Xuming He, Associate Professor

Xuming He, Associate Professor

Tel:  (021) 20685378
Email: hexm@@shanghaitech.edu.cn
Office: Room 1A-304D, SIST Building
Major: CS
Website: https://xmhe.bitbucket.io/


Computer Vision: Scene understanding, Semantic segmentation, Object detection, Vision and language

Machine Learning: Graphical models, Neural networks, Weakly-supervised and meta-learning, Approximate inference


Xuming He received the B.Sc. and M.Sc. degrees in electronics engineering from Shanghai Jiao Tong University, in 1998 and 2001, respectively, and Ph.D. degree in computer science from the University of Toronto (machine learning group) in 2008. He held a postdoctoral position in Prof Alan Yuille’s group at the University of California at Los Angeles (UCLA) from 2008 to 2010. After that, he joined in National ICT Australia (NICTA) as a Researcher in 2010 and has been a Senior Researcher since 2013. He was also an adjunct Research Fellow level B from 2010 to 2012 and level C since 2013 at the Australian National University (ANU). He will join in ShanghaiTech as an associate professor, PI in December, 2016.

His general research interests lie in machine learning, computer vision and biological vision.  In particular, his current research focuses on semantic segmentation, object detection, 3D scene understanding, visual motion analysis, efficient inference and learning in structured models, and artificial vision. He has more than 50 conference and journal publications, including CVPR, ICCV, ECCV, AAAI, NIPS, IEEE TIP, IEEE TPAMI, Journal of Vision, etc.


1 Shipeng Yan, Songyang Zhang, Xuming He, A Dual Attention Network with Semantic Embedding for Few-shot Learning, AAAI Conference on Artificial Intelligence (AAAI), USA, 2019

2 Yansheng Ming, Hongdong Li, Xuming He, Contour Completion without Region Segmentation, IEEE Transactions on Image Processing, 2016, 25(8): 3597-3611

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

4 Xuming He, Richard S. Zemel, Learning Hybrid Models for Image Annotation with Partially Labeled Data, Annual Conference on Neural Information Processing Systems (NIPS), Vancouver, Canada, 2009

5 Xuming He, Richard Zemel, Miguel Carreira-Perpinan, Multiscale Conditional Random Fields for Image Labeling, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Washington DC, USA, 2004