Abstract. We address the problem of comparing sets of images for object recognition, where the sets may represent arbitrary variations in an object's appearance due to changin...
Abstract. Successful multi-target tracking requires solving two problems - localize the targets and label their identity. An isolated target's identity can be unambiguously pr...
Abstract. We propose a probabalistic model of single source multimodal generation and show how algorithms for maximizing mutual information can find the correspondences between com...
In this paper, the geometry of a general class of projections from ??? to ?! is examined, as a generalization of classic multiple view geometry in computer vision. It is shown that...
Abstract. We propose a new tracking technique that is able to capture non-rigid motion by exploiting a space-time rank constraint. Most tracking methods use a prior model in order ...