Guang-Tong Zhou

About

I am currently a Research Scientist at Meta. Before joining Meta, I worked as a Machine Learning Researcher at Oracle Labs Vancouver in Canada. I earned my Ph.D. in 2015 from Simon Fraser University under the supervision of Dr. Greg Mori. During my Ph.D., I interned at Disney Research in fall 2013, and SAP from fall 2014 to spring 2015.

I am interested in Machine Learning and Computer Vision research, and the focus is to develop machine learning algorithms and semantic representations for high-level understanding of image, video and network data. I am also experienced in building end-to-end large-scale machine learning systems for Ads Recommender Systems and Cloud Security.

Publication

	Structured Label Inference for Visual Understanding. Nelson Nauata, Hexiang Hu, Guang-Tong Zhou, Zhiwei Deng, Zicheng Liao and Greg Mori. IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI), 2019. [PDF]
	Recalling Holistic Information for Semantic Segmentation. Hexiang Hu, Zhiwei Deng, Guang-Tong Zhou, Fei Sha and Greg Mori. arXiv:1611.08061, 2016. [PDF] [arXiv]
	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. [PDF] [arXiv]
	Toward Scene Recognition by Discovering Semantic Structures and Parts. Guang-Tong Zhou. Ph.D. Thesis, Simon Fraser University, 2015. [PDF]
	Discovering Human Interactions in Videos with Limited Data Labeling. Mehran Khodabandeh, Arash Vahdat, Guang-Tong Zhou et al. Workshop on Group and Crowd Behavior Analysis and Understanding (at CVPR), 2015. [PDF]
	Hierarchical Maximum-Margin Clustering. Guang-Tong Zhou, Sung Ju Hwang, Mark Schmidt, Leonid Sigal and Greg Mori. arXiv:1502.01827, 2015. [PDF] [arXiv]
	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. [PDF]
	Discovering Video Clusters from Visual Features and Noisy Tags. Arash Vahdat, Guang-Tong Zhou and Greg Mori. European Conference on Computer Vision (ECCV), 2014. [PDF] [Supplementary]
	Latent Maximum Margin Clustering. Guang-Tong Zhou, Tian Lan, Arash Vahdat and Greg Mori. Neural Information Processing Systems (NIPS), 2013. [PDF] [Code]
	Learning Class-to-Image Distance with Object Matchings. Guang-Tong Zhou, Tian Lan, Weilong Yang and Greg Mori. IEEE Computer Vision and Pattern Recognition (CVPR), 2013. [PDF] [SUN 09 Scene Labels]
	Mass Estimation. Kai Ming Ting, Guang-Tong Zhou, Fei Tony Liu and Swee Chuan Tan. Machine Learning Journal (MLJ), 90(1):127-160, 2013. [PDF] [Details]
	Relevance Feature Mapping for Content-Based Multimedia Information Retrieval. Guang-Tong Zhou, Kai Ming Ting, Fei Tony Liu and Yilong Yin. Pattern Recognition (PR), 45(4):1707-1720, 2012. [PDF]
	Relevance Feature Mapping for Content-Based Image Retrieval. Guang-Tong Zhou, Kai Ming Ting, Fei Tony Liu and Yilong Yin. International Workshop on Multimedia Data Mining (at KDD), 2010. [PDF]
	Mass Estimation and Its Applications. Kai Ming Ting, Guang-Tong Zhou, Fei Tony Liu and Swee Chuan Tan. ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2010. [PDF] [Details]
	K-means Based Fingerprint Segmentation with Sensor Interoperability. Gongping Yang, Guang-Tong Zhou, Yilong Yin and Xiukun Yang. EURASIP Journal on Advances in Signal Processing (EJASP), 2010(1):729378, 2010. [PDF]

Timeline

[ Biography ]

I am currently a Staff Research Scientist at Meta. Before joining Meta in 2018, I have worked as a Machine Learning Researcher (Principal Member of Technical Staff) at Oracle Labs Vancouver since 2015. I obtained my Ph.D. from the School of Computing Science, Simon Fraser University, Canada. My thesis advisor is Dr. Greg Mori, and my thesis title is Toward Scene Recognition by Discovering Semantic Structures and Parts. I am interested in machine learning and computer vision research, and the focus is to develop machine learning algorithms and semantic representations for high-level understanding of image and video data.

I received my B.Sc. and M.Sc. from Shandong University, China, in 2007 and 2010, respectively. During my master's study, I worked with Dr. Yilong Yin in the MLA Group on fingerprint recognition problems. I visited Dr. Zhi-Hua Zhou's LAMDA Group in Nanjing University, and researched on content-based image retrieval in 2008. After that, I spent six months at Monash University, Australia, where I worked on mass estimation with Dr. Kai Ming Ting. I later joined Simon Fraser University as a graduate student and worked under the supervision of Dr. Jian Pei on contextual outlier detection in 2011. In fall 2013, I interned at Disney Research with Dr. Leonid Sigal, working on automatic discovery of scene parts. I also interned at SAP from fall 2014 to spring 2015, and the project is to develop a proof-of-concept system for graph visualization.