Event Location: NSH 1507
Bio: Michael S. Ryoo is an Assistant Professor of the School of Informatics and Computing at Indiana University. His research interest is within the areas of Computer Vision and Human-Robot Interaction, with a particular emphasis on human activity recognition, first-person vision, and wearable/ubiquitous cameras. Before joining IU, Dr. Ryoo was a staff researcher within the Robotics Section of the NASA’s Jet Propulsion Laboratory (JPL) from 2011 to 2015. Dr. Ryoo received the Ph.D. degree from the University of Texas at Austin in 2008, and the B.S. degree from the Korea Advanced Institute of Science and Technology (KAIST) in 2004. He organized a number of tutorials and workshops at major Computer Vision conferences, and was the corresponding author of the activity recognition survey paper published by ACM Computing Surveys on 2011. Dr. Ryoo is also currently affiliated with JPL as their Research Affiliate.

Abstract:
We are entering the era of big video data where cameras are ubiquitous. In particular, the amount of videos from wearable cameras and robots is explosively rising. These videos, taken from an actor’s own viewpoint, are called ‘first-person videos’ or ‘egocentric videos’. In this seminar, we discuss different types of videos robots are expected to face in their everyday operation, and overview approaches to recognize human activities from such videos. We present features and recognition algorithms necessary for activity-level understanding of first-person videos, and describe how they make recognition of human-human (and human-robot) interactions possible. Approaches for human activity ‘prediction’ from streaming videos will also be described, which allow the robots to infer humans’ intended activities at their early stage.