We present a semi-supervised source separation methodology to denoise speech by modeling speech as one source and noise as the other source. We model speech using the recently pro...
We consider the problem of learning multiscale graphical models. Given a collection of variables along with covariance specifications for these variables, we introduce hidden var...
Myung Jin Choi, Venkat Chandrasekaran, Alan S. Wil...
Abstract. In this article we present a model of realistic drawing accounting for visuomotor coordination, namely the strategies adopted to coordinate the processes of eye and hand ...
Ruben Coen Cagli, Paolo Coraggio, Paolo Napoletano...
We devise techniques to manipulate a collection of loosely interpenetrating spheres in threedimensional space. Our study is motivated by the representation and manipulation of mol...
We introduce a discriminative hidden-state approach for the recognition of human gestures. Gesture sequences often have a complex underlying structure, and models that can incorpo...
Sy Bor Wang, Ariadna Quattoni, Louis-Philippe More...