Bayesian networks with mixtures of truncated exponentials (MTEs) support efficient inference algorithms and provide a flexible way of modeling hybrid domains (domains containing ...
Helge Langseth, Thomas D. Nielsen, Rafael Rum&iacu...
We propose a novel directed graphical model for label propagation in lengthy and complex video sequences. Given hand-labelled start and end frames of a video sequence, a variation...
Ignas Budvytis, Vijay Badrinarayanan, Roberto Cipo...
Deep belief networks are a powerful way to model complex probability distributions. However, it is difficult to learn the structure of a belief network, particularly one with hidd...
Ryan Prescott Adams, Hanna M. Wallach, Zoubin Ghah...
Retrieving videos using key words requires obtaining the semantic features of the videos. Most work reported in the literature focuses on annotating a video shot with a fixed numb...
This paper addresses scene understanding in the context of a moving camera, integrating semantic reasoning ideas from monocular vision with 3D information available through struct...