Summary
Vinh Tran is a research scientist with 9 years of experience specializing in computer vision and human action understanding, now applying generative AI to digital humans at SpreeAI. He earned a PhD in Computer Science from Stony Brook University, where his research advanced early action recognition, action anticipation, cross-modal text-video retrieval, and hands/active-object detection in first-person videos. Vinh has bridged academia and industry through internships and visiting roles—contributing scene text recognition techniques at VinAI and building an award-winning video browsing tool at the National Institute of Informatics. He combines strong teaching experience in machine learning with hands-on research deployment, favoring knowledge distillation and cross-modal similarity as practical levers for training on unannotated data. Known for turning complex temporal and multimodal problems into tractable systems, he blends deep technical rigor with a pragmatic focus on real-world video understanding applications.
9 years of coding experience
7 years of employment as a software developer
Master of Science - MS Information Systems, Master of Science - MS Information Systems at VNUHCM - University of Science
Doctor of Philosophy - PhD Computer Science, Doctor of Philosophy - PhD Computer Science at Stony Brook University
Vietnamese, English