Department of Computer Science and Technology
Bachelor of Computer Science & Technology, Tsinghua University, Beijing, China, 1995;
Ph.D. in Computer Science & Technology, Tsinghua University, Beijing, China, 2003.
ICCI: Financial Chair (2010).
Visual Information Analysis and Retrieval
National Natural Science Foundation of China: Research on Semantic Modeling for Large Quantity Videos (2007-2009).
My research focuses on visual information analysis and retrieval, whose purpose is to improve the precision and recall rate of image and video retrieval with the help of machine learning algorithms. Some of my research results have been published in journals such as IEEE Transactions on Circuits and Systems for Video Technology and conferences including ACM Multimedia.
In the area of visual information analysis, my contributions include a semantic modeling method which fuses rich features under boost framework, and a region annotation method using spatial context in the view of structural prediction. In visual information retrieval, I have investigated methods of extracting users' information requirements from queries and feedbacks. Besides, I have proposed new training and prediction methods for SVM, aiming to support real-time interactive video search. I have also developed a high-performance indexing algorithm for large-scale, high-dimensional databases.
Our visual information analysis system has achieved best performance for several times in TRECVID, a benchmark for content based video retrieval. Furthermore, some of my proposed algorithms have been adopted in monitoring and management systems for video and audio programs over Internet, and have been deployed in several departments and provincial governments since 2007.
Technology Innovation Award by State Administration of Radio Film and Television, Second Class-Monitoring and Management System for Audio-Visual Programs over Internet (2009).
 D. Wang, Z. K. Wang, J. M. Li, B. Zhang, X. R. Li. Query representation by structured concept threads with application to interactive video retrieval, JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION, vol. 20, no. 2, pp. 104-116, 2009
 J. H. Yuan, H. Y. Wang, L. Xiao, W. J. Zheng, J. M. Li, F. Z. Lin, B. Zhang. A formal study of shot boundary detection, IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, vol. 17, no. 2, pp 168-186, 2007
 J. H. Yuan, J. M. Li, B. Zhang. Exploiting spatial context constraints for automatic image region annotation, Proceedings of the Fifteenth ACM International Conference on Multimedia (MM 2007), 2007, pp. 595-604
 J. H. Yuan, J. M. Li, B. Zhang. Learning concepts from large scale imbalanced data sets using support cluster machines, Proceedings of the 14th Annual ACM International Conference on Multimedia (MM 2006), 2006, pp. 441-450
 J. M. Li, B. Zhang, F. Z. Lin. An Improvement Algorithm to Sequential Minimal Optimization. Journal of Software, vol. 14, no. 5, pp. 918-924, 2003