We show how a preselection of hidden variables can be used to efficiently train generative models with binary hidden variables. The approach is based on Expectation Maximization (...
In this paper, we propose a symmetric stereo model to handle occlusion in dense two-frame stereo. Our occlusion reasoning is directly based on the visibility constraint that is mo...
Adaptive background modeling/subtraction techniques are popular, in particular, because they are able to cope with background variations that are due to lighting variations. Unfor...
Leonid Taycher, John W. Fisher III, Trevor Darrell
In this paper we present a new framework for image segmentation using probabilistic multinets. We apply this framework to integration of regionbased and contour-based segmentation ...
Bayesian inference methods are commonly applied to the classification of brain Magnetic Resonance images (MRI). We use the Maximum Evidence (ME) approach to estimate the most prob...