A sparse representation of Support Vector Machines (SVMs) with respect to input features is desirable for many applications. In this paper, by introducing a 0-1 control variable t...
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...
Discriminative methods for visual object category recognition are typically non-probabilistic, predicting class labels but not directly providing an estimate of uncertainty. Gauss...
Ashish Kapoor, Kristen Grauman, Raquel Urtasun, Tr...
Many complex, real world phenomena are difficult to study directly using controlled experiments. Instead, the use of computer simulations has become commonplace as a feasible alte...
We consider the problem of monocular 3d body pose tracking from video sequences. This task is inherently ambiguous. We propose to learn a generative model of the relationship of bo...
Tobias Jaeggli, Esther Koller-Meier, Luc J. Van Go...