Abstract This paper proposes a real-time high-precision method to track an unknown face in front of an information system by selecting appropriate model to a video image. Active Ap...
In this paper, we propose two novel methods for face recognition under arbitrary unknown lighting by using spherical harmonics illumination representation, which require only one t...
We present a Resolution-Invariant Image Representation (RIIR) framework in this paper. The RIIR framework includes the methods of building a set of multi-resolution bases from tra...
We propose statistical learning methods for approximating implicit surfaces and computing dense 3D deformation fields. Our approach is based on Support Vector (SV) Machines, which...
Most practically relevant domains include some degree of conceptual dynamics, i.e. new conceptual elements arise, and some old ones become irrelevant. This type of change imposes a...