Summary
Zehua Zhang is an AI research scientist specializing in computer vision and machine learning with nine years of experience and a Ph.D. from Indiana University Bloomington. His work centers on video understanding, spanning self-supervised video representation learning, action recognition/anticipation across first- and third-person views, multimodal fusion, and computational human attention modeling. He currently researches applied CV problems at Meta after contributing to Reality Labs and internships at Honda Research Institute and Midea, bringing both academic rigor and product-minded solutions for AR/VR and autonomous systems. Zehua’s projects frequently bridge theory and real-world sensing—e.g., attention modeling for driving and multimodal fusion for embodied agents—highlighting a knack for translating complex models into domain-relevant outcomes. Based in Redmond, he combines deep research experience with practical industry impact, often working on problems that improve perception in interactive and safety-critical environments.
9 years of coding experience
5 years of employment as a software developer
Doctor of Philosophy (Ph.D.), Computer Science, Doctor of Philosophy (Ph.D.), Computer Science at Indiana University Bloomington
Bachelor of Engineering (B.Eng.), Automation, Bachelor of Engineering (B.Eng.), Automation at 西安交通大学