Hierarchical models have been extensively studied in various domains. However, existing models assume fixed model structures or incorporate structural uncertainty generatively. In...
We propose a face difference model that decomposes face difference into three components, intrinsic difference, transformation difference, and noise. Using the face difference mod...
This work presents a novel people tracking approach, able to cope with frequent shape changes and large occlusions. In particular, the tracks are described by means of probabilist...
Rita Cucchiara, Costantino Grana, Giovanni Tardini...
Previous work has shown that the difficulties in learning deep generative or discriminative models can be overcome by an initial unsupervised learning step that maps inputs to use...
Pascal Vincent, Hugo Larochelle, Yoshua Bengio, Pi...
In this paper we argue that gestures based on nonaccidental motion features can be reliably detected amongst unconstrained background motion. Specifically, we demonstrate that hu...