Han Chen

Research Assistant at The Chinese University of Hong Kong

New Territories, Hong Kong SAR
email-iconphone-icongithub-logolinkedin-logotwitter-logostackoverflow-logofacebook-logo
Join Prog.AI to see contacts
email-iconphone-icongithub-logolinkedin-logotwitter-logostackoverflow-logofacebook-logo
Join Prog.AI to see contacts

Summary

🤩
Rockstar
Han Chen is a research-focused software engineer with nine years of experience bridging academic projects and industrial R&D in Hong Kong. Currently a Research Assistant at The Chinese University of Hong Kong and a Research Scientist at TCL Corporate Research (HK), he specializes in machine learning for computer vision, particularly object detection and instance recognition. His open-source contributions to the well-regarded SimpleDet framework include FP16 training for RetinaNet, FPN refactors, and metric fixes—work that improves both performance and maintainability. Comfortable operating at the intersection of research and production, he brings a pragmatic approach to model optimization and codebase hygiene. Based in the New Territories, he combines deep technical craft with a collaborator’s mindset, often translating experimental ideas into robust, reusable components.
code9 years of coding experience
github-logo-circle

Github Skills (8)

retinanet10
net10
object-detection10
computer-vision10
mxnet10
machine-learning10
python10
loss9

Programming languages (5)

C++CSSGoLuaPython

Github contributions (5)

github-logo-circle
tusen-ai/simpledet

Jan 2019 - Aug 2019

A Simple and Versatile Framework for Object Detection and Instance Recognition
Role in this project:
userML Engineer
Contributions:14 commits, 25 PRs, 13 pushes in 6 months
Contributions summary:Han primarily focused on enhancing the SimpleDet framework for object detection and instance recognition. Their contributions included implementing FP16 training for RetinaNet, refactoring the FPN module, and refactoring and fixing various components of the RetinaNet architecture, including the metric calculation. These changes demonstrate a focus on improving performance and functionality within the object detection framework.
backboneefficientnetdeep-learningrecognitionobject-detection
xchani/simpledet

Feb 2019 - Sep 2020

A Simple and Versatile Framework for Object Detection and Instance Recognition
Contributions:73 pushes, 4 branches in 1 year 6 months
recognitionobject-detectioncomputer-visionversatile
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.
Request Free Trial
Han Chen - Research Assistant at The Chinese University of Hong Kong