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...
—This paper introduces a new approach to develop robots that can learn general affordance relations from their experiences. Our approach is a part of larger efforts to develop a ...
Erdem Erdemir, Carl B. Frankel, Kazuhiko Kawamura,...
We present an on-line crosslayer control technique to characterize and approximate optimal policies for wireless networks. Our approach combines network utility maximization and ad...
We present a polynomial update time algorithm for the inductive inference of a large class of context-free languages using the paradigm of positive data and a membership oracle. W...
Abstract. The paper proposes a dialectic approach to exploit discrepancies of viewpoints for learning. The approach is illustrated with an elaborated example. A computational frame...