Abstract. Supervised classifiers require manually labeled training samples to classify unlabeled objects. Active Learning (AL) can be used to selectively label only “ambiguous...
We present an approach to real-time person tracking in crowded and/or unknown environments using multi-modal integration. We combine stereo, color, and face detection modules into...
Trevor Darrell, Gaile G. Gordon, Michael Harville,...
The notion of using context information for solving highlevel vision problems has been increasingly realized in the field. However, how to learn an effective and efficient context...
In this paper, we propose a new object-based video coding/transmission system using the emerging Motion JPEG 2000 standard [1] for the efficient storage and delivery of video surve...
This work introduces a new family of link-based dissimilarity measures between nodes of a weighted directed graph. This measure, called the randomized shortest-path (RSP) dissimil...
Luh Yen, Marco Saerens, Amin Mantrach, Masashi Shi...