Contact information

Tel: +86 (0755) 2603-6462

Email:

Address: Room 1709, Building Xinxi, Tsinghua Campus, University City, Xili Town

Office Hours:

  • 个人简历
  • 教学
  • 研究领域
  • 研究成果
  • 奖励荣誉
  • Biography

    About me

    Dr. Chun YUAN is currently an Professor in the Graduate school at Shen Zhen, Tsinghua University, IEEE Senior Member. He received the M.S. and Ph.D. degrees from the Department of Computer Science and Technology, Tsinghua University, Beijing, China, in 1999 and 2002, respectively. He once worked at the INRIA-Rocquencourt, Paris, France, as a Post-doc research fellow from 2003 to 2004. In 2002, he worked at Microsoft Research Asia, Beijing, China, as an intern. His research interests include computer vision, machine learning, multimedia technologies and reinforcement learning. He has published more than 160 papers in high-level academic journals and conferences, He has been the invited-reviewer of many high rank international academic Journals such as TIP, TNNLS, TMM, TCSVT,T-Cybernetics and so on.


    URL: http://www.sz.tsinghua.edu.cn/

    Google scholar: https://scholar.google.com/citations?hl=en&user=fYdxi2sAAAAJ

    DBLP: https://dblp.org/pers/hd/y/Yuan:Chun


    Education

    Postdoc,Postdoctor in INRIA_Rocquencourt (Institute of national research on information and automation, France)  2003-2004, Tutored by Prof. Philipe Pucheral, In SMIS Project, Major in Database security System

    Ph.D. ,Institute of HCI and Media Integration, Department of Computer Science and TechnologyDepartment of  Computer Science and Technology in Tsinghua University, P.R.China, 2000-2002, tutored by Prof.Zhong Yuzhuo, Major in Multimedia technology

    MasterInstitute of HCI and Media Integration, Department of Computer Science and TechnologyDepartment of  Computer Science and Technology in Tsinghua University, P.R.China, 1997-2000, tutored by Prof.Zhong Yuzhuo, Major in Multimedia technology

    B.E.,Department of Automation in Tianjin Institute of Light Industry, P.R.China 1987-1991


    Professional Experience

    2015/01—2015/02: Visiting EECS Department, Northwestern University,USA;

    2014/072014/08: Visiting Department of Machine Learning, CMU Computer College, Carnegie Melody University, USA;

    2021/12now:  Professor, Graduate School at Shenzhen, Tsinghua University;

    2011/06—now: Ph.D.Tutor, Graduate School at Shenzhen, Tsinghua University;

    2006/12 —now: Associate Professor, Graduate School at Shenzhen, Tsinghua University;

    2005/05—2006/12: Lecturer, Division of Information Science and Technology, Graduate School at Shenzhen, Tsinghua University;

    2003/03—2004/12: Postdoctoral researcher at the French National Institute for Information and Automation (INRIA-Rocquencourt, Paris);

    2002/02—2002/09: Microsoft Research Asia, Internet media Group, Internship;

    1999/09—2002/12: Department of Computer Science and Technology, Tsinghua University, Institute of Human-Computer Interaction and Media Integration, PhD;

    1997/03—1999/07: Department of Computer Science and Technology, Tsinghua University, Institute of Human-Computer Interaction and Media Integration, Master;


    Additional Positions

    Reviewer

    Invited reviewer of  IEEE Transaction on Multimedia

    Invited reviewer of  IEEE Transactions on Image Processing

    Invited reviewer of  IEEE Transaction on Cybernetics

    Invited reviewer of  IEEE Transactions on Neural Networks and Learning Systems

    Invited Reviewer of  Information Access

    Invited Reviewer of  IEEE Transaction on Information Industry

    Invited reviewer of  IEEE Transactions on Industrial Electronics

    Invited Reviewer of  Transaction on Circuits and Systems for Video Technology

     

    Academic conference services:

    PC Member of IJCAI 2021

    PC Member of AAAI 2019

    PC Member of ACMMM2019

    Session-Chair of ICME 2019

    PC Member of ChinaMM 2019

    PC Member of ChinaMM 2018

    PC Member of NeuralIPS 2018

    General-Chair of IEEE ICCE_China 2013

    Co-Chair of IEEE ICCE_China 2012

    Session-Chair of IEEE AIAED2019

     


    Opening

    Personal Webpage

    Download CV

  • Current Courses

    “Computer Vision” 

    (1) Type: Professional Foundation Course

    (2) Target audience: Master's and PhD students in information science

    “Big Data Machine Learning "

    (1) Type: Basic Theory Course

    (2) Target audience: Master's and PhD students in information science

    Online Course  “Big Data Machine Learning” 

    (1)    Xue Xi Qiang Guang website: “https://www.xuexi.cn 113 series  270k thumbs up

    (2)    Xuetang Online: https://next.xuetangx.com/course/THU08091001026/1076286, 140K registered user

    (3)    EDX:  https://www.edx.org/edxchina,


    Master’s & Ph.D. Advising

  • Research Interests

    1. Computer Vision

    2. Machine Learning

    3. Multimedia technologies and security

    4. Reinforcement Learning


    Projects

    Research Output

    NSFC

    [1]Nature Science Funding of China (NSFC), “Deep Learning based complex objects detection and real time tracking in Airport surveillance”, 2018-2021 (U1833101)

    [2]NSFC, “super-resolution video fast encoding in Airport field”, 2015-2018 (U1433112)

    [3]NSFC, “Distributed Video Coding for WMSN key technology research”, 2008-2012 (61170253)

    [4]NSFC, “Key Technology of Distributed Hierarchical Video Server” (69973025)

    [5]NSFC, “Decoding Performance Machine Application of LDPC Code” (U0675001)

    National 863

    [1]“Dynamic media business support platform and application demonstration” (2015AA015803

    [2] “3DTV content creation, coding and reconstruction of key technologies and prototype systems research” (2009AA01Z327)

    National Foundational High Technology Basic Project

    [1]“Intelligent digital TV terminal infrastructure software development and industrialization” (2013ZX01039001-002)

    Project Co-operation between Guangdong Province and Hongkong

    [1] "Research about real-time audio-visual platform based on the cloud computing research”

    International Science and Technology Cooperation Projects

    [1]"Sub-pixel Fast Stereo Matching Algorithm and Implementation” (with University of Technology Sydney, Australia)

    [2]“Medical Data Privacy Protection Platform” (with Emory University, USA)

    Project from Shenzhen Government

    [1]Shenzhen Science and Technology Innovation Committee, “DDPG algorithm research by course learning and self-Reinforcement learning”, 2019-2021, CNY 300,000.

    [2]“Shenzhen triple play smart home demonstration project”, 2012-2015, CNY 1.2 million.

    [3]. Shenzhen Science and Technology Innovation Committee, “Deep Learning Based Video Object Tracking and Content Analysis”, 2016-2019, CNY 2 million.

    Projects from Industry

    [1]“Virtual Human Body Construction”, Tencent Co. 2014-2015

    [2]“Visual Language Embedding and mutual retrieval”, Tencent Co. 2017-2019

    [3]“Matching evaluation between Video content and its caption”, Tencent Co. 2018-2019

    [4]“Human instance segmentation in video”, Huawei  2018-2020

    [5]“Advertisement Implantation in Video”, Huawei Co. 2010-2013

    [6]“Implementation of Scalable Video Coding over STi7108 Chipset”, ST Semiconductor Co. 2009-2010

    [7]“Light Weight Multimedia Environment in Set Top Box”, NTT (Japan) Co. 2009-2012

    “BML improvement in server side”, NTT (Japan) Co. 2008-2010

     


  • Selected Publications

    2022

    [1]Lei LiChun Yuan et al., Cross-modal Representation Learning and Relation Reasoning for Bidirectional Adaptive Manipulation, IJCAI2022 (CCF A)

    [2]Binjie ZhangChun Yuan et al., Towards Universal Backward-Compatible Representation LearningIJCAI2022 (CCF A)

    [3]Zhihui LinChun Yuan et al., SWEM: Towards Real-Time Video Object Segmentation with Sequential Weighted Expectation-MaximizationCVPR2022 (CCF A)

    [4]Zhendong YangChun Yuan et al., Focal and Global Knowledge Distillation for Detectors CVPR2022 (CCF A)

    [5]Lei Li, Chun Yuan et al., Structural Supervision for Word Alignment and Machine Translation, ACL 2022 (CCF A)

    [6]Binjie Zhang, Chun Yuan*, et al., Hot-Refresh Model Upgrades with Regression-Free Compatible Training in Image Retrieval, ICLR 2022 (CCF A)

    [7]Ke Zhang, Chun Yuan*,et al., Weakly Supervised Instance Segmentation By Exploring Entire Object RegionsIEEE Transaction on Multimedia 2022 (THU A)

     

    2021

    [1]Jianyin Cai, Chun Yuan, et al., Deep Interactive Video Inpainting: an Invisibility Cloak for Harry Potter, ACM MM2021 (CCF A)

    [2]Zhengzhuo Xu, Zenghao Chai, Chun Yuan*Towards Calibrated Model for Long-Tailed Visual Recognition from Prior Perspective, NeurIPS2021 (CCF A)

    [3]Lei Li, Chun Yuan*VQMG: Hierarchical Vector Quantised and Multi-hops Graph Reasoning for Explicit Representation Learning, ACM MM2021 (CCF A)

     

    2020

    [1]Meng Wei, Chun Yuan, Xiaoyu Yue, Kuo Zhong, HOSE-Net: Higher Order Structure Embedded Network for Scene Graph Generation, ACMMM2020 (CCF A)

    [2]Lu, Yuwu; Wang, Wenjing; Yuan, Chun; Li, Xuelong; Lai, Zhihui, Manifold Transfer Learning Via Discriminant Regression Analysis, IEEE Transaction on Multimedia2020 in press (THU A)

    [3]Kuo Zhong, Ying Wei, Chun Yuan, Haoli Bai, Junzhou Huang, TranSlider: Transfer Ensemble Learning from Exploitation to Exploration KDD2020 (CCF A)

    [4]Zhihui Lin, Chun Yuan, Maomao Li, Yangyang Cheng, AF-SVG: Hierarchical Stochastic Video Generation with Aligned Features, IJCAI2020 (CCF A)

    [5]Jianyin Cai, Chun Yuan, Cheng Shi, Lei Li, Yangyang Cheng, Ying Sha, Feature Augmented Memory with Global Attention Network for VideoQA, IJCAI2020 (CCF A)

    [6]Yuwei Zhang, Peng Zhang, Chun Yuan, and Zhi Wang, Texture and Shape biased Two-Stream Networks for Clothing Classification and Attribute Recognition CVPR2020  (CCF A)

    [7]Zhihui Lin, Maomao Li, Zhuobin Zheng, Yangyang Cheng, Chun Yuan, Self-Attention ConvLSTM for Spatiotemporal Prediction, AAAI2020 (CCF A)

    [8]Lishu Luo, Chun Yuan, Ke Zhang, Yuwu Zhang, Double Shot: Preserve and Erase Based Class Attention Networks for Weakly Supervised Localization (PECA-Net) ICME2020 (CCF B)

    [9]Chenxi Yuan , Yang Bai, Chun Yuan Bridge the Gap: High-level Semantic Planning for Image Captioning Coling, Coling2020 (CCF B)

    [10]Chenxi Yuan, Chun Yuan,Yang Bai Ziran Li, Logic Enhanced Commonsense Inference with Chain Transformer, CIKM 2020 (CCF B)

     

    2019

    [1]Zhuobin Zheng, Chun Yuan, Zhihui Lin, Yangyang Cheng, Self-Supervised Mixture-of-Experts by Uncertainty Estimation, AAAI 2019 (CCF A)

    [2]Zhiming Ma, Chun Yuan,  Image-to-Tree: A Tree-structured Decoder for Image Captioning, ICME 2019 (CCF B)

    [3]Maomao Li, Chun Yuan, et al. Stochastic Video Generation with Disentangled Representations ICME 2018 (CCF B)

    [4]Zhuobin Zheng, Youcheng Ben, Chun Yuan, Multi-Scale Visual Semantics Aggregation with Self-Attention for End-to-End Image-Text Matching, ACML 2019 (CCF C)

     

    2018

    [1]Qiurui Wang, Chun Yuan, Jingdong Wang, Wenjun Zeng, Learning Attentional Recurrent Neural Network for Visual Tracking. IEEE Transactions on Multimedia.in press 2018

    [2]Yuwu Lu, Chun Yuan, Wenwu Zhu, Xuenong Li, Structurally Incoherent Low-Rank Nonnegative Matrix Factorization for Image Classification, IEEE Transaction on Image Processing, in press 2018 (CCF A)

    [3]Yuwu Lu, Chun Yuan, Xuenong Li, Zhihui Lai, David Zhang, Structurally Incoherent Low-Rank 2DLPP for Image Classification, IEEE Transactions on Circuits and Systems for Video Technology, in press 2018

    [4]Zhou Cheng, Chun Yuan, Jiancheng Li, Haiqin Yuang, TreeNet: Learning sentence representations with unconstrained tree structure, in press, IJCAI 2018  (CCF A)

    [5]Zhuobin Zheng, Chun Yuan, Zhihui Lin, Yangyang Cheng, Hanghao Wu, Self-Adaptive Double bootstrapped DDPGin press, IJCAI 2018  (CCF A)

    [6]Yuwu Lu, Chun Yuan, Xuenong Li, Zhihui Lai, David Zhang, Horizontal and Vertical Nuclear Norm-Based 2DLDA for Image Representation, IEEE Transactions on Circuits and Systems for Video Technology, in press 2018

    [7]Youcheng Ben, Chun Yuan, Densely stacked generative adversarial networks, ICME 2018

    [8]Zhiguan Lin, Chun Yuan, Robust Visual Tracking in Low-Resolution Sequence. IEEE International Conference on Image Processing ICIP 2018,In press

    [9]Dali Yang, Chun Yuan. Hierarchical Context Encoder for Events Captioning in Videos, IEEE International Conference on Image Processing, ICIP2018, In Press

    [10]Yipeng Ma, Chun Yuan,Efficient Multi-level Correlating for Visual TrackingACCV2018  CCF C

    [11]Shreyank, Chun Yuan, ColorNet: Investigating the importance of color and color spaces for image classification, ACCV2018         CCF C

     


    Books

    1. Digital TV Set Top Box and Multimedia Home Gateway, Publication by Tsinghua Press. 2008.11

    2. Information security Principle and Application》,Publication of Electronic Industry Press. 2009

    3.   Computer Vision: Principles, Algorithms, Applications, LearningE.R. Davis, translated by Yuan Chun and Liu Jing, Machinery Industry Press, 2020.7


    Patents

    Others

  • Awards and Honors

    l  2020 National Excellent Online Open Course, Big Data Machine Learning online course

    l  2020 Excellence Award, Tencent AI Lab Rhino Bird Special Research Project

    l  2018 Outstanding Instructor Award, Tencent AI Lab Rhino Bird Elite Talent Training Program

    l  2018 Outstanding Teacher, Tsinghua University Shenzhen Graduate School

    l  2020 Tsinghua University Excellent Master's Thesis,Zhiyu Wang, “Instance segmentation and target detection based on multi-feature fusion”

    l  2019 Tsinghua University Excellent Master's Thesis,Youcheng Ben “Multi-Scale Visual Semantics Aggregation for End-to-End Image-Text Matching”

    l  2018 Tsinghua University Excellent Master's Thesis,Zhou Cheng “Structural Perceptual Convolution and Its Application in Image Semantic Segmentation”

    l  2017 Tsinghua University Excellent Master's Thesis, Liang Yuan “Deep Map Super Resolution Algorithm Research”

    l  2015 Tsinghua University Excellent Master's Thesis, Gangbiao Chen “Significance Detection Based on Depth and Sparse Features”

    l  2013 Tsinghua University Excellent Master's Thesis, Shanli Liang, “Research and Application of Video Depth Recovery Technology Based on Adaptive Image Segmentation”

    l  2013 Tsinghua University Excellent Master's Thesis, Xin Wang, “Significance Detection Based on Depth and Sparse Features”

    l  2011 Tsinghua University Excellent Master's Thesis, Fangshen Shu, “Significance Detection Based on Depth and Sparse Features”

    l  Yuan Chun, Zhong Yu, Liu Yang, Zhang Wei, Liu Lie, Liu Yuan, Zhu Bin, Wu Zhiyong, et al. Digital Media Copyright Protection Platform Based on P2P Framework, Shenzhen Science and Technology Innovation Award, 2007, the first person to complete

    l  Best Paper Award, Liang S, Yuan C. Dense Depth Recovery Based on Adaptive Segmentation, IEEE International Colloquia on Consumer Electronics - China (ICCE), 2013.Best paper award.  ICCE-China 2013

    l  Excellent Service Award, IEEE Consumer Electronic Society, 2013

    l  Service Award, in recognition and appreciation of contributions to 2012 Global High Tech Congress on Electronics (GHTCE) as program Co-Chair, IEEE, 2012

    l  Distinguished Expert Award,  IEEE Consumer Electronic Society, 2012

    l  Distinguished Expert Award, in recognition of successful collaboration in the organization of ICCE China, 2012

    l  Outstanding Service Award, in recognition of successful collaboration in the organization of ICCE China, 2012

    l  User-friendly award,  Project of Lightweight Interactive multimedia environment,  ITU-T IPTV Challenge 2011.9

    l  Second Prize, The State Scientific and Technological Progress Award, 2009

    l  Science and Technology Innovation Award, Project of Digital rights management on P2P network, Shenzhen Government, 2008

    l  Outstanding Teacher Award,   Graduate School at Shenzhen, Tsinghua University,2008

    l  INRIA Postdoc fellowship,  INRIA, France, 2003-2004

    l  Tsinghua-Motorola Outstanding Graduate Student Scholarship,  Tsinghua University 2002