— A novel framework to context modeling, based on the probability of co-occurrence of objects and scenes is proposed. The modeling is quite simple, and builds upon the availabili...
Abstract. Even a relatively unstructured captioned image set depicting a variety of objects in cluttered scenes contains strong correlations between caption words and repeated visu...
An important direction in database research for non-standard applications (e.g. engineering or design applications) deals with adequate support for complex objects. Without doubt,...
Whenever multiple representations or models of a system exist, there is the possibility of defining how they relate. In model driven software development, it is essential that th...
A typical way to perform video annotation requires to classify video elements (e.g. events and objects) according to some pre-defined ontology of the video content domain. Ontolo...