This paper presents a bottom-up approach that combines audio and video to simultaneously locate individual speakers in the video (2-D source localization) and segment their speech ...
Abstract--We investigate parameter-based and distributionbased approaches to regularizing the generative, similarity-based classifier called local similarity discriminant analysis ...
We present a new, robust and computationally efficient method for estimating the probability density of the intensity values in an image. Our approach makes use of a continuous r...
We describe a method for learning classes of facial motion patterns from video of a human interacting with a computerized embodied agent. The method also learns correlations betwe...
Abstract-- The advance of high-throughput experimental technologies poses continuous challenges to computational data analysis in functional and comparative genomics studies. Gene ...