Hao-Shu Fang, Jinkun Cao, Yu-Wing Tai, Cewu Lu
*Submitted to IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018.
Learning pose grammar to encode human body configuration for 3d pose estimation [arXiv]
Hao-Shu Fang, Yuanlu Xu, Wenguan Wang, Xiaobai Liu, Song-Chun Zhu
(Oral) AAAI Conference on Artificial Intelligence, (AAAI), 2018. (* contributed equally).
RMPE: Regional Multi-person Pose Estimation [arXiv]
Hao-Shu Fang, Shuqin Xie, Yu-Wing Tai, Cewu Lu.
IEEE International Conference on Computer Vision (ICCV), 2017.
Center for VCLA, UCLA: 06,2017-09,2017
Visiting Undergraduate Research Intern, focusing on 3D pose estimation.
Advised by Prof. Song-Chun Zhu
Tencent, YouTu Lab: 02,2017-06,2017
Research Intern, focusing on recognizing human-object-interaction.
Advised by Prof. Yu-Wing Tai
Machine Vision and Intelligence Group, SJTU, 06,2016 – present
Research Assistant, focusing on human pose estimation, part segmentation and deep reinforcement learning.
Advised by Prof. Cewu Lu
Computer Vision Research & Engineer Intern
Object Detection&Classification, Scene Classification, Model compression,Pose Estimation
ICCV 2017 Workshop, COCO Keypoints Challenge, 2017.10
8 mAP higher than the champion from last year. The 6th place.
CVPR 2017 Workshop, Look Into Person (LIP) Challenge, 2017.5
Third place at the 1st Look Into Person (LIP) Challenge of CVPR’17 workshop on Visual Understanding of Humans in Crowd Scene
Microsoft Beauty of Programming 2016, 2016.3 – 2016.5
Enter the finalist (60/20000) and our team gets the Best Demo prize(Top 0.1%).
ASC16 Student Supercomputer Challenge, 2016.1 - 2016.4
Our team is the 2nd among 178 teams
Microsoft Penta Hackathon, 2015.11
Our Team ranks top 12. The demo of our product is here: https://youtu.be/7uL-M7eat9Q
Intel Parallel Application Challenge 2015, 2015.5 - 2015.11
Compete with more than 200 teams from all over the country. Our team is the 4th.