Most state-of-the-art approaches to action recognition rely on global representations either by concatenating local information in a long descriptor vector or by computing a single...
This paper describes the participation of Idiap-MULTI to the Robot Vision Task at imageCLEF 2010. Our approach was based on a discriminative classification algorithm using multiple...
Vision-based tracking is a basic elementary task in many computer vision-based applications such as video surveillance and monitoring, sensing and navigation in robotics, video co...
Harini Veeraraghavan, Paul R. Schrater, Nikolaos P...
Classification problems with a very large or unbounded set of output categories are common in many areas such as natural language and image processing. In order to improve accurac...
Ivan Titov, Alexandre Klementiev, Kevin Small, Dan...
We describe a novel method for directing the attention of an automated surveillance system. Our starting premise is that the attention of people in a scene can be used as an indica...