Abstract. In this paper, we introduce background cut, a high quality and realtime foreground layer extraction algorithm. From a single video sequence with a moving foreground objec...
Learning by demonstration can be a powerful and natural tool for developing robot control policies. That is, instead of tedious hand-coding, a robot may learn a control policy by ...
We propose a new local learning scheme that is based on the principle of decisiveness: the learned classifier is expected to exhibit large variability in the direction of the test ...
Abstract. We propose a new generative model, and a new image similarity kernel based on a linked hierarchy of probabilistic segmentations. The model is used to efficiently segment ...
Abstract. Post's correspondence problem (PCP) is a classic undecidable problem. Its theoretical unbounded search space makes it hard to judge whether a PCP instance has a solu...