The performance of supervised learners depends on the presence of a relatively large labeled sample. This paper proposes an automatic ongoing learning system, which is able to inco...
In this paper, we present a novel approach to learning semantic localized patterns with binary projections in a supervised manner. The pursuit of these binary projections is refor...
A scattering vector is a local descriptor including multiscale and multi-direction co-occurrence information. It is computed with a cascade of wavelet decompositions and complex m...
In this paper, we propose a supervised Smooth Multi-Manifold Embedding (SMME) method for robust identity-independent head pose estimation. In order to handle the appearance variati...
We present a theory for constructing linear subspace approximations to face-recognition algorithms and empirically demonstrate that a surprisingly diverse set of face-recognition a...