Existing approaches to multi-view learning are particularly effective when the views are either independent (i.e, multi-kernel approaches) or fully dependent (i.e., shared latent ...
Mathieu Salzmann, Carl Henrik Ek, Raquel Urtasun, ...
This paper presents a novel motion localization approach for recognizing actions and events in real videos. Examples include StandUp and Kiss in Hollywood movies. The challenge ca...
Abstract— Cooperative diversity facilitates spatio-temporal communications without requiring the deployment of physical antenna arrays. While physical layer studies on cooperativ...
Gentian Jakllari, Srikanth V. Krishnamurthy, Micha...
A framework for analyzing the computational capabilities and the limitations of the evolutionary process of random change guided by selection was recently introduced by Valiant [V...
The appearance of a rough surface is affected by the direction from which it is lit and texture classifiers should account for this. We propose a classifier that is robust to ligh...
Mike J. Chantler, Ged McGunnigle, A. Penirschke, M...