We propose a novel technique for the automatic classification of vocal and non-vocal regions in an acoustic musical signal. Our technique uses a combination of harmonic content a...
The probabilistic network technology is a knowledgebased technique which focuses on reasoning under uncertainty. Because of its well defined semantics and solid theoretical founda...
We propose a robust scene recognition system for baseball broadcast videos. This system is based on the data-driven approach which has been successful in continuous speech recogni...
We investigate the issue of sign language automatic phonetic subunit modeling, that is completely data driven and without any prior phonetic information. A first step of visual p...
Methods for expanding the dynamic range of digital photographs by combining images taken at different exposures have recently received a lot of attention. Current techniques assum...
Chris Pal, Richard Szeliski, Matthew Uyttendaele, ...