Multimedia ontology population through semantic analysis and hierarchical deep features extraction techniques

Abstract The rapid increase of available data in different complex contexts needs automatic tasks to manage and process contents. Semantic Web technologies represent the silver bullet digital Internet ecosystem allow human machine cooperation achieving these goals. Specific as ontologies are standard conceptual representations this view. It aims transform into an interoperability format providing a common vocabulary for given domain defining, with levels formality, meaning informative objects their possible relationships. In work, we focus our attention on Ontology Population multimedia realm. An multi-modality framework images ontology population is proposed implemented. allows enrichment new content. Our approach combines textual visual information through natural language processing techniques, convolutional neural network used features extraction task. based hierarchical methodology using descriptors semantic levels. results evaluation shows effectiveness approach.