About
My name is Chao Xu (徐超). I am working as algorithm engineer in
Tencent GY-Lab(光影研究室), Shanghai, supervised by
Gang Yu
.
I obtained my Master of Engineering in the
Department of Computer Science and Engineering
at Shanghai Jiao Tong University(SJTU), working in
Machine Vision and Intelligence Group(MVIG)
under the supervision of Prof.Cewu Lu.
Before then, I got my Bachelor of Engineering in the
School of Cyber Science and Engineering
at SJTU. My main research interests include computer vision, object detetection and pose estimation. I am interested in cloud computing, too.
Projects involved
- Alphapose
- Real-Time and Accurate Multi-Person Pose Estimation & Tracking System, which is first open-source system that achieves 70+ mAP (75 mAP) on COCO dataset.
- [code]
Publications
- D&D: Learning Human Dynamics from Dynamic Camera
- Jiefeng Li, Siyuan Bian, Chao Xu, Gang Liu, Gang Yu, Cewu Lu
- European Conference on Computer Vision (ECCV oral), 2022
- [paper]
[github page]
- HybrIK: A Hybrid Analytical-Neural Inverse Kinematics Solution for 3D Human Pose and Shape Estimation
- Jiefeng Li, Chao Xu, Zhicun Chen, Siyuan Bian, Lixin Yang, Cewu Lu
- IEEE Conference on Computer Vision and Pattern Recognition (CVPR Poster), 2021
- [paper]
[project page]
- Environment Upgrade Reinforcement Learning for Non-differentiable Multi-stage Pipelines
- Shuqin Xie, Zitian Chen, Chao Xu, Cewu Lu
- IEEE Conference on Computer Vision and Pattern Recognition (CVPR Spotlight), 2018
- [paper]
Education
- Shanghai Jiao Tong University, Shanghai, China (Sep 2018 - Mar 2021)
- Master of Engineering, Computer Science and Technology
- [home page]
- Shanghai Jiao Tong University, Shanghai, China (Sep 2014 - Jun 2018)
- Bachelor of Engineering, Cyber Science and Engineering
- access to the title of Outstanding Graduates
- [home page]
Work experience
- Algorithm Engineer (Apr 2021 - Now)
- Tencent Technology Co ., Ltd, Shanghai, China
-
Research on 3d human pose estimation and shape reconstruction.
Develop GAN related technologies, like motion transfer and virutal try-on.
The research results are applied in many productions in QQ short-video community(QQ小世界) and Tencent Weishi(微视), experienced by millions of users.
- [home page]
- Algorithm Intern (Jun 2020 - Oct 2020)
- Tencent Technology Co ., Ltd, Shanghai, China
- Research on 3d human pose estimation and shape reconstruction.
- [home page]
- Algorithm Intern (Dec 2017 - Oct 2018)
- Hangzhou Hikvision Digital Technology Co ., Ltd, Shanghai, China
- Research on video action recognition
- [home page]
- Machine learning Intern (Jul 2017 - Sep 2017)
- Tencent youtu xlab, Shenzhen, Guangdong, China
- Superviesd by
Yu-Wing TAI
.
Research on human image synthesis with motion imitation and maintaining the deployment and docker images of the cluster server
- [home page]
- Cloud computing Intern (Jul 2016 - Sep 2016)
- Shanghai qianyun Information Technology Co., Ltd, Shanghai, China
- Research and test on Openstack embedded product
- [home page]