Deep belief networks are a powerful way to model complex probability distributions. However, it is difficult to learn the structure of a belief network, particularly one with hidd...
Ryan Prescott Adams, Hanna M. Wallach, Zoubin Ghah...
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 describe an approach to segmenting foreground regions corresponding to a group of people into individual humans. Given background subtraction and ground plane homography, hierar...
Zhe Lin, Larry S. Davis, David S. Doermann, Daniel...
In time-series analysis it is often assumed that observed data can be modelled as being derived from a number of regimes of dynamics, as e.g. in a Switching Kalman Filter (SKF) [1,...
Vision is an important sensor used for mobile robot navigation. One approach to localization which is based on vision is to compute camera egomotion with respect to base images. W...