Xuming He

alt text 

Associate Professor
School of Information Science and Technology
ShanghaiTech University

Address

Room 1A-304D, SIST Building
393 Middle Huaxia Road
Pudong, Shanghai, 201210, China

Contact

Phone: +86 21 20685378
Email: hexumi at gmail

New: Prospective graduate students: please check admission website. 学科方向: 计算机科学与技术.

New: We also have multiple research projects (3 to 6 months) for undergrad students in SIST.

News

Research Interest

  • Image parsing and semantic segmentation

  • 3D object and scene representations

  • Learning and inference in undirected graphical models

  • Understanding human vision system

  • Image, language and knowledge representation

Selected Publications

  • Buyu Liu, Xuming He, Multiclass Semantic Video Segmentation With Object-Level Active Inference, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015 [pdf] [suppl zip]

  • Xuming He, Stephen Gould, An Exemplar-based CRF for Multi-instance Object Segmentation, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2014 [pdf]

  • Yansheng Ming, Hongdong Li, Xuming He, Connected Contours: a Contour Completion Model That Respects Closure-Effect, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2012 [pdf]

  • Shuang Wu, Xuming He, Hongjing Lu, and Alan Yuille, A Unified Model of Short-range and Long-range Motion Perception, Annual Conference on Neural Information Processing Systems (NIPS), 2010, Vancouver, Canada [pdf]

  • Xuming He, and Richard S. Zemel, Learning Hybrid Models for Image Annotation with Partially Labeled Data, Annual Conference on Neural Information Processing Systems (NIPS), 2008 [pdf]

  • Xuming He, Richard Zemel, and Miguel Carreira-Perpinan, Multiscale Conditional Random Fields for Image Labelling, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2004 [pdf]