— Both theory and a wealth of empirical studies have established that ensembles are more accurate than single predictive models. Unfortunately, the problem of how to maximize ens...
Belief propagation (BP) is an effective algorithm for solving energy minimization problems in computer vision. However, it requires enormous memory, bandwidth, and computation beca...
Chao-Chung Cheng, Chia-Kai Liang, Homer H. Chen, L...
Manually labeled landmark sets are often required as in-
puts for landmark-based image registration. Identifying an
optimal subset of landmarks from a training dataset may be
us...
Anand A. Joshi, David W. Shattuck, Dimitrios Panta...
Face recognition algorithms need to deal with variable
lighting conditions. Near infrared (NIR) image based face
recognition technology has been proposed to effectively
overcome...
The study of 2D shapes and their similarities is a central problem in the field of vision. It arises in particular from the task of classifying and recognizing objects from their ...