Graph-Based Visual Saliency

Explore this paper's citation graph

Summary

A new bottom-up visual saliency model, Graph-Based Visual Saliency (GBVS), is proposed, which powerfully predicts human fixations on 749 variations of 108 natural images, achieving 98% of the ROC area of a human-based control, whereas the classical algorithms of Itti & Koch achieve only 84%.

Published
2006-12-04
Cited by
3,876
References
14
Access
Open access

References

Cited by

Related papers

No related papers recorded.