Abstract. This paper presents an architecture that enables the recognizer to learn incrementally and, thereby adapt to document image collections for performance improvement. We ar...
Graph transduction methods label input data by learning a classification function that is regularized to exhibit smoothness along a graph over labeled and unlabeled samples. In pr...
The appearance of a scene is a function of the scene contents, the lighting, and the camera pose. A set of n-pixel images of a non-degenerate scene captured from different perspec...
Hua Yang, Marc Pollefeys, Greg Welch, Jan-Michael ...
This paper describes a novel approach for obtaining semantic interoperability among data sources in a bottom-up, semiautomatic manner without relying on pre-existing, global seman...
Karl Aberer, Manfred Hauswirth, Philippe Cudr&eacu...
This paper proposes a new framework for image segmentation based on the integration of MRFs and deformable models using graphical models. We first construct a graphical model to r...