Thursday 13 Dec 2012: Tracking and Recognition of Body and Face Gestures
Dr. Ioannis (Yiannis) Patras - School of Electronic Engineering and Computer Science, Queen Mary, University of London
Harrison 170 15:00-16:00
Abstract: Recent years have witnessed an unprecedented interest in the visual analysis of human motion that is stimulated by applications that include computer games, animated films and entertainment, human computer interaction, surveillance/security and multimedia retrieval. In the first part of this talk we give an overview of our recent works on tracking and localisation using local predictors. This includes a coupled classification-prediction tracking scheme and variations of the local implicit shape model for object / body gesture localisation. We show the benefits of such approaches in the presence of occlusion and clutter. In the second part of the talk, we present our works on pose estimation and gesture recognition using tensor representations in large margin regression and classification schemes, respectively. These are extensions of the classical Support Vector Machines that can have significantly improved performance in the presence of small training data sets. We close with an overview of open problems and promising future research directions.
Bio: Ioannis (Yiannis) Patras received the the Ph.D. degree from the Department of Electrical Engineering, Delft University of Technology, The Netherlands, in 2001. He is a Senior Lecturer in Computer Vision in the School of Electronic Engineering and Computer Science in the Queen Mary, University of London. He is/has been in the organizing committee of IEEE SMC 2004, Face and Gesture Recognition 2008, ICMR2011, ACM Multimedia 2013 and was the general chair of WIAMIS 2009. He is associate editor in the Image and Vision Computing Journal. His research interests lie in the areas of Computer Vision and Pattern Recognition, with emphasis on Human Sensing and its applications in Multimedia Retrieval and Multimodal Human Computer Interaction. His main research interests are in the analysis of human motion, including tracking and recognition of facial and body gestures. He is a senior member of IEEE.