A Framework Integrating Signal / Semantic Visual Characterizations for Conceptual Video Retrieval
Mbarek Charhad Sadek Mansouri · Zenodo (CERN European Organization for Nuclear Research) · 2014
Most of the video indexing and retrieval systems suffer from the lack of a comprehensive video model capturing the image semantic richness, the conveyed signal information and the spatial relations between visual entities. To remedy such shortcomings, we present in this paper a video model integrating visual semantics, spatial and signal characterizations. It relies on an expressive representation formalism handling high-level video descriptions and a full-text query framework in an attempt to operate video indexing and retrieval beyond trivial lowlevel processes, semantic-based keyword annotation and retrieval frameworks.