Zhitao Yang
高级算法研发工程师 at SenseTime 商汤科技
Shenzhen, Guangdong Province, China
Summary
🤩
Rockstar🎓
Top SchoolZhitao Yang is a senior algorithm R&D engineer based in Shenzhen with 8 years of experience bridging deep learning, engineering, and scientific rigor from a background in nuclear science. Currently at SenseTime, he focuses on advanced computer vision and model tooling, and his open-source contributions to the well-known OpenMMLab mmhuman3d project improve multi-person 2D/3D keypoint visualization and demo pipelines. Previously he led backend engineering at a data company, combining system-level implementation with technical leadership. Trained at Tsinghua and holding a master’s in Nuclear Energy Science and Engineering, he brings a rare mix of physics-driven problem solving and practical ML engineering to production-facing research.
8 years of coding experience
Bachelor's degree, Nuclear Science and Techonoloy, Bachelor's degree, Nuclear Science and Techonoloy at 清华大学Master's degree, Nuclear Energy Science and Engineering, Master's degree, Nuclear Energy Science and Engineering at 核工业第二研究设计院Bachelor’s Degree of Engineering, Nuclear Science and Engineering, Bachelor’s Degree of Engineering, Nuclear Science and Engineering at 清华
Japanese, Chinese
Github Skills (10)
video-processing10
computer-vision10
opencv10
visualization10
visualizations10
python10
keypoint10
feature-detection10
machine-learning9
pytorch9
Programming languages (4)
Github contributions (5)
open-mmlab/mmhuman3d
Jul 2021 - Dec 2021
OpenMMLab 3D Human Parametric Model Toolbox and Benchmark
Role in this project:
ML Engineer
ML EngineerContributions:7 reviews, 7 commits, 2 PRs in 4 months
Contributions summary:Zhitao's commits primarily involve modifications to the `mmhuman3d/core/visualization` module, specifically focusing on keypoint visualization functions. These updates introduce the ability to visualize 2D and 3D keypoints, including functionalities for rendering keypoints to videos and drawing bounding boxes. The code changes indicate enhancements to visualize multi-person data and the integration of improved color palettes for better visual clarity in keypoint representations. The user is also responsible for updating smplify_demo.py file.
pytorchstructure-from-motionfeature-matchingdeep-learningparametric
maoXyzt/Notes
Jun 2021 - Apr 2025
Personal notes
Contributions:4 PRs, 359 pushes, 1 branch in 3 years 10 months
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.