Event Location: NSH 1507
Bio: Wongun Choi received his BS degree in Electrical Engieering in the Seoul National University in 2008 and MS degree in Electrical and Computer Engineering in the University of Michigan, Ann Arbor in 2011. Currently, he is working toward his Ph.D degree at the Computer Vision Lab in the University of Michigan, Ann Arbor. His research interests include object tracking, object detection, scene understanding and activity recognition.

Abstract: Understanding human motions and activities in videos is an important problem in many application domains, including surveillance, robotics, video indexing, and sports analysis. Although much progress has been made in classifying single person’s activities in simple videos, little efforts have been made toward the interpretation of behaviors of multiple people in natural videos. In this talk, I will present my research endeavor toward the understanding of behaviors of multiple people in natural unconstrained videos. I identify three major challenges in this problem: i) identifying individual properties of people in videos, ii) understanding interactions between people, and iii) discovering multiple activities, which are happening simultaneously. I discuss how we solve these challenging problems using various computer vision and machine learning technologies. I conclude with a number of observations that we found in this line of research and possible future research directions.