Past talk · AI/ML Seminar Series
Visual Recognition beyond Appearances, and its Robotic Applications
Assistant Professor, School of Computing, Informatics, and Decision Systems Engineering, Arizona State University
- Date & time
- Monday, January 25, 2021 · 1:00 PM
- Location
- Online (live stream)
Abstract
The goal of Computer Vision is to develop algorithms to answer What is Where at When from visual appearance. The speaker recognizes the importance of studying underlying entities and relations beyond visual appearance, following an Active Perception paradigm. This talk presents efforts ranging from reasoning beyond appearance for visual question answering, image understanding, and video captioning, through temporal knowledge distillation with incremental knowledge transfer, to their roles in a robotic visual learning framework via a robotic indoor object search task. The talk also features the Active Perception Group's ongoing projects in autonomous driving, AI security, and healthcare.
About the speaker
Yezhou Yang is an Assistant Professor at Arizona State University, directing the ASU Active Perception Group. His interests lie in cognitive robotics, computer vision, and robot vision. Before ASU he was a Postdoctoral Research Associate at the University of Maryland Institute for Advanced Computer Studies. He is a recipient of a Qualcomm Innovation Fellowship, an NSF CAREER award, and an Amazon AWS Machine Learning Research Award.