Greg Mori

Associate Professor
School of Computing Science
Simon Fraser University
8888 University Drive
Burnaby, BC
CANADA V5A 1S6

Office: TASC1 8007
Phone: (778) 782-7111
Fax: (778) 782-3045
mori@cs.sfu.ca

Ph.D. in Computer Science, University of California at Berkeley, 2004.
Hon. B.Sc. in Computer Science and Mathematics, University of Toronto, 1999.
Greg Mori

QUICK LINKS

[Publication list], [Students and Postdocs], [Teaching]


RESEARCH INTERESTS

My research is in computer vision, and is concerned with developing algorithms that automatically interpret images and videos, particularly those containing people. I have made significant contributions towards solving the problems of human pose estimation and human action recognition. At a broad level, the methodology followed is to construct features and representations that capture our intuition regarding these vision problems. We operationalize these via machine learning algorithms, adapting them to suit our purposes.

Specific examples of features and representations include work on superpixels for representing images, motion features for human action recognition, and our bag-of- words model for video sequences. We have developed variants of machine learning algorithms for models such as the hidden Conditional Random Field (hCRF) and Latent Dirichlet Allocation (LDA) to implement these ideas.

Research interests keywords:

  • computer vision
  • machine learning
  • video analysis
  • human activity recognition
  • human body pose estimation
  • pedestrian detection and tracking
  • object recognition
Please see the Vision and Media Lab for a list of research projects, or my list of publications for more details.

STUDENT NEWS

Arash Vahdat (PhD) and Guang-Tong Zhou (PhD) had a paper accepted to the European Conference on Computer Vision (ECCV), 2014. An approach for discovering clusters of related internet videos is presented, utilizing noisy tag labels and image features.
Yasaman Sefidgar successfully defended her M.Sc. thesis Discriminative Key-Segment Model for Interaction Detection. Congratulations Yasaman!
Amir Bakhtiari successfully defended his M.Sc. thesis Detecting Pedestrians Using Motion Patterns: A Latent Tracking Approach. Congratulations Amir!
Nataliya Shapovalova (PhD) had a paper accepted to Neural Information Processing Systems (NIPS), 2013. A joint model for visual saliency and action recognition in videos is described, trained in a latent SVM framework utilizing eye gaze data.
Guang-Tong Zhou (PhD), Tian Lan (PhD), and Arash Vahdat (PhD) had a paper accepted to Neural Information Processing Systems (NIPS), 2013. The paper describes an approach for clustering with latent variables under a max-margin criterion, with application to videos of human activities.
Tian Lan successfully defended his Ph.D. thesis From Flat to Hierarchical: Modeling Structures in Visual Recognition. Congratulations Tian!
Arash Vahdat (PhD) had a paper accepted to IEEE International Conference on Computer Vision (ICCV), 2013. An algorithm for predicting a set of tags that describe and image or video is described, trained from noisy tag annotations.
Arash Vahdat (PhD) and Kevin Cannons (PDF) had a paper accepted to IEEE International Conference on Computer Vision (ICCV), 2013. A compositional model for video event recognition is presented, based on a novel multiple kernel learning algorithm that incorporates latent variables.
Tian Lan (PhD) had a paper accepted to IEEE International Conference on Computer Vision (ICCV), 2013. A multi-level object detection framework that models sub-categories through to visual composites is developed.
Hossein Hajimirsadeghi (PhD) and Jinling Li (MSc) had a paper accepted to the Conference on Uncertainty in Artificial Intelligence (UAI), 2013. A multiple instance learning algorithm is developed, which models varying levels of positive instances in a bag. A discriminative training algorithm is proposed, based on efficient inference of cardinality-based clique potential functions.
Tian Lan (PhD) had a paper accepted to IEEE Computer Vision and Pattern Recognition (CVPR), 2013. This work develops an image tag ranking algorithm that can determine which keywords are more relevant to a given image.
Guang-Tong Zhou (PhD), Tian Lan (PhD), and Weilong Yang had a paper accepted to IEEE Computer Vision and Pattern Recognition (CVPR), 2013. An image classification algorithm that matches a set of objects to an image is developed.
Yuke Zhu (BSc) and Tian Lan (PhD) had a paper on activity recognition accepted to IAPR Conference on Machine Vision Applications (MVA), 2013. Latent variable models were used to analyze nursing home surveillance video.
[less new news]

TEACHING

STUDENTS AND POSTDOCS

Current Former
  • Yang Wang, Learning Structured Models for Human Actions and Poses, Ph.D. Summer 2009 (then NSERC postdoc at UIUC, now Asst. Prof. at U Manitoba)
  • Mani Ranjbar, Optimizing Non-Decomposable Loss Functions In Structured Prediction, Ph.D. Summer 2012 (now at D-Wave Systems)
  • Weilong Yang, Discriminative Latent Variable Models For Visual Recognition, Ph.D. Fall 2012 (now at Google Research)
  • Tian Lan, From Flat to Hierarchical: Modeling Structures in Visual Recognition, Ph.D. Summer 2013 (now postdoc at Stanford)
  • Payam Sabzmeydani, Detecting Pedestrians in Still Images Using Learned Shape Features, M.Sc. Fall 2006 (then at Koolhaus Games, now at AirG)
  • Andy Rova, Eigen-CSS Shape Matching and Recognizing Fish in Underwater Video, M.Sc. Spring 2007
  • Topher Johnson, Responsive Video-Based Motion Synthesis Using Motion Graphs, M.Sc. Summer 2007 (now at Blast Radius)
  • Maryam Moslemi, Clustering and Visualizing Actions of Humans and Animals Using Motion Features, M.Sc. Fall 2007 (then UIUC M.Sc. student, now at Salesforce.com)
  • Alireza Fathi, Efficient Human Figure Tracking Using Motion Exemplars, M.Sc. Summer 2008 (next Georgia Tech Ph.D. student)
  • William Ma, Motion Estimation For Functional Medical Imaging Studies Using A Stereo Video Head Pose Tracking System, M.Sc. Summer 2009 (now at Leovation)
  • Mohammad Norouzi, Convolutional Restricted Boltzmann Machines for Feature Learning, M.Sc. Fall 2009 (next U of Toronto Ph.D. student)
  • Weilong Yang, Learning Transferable Distance Functions For Human Action Recognition And Detection, M.Sc. Spring 2010 (next SFU Ph.D. student)
  • Bahman Yari Saeed Khanloo, Combining Simple Trackers Using Structural SVMs For Offline Single Object Tracking, M.Sc. Summer 2010 (now CWI Ph.D. student)
  • Tian Lan, Beyond Actions: Discriminative Models For Contextual Group Activities, M.Sc. Summer 2010 (next SFU Ph.D. student)
  • Ferdinand Stefanus, Automatic Pedestrian Detection and Tracking with a Multiple-Cue Max-Margin Framework, M.Sc. Fall 2010 (next MacDonald, Dettwiler and Associates Ltd. (MDA))
  • Arash Vahdat, A Key Pose Model For Human Interaction Recognition And Color From Gray By Optimized Color Ordering, M.Sc. Spring 2011 (next SFU Ph.D. student)
  • Bo Gao, Exemplar-Based Human Interaction Recognition: Features And Key Pose Sequence Model, M.Sc. Summer 2011 (next Software Engineer at Trusterra Inc., then Fortinet, then Microsoft)
  • Pengfei Yu, Image Classification Using Latent Spatial Pyramid Matching, M.Sc. Summer 2011 (next Software Test Engineer at Microsoft, then Facebook)
  • Brian Milligan, Selecting And Commanding Groups Of Robots Using A Vision-Based Natural User Interface, M.Sc. Summer 2012 (next Big Park / Microsoft)
  • Zhi Feng Huang, Latent Boosting For Action Recognition, M.Sc. Summer 2012 (next Apple)
  • Amir Bakhtiari, Detecting Pedestrians Using Motion Patterns: A Latent Tracking Approach, M.Sc. Fall 2013 (next Vidigami)
  • Yasaman Sefidgar, Discriminative Key-Segment Model for Interaction Detection, M.Sc. Spring 2014
  • Jen Fernquist, NSERC Undergraduate Student Research Award (USRA), Summer 2006 (next MDA, then UBC M.Sc. student, then Google)
  • Chris Lundgren, NSERC Undergraduate Student Research Award (USRA), Summer 2006 (next Safe Software)
  • Angelica Lim, NSERC Undergraduate Student Research Award (USRA), Spring 2008 (then at Google, next Monbukagakusho at Kyoto U.)
  • Bo Chen, CMPT 415 Directed Studies, RA, Spring 2007, Summer 2007, Summer 2008 (then UBC M.Sc. student, next Caltech Ph.D. student)
  • Mark Bayazit, NSERC Undergraduate Student Research Award (USRA), RA, Summer 2008, Fall 2008 (next at ShipSmartly.com Enterprises Inc.)
  • Aditya Ramesh, NSERC Undergraduate Student Research Award (USRA), Summer 2009 (next Stanford M.Sc. student)
  • Ben Reilly, RA, Spring 2011 (next Toronto M.Sc.)
  • Jia Sun, RA, Spring 2011 (next SFU B.Sc.)
  • Wesley May, NSERC Undergraduate Student Research Award (USRA), Summer 2011 (next Toronto M.Sc.)
  • Youyou Yang, RA Fall 2011, Spring 2012
  • Pouria Mahmoudi Saghalati, NSERC Undergraduate Student Research Award (USRA), Summer 2012
  • Yuke Zhu, RA Summer 2012, Fall 2012 (next Stanford M.Sc. student)

Are you a prospective student? Please read this page for prospective students.

SERVICE

VITA

AFFILIATIONS


Vision and Media Lab


Scientific Data Aquisition, Transportation and Storage Research Lab (SDATS)


Technology for Injury Prevention in Seniors (TIPS)