Jinheng Xie

Student Researcher at Google DeepMind

Singapore, Singapore
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
🎓
Top School
Jinheng Xie is a PhD student in Electrical and Computer Engineering at NUS and a researcher with seven years of experience applying machine learning to real-world problems. Currently a student researcher at Google DeepMind/Google in Singapore, he brings hands-on research experience from a multi-year research internship at Tencent. His technical work spans deep learning for vision and sequence tasks, including contributions to a CRNN-based Chinese character recognition repository where he improved preprocessing, data loading, and training pipelines to boost model robustness. Comfortable bridging research and engineering, he debugs demos and integrates configuration-driven training—skills that help move prototypes toward reproducible experiments. Fluent in both academic and industry research settings, he combines rigorous PhD-level inquiry with practical systems engineering.
code8 years of coding experience
bookDoctor of Philosophy - PhD, Electrical and Computer Engineering, Doctor of Philosophy - PhD, Electrical and Computer Engineering at National University of Singapore (NUS)
github-logo-circle

Github Skills (15)

cran10
datasets10
data-preprocessing10
data-loading10
computer-vision10
machine-learning10
pytorch10
deep-learning10
trainings10
crc10
python10
load-data10
modeling10
data-set10
tensorflow3

Programming languages (7)

JavaC++CGoJupyter NotebookMATLABPython

Github contributions (5)

github-logo-circle
(CRNN) Chinese Characters Recognition.
Role in this project:
userML Engineer
Contributions:58 commits, 7 PRs, 161 pushes in 2 years 8 months
Contributions summary:Jinheng contributed to the Chinese characters recognition project by adding and modifying code related to data preprocessing, dataset loading, and model training. The user added functionalities for processing labels and updating the data loading pipeline, which is essential for training the character recognition model. They also modified the training script, incorporated configuration settings, and debugged the demo to improve the overall performance of the CRNN-based model.
chineserecognitionchinese-charactersdeep-learningocr
Sierkinhane/crnn_ctpn

Aug 2018 - Nov 2019

Unified text detection and recognition
Contributions:41 commits, 35 pushes, 1 branch in 1 year 2 months
text-detection
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