Dr Tao Xiang
Overall research goal: design a computer system that understands what it sees
Specifically, my research interests include computer vision, machine learning, pattern recognition, and data mining. The basic idea is to develop algorithms and models for automated analysis of video content. In particular, I aim to address the problems of extracting informative and concise features from video, constructing dynamic models in the feature space, developing effective and efficient algorithms for learning the structure and parameters of the models, and applying the models to interpret the video content. Recently I have been focused on video behaviour analysis for anomaly detection, human action recognition, multi-sensor data fusion for behaviour monitoring, adaptive and incremental learning, model order selection and feature selection, and biometrics.
Programme committee member of IEEE Conference on Advanced Video and Signal Based Surveillance (2005), International Symposium on Visual Computing (2006), and International Conference on Visual Information Engineering (2007).
Member of Institute of Electrical and Electronics Engineers (IEEE) and British Machine Vision Association & Society for Pattern Recognition (BMVA)
Invited talks at the Royal Statistical Society and Beijing University, 2005, and Queen’s University Belfast, 2004.
Journal reviewer for Neurocomputing, IEEE Transactions on Multimedia, IEEE Transactions on Circuits and Systems for Video Technology, Image Vision Computing (IVC), Machine Vision and Applications, International Journal of Robotics and Automation, and Pattern Recognition Letters.