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...
The authors present TWIG, a visually grounded wordlearning system that uses its existing knowledge of vocabulary, grammar, and action schemas to help it learn the meanings of new ...
This work extends a semi-automatic grammar induction approach previously proposed in [1]. We investigate the use of Information Gain (IG) in place of Mutual Information (MI) for g...
In this theoretical paper, we compare the "classical" learning techniques used to infer regular grammars from positive examples with the ones used to infer categorial gra...
We present a new method for segmenting actions into primitives and classifying them into a hierarchy of action classes. Our scheme learns action classes in an unsupervised manner ...