Abstract
Video is a complex media which poses some problems due to the huge amount of data it involves, and to the difficulty to represent and retrieve some information from its content. We propose to annotate the content of a video using Conceptual Graphs. This simple but powerful formalism can be exploited in order to query the content of a video using a graph matching algorithm. In this paper, we present the four models of a system called VISU for the generation of adaptive video summaries: an annotation model, a strata model, a cinematographic structure model and a query model. The query which describes the expected content of a summary to be generated is expressed using Conceptual Graphs. The segments of frames which constitute the result to the query are selected from a measure of relevance adapted from the Information Retrieval domain. Also, the duration of the expected summary can be controlled through the query. MOTS-CLES : video, annotation, strate, resume, Graphe Conceptuel
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
