Yang Zhou
Senior Research Scientist at Adobe
Virginia, United States
Summary
🤩
Rockstar🎓
Top SchoolYang Zhou is a Senior Research Scientist at Adobe Research with nine years of experience at the intersection of computer vision, graphics, and deep learning, focused on video generation, digital humans, and audio-visual learning. He earned a PhD from UMass Amherst and advanced degrees from Georgia Tech and Shanghai Jiao Tong University, bringing strong academic foundations to product-facing research. At Adobe he has shipped and maintained projects like MakeItTalk, contributing both modeling and full-stack engineering to audio-driven facial animation and puppet-generation tools. His work aims to empower artists and animators by translating deep learning advances into practical creative tools and VFX workflows. Based in Virginia, he combines rigorous research with hands-on implementation and testing, often refining training pipelines and end-to-end systems. An early game-design stint and recurring intern roles reflect a practical curiosity for interactive media that informs his research-driven engineering.
9 years of coding experience
8 years of employment as a software developer
Master of Engineering (Meng), Electrical and Computer Engineering, Master of Engineering (Meng), Electrical and Computer Engineering at Georgia Institute of TechnologyDoctor of Philosophy (PhD), Computer Science, Doctor of Philosophy (PhD), Computer Science at University of Massachusetts AmherstMaster of Engineering (MEng), Electrical Engineering, Master of Engineering (MEng), Electrical Engineering at Shanghai Jiao Tong University
Github Skills (8)
argparse10
computer-vision10
machine-learning10
opencv10
python10
image-processing10
testing9
tensorflow5
Programming languages (3)
Github contributions (5)
yzhou359/MakeItTalk
Mar 2021 - Dec 2021
Role in this project:
ML Engineer
ML EngineerContributions:7 commits, 24 pushes, 49 comments in 8 months
Contributions summary:Yang's commits center on the development of a "puppet generation tool" within a project related to facial landmark detection and image manipulation. The primary contribution appears to be the addition of this new tool, along with modifications to existing scripts and functions. The code changes reveal interactions with libraries for face alignment, image processing, and potential integration with a deep learning model for facial feature extraction. The user is likely responsible for integrating the puppet generation tool into an existing pipeline.
adobe-research/MakeItTalk
Oct 2020 - Apr 2021
Role in this project:Full-stack Developer
Full-stack DeveloperContributions:28 commits, 3 PRs, 6 pushes in 6 months
Contributions summary:Yang primarily focused on updating test code arguments and parameters. Their changes included modifying argument parsers in the `main_end2end.py` and `main_end2end_cartoon.py` files, indicating a focus on refining the project's testing infrastructure and end-to-end functionality. These adjustments likely involved improving the testing process and ensuring the correct execution of the project's core features. Further contributions updated training content, specifically in `src/approaches/train_content.py` indicating a hand in the model training and performance.
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.