Loading [MathJax]/extensions/MathMenu.js
Multi-graph similarity reinforcement for image annotation refinement | IEEE Conference Publication | IEEE Xplore

Multi-graph similarity reinforcement for image annotation refinement


Abstract:

In image annotation refinement, word correlations among candidate annotations are used to reserve high relevant words and remove irrelevant words. Existing methods build ...Show More

Abstract:

In image annotation refinement, word correlations among candidate annotations are used to reserve high relevant words and remove irrelevant words. Existing methods build word correlations on textual annotations of images. In this paper, visual contents of images are utilized to explore better word correlations by using multi-graph similarity reinforcement method. Firstly, image visual similarity graph and word correlations graph are built respectively. Secondly, the two graphs are iteratively reinforced by each other through image-word transfer matrix. Once the two graphs converge to steady states, the new word correlations graph is used to refine the candidate annotations. The experiments show that our method performs better than method not considering visual content of images.
Date of Conference: 12-15 October 2008
Date Added to IEEE Xplore: 12 December 2008
ISBN Information:

ISSN Information:

Conference Location: San Diego, CA, USA

References

References is not available for this document.