We propose a novel method for automatically discover-ing key motion patterns happening in a scene by observing the scene for an extended period. Our method does not rely on object ...
We motivate an approach to evaluating the utility of life-like interface agents that is based on human eye movements rather than questionnaires. An eye tracker is employed to obta...
We propose a new algorithm for learning kernels for variants of the Normalized Cuts (NCuts) objective – i.e., given a set of training examples with known partitions, how should ...
Real-world action recognition applications require the development of systems which are fast, can handle a large variety of actions without a priori knowledge of the type of actio...
Physical human-robot interaction can be significantly improved when being aware about the role each partner takes in a joint manipulation task. This holds especially in computer ...