We present a two-layer hierarchical formulation to exploit different levels of contextual information in images for robust classification. Each layer is modeled as a conditional f...
Research in advanced context-aware systems has clearly shown a need to capture the inherent uncertainty in the physical world, especially in human behavior. Modelling approaches th...
Michael Angermann, Patrick Robertson, Thomas Stran...
We present a new reordering model estimated as a standard n-gram language model with units built from morphosyntactic information of the source and target languages. It can be see...
Abstract. We propose a novel method for addressing the model selection problem in the context of kernel methods. In contrast to existing methods which rely on hold-out testing or t...
This paper introduces the MREF framework for representing and correlating information at a higher semantic level than is possible with Web-based information systems today. The rol...