We formulate stereo matching as an extremal surface extraction problem. This is made possible by embedding the disparity surface inside a volume where the surface is composed of v...
Abstract. We develop a segmentation technique for dynamic PET incorporating the physiological parameters for different regions via kinetic modeling. We demonstrate the usefulness o...
Ahmed Saad, Benjamin Smith 0002, Ghassan Hamarneh,...
Probabilistic graphical models such as Bayesian Networks have been increasingly applied to many computer vision problems. Accuracy of inferences in such models depends on the quali...
We propose a latent variable model to enhance historical analysis of large corpora. This work extends prior work in topic modelling by incorporating metadata, and the interactions...
William Yang Wang, Elijah Mayfield, Suresh Naidu, ...
We present a novel off-line algorithm for target segmentation and tracking in video. In our approach, video data is represented by a multi-label Markov Random Field model, and seg...