Video Data Visualization System: Semantic Classification And Personalization
This work addresses the problem of managing and exploring large video datasets for users needing semantic organization and personalization, though it appears incremental in combining existing techniques.
The authors developed a video data visualization system that uses semantic classification to organize and explore large video collections, projecting semantic classes into a visualization space with nodes representing keyframes and edges showing document-class relationships, and incorporated user profiling to personalize the system.
We present in this paper an intelligent video data visualization tool, based on semantic classification, for retrieving and exploring a large scale corpus of videos. Our work is based on semantic classification resulting from semantic analysis of video. The obtained classes will be projected in the visualization space. The graph is represented by nodes and edges, the nodes are the keyframes of video documents and the edges are the relation between documents and the classes of documents. Finally, we construct the user's profile, based on the interaction with the system, to render the system more adequate to its references.