We present a two-layer hierarchical formulation to exploit different levels of contextual information in images for robust classification. Each layer is modeled as a conditional f...
We consider the problem of multi-task reinforcement learning where the learner is provided with a set of tasks, for which only a small number of samples can be generated for any g...
Abstract. We describe a flexible object recognition and modelling system (FORMS) which represents and recognizes animate objects from their silhouettes. This consists of a model fo...
The Hierarchical Hidden Markov Model (HHMM) is a well formalized tool suitable to model complex patterns in long temporal or spatial sequences. Even if effective algorithms are ava...
Abstract. A novel approach to create a general vision system is presented. The proposed method is based on a visual grammar representation which is transformed to a Bayesian networ...