We present an active learning framework to simultaneously learn appearance and contextual models for scene understanding tasks (multi-class classification). Existing multi-class a...
Predicting the running time of a parallel program is useful for determining the optimal values for the parameters of the implementation and the optimal mapping of data on processo...
This work describes an approach for the interpretation and explanation of human behavior in image sequences, within the context of a Cognitive Vision System. The information source...
Some theoretical models used in IS research may lack explanatory power and consistency because of their failure to provide an adequate means of accounting for contextual and situa...
Abstract. This paper presents a statistical framework based on Principal Component Analysis (PCA) for discovering the contextual factors which most strongly influence user behavio...