Coarse-to-fine approaches use sequences of increasingly fine approximations to control the complexity of inference and learning. These techniques are often used in NLP and visio...
The problem of interactive foreground/background segmentation in still images is of great practical importance in image editing. The state of the art in interactive segmentation is...
Andrew Blake, Carsten Rother, M. Brown, Patrick P&...
Abstract. We generalize a learning algorithm originally devised for deterministic all-accepting weighted tree automata (wta) to the setting of arbitrary deterministic wta. The lear...
RVRL (Rule Value Reinforcement Learning) is a new algorithm which extends an existing learning framework that models the environment of a situated agent using a probabilistic rule...
Languages that combine predicate logic with probabilities are needed to succinctly represent knowledge in many real-world domains. We consider a formalism based on universally qua...