Ana B. Benitez, Shih-Fu Chang. Organization and Browsing of Annotated Images Using Multiresolution Knowledge Networks. ADVENT Technical Report #007 Columbia University, 2003.
Download paper:
Adobe portable document (pdf) 
Copyright notice:This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. These works may not be reposted without the explicit permission of the copyright holder.
This paper presents novel methods for organizing and browsing annotated images using multiresolution networks that represent knowledge about the images (e.g., objects, events and interactions). At the highest resolution, images are organized by perceptual knowledge (e.g., image clusters and visual relations), semantic knowledge (e.g., word senses and semantic relations), and statistical interrelations discovered from the collection. This process drives on the integrated processing of both images and annotations and the use of the electronic dictionary WordNet. Knowledge networks at lower resolutions are constructed by clustering similar concepts together. Users can then browse the annotated images by navigating the resulting knowledge network pyramid. Ideas from fish-eye views and spring modeling are exploited for displaying concepts using text and image example, and for drawing networks, respectively. Although the network pyramid is hierarchical, the navigation is not restricted to the hierarchy. Experiments are being conducted with users to evaluate the effectiveness, efficiency, and subjective satisfaction of the users in performing common browsing tasks such as image search. In these experiments, the proposed techniques are being compared to the sequential navigation of concepts in the initial knowledge network
@TechReport{dvmmPub13,
Author = {Benitez, Ana B. and Chang, Shih-Fu},
Title = {Organization and Browsing of Annotated Images Using Multiresolution Knowledge Networks},
Institution = {Columbia University},
Year = {2003}
}
Get EndNote Reference (.ref)
For problems or questions regarding this web site contact The
Web Master.
This document was translated automatically from BibTEX by bib2html (Copyright 2003 © Eric Marchand, INRIA, Vista Project).
