We present a novel representation of cyclic human locomotion based on a set of spatio-temporal curves of tracked points on the surface of a person. We start by extracting a set of...
Abstract. In this paper, we propose a new approach to learn structured visual compound models from shape-based feature descriptions. We use captioned text in order to drive the pro...
Jan Moringen, Sven Wachsmuth, Sven J. Dickinson, S...
How can knowing about some categories help us to discover new ones in unlabeled images? Unsupervised visual category discovery is useful to mine for recurring objects without huma...
Abstract. In this paper we investigate a new method of learning partbased models for visual object recognition, from training data that only provides information about class member...
In this paper we present decomposable priors, a family of priors over structure and parameters of tree belief nets for which Bayesian learning with complete observations is tracta...