Abstract: Visual recognition involves reasoning about structured relations at multiple levels of detail.  For example, human behaviour analysis requires a comprehensive labeling covering individual low-level actions to pair-wise interactions through to high-level events.  Scene understanding can benefit from considering labels and their inter-relations.  In this talk I will present recent work by our group building deep learning approaches capable of modeling these structures.  I will present models for learning trajectory features that represent individual human actions, and hierarchical temporal models for group activity recognition.  General purpose structured inference machines will be described, building from notions of message passing within graphical models.  These will be used in models for inferring individual and group activity and modeling structured relations for image labeling problems.

Bio: Greg Mori received the Ph.D. degree in Computer Science from the University of California, Berkeley in 2004.  He received an Hon. B.Sc. in Computer Science and Mathematics with High Distinction from the University of Toronto in 1999.  He spent one year (1997-1998) as an intern at Advanced Telecom munications Research (ATR) in Kyoto, Japan. He spent part of 2014-2015 as a Visiting Scientist at Google in Mountain View, CA.  After graduating from Berkeley, he returned home to Vancouver and is currently a Professor and the Director of the School of Computing Science at Simon Fraser University.  Dr. Mori’s research interests are in computer vision and machine learning.  Dr. Mori has served on the organizing committees of the major computer vision conferences (CVPR, ECCV, ICCV).  Dr. Mori is an Associate Editor of IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) and an Editorial Board Member of the International Journal of Computer Vision (IJCV).

Host: Kris Kitani

For Appointment: Chris Downey (cdowney@andrew.cmu.edu)