Symbol spotting problem requires feature extraction strategies able to generalize from training samples and to localize the target object while discarding most part of the image. ...
Abstract. This paper proposes a new approach to learning a discriminative model of object classes, incorporating appearance, shape and context information efficiently. The learned ...
Jamie Shotton, John M. Winn, Carsten Rother, Anton...
Abstract—This paper addresses a so far neglected area of human-robot interaction by approaching situation awareness from the point of view of naïve users. In particular, we pres...
Traditional approaches for modeling a closed manifold surface with either regular tensor-product or triangular splines (defined over an open planar domain) require decomposing th...
In this paper we present a two-level generative model for representing the images and surface depth maps of drapery and clothes. The upper level consists of a number of folds whic...