James Rehg

James Rehg

Professor
Interactive Computig
Academic Specialty: 
Computer Vision
James M. Rehg (pronounced "ray") received his Ph.D. in Electrical and Computer Engineering from CMU in 1995. His dissertation work resulted in DigitEyes, the first video-based real-time system for tracking the full DOF of the human hand. He joined the Cambridge Research Lab of the Digital Equipment Corp. in 1995, and in 1996 he became the Manager of the Computer Vision Research Group. He led a wide range of research activities in computer vision and machine learning over the next five years. His collaboration with Michael Jones resulted in a widely-used technique for detecting skin in images, which is currently used in Google Image Search. In collaboration with Vladimir Pavlovic and Kevin Murphy, Dr. Rehg pioneered the use of probabilistic graphical models (specifically, switching linear dynamic systems) in video-based tracking. His collaboration with Tat-Jen Cham on tracking Fred Astaire's dance movements resulted in one of the first applications of computer vision analysis to movie footage. In 2001, Dr. Rehg joined the College of Computing in the Georgia Institute of Technology at the rank of Associate Professor. In 2009, he was promoted to Full Professor within the School of Interactive Computing. He co-directs the Computational Perception Lab and is the Associate Director of Research within the Center for Robotics and Intelligent Machines (RIM@GT). Dr. Rehg has authored more than 100 peer-reviewed scientific papers and holds 23 issued US patents. His research interests include computer vision, medical imaging, robot perception, machine learning, and pattern recognition. He is currently leading a multi-institution effort to develop the science and technology of Behavior Imaging, the capture and analysis of social and communicative behavior using multi-modal sensing, to support the study and treatment of developmental disorders such as autism. Dr. Rehg is active in the program and organizing committees of the major conferences in computer vision, robotics, and machine learning. In 2009, he served as the General co-Chair of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), one of the top international conferences in computer vision. In 2010, he was an Associate Editor for the IEEE Intl. Conf. on Robotics and Automation (ICRA). He has co-organized numerous workshops, including the First IEEE Workshop on Projector-Camera Systems (PROCAMS 03), and the First IEEE Workshop on Visual Place Categorization (VPC 09). He has served on the Editorial Board of the International Journal of Computer Vision, one of the top two international journals in computer vision, since 2004. He is a Senior Editor of the Encyclopedia of Computer Vision, to be published by Springer in 2011. In 2001, Dr. Rehg received the NSF Career Award and in 2005 he received the Raytheon Faculty Fellowship from Georgia Tech. He and his students have been the recipient of several best paper awards, including the Distinguished Student Paper Award at the Intl. Conf. on Machine Learning in 2005 and the Best Student Paper Prize at the British Machine Vision Conference in 2010.