In this paper we propose a novel order-recursive training algorithm for kernel-based discriminants which is computationally efficient. We integrate this method in a hybrid HMM-bas...
We investigate the problem of anomaly detection for video surveillance applications. In our approach, we use a compression-based similarity measure to determine similarity between...
We present a Computer Vision based system that enables multiple people to interact naturally with a large display table using their own bare-hand gestures. The display presents an...
We describe a new expression database which contains video sequences of both played and natural expressions and an expression classification system based on warped optical flow fi...
James Skelley, Robert Fischer, Arup Sarma, Bernd H...
This paper considers the application of pattern recognition techniques in modern computer games. Towards the problem of realizing more life-like behavior for artificial game chara...
Christian Thurau, Thomas Hettenhausen, Christian B...