We propose a first attempt to classify events in static images by integrating scene and object categorizations. We define an event in a static image as a human activity taking pla...
This paper describes the participation of MIRACLE research consortium at the Query Parsing task of GeoCLEF 2007. Our system is composed of three main modules. First, the Named Geo...
Most work on Predictive Representations of State (PSRs) has focused on learning and planning in unstructured domains (for example, those represented by flat POMDPs). This paper e...
David Wingate, Vishal Soni, Britton Wolfe, Satinde...
We investigate a biologically motivated approach to fast visual classification, directly inspired by the recent work [13]. Specifically, trading-off biological accuracy for comput...
The paper considers the problem of defining concepts within formal ontologies. A number of distinct modes of definition are identified, which represent alternative viewpoints on t...