This paper explores the use of volumetric features for action recognition. First, we propose a novel method to correlate spatio-temporal shapes to video clips that have been autom...
Current sign language recognition systems are still designed for signer-dependent operation only and thus suffer from the problem of interpersonal variability in production. Appli...
Despite the ready availability of digital recording technology and the continually decreasing cost of digital storage, browsing audio recordings remains a tedious task. This paper...
Sunil Vemuri, Philip DeCamp, Walter Bender, Chris ...
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 extraction of optimal features, in a classification sense, is still quite challenging in the context of large-scale classification problems (such as visual recognition), inv...