Getting trapped in suboptimal local minima is a perennial problem in model based vision, especially in applications like monocular human body tracking where complex nonlinear para...
The cluster assumption is exploited by most semi-supervised learning (SSL) methods. However, if the unlabeled data is merely weakly related to the target classes, it becomes quest...
Triangulation consists in finding a 3D point reprojecting the best as possible onto corresponding image points. It is classical to minimize the reprojection error, which, in the p...
Searching for optimal solutions to a problem using lower bounds obtained from a relaxation is a common idea in Heuristic Search and Planning. In SAT and CSPs, however, explicit rel...
Abstract. Concept approximation is an inference service for Description Logics that provides “translations” of concept descriptions from one DL to a less expressive DL. In [4] ...