Hi! I’m Minjie, an associate professor at Hunan University and a cooperative research fellow at The University of Tokyo cooperating with Prof. Yoichi Sato. My research interests include computer vision, human-machine interactions, and robotics.

I received my Ph.D. in Information Science and Technology at The University of Tokyo, supervised by Prof. Yoichi Sato and co-advised by Dr. Kris Kitani. I received my M.S. in Communication and Information Engineering and B.S. in Electronics and Information Engineering at Northwestern Polytechnical University.


  • (November 4, 2021) Our work on audio-visual event localization has been accepted to IEEE Transactions on Multimedia!
  • (August 2, 2021) One paper entitled “DriverSonar: Fine-Grained Dangerous Driving Detection Using Active Sonar” has been accepted to UbiComp 2021.
  • (October 5, 2020) One paper entitled “First and third-person video co-analysis by learning spatial-temporal joint attention” has been accepted to IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)!
  • (June 26, 2020) Our work on jointly estimating egocentric gaze and action is accepted to IEEE Transactions on Image Processing!
  • (February 23, 2020) Our work on domain adaptive hand segmentation is accepted to CVPR 2020! [Project page]
  • (November 26, 2019) Our work on joint attention discovery is accepted to IEEE Transactions on Human-Machine Systems! [Project page]
  • (August 21, 2019) Our work on video-based skill assessment has been accepted to ICCV workshop of Egocentric Perception, Interaction and Computing.