The appearance of dynamic scenes is often largely governed by a latent low-dimensional dynamic process. We show how to learn a mapping from video frames to this lowdimensional rep...
A natural language generation system must generate expressions that allow a reader to identify the entities to which they refer. This paper describes the creation of referring-exp...
Jill Nickerson, Stuart M. Shieber, Barbara J. Gros...
Abstract. Learning Objects (LOs) play a key role for supporting eLearning. In general, however, the development of LOs remains a vague issue, because there is still no clearly defi...
Supervised methods for learning an embedding aim to map high-dimensional images to a space in which perceptually similar observations have high measurable similarity. Most approac...
Graham Taylor, Ian Spiro, Rob Fergus, Christoph Br...
In this paper we present a coherent approach using the hierarchical HMM with shared structures to extract the structural units that form the building blocks of an education/traini...