Word Concept Analysis and Description for Cross-media Reference Based on Mental Image Directed Semantic Theory

摘要

In general, it is very difficult for people to exploit necessary information from the immense multimedia contents over the WWW. It is still more difficult to search for desirable contents by queries in different media, for example, text queries for pictorial contents. In this case, intelligent systems facilitating cross-media reference are very helpful. Mental Image Directed Semantic Theory (MIDST) has proposed a omnisensual mental image model and a formal language L_(md) for describing it. This paper presents the outline of word concept analysis and description based on L_(md),, and its application to cross-media reference between linguistic and pictorial expressions of space and lime.