This paper presents motion field histograms as a new way of extracting facial features and modeling expressions. Feature are based on local receptive field histograms, which are r...
Sparse Orthonormal Transforms (SOT) has recently been proposed as a data compression method that can achieve sparser representations in transform domain. Given initial conditions,...
Abstract. In traditional software systems, significant attention is devoted to keeping modules well separated and coherent with respect to functionality, thus ensuring that changes...
Alexander Maedche, Boris Motik, Ljiljana Stojanovi...
This paper presents an approach on high-level feature detection within video documents, using a Region Thesaurus. A video shot is represented by a single keyframe and MPEG-7 featur...
Evaggelos Spyrou, Giorgos Tolias, Yannis S. Avrith...
— We study the inversion of a random field from pointwise measurements collected by a sensor network. We assume that the field has a sparse representation in a known basis. To ...