Short Bio

I am a researcher in Microsoft Research Asia. I work on computer vision problems with special focus on single and multiple camera 3D human pose estimation and tracking. I address the 3D human pose estimation problem from different perspectives: (1) Representation (sparse coding and activated simplex models); (2) Feature fusion (VoxelPose, CrossFusion, IMU-Fusion); (3) Context modeling (LCN, LCN-Journal); (4) Physical constraints (e.g. optimization-based, learning-based); (5) Unsupervisded learning (Dual Network Learning). I also worked on multi-object tracking (FairMOT)