We consider the problem of learning a mapping function from low-level feature space to high-level semantic space. Under the assumption that the data lie on a submanifold embedded ...
Learning the user’s semantics for CBIR involves two different sources of information: the similarity relations entailed by the content-based features, and the relevance relatio...
Stereo matching and volumetric reconstruction are the most explored 3D scene recovery techniques in computer vision. Many existing approaches assume perspective input images and us...
A dynamic layer representation is proposed in this paper for tracking moving objects. Previous work on layered representations has largely concentrated on two-/multiframe batch fo...