A Multi-Level Pyramid for Classifying Visual Information Attributes
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).
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.
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.
A. Jaimes and S.-F. Chang,
Conceptual Framework for Indexing Visual Information at Multiple Levels,
Internet Imaging 2000, IS&T/SPIE, San Jose, CA, January 2000.
For problems or questions
regarding this web site contact The