A new approach to tracking weakly modeled objects in a semantically rich domain is presented. We define a closed-world as a space-time region of an image sequence in which the co...
Abstract— This paper presents a method for detecting independent temporally-persistent motion patterns in image sequences. The result is a description of the dynamic content of a...
The move towards a semantic web will produce an increasing number of presentations whose creation is based upon semantic queries. Intelligent presentation generation engines have ...
We present a framework for categorical shape recognition. The coarse shape of an object is captured by a multiscale blob decomposition, representing the compact and elongated part...
Ali Shokoufandeh, Lars Bretzner, Diego Macrini, M....
Abstract. This paper presents a novel approach to unsupervised texture segmentation that relies on a very general nonparametric statistical model of image neighborhoods. The method...