We propose a novel approach for modeling, tracking and recognizing facial expressions. Our method works on a low dimensional expression manifold, which is obtained by Isomap embed...
This paper reports our recent exploration of the layer-by-layer learning strategy for training a multi-layer generative model of patches of speech spectrograms. The top layer of t...
Li Deng, Michael L. Seltzer, Dong Yu, Alex Acero, ...
Abstract. Courseware validation should locate Learning Objects inconsistent with the courseware instructional design being used. In order for validation to take place it is necessa...
This article introduces an approach to adaptive wayfinding support for lifelong learners based on self-organisation theory. It describes an architecture which supports the recordin...
An effective object recognition scheme is to represent and match images on the basis of histograms derived from photometric color invariants. A drawback, however, is that certain c...