We propose a family of learning algorithms based on a new form of regularization that allows us to exploit the geometry of the marginal distribution. We focus on a semi-supervised...
A large body of research in machine learning is concerned with supervised learning from examples. The examples are typically represented as vectors in a multi-dimensional feature ...
This paper systematically investigates the effectiveness of different visual feature coding schemes for facilitating the learning of time-delayed dependencies among disjoint multi-...
Supervised learning of a parts-based model can be for-
mulated as an optimization problem with a large (exponen-
tial in the number of parts) set of constraints. We show how
thi...
M. Pawan Kumar, Andrew Zisserman, Philip H.S. Torr
Bayesian approaches to supervised learning use priors on the classifier parameters. However, few priors aim at achieving "sparse" classifiers, where irrelevant/redundant...