Kai Su

I am a M.Sc. student in PALM Group at Southeast University, supervised by Prof. Xin Geng. My research interests are in computer vision and machine learning.

Publications & Preprints

  • A Context-and-Spatial Aware Network for Multi-Person Pose Estimation
    Dongdong Yu, Kai Su, Xin Geng, Changhu Wang
    arXiv preprint, arXiv: 1905.05355, 2019.
    [PDF]
  • Multi-Person Pose Estimation with Enhanced Channel-wise and Spatial Information
    Kai Su†, Dongdong Yu†, Zhenqi Xu, Xin Geng, Changhu Wang
    In: Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition (CVPR 2019), Long Beach, CA, 2019.
    († indicates equal contribution.)
    [PDF]
  • Soft Facial Landmark Detection by Label Distribution Learning
    Kai Su and Xin Geng
    In: Proceedings of the 33rd AAAI Conference on Artificial Intelligence (AAAI 2019), Honolulu, Hawaii, 2019.
    [PDF]
  • Multi-Person Pose Estimation for Pose Tracking with Enhanced Cascaded Pyramid Network
    Dongdong Yu†, Kai Su†, Jia Sun, and Changhu Wang
    ECCV PoseTrack Workshop, 2018.
    († indicates equal contribution.)
    [PDF]

Contests

  • 1st place (Winner) in the Single-Person Human Pose Estimation Track of the Augmented Human: Human-centric Understanding and 2D/3D Synthesis, and the third Look Into Person (LIP) Challenge
    CVPR LIP Workshop, 2019.
    Team ByteDance-SEU, [slides]
  • 2nd place (Runner-Up) in the Single-Person Human Parsing Track of the Augmented Human: Human-centric Understanding and 2D/3D Synthesis, and the third Look Into Person (LIP) Challenge
    CVPR LIP Workshop, 2019.
    Team ByteDance-SEU, [slides]
  • 3rd place in the Multi-Person Pose Tracking of the PoseTrack Challenge
    ECCV PoseTrack Workshop, 2018.
    Team Miracle
  • 5th place in the COCO Keypoint Detection of the COCO + Mapillary Joint Challenge
    ECCV COCO Workshop, 2018.
    Team ByteDance-SEU
  • 2nd place (Runner-Up) in the Single-Person Human Pose Estimation Track of the Visual Understanding of Humans in Crowd Scene and the 2nd Look Into Person (LIP) Challenge
    CVPR LIP Workshop, 2018.
    Team ByteDance-SEU-Baseline, [slides]
  • 7th/620 place in the Ucar Artificial Intelligence Cup, Ucar and IEEE Computer Society, 2017.
    Team palm

Dongdong Yu (ByteDance), Xin Geng (SEU), Changhu Wang (ByteDance)

Find Me

[Douban], [Github], [Weibo]