This article presents a method aiming at quantifying the visual similarity between an image and a class model. This kind of problem is recurrent in many applications such as objec...
Abstract. It is generally accepted that some of the problems and ambiguities at the low level of processing can not be resolved without taking into account contextual expectations....
Abstract. A method for exploiting the information in low-level image segmentations for the purpose of object recognition is presented. The key idea is to use a whole ensemble of se...
: In this paper we describe a method for tracking walking humans in the visual field. Active contour models are used to track moving objects in a sequence of images. The resulting ...
: This paper addresses the inference of probabilistic classification models using weakly supervised learning. The main contribution of this work is the development of learning meth...