Using Coherent Semantic Subpaths to Derive Emergent Semantics

We contend that the author of a Web page cannot completely define that document’s semantics and that semantics emerge through use. Semantics is context-sensitive. User browsing paths over a multimedia collection provide, we believe, the necessary context to derive semantics. We attempt to use information from several modalities to improve retrieval using a single modality. We have developed and tested several algorithms to detect breakpoints and cluster Web pages into groups that exhibit uniform semantics. We have also used visual-keywords to improve textual-keyword based searches.

[1]  Marvin B. Shapiro.  The choice of reference points in best-match file searching , 1977, CACM.

[2]  William I. Grosky,et al.  Narrowing the semantic gap - improved text-based web document retrieval using visual features , 2002, IEEE Trans. Multim..

[3]  Richard P Taylor.  Order in Pollock's chaos. , 2002, Scientific American.

[4]  Cyrus Shahabi,et al.  Knowledge discovery from users Web-page navigation , 1997, Proceedings Seventh International Workshop on Research Issues in Data Engineering. High Performance Database Management for Large-Scale Applications.

[5]  Kyuseok Shim,et al.  WALRUS: a similarity retrieval algorithm for image databases , 1999, IEEE Transactions on Knowledge and Data Engineering.

[6]  Elizabeth R. Jessup,et al.  Matrices, Vector Spaces, and Information Retrieval , 1999, SIAM Rev..

[7]  Jaideep Srivastava,et al.  Automatic personalization based on Web usage mining , 2000, CACM.

[8]  Minh N. Do,et al.  Integrated Browsing and Searching of Large Image Collections , 2000, VISUAL.

[9]  Simone Santini,et al.  Emergent Semantics through Interaction in Image Databases , 2001, IEEE Trans. Knowl. Data Eng..

[10]  Marco La Cascia,et al.  Unifying Textual and Visual Cues for Content-Based Image Retrieval on the World Wide Web , 1999, Comput. Vis. Image Underst..