We present an approach for tracking varying number of objects through both temporally and spatially significant occlusions. Our method builds on the idea of object permanence to r...
One problem with the adaptive tracking is that the data that are used to train the new target model often contain errors and these errors will affect the quality of the new target...
Abstract. This paper presents a novel pixelwise representation for visual tracking that models both the spatial structure and dynamics of a target in a unified fashion. The represe...
If you were told that some object A was perfectly (or somewhat, or not at all) in some direction (e.g., west, above-right) of some reference object B, where in space would you loo...
Abstract. In this paper, we describe an unsupervised learning framework to segment a scene into semantic regions and to build semantic scene models from longterm observations of mo...