Semantic Scene Graph Generation Using RDF Model and Deep Learning

Over the last several years, in parallel with general global advancement mobile technology and a rise social media network content consumption, multimedia production reproduction has increased exponentially. Therefore, enabled by rapid recent advancements deep learning technology, research on scene graph generation is being actively conducted to more efficiently search for classify images desired users within large amount of content. This approach lets accurately find they are searching expressing meaningful information image as nodes edges graph. In this study, we propose method based using Resource Description Framework (RDF) model clarify semantic relations. Furthermore, also use convolutional neural (CNN) recurrent (RNN) models generate expressed controlled vocabulary RDF understand relations between object tags. Finally, experimentally demonstrate through testing that our proposed technique can express effectively than existing approaches.