Abstract. The exploitation of video data requires to extract information at a rather semantic level, and then, methods able to infer "concepts" from low-level video featu...
Adaptive software systems are intended to modify their appearance, performance or functionality to the needs and preferences of different users. A key bottleneck in building effec...
This paper addresses automatic image annotation problem and its application to multi-modal image retrieval. The contribution of our work is three-fold. (1) We propose a probabilis...
We view the task of change detection as a problem of object recognition from learning. The object is defined in a 3D space where the time is the 3rd dimension. We propose two com...
The intuition that different text classifiers behave in qualitatively different ways has long motivated attempts to build a better metaclassifier via some combination of classifie...