Re-Search

Providing searching service for multimedia data (images/videos) in a mobile environment is considered is highly desirable for mobile users. Meaningful metadata such as time (when), location (where), names of people (who), landmarks (what), and events (inferred from when, who, where, and what) should be obtained to organize large repositories of photos for efficient sharing, browsing, and searching. Although digital cameras can provide the when and where, obtaining the who and what will depend largely on analyzing photo content and the relationships among events and photographs. And the grand challenge -- event recognition -- will depend on intelligent detection of the synergistic relationship between context and content.

Open Issue: Analyzing photo content to mining the context information and the event of photographs. Can visual attention be utilized in this situation?

Reference:
1. Edward Chang's talk: Personal Image Organization and Search - http://www.natea.org/sv/events/2005/012005_image_analysis.html
2. Statistical Models and Algorithms for Image Annotation and Retrieval: The Mathematics of Perception E. Y. Chang, A book chapter in Digital Multimedia Perception (invited).
3. Inferring Image Metadata From Context and Content, C. Tsai, A. Qamra, and E. Y. Chang
4. EXTENT for Photo Annotation (US Patent), E. Y. Chang, Workshop on Computer Vision Meets Databases (CVDB) in cooperation with ACM International Conference on Management of Data (SIGMOD), Baltimore, June 2005.
5. Multimodal Metadata Fusion, Y. Wu, E. Y. Chang, and B. Tseng, UCSB Technical Report, May 2005 (submitted).