Education

• B.S. in Shanghai Jiao Tong University, Electronic Engineering, 2014
  • GPA: 92.54/100 Rank:2/170
• M.Sc. in Shanghai Jiao Tong University, Computer Science, 2018

Publications

HMOR: Hierarchical Multi-Person Ordinal Relations for Monocular Multi-Person 3D Pose Estimation [Paper] Jiefeng Li*, Can Wang*, Wentao Liu, Chen Qian, Cewu Lu
(Spotlight) European Conference on Computer Vision, (ECCV), 2020.

Detailed 2D-3D Joint Representation for Human-Object Interaction [Paper][Code][Benchmark][Video]
Yong-Lu Li, Xinpeng Liu, Han Lu, Shiyi Wang, Junqi Liu, Jiefeng Li, Cewu Lu
IEEE Conference on Computer Vision and Pattern Recognition, (CVPR), 2020.

CrowdPose: Efficient Crowded Scenes Pose Estimation and a New Benchmark [Paper][Code][Dataset][News][Demo]
Jiefeng Li, Can Wang, Hao Zhu, Yihuan Mao, Hao-Shu Fang, Cewu Lu
(Oral) IEEE Conference on Computer Vision and Pattern Recognition, (CVPR), 2019.

Pose Flow: Efficient Online Pose Tracking [Paper][Code][News]
Yuliang Xiu, Jiefeng Li, Haoyu Wang, Yinghong Fang, Cewu Lu
British Machine Vision Conference, (BMVC), 2018.

Research experience

Sensetime: 03/2018 - 06/2020
Research Intern, focusing on multi-person 3D pose estimation.
Advised by Dr. Wentao Liu & Chen Qian

Machine Vision and Intelligence Group, SJTU, 05/2017 – present
Research Assistant, focusing on 2D/3D human pose estimation.
Advised by Prof. Cewu Lu

Competitions

• ICCV 2017 Workshop, COCO Keypoints Challenge, 2017.10
  8 mAP higher than the champion from last year.
  The 6th place.

• The Challenge Cup, 2017.03
  Develop a Academic Visualize System, participate the contest on behalf of SJTU.
  Awarded Outstanding Winner.

• Shanghai Undergraduate Electronics Design Contest, 2016.08
  Develop a Long Wave Transmission System.
  Win the 2nd prize, Rank 3/50.

Skills

• Lauguages: Python, Lua, C/C++, MATLAB, etc.
• Frameworks: Torch, PyTorch, Tensorflow, MXNet, etc.