We show that the automatically induced latent variable grammars of Petrov et al. (2006) vary widely in their underlying representations, depending on their EM initialization point...
Learning the user’s semantics for CBIR involves two different sources of information: the similarity relations entailed by the content-based features, and the relevance relatio...
Semantic-based image retrieval has attracted great interest in recent years. This paper proposes a region-based image retrieval system with high-level semantic learning. The key f...
Abstract— This paper presents an approach to create topological maps from geometric maps obtained with a mobile robot in an indoor-environment using range data. Our approach util...
We present a method for dependency grammar induction that utilizes sparse annotations of semantic relations. This induction set-up is attractive because such annotations provide u...