“Energy” models for continuous domains can be applied to many problems, but often suffer from high computational expense in training, due to the need to repeatedly minimize t...
Abstract. In this paper, we present a statistical approach for the automatic generation of dialogs by means of a user simulator. This technique can be used to generate dialogs with...
Traditionally listener response prediction models are learned from pre-recorded dyadic interactions. Because of individual differences in behavior, these recordings do not capture...
Iwan de Kok, Derya Ozkan, Dirk Heylen, Louis-Phili...
The automatic annotation of images presents a particularly complex problem for machine learning researchers. In this work we experiment with semantic models and multi-class learnin...
We propose a novel method for removing irrelevant frames from a video given user-provided frame-level labeling for a very small number of frames. We first hypothesize a number of w...