Xiaodong Yang is a Research Scientist at NVIDIA Research. His research interests are in the areas of computer vision, machine learning, deep learning, and multimedia. He has been working on image and video understanding, gesture and activity recognition, video surveillance event detection, dynamic facial analytics, multimedia search, assistive technology, etc. He received his Ph.D. from City University of New York in 2015 and B.S. from Huazhong University of Science and Technology in 2009.
Three papers accepted by CVPR 2018 on visual sequence learning, optical flow estimation, and video generation.
Our dynamic facial analysis work, part of NVIDIA AI Co-Pilot, featured in NVIDIA Blog.
One paper accepted by CVPR 2017 on face alignment and head pose estimation.
Our paper on 3D action recognition wins JVCI Best Paper Award!
One full (oral) paper accepted by ACM Multimedia 2016 on video classification.
One paper accepted by TPAMI on action recognition.