In this paper we present a method for learning classspecific
features for recognition. Recently a greedy layerwise
procedure was proposed to initialize weights of deep
belief ne...
Mohammad Norouzi (Simon Fraser University), Mani R...
Gaussian mixture model - universal background model (GMMUBM) is a standard reference classifier in speaker verification. We have recently proposed a simplified model using vect...
Tomi Kinnunen, Juhani Saastamoinen, Ville Hautam&a...
In this paper an experiment was conducted to measure the effect of framing a high definition television (HDTV) clip. One group of participants was told they were watching a brand n...
Dirkjan Joor, Wilco Beekhuizen, Lidwien van de Wij...
We present a new approximate inference algorithm for Deep Boltzmann Machines (DBM's), a generative model with many layers of hidden variables. The algorithm learns a separate...
Many problems in computer vision can be modeled using
conditional Markov random fields (CRF). Since finding
the maximum a posteriori (MAP) solution in such models
is NP-hard, mu...
Stephen Gould (Stanford University), Fernando Amat...