Greg MoriResearch Director
Borealis AI Vancouver
School of Computing Science
Simon Fraser University
8888 University Drive
CANADA V5A 1S6
Faculty office: TASC1 8007
Phone: (778) 782-7111
Fax: (778) 782-3045
Ph.D. in Computer Science, University of California at Berkeley, 2004.
Hon. B.Sc. in Computer Science and Mathematics, University of Toronto, 1999.
Dr. Greg Mori was born in Vancouver and grew up in Richmond, BC. He
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 Telecommunications Research
(ATR) in Kyoto, Japan. After graduating from Berkeley, he
returned home to Vancouver and is currently a Professor in
the School of Computing Science at Simon Fraser University.
He was a Visiting Scientist at Google in Mountain View, California in 2014-2015. He served as Director of the School of Computing Science from 2015-2018. He is now Research Director for RBC's Borealis AI Vancouver lab.
Dr. Mori conducts research in computer vision and machine learning, and teaches classes in data structures and programming, artificial intelligence, computer vision, and machine learning. He served on the editorial boards of IJCV and T-PAMI, the top journals in computer vision, and on the organizing committees for NIPS, CVPR, ICCV, and ECCV, the top conferences in computer vision and machine learning. He will be a Program Chair for CVPR 2020. He is privileged to have worked with many excellent students while at SFU.
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
Specific examples of features and representations include work on superpixels for representing images, motion features for human action recognition, and our structured models for video sequences and group activities. We have developed variants of machine learning algorithms such as hidden Conditional Random Fields (hCRF), Latent Dirichlet Allocation (LDA), latent SVMs, and deep networks to implement these ideas.
Research interests keywords:
|Yifang Fu successfully defended her M.Sc. thesis Deep Video Visual Relation Detection. Congratulations Yifang!|
|Jiawei He (PhD) and Yu Gong had a paper accepted to the Bayesian Deep Learning Workshop (at NeurIPS), 2018. A method for learning latent dependency structures in VAEs is developed.|
|Jiawei He (PhD) had a paper accepted to the Symposium on Advances in Approximate Bayesian Inference (at NeurIPS), 2018. The paper describes a semantic prior for image generation.|
|Mostafa S. Ibrahim successfully defended his Ph.D. thesis Deep Models for Multi-Person Activity Understanding. Congratulations Mostafa!|
|Zhiwei Deng (PhD), Jiacheng Chen (BSc), and Yifang Fu (MSc) had a paper accepted to Neural Information Processing Systems (NIPS), 2018. A programmatic approach to constructing priors for VAE-based generative models for complex scenes is proposed.|
|Jiawei He (PhD) had a paper accepted to the European Conference on Computer Vision (ECCV), 2018. A temporal variational auto-encoder for synthesizing controllable sequences of human motion is presented.|
|Changan Chen (BSc) and Fred Tung (PDF) had a paper accepted to the European Conference on Computer Vision (ECCV), 2018. A deep network compression algorithm for meeting operational performance constraints is presented.|
|Ruizhi Deng (MSc) and Zhiwei Deng (PhD) had a paper accepted to the European Conference on Computer Vision (ECCV), 2018. A sparse aggregation approach for deep neural networks is proposed and analyzed.|
|Fabien Baradel (visiting PhD) had a paper accepted to the European Conference on Computer Vision (ECCV), 2018. An object reasoning approach to video understanding is presented.|
|Moustafa S. Ibrahim (PhD) had a paper accepted to the European Conference on Computer Vision (ECCV), 2018. A relational neural network layer for supervised and unsupervised learning of human-contextual feature learning for group activity recognition is presented.|
|Mengyao Zhai (PhD), Ruizhi Deng (MSc), Jiacheng Chen (BSc), Lei Chen (PhD) and Zhiwei Deng (PhD) had a paper accepted to the British Machine Vision Conference (BMVC), 2018. An adaptive rendering approach for generating images of human action is developed.|
|Fred Tung (PDF) had a paper accepted to IEEE Computer Vision and Pattern Recognition (CVPR), 2018. Deep network weight pruning and quantization are learned in parallel with training.|
|Jiawei He (PhD), Zhiwei Deng (PhD), and Moustafa S. Ibrahim (PhD) had a paper accepted to IEEE Winter Conf. on Applications of Computer Vision (WACV), 2018. A class-independent action tublet network for human action localization is presented.|
|Akash Abdu Jyothi successfully defended his M.Sc. thesis Generating Natural Language Summaries for Image Sets. Congratulations Akash!|
|Nelson Nauata successfully defended his M.Sc. thesis Structured Label Inference for Visual Understanding. Congratulations Nelson!|
|Jon Smith successfully defended his M.Sc. thesis REP3D: 3D Human Motion Capture Dataset for Athletic Movement. Congratulations Jon!|
Are you a prospective student? Please read this page for prospective students.