James M. Rehg

           Professor
           School of Interactive Computing
           College of Computing
           Georgia Institute of Technology

News:

7/15/11: Keynote Talk at UAI 2011

6/13/11: Keynote Talk at MVA 2011

9/24/10: Yu-Ying Liu finalist for MICCAI 10 Young Scientist Award

9/04/10: David Tsai and Matthew Flagg awarded Best Student Paper Prize at BMVC 2010

8/19/10: Georgia Tech awarded $10M NSF Expedition in Computational Behavioral Science

Recent Publications

J. Wu and J. M. Rehg. "CENTRIST: A Visual Descriptor for Scene Categorization." To appear in IEEE Trans. PAMI. Accepted for publication.
[ PDF ] : [ Project Webpage ]

M. J. Schuster, J. K. Okerman, H. Nguyen, J. M. Rehg, and C. Kemp. "Perceiving Clutter and Surfaces for Object Placement in Indoor Environments."In Proc. HUMANOIDS 2010, Nashville, TN, 2010.
[ PDF ]

H. Zhou, T. Hermans, A. Karandikar, and J. M. Rehg. "Movie Genre Classification via Scene Categorization." In Proc. ACM Multimedia 2010, Firenze, Italy. Short paper
[ PDF ]

D. Tsai, M. Flagg, and J. M. Rehg. "Motion Coherent Tracking with Multi-label MRF Optimization."In Proc. British Machine Vision Conference (BMVC 2010), Aberystwyth, UK. Winner Best Student Paper Award
[ PDF ] : [ Project Webpage ]

Y.-Y. Liu, M. Chen, H. Ishikawa, G. Wollstein, J. Schuman, and J. M. Rehg. "Automated Macular Pathology Diagnosis in Retinal OCT Images Using Multi-Scale Spatial Pyramid with Local Binary Patterns." In Proc. MICCAI 2010, Beijing, China. Oral presentation
[ PDF ]

K. Prabhakar, S. Oh, P. Wang, G. Abowd, and J. M. Rehg. "Temporal Causality for the Analysis of Visual Events." In CVPR 2010, San Francisco, CA. Oral presentation
[ PDF ]

Projects

Behavior Imaging - We are developing methods for measuring, recognizing, and quantifying childrens' social and communicative behavior using video, audio, and wearable sensor data
Causality in Video Event Analysis - Research on methods for temporal causal analysis of audio-visual events
Egocentric Video - Research on object and activity recognition from wearable sensor data
Large Scale Categorization and Retrieval of Images and Video - We are developing methods for image and video analysis that are capable of scaling to and exploiting very large dataset sizes
Computer-Assisted Diagnosis of OCT Imagery - Research on automated analysis of OCT images of the retina to assist in the diagnosis of macular pathologies
Dynamic Scene Understanding for High-Speed Driving - We are developing video event analysis methods to support high-speed autonomous driving
Clutter Manipulation - We are developing techniques for perception and manipulation of clutter in real-world environments, using the PR2 mobile manipulator
Place Categorization - Research on automatically categorizing places within a 3-D environment to support mobile robot navigation

Teaching

Fall 2011
Introduction to Probabilistic Graphical Models (CS 8803 PGM)
MWF 3:00-4:00
CCB 102

Spring 2011
Introduction to Behavior Imaging (CS 4803/8803 BHI)
MWF 2:00 - 3:00
ES&T L1175

Fall 2010
Computer Vision (CS 4495/7495)
Tu-Th 4:30 - 6:00
CCB 16

Ph.D. Students

Alumni

Contact

The best way to reach me is by email.
rehg@cc.gatech.edu
Phone: 404-894-9105

Office: CCB 315 (Directions)

Affiliations

co-Director, Computational Perception Lab
Associate Director of Research, Center for Robotics and Intelligent Machines (RIM@GT)
Health Systems Institute
GVU Center

Sponsors and Programs

National Science Foundation Expeditions in Computing Program, Expedition in Computational Behavioral Science
Army Research Office MURI Program, MURI on Autonomous High-Speed Driving
DARPA IPTO PerSEAS Program
Willow Garage PR2 Program
Additional NSF and NIH awards
Corporate sponsors include Google, Intel, Microsoft, and Mitsubishi

Biography

Short Bio

Long Bio

Consulting

Dr. Rehg has an active consulting practice based upon his expertise and experience in computer vision, robotics, medical imaging, machine learning, pattern recognition, and human-computer interaction. Some of his current and past clients include Disney, Intel, iRobot, Mitsubishi, and Mobile Intelligence.