Abstract. We propose a method of unsupervised learning from stationary, vector-valued processes. A low-dimensional subspace is selected on the basis of a criterion which rewards da...
Abstract. Extraction of visual descriptors is a crucial problem for stateof-the-art visual information analysis. In this paper, we present a knowledgebased approach for detection o...
Paraskevi K. Tzouveli, Georgios Andreou, Gabriel T...