We show how features can easily be added to standard generative models for unsupervised learning, without requiring complex new training methods. In particular, each component mul...
Taylor Berg-Kirkpatrick, Alexandre Bouchard-C&ocir...
Image superresolution involves the processing of an image sequence to generate a still image with higher resolution. Classical approaches, such as bayesian MAP methods, require ite...
This paper presents a sound source (talker) localization method using only a single microphone, where a HMM (Hidden Markov Model) of clean speech is introduced to estimate the aco...
We demonstrate a system built using probabilistic techniques that allows for remarkably accurate localization across our entire office building using nothing more than the built-...
Andreas Haeberlen, Eliot Flannery, Andrew M. Ladd,...
To segregate overlapping objects into depth layers requires the integration of local occlusion cues distributed over the entire image into a global percept. We propose to model thi...