In this contribution, we explore the possibilities of learning in large-scale, multimodal processing systems operating under real-world conditions. Using an instance of a large-sca...
We propose a new method to measure “visualness” of concepts, that is, what extent concepts have visual characteristics. To know which concept has visually discriminative power...
Video is increasingly important to digital libraries and archives as both primary content and as context for the primary objects in collections. Services like YouTube not only off...
Gary Marchionini, Chirag Shah, Christopher A. Lee,...
Detection of interactions among data items constitutes an essential part of knowledge discovery. The cascade model is a rule induction methodology using levelwise expansion of a la...
Background: Methods for predicting protein function directly from amino acid sequences are useful tools in the study of uncharacterised protein families and in comparative genomic...
Markus Brameier, Josien Haan, Andrea Krings, Rober...