个人简历

个人信息
　　梁玮，现任北京理工大学计算机学院副教授，博士生导师，硕士生导师。2005年7月于北京理工大学计算机学院获得计算机应用技术工学博士学位。2014年至2015年在加州大学洛杉矶分校（ULCA）访问。作为项目负责人主持国家自然科学基金两项，主持北京市自然科学基金一项，973子课题一项。做为核心骨干参加了国家自然科学基金、国防基础科研项目、863项目以及与航天科技集团合作项目等多项课题的研究工作。发表学术论文50余篇。

研究领域

计算机视觉，机器学习，智能人机交互"承担科研情况
　　作为项目负责人承担国家自然科学基金一项，北京市自然基金一项，国家973子课题一项，北京理工大学基础研究基金一项"

近期论文

代表性学术成果
1. Wei Liang, Yibiao Zhao, Yixin Zhu, Song-Chun Zhu. Evaluating Human Cognition of Containing Relations with Physical Simulation. The Annual Meeting of the Cognitive Science Society, 2015.
2. Yu Kong, Wei Liang, Zhen Dong, Yunde Jia. Recognising Human Interaction from Videos by a Discriminative Models. IET Computer Vision, Volume: 8, Issue: 4 Pages: 277-286, 2014.
3. Han Wang, Wei Liang_, Xinxiao Wu, Peng Teng，Scene Image Retrieval via Re-Ranking Semantic and Packed Dense Interest Points, Neurocomputing, 119: 65-73, 2013.
4. Yang He, Mingtao Pei, Min Yang, Yuwei Wu and Wei Liang. Robust Visual Tracking via Spatio-Temporal Cue Integration. International Society for Optics and Photonics (ICGIP), 2013,
5. Jiaolong Yang, Wei Liang, Yunde Jia, Face Pose Estimation with Combined 2D and 3D HOG Features, 21st International Conference on Pattern Recognition, JAPAN, NOV. 2012.
6. Lei Han, Xinxiao Wu, Wei Liang, Yunde Jia, Guanming Hou. Discriminative human action recognition in the learned hierarchical manifold space. Image and Vision Computing, 2010 28(5) 836－839.
7. Xinxiao Wu，Yunde Jia and Wei Liang, Incremental Discriminant-Analysis of Canonical Correlations for Action Recognition, Pattern Recognition 43(12)， Dec. 2010.
8. Xinxiao Wu, Wei Liang, Yunde Jia. Action recognition feedback based framework for human pose reconstruction from monocular images. Pattern Recognition Letters. , 30 (12): 1077-1085, 2009.
9. Xinxiao Wu, Wei Liang, Yunde Jia. Tracking articulated objects by learning intrinsic structure of Motion. Pattern Recognition Letters,30(3):267-274, Feb, 2009.
10. Xinxiao Wu, Wei Liang and Yunde Jia，Incremental Discriminative-Analysis of Canonical Correlations for Action Recognition, International Conference on Computer Vision (ICCV2009), Kyoto, Japan, Sept. 2009.