This paper studies the problem of combining region and boundary cues for natural image segmentation. We employ a large database of manually segmented images in order to learn an o...
It’s common experience for human vision to perceive full 3D shape and scene from a single 2D image with the occluded parts “filled-in” by prior visual knowledge. In this pa...
Optimal labeling problems are NP-hard in many practically important cases. Sufficient conditions for optimal label detection in every pixel are formulated. Knowing the values of th...
Object recognition, i. e. classification of objects into one of several known object classes, generally is a difficult task. In this paper we address the problem of detecting an...
A software framework for the parallel execution of sequential programs using C++ classes is presented. The functional language Concurrent ML is used to implement the underlying ha...