Xuming He


Department of Computer Science

University of Toronto

Pratt Building, # PT283E
6 King's College Road
Toronto, Ontario
Canada M5S 3G4

Phone: (o) (416)946-4005

Email : h e x m a t c s t o r o n t o e d u

I am a PhD student in the Machine Learning group  at the Department of Computer Science, University of Toronto. My research focuses on statistical learning methods and their applications in computer vision. My supervisor is Dr. Rich. Zemel. Before I came to Canada, I graduated from the Department of Electronic Engineering at Shanghai Jiao Tong University, P. R. China.

Recently, I have moved to CIVS Lab at UCLA. (See my webpage there >>.)

Research Projects


Xuming He and Richard S. Zemel
Latent Topic Random Fields: Learning using a taxonomy of labels
To appear in CVPR, 2008

Xuming He
Learning Structured Prediction models for Image Labeling. (pdf)
PhD Thesis, 2008

Liam Stewart, Xuming He, and Richard S. Zemel
Learning Flexible Features for Conditional Random Fields
To appear in IEEE Transactions on PAMI, 2008

Xuming He, Richard Zemel, and Volodymyr Mnih

Topological Map Learning from Outdoor Image Sequences. (Tech-Report version: pdf)
In Journal of Field Robotics, Volume 23, Issue 11-12 , P. 1091 - 1104, 2007

Xuming He, Richard Zemel, and Deb Ray
Learning and incorporating top-down cues in image segmentation. (pdf)
In ECCV 2006: 9th European Conference on Computer Vision.

Xuming He, Richard Zemel, and Volodymyr Mnih
Learning Landmarks for Localization via Manifolds.
In NIPS Workshop on Machine Learning Based Robotics in Unstructured Environments, 2005

Xuming He, Richard Zemel, and Miguel Carreira-Perpinan
Multiscale conditional random fields for image labelling. (pdf)
In IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2004

Teaching Assistant

Useful Links

Last updated by Jan, 2008