Among the various types of semantic concepts modeled, events pose the greatest challenge in terms of computational power needed to represent the event and accuracy that can be ach...
In traditional game theory, players are typically endowed with exogenously given knowledge of the structure of the game—either full omniscient knowledge or partial but fixed in...
Matt Lepinski, David Liben-Nowell, Seth Gilbert, A...
Large scale learning is often realistic only in a semi-supervised setting where a small set of labeled examples is available together with a large collection of unlabeled data. In...
A scalable podcast solution developed at the University of Washington makes the podcasting of class lectures easy for faculty by automating the capture, uploading, and delivery of...
In this paper, we propose a novel transductive learning framework named manifold-ranking based image retrieval (MRBIR). Given a query image, MRBIR first makes use of a manifold ra...