About me

I am a 3rd year PhD student at Simon Fraser University at VML lab advised by Professor Greg Mori.

Previously, I completed my MSc. degree in the same university and received the BEng. degree from Beijing University of Posts and Telecomms.

I recently gave a talk at Vector Institute's Endless Summer School 2019 on generative models, modular networks and graph reasoning.

Research experience

Tsinghua KEG Simon Fraser University Disney Research Facebook Reality Labs

Publications

Learning to Search Person in Interactive Enviroment.

Sha Hu, Wang Zhu, Zhiwei Deng and Greg Mori.

Under submission to IROS

A Generative Process for Automatic Graph Reasoning.

Zhiwei Deng and Greg Mori.

Under submission to ICML

Learning Structured Inference Neural Networks with Label Relations.

Nelson Nauata, Hexiang Hu, Guang-tong Zhou, Zhiwei Deng, Zicheng Liao and Greg Mori.

IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), 2019.

Probabilistic Neural Programmed Networks for Scene Generation.

Zhiwei Deng, Jiacheng Chen, Yifang Fu and Greg Mori.

[paper], [project page], [supp], [poster]

Neural Information Processing Systems(NeurIPS) 2018 (Spotlight, 3.5% acceptance rate)

Sparsely Aggregated Convolutional Networks.

Ligeng Zhu, Ruizhi Deng, Michael Maire, Zhiwei Deng and Greg Mori.

[PDF] , [Project Page] , ECCV 2018

Factorized Variational Autoencoders for Modeling Audience Reactions to Movies.

Zhiwei Deng, Rajitha Navarathna, Peter Carr, Stephan Mandt, Yisong Yue, Iain Matthews and Greg Mori.

[PDF] , CVPR 2017. (Press Coverage PHYS.ORG | Caltech News | EurekAlert!)

Recalling Holistic Information for Semantic Segmentation.

Hexiang Hu*, Zhiwei Deng*, Guang-tong Zhou, Fei Sha and Greg Mori.
(* indicates equal contribution)

Arxiv, 2016.

Structure Inference Machines: Recurrent Neural Networks for Analyzing Relations in Group Activity Recognition.

Zhiwei Deng, Arash Vahdat, Hexiang Hu and Greg Mori.

IEEE Computer Vision and Pattern Recognition (CVPR), 2016.

Learning Structured Inference Neural Networks with Label Relations.

Hexiang Hu, Guang-tong Zhou, Zhiwei Deng, Zicheng Liao and Greg Mori.

IEEE Computer Vision and Pattern Recognition (CVPR), 2016.

A Hierarchical Deep Temporal Model for Group Activity Recognition.

Moustafa Ibrahim, Srikanth Muralidharan, Zhiwei Deng, Arash Vahdat, Greg Mori.

IEEE Computer Vision and Pattern Recognition (CVPR), 2016.

Deep Structured Models For Group Activity Recognition.

Zhiwei Deng, Mengyao Zhai, Lei Chen, Yuhao Liu, Srikanth Muralidharan, Mehrsan Roshtkhari, and Greg Mori.

The British Machine Vision Conference (BMVC), 2015, (oral, acceptance rate=7%).

Learning Action Primitives for Multi-Level Video Event Understanding.

Tian Lan, Lei Chen, Zhiwei Deng, Guang-Tong Zhou, and Greg Mori.

International Workshop on Visual Surveillance and Re-Identification (at ECCV), 2014.

Service

Reviewers for: NIPS 2017, CVPR 2018, ICML 2018, ECCV 2018, NIPS 2018, CVPR 2019, ICML 2019, PAMI