Dingquan Li
副研究员 at 鹏城实验室
Shenzhen, Guangdong Province, China
Summary
👤
Senior🎓
Top SchoolDingquan Li is an accomplished research scientist and engineer with nine years of experience at the intersection of computer vision, machine learning, and video coding, currently serving as Associate Researcher at Peng Cheng Laboratory. He holds a PhD in Applied Mathematics from Peking University and combines strong theoretical foundations with hands-on systems work in data representation, compression, quality assessment, and perceptual optimization. His contributions span from national lab research to practical open-source fixes—such as improving Python 3 compatibility and MAE implementations in the widely used scikit-video project—reflecting attention to reproducibility and robustness. Based in Shenzhen, he blends multidisciplinary training in electronics and mathematical finance with a pragmatic focus on perceptual quality metrics, often bridging academic rigor and production-ready implementations.
9 years of coding experience
6 years of employment as a software developer
理学博士, 应用数学, 理学博士, 应用数学 at 北京大学Bachelor of Science (BSc), 数学与应用数学（数理金融与精算科学）, Bachelor of Science (BSc), 数学与应用数学（数理金融与精算科学） at Nankai UniversityBachelor of Engineering (BE), 电子科学与技术, Bachelor of Engineering (BE), 电子科学与技术 at 南开大学韶关市第一中学
Chinese, Chinese, 客家话, Chinese
Github Skills (5)
video-processing10
python10
numpy10
scientific-computing9
360-video7
Programming languages (6)
Github contributions (5)
scikit-video/scikit-video
Apr 2018 - Apr 2018
Video Processing in Python
Role in this project:
Backend Developer
Backend DeveloperContributions:7 commits, 4 PRs, 3 comments in 4 days
Contributions summary:Dingquan primarily contributed to bug fixes and code improvements within the scikit-video library, focusing on the Python implementation. Their work included fixing Python 3 compatibility issues, correcting typos, and standardizing inputs across several modules. They also refactored code related to mean absolute error (MAE), demonstrating a focus on improving existing functionalities and ensuring code accuracy.
pythonscientific-computingffmpeg-wrappervideo-processingvideo
lidq92/WaDIQaM
Apr 2018 - May 2021
[unofficial] Pytorch implementation of WaDIQaM in TIP2018, Bosse S. et al. (Deep neural networks for no-reference and full-reference image quality assessment)
Contributions:1 release, 29 commits, 24 pushes in 3 years 1 month
pytorchblind-image-quality-assessmentfull-reference-iqadeep-learningneural-networks
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.