—Recently, many object localization models have shown that incorporating contextual cues can greatly improve accuracy over using appearance features alone. Therefore, many of the...
Brian McFee, Carolina Galleguillos, Gert R. G. Lan...
The research described here is part of a larger project with the objective of determining if a writer believes a proposition to be true or false. This task requires a deep underst...
We propose a joint representation and classification framework that achieves the dual goal of finding the most discriminative sparse overcomplete encoding and optimal classifier p...
An important problem in image labeling concerns learning with images labeled at varying levels of specificity. We propose an approach that can incorporate images with labels drawn...
Abstract. We present a goal-based approach for visualizing and browsing the search space of available Web services. A goal describes an obthat a client wants to solve by using Web ...