The dimensionality curse has profound e ects on the effectiveness of high-dimensional similarity indexing from the performance perspective. One of the well known techniques for im...
In many image retrieval applications, the mapping between highlevel semantic concept and low-level features is obtained through a learning process. Traditional approaches often as...
In this paper we present a VRML97-X3D extension to describe precomputed visibility relationships in the context of progressive transmission as well as real time visualization of m...
Shadows, particularly soft shadows, play an important role in the visual perception of a scene by providing visual cues about the shape and position of objects. Several recent alg...
Lionel Atty, Nicolas Holzschuch, Marc Lapierre, Je...
Decomposing video frames into coherent two-dimensional motion layers is a powerful method for representing videos. Such a representation provides an intermediate description that e...