BIOGRAPHY

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 Senior Research Director for RBC's Borealis AI.

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. Dr. Mori received the Canadian Image Processing and Pattern Recognition Society (CIPPRS) Award for Research Excellence and Service in 2008. Dr. Mori received NSERC Discovery Accelerator Supplement awards in 2008 and 2015. He received the ICCV Helmholtz Prize in 2017. He served on the editorial boards of IJCV and T-PAMI, the top journals in computer vision, and on the organizing committees for CVPR, ICCV, ECCV, NeurIPS, and ICLR, the top conferences in computer vision and machine learning. He was a Program Chair for CVPR 2020 and will be a General Chair for CVPR 2023. He is privileged to have worked with many excellent students while at SFU.

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 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:

Please see the Vision and Media Lab for a list of research projects, or my list of publications for more details.

STUDENT NEWS

	Mengyao Zhai successfully defended her Ph.D. thesis Towards Lifelong Learning for Generative Adversarial Networks. Congratulations Mengyao!
	Mohammad Hadi Salari successfully defended his M.Sc. thesis Kronecker-factored Hessian Approximation for Continual Learning. Congratulations Hadi!
	Hamed Shirzad successfully defended his M.Sc. thesis Graph Generation Using Tree Decomposition. Congratulations Hamed!
	Mengyao Zhai (PhD) and Lei Chen (PhD) had a paper accepted to IEEE/CVF Computer Vision and Pattern Recognition (CVPR), 2021. A lifelong learning approach for conditional image generation is presented.
	Xiaobin Chang (PDF) had a paper accepted to IEEE/CVF Computer Vision and Pattern Recognition (CVPR), 2021. Discriminative prototypes are learned for dynamic time warping based sequence matching.
	Sha Hu (PhD) had a paper accepted to International Conference on Robotics and Automation (ICRA), 2021. Multi-fidelity Bayesian optimization is used to efficiently search for robot designs using simpler tasks and fewer epochs of learning.
	Nazanin Mehrasa successfully defended her Ph.D. thesis Towards Event Analysis in Time-series Data: Asynchronous Probabilistic Models and Learning from Partial Labels.. Congratulations Nazanin!
	Yu Gong (PhD) had a paper accepted to International Conference on Artificial Intelligence and Statistics (AISTATS), 2021. A variational autoencoder modeling masks for data imputation is presented.
	Ruizhi Deng (PhD) had a paper accepted to Neural Information Processing Systems (NeurIPS), 2020. A normalizing flow model for time series data is presented.
	Srikanth Muralidharan successfully defended his Ph.D. thesis Multi-person Video Understanding with Deep Neural Networks. Congratulations Srikanth!
	Mengyao Zhai (PhD), Lei Chen, Fred Tung (PDF), Jiawei He (PhD), and Megha Nawhal (PhD) had a paper accepted to European Conference on Computer Vision (ECCV), 2020. PiggybackGAN, a lifelong learning framework with filter reuse for image generation is presented.
	Megha Nawhal (PhD) and Mengyao Zhai (PhD) had a paper accepted to European Conference on Computer Vision (ECCV), 2020. Zero-shot generation of human-object interaction videos is achieved via a novel graph-based GAN discriminator.
	Sha Hu (PhD) had a paper accepted to IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2020. Strategies for crowd navigation are learned from graph-based representations of people.
	Jiawei He successfully defended his Ph.D. thesis Theoretical and Applicational Advances in Variational Autoencoders. Congratulations Jiawei!
	Zhiwei Deng successfully defended his Ph.D. thesis Learning Deep Structured Models for Visual Understanding. Congratulations Zhiwei!
	Yu Gong successfully defended his M.Sc. thesis Latent Structure Learning in Variational Autoencoders. Congratulations Yu!
	Akash Abdu Jyothi (PhD), Thibaut Durand (PDF), and Jiawei He (PhD) had a paper accepted to IEEE/CVF International Conference on Computer Vision (ICCV), 2019. A VAE model for counts and layouts of objects in scenes, capable of capturing diverse quantities and arrangements for image generation.
	Mengyao Zhai (PhD), Lei Chen, Fred Tung (PDF), Jiawei He (PhD), and Megha Nawhal (PhD) had a paper accepted to IEEE/CVF International Conference on Computer Vision (ICCV), 2019. A framework for continual learning of conditional generation, alleviating the need for maintaining input conditions as well as desired output.
	Fred Tung (PDF) had a paper accepted to IEEE/CVF International Conference on Computer Vision (ICCV), 2019. Knowledge distillation between student and teacher neural networks by maintaining *similarities* of activations among semantically related training examples, rather than the standard mimicking of actual outputs.
	Ruizhi Deng successfully defended his M.Sc. thesis Adaptive Appearance Rendering. Congratulations Ruizhi!
	Jiawei He (PhD) and Yu Gong had a paper accepted to the International Conference on Learning Representations, 2019. A method for learning latent dependency structures in VAEs is developed.
	Nazanin Mehrasa (PhD), Akash Abdu Jyothi (PhD), Thibaut Durand (PDF), and Jiawei He had a paper accepted to IEEE/CVF Computer Vision and Pattern Recognition (CVPR), 2019. The paper develops a novel variational autoencoder model for point process time series data.
	Thibaut Durand (PDF) and Nazanin Mehrasa (PhD) had a paper accepted to IEEE/CVF Computer Vision and Pattern Recognition (CVPR), 2019. Learning classifiers from partial annotations is explored in this work.
	Yifang Fu successfully defended her M.Sc. thesis Deep Video Visual Relation Detection. Congratulations Yifang!
	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 (NeurIPS), 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.

TEACHING

• CMPT 225: Data Structures and Programming [Spring 2013, Spring 2012, Spring 2010]
• CMPT 310: Artificial Intelligence [Fall 2008, Fall 2007, Fall 2006, Fall 2005, Summer 2005, Fall 2004]
• CMPT 419/726: Machine Learning [Fall 2019, Fall 2018, Fall 2016, Fall 2015, Fall 2014, Fall 2013, Fall 2011, Fall 2009, Summer 2008]
• CMPT 882: Recognition Problems in Computer Vision [Summer 2009, Fall 2007, Fall 2006, Fall 2005, Fall 2004]
• CMPT 888: Human Activity Recognition [Summer 2010]
• Statistical and Structural Recognition of Human Actions [ECCV 2010 tutorial]
• Emerging Topics in Human Activity Recognition [CVPR 2014 tutorial]
• Human Activity Recognition [CVPR 2018 tutorial] [slides]

STUDENTS AND POSTDOCS

Current

• Ph.D.: Ruizhi Deng, Yu Gong, Sha Hu, Akash Abdu Jyothi, Mehran Khodabandeh, Megha Nawhal

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

SERVICE

• Program Chair, IEEE Computer Vision and Pattern Recognition (CVPR 2020)
• Program Chair, Asian Conference on Computer Vision (ACCV 2018)
• Program Chair, IEEE Winter Conference on Applications of Computer Vision (WACV 2016)
• Associate Editor, IEEE Transactions on Pattern Analysis and Machine Intelligence (2010-2018)
• Editorial Board, International Journal of Computer Vision (2013-2019)
• Area Chair:
  • IEEE Computer Vision and Pattern Recognition (CVPR 2012, 2014, 2017, 2018)
  • IEEE International Conference on Computer Vision (ICCV 2015)
  • European Conference on Computer Vision (ECCV 2014, 2018)
  • Neural Information Processing Systems (NeurIPS 2017, 2018, 2019, 2020)
  • International Conference on Learning Representations (ICLR 2021)
• Outstanding Reviewer Award (ICCV 2009, CVPR 2010)

VITA

• Publication list
• Brief biography
• Full curriculum vitae