A Multi-Level Pyramid for Classifying Visual Information Attributes

Project's Home Page | Current Research Areas > Multimedia Indexing and Content Management >



A new conceptual framework for classifying visual information (image, video, etc.) attributes. The framework, which draws on research from severl fields related to image/video indexing (Cognitive Psychology, Information Sciences, Content-Based Retrieval, etc.) classifies visual attributes (and relationships) into 10 levels, distinguishing between Syntax (form) and Semantics (meaning).


Student Researchers: Alejandro Jaimes, Ana B. Benitez

Faculty: Prof. Shih-Fu Chang

Collaborators: Prof. Corinne Jörgensen of Florida State University School

Contact: Shih-Fu Chang


C. Jorgensen, A. Jaimes, A. B. Benitez, and S.-F. Chang, A Conceptual Framework and Research for Classifying Visual Descriptors, Journal of the American Society for Information Science (JASIS), Invited Paper on Special Issue on Image Access: Bridging Multiple Needs and Multiple Perspectives, Sep 2001.
(Paper: PDF)

A. Jaimes, A. B. Benitez, C. Jorgensen, and S.-F. Chang, Experiments in Indexing Multimedia Data at Multiple Levels, ASIS SIG Classification Research Workshop, Idea Mart: Classification for User Support and Learning, Chicago, IL, Nov 2000.
(Paper: PDF)

A. Jaimes and S.-F. Chang, A Conceptual Framework for Indexing Visual Information at Multiple Levels, Internet Imaging 2000, IS&T/SPIE, San Jose, CA, January 2000.
(Paper: PDF)

For problems or questions regarding this web site contact The Web Master.
Last updated: June 21, 2003.