We present a two-layer hierarchical formulation to exploit different levels of contextual information in images for robust classification. Each layer is modeled as a conditional f...
Abstract. In this paper, we present a general approach to shape characterization and deformation analysis of 2D/3D deformable visual objects. In particular, we define a reference ...
We present a novel real-time technique for computing inter-object ambient occlusion. For each occluding object, we precompute a field in the surrounding space that encodes an app...
Thie paper presents a representation echeme for polyhedral objects in arbitrary dimensions. Each object ie represented as the algebraic sum of convex polyhedra (cells). Each cell ...
In this paper, we propose classifier ensemble selection for Named Entity Recognition (NER) as a single objective optimization problem. Thereafter, we develop a method based on gen...