Human action video sequences can be considered as nonlinear dynamic shape manifolds in the space of image frames. In this paper, we address learning and classifying human actions ...
This paper describes a novel approach for obtaining semantic interoperability among data sources in a bottom-up, semiautomatic manner without relying on pre-existing, global seman...
Karl Aberer, Manfred Hauswirth, Philippe Cudr&eacu...
This paper addresses the issue of unsupervised network anomaly detection. In recent years, networks have played more and more critical roles. Since their outages cause serious eco...
We present a class of richly structured, undirected hidden variable models suitable for simultaneously modeling text along with other attributes encoded in different modalities. O...
The collaborative filtering approach to recommender systems predicts user preferences for products or services by learning past useritem relationships. In this work, we propose no...