Abstract :
Text-based search engines have been flourishing. However, despite increasing needs of tools for organizing and searching imagery and video content, we have not seen a successful deployment of a Web-scale multimedia search engine. This talk (and paper) analyzes main technical challenges of such a deployment, and presents remedies in three areas: feature extraction, similarity characterization, and scalability.
Keywords :
feature extraction; multimedia databases; search engines; text analysis; Web-scale multimedia data management; feature extraction; similarity characterization; text-based search engines; Cameras; Data mining; Feature extraction; Indexing; Layout; Organizing; Scalability; Search engines; Shape; Statistical learning;
