Multi-label Image Retrieval. CoRR abs/2208.06866 (2022)\r
\r
Zhihui Lin, Tianyu Yang, Maomao Li, Ziyu Wang, Chun Yuan, Wenhao Jiang, Wei Liu: SWEM: Towards Real-Time Video Object Segmentation with Sequential Weighted Expectation-Maximization. CoRR abs/2208.10128 (2022)\r
\r
Zhendong Yang, Zhe Li, Yuan Gong, Tianke Zhang, Shanshan Lao, Chun Yuan, Yu Li: Rethinking Knowledge Distillation via Cross-Entropy. CoRR abs/2208.10139 (2022)\r
\r
Zhendong Yang, Zhe Li, Ailing Zeng, Zexian Li, Chun Yuan, Yu Li: ViTKD: Practical Guidelines for ViT feature knowledge distillation. CoRR abs/2209.02432 (2022)\r
\r
Jiayin Cai, Changlin Li, Xin Tao, Chun Yuan, Yu-Wing Tai: DeViT: Deformed Vision Transformers in Video Inpainting. CoRR abs/2209.13925 (2022)\r
\r
Jinjin Gu, Haoming Cai, Chenyu Dong, Ruofan Zhang, Yulun Zhang, Wenming Yang, Chun Yuan: Super-Resolution by Predicting Offsets: An Ultra-Efficient Super-Resolution Network for Rasterized Images. CoRR abs/2210.04198 (2022)\r
\r
Manyi Zhang, Yuxin Ren, Zihao Wang, Chun Yuan: Tackling Instance-Dependent Label Noise with Dynamic Distribution Calibration. CoRR abs/2210.05126 (2022)\r
\r
Binjie Zhang, Shupeng Su, Yixiao Ge, Xuyuan Xu, Yexin Wang, Chun Yuan, Mike Zheng Shou, Ying Shan: Darwinian Model Upgrades: Model Evolving with Selective Compatibility. CoRR abs/2210.06954 (2022)\r
\r
Yiming Zhu, Hongyu Liu, Yibing Song, Ziyang Yuan, Xintong Han, Chun Yuan, Qifeng Chen, Jue Wang: One Model to Edit Them All: Free-Form Text-Driven Image Manipulation with Semantic Modulations. CoRR abs/2210.07883 (2022)\r
\r
Hao Li, Jinguo Zhu, Xiaohu Jiang, Xizhou Zhu, Hongsheng Li, Chun Yuan, Xiaohua Wang, Yu Qiao, Xiaogang Wang, Wenhai Wang, Jifeng Dai: Uni-Perceiver v2: A Generalist Model for Large-Scale Vision and Vision-Language Tasks. CoRR abs/2211.09808 (2022)\r
\r
Manyi Zhang, Chun Yuan, Jun Yao, Weiran Huang: Learning with Noisily-labeled Class-imbalanced Data. CoRR abs/2211.10955 (2022)\r
\r
Yunpeng Bai, Yanbo Fan, Xuan Wang, Yong Zhang, Jingxiang Sun, Chun Yuan, Ying Shan: High-fidelity Facial Avatar Reconstruction from Monocular Video with Generative Priors. CoRR abs/2211.15064 (2022)\r
\r
Zhengzhuo Xu, Ruikang Liu, Shuo Yang, Zenghao Chai, Chun Yuan: Learning Imbalanced Data with Vision Transformers. CoRR abs/2212.02015 (2022)\r
\r
Zixiao Wang, Junwu Wang, Chun Yuan, Jue Wang: Truncate-Split-Contrast: A Framework for Learning from Mislabeled Videos. CoRR abs/2212.13495 (2022)