Automatically Joining Pictures to Multiple Taxonomies

Automatically providing semantics to multimedia objects is still a major open problem. In this paper we describe recent advances within this context and how they have been implemented within the Scenique image retrieval and browsing system. Scenique is based on a multi-dimensional model, where each dimension is a tree-structured taxonomy of concepts, also called semantic tags, that are used to describe the content of images.We describe an original algorithm that, by exploiting low-level visual features, tags, and metadata associated to an image, is able to predict a high-quality set of semantic tags for that image.