This paper addresses the problem of deriving measures that express the degree of the reliability of motion vectors estimated by a Block Matching motion estimation method. We expre...
Ioannis Patras, Emile A. Hendriks, Reginald L. Lag...
We present a method for solving the global illumination problem for synthetic diffuse objects. The approach generates realistic shading for applications where a synthetic object i...
General dissimilarity-based learning approaches have been proposed for dissimilarity data sets [11, 10]. They arise in problems in which direct comparisons of objects are made, e....
We present an example of a joint spatial and temporal task learning algorithm that results in a generative model that has applications for on-line visual control. We review work o...
We present in this paper a new multi-class Bayes classifier that permits using separate feature vectors, chosen specifically for each class. This technique extends previous work o...