Multiple images of a scene are related through 20/3D view transformations and linear and non-linear camera transformations. In all the traditional techniques to compute these tran...
A compressed-domain transformation is one that operates directly on the compressed format, rather than requiring conversion to an uncompressed format prior to processing. Performi...
A key challenge in applying kernel-based methods for discriminative learning is to identify a suitable kernel given a problem domain. Many methods instead transform the input data...
Many successful models for scene or object recognition transform low-level descriptors (such as Gabor filter responses, or SIFT descriptors) into richer representations of interme...
Y-Lan Boureau, Francis Bach, Yann LeCun, Jean Ponc...
The dissemination of information available through the World Wide Web makes universal access more and more important and supports visually disabled people in their everyday life. ...