Harel, Jonathan and Koch, Christof and Perona, Pietro (2007) Graph-Based Visual Saliency. In: Advances in Neural Information Processing Systems 19 (NIPS 2006). Advances in Neural Information Processing Systems. No.19. MIT Press , Cambridge, MA, pp. 545-552. ISBN 0-262-19568-2 http://resolver.caltech.edu/CaltechAUTHORS:20160315-111145907
- Published Version
See Usage Policy.
Use this Persistent URL to link to this item: http://resolver.caltech.edu/CaltechAUTHORS:20160315-111145907
A new bottom-up visual saliency model, Graph-Based Visual Saliency (GBVS), is proposed. It consists of two steps: first forming activation maps on certain feature channels, and then normalizing them in a way which highlights conspicuity and admits combination with other maps. The model is simple, and biologically plausible insofar as it is naturally parallelized. This model 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%.
|Item Type:||Book Section|
|Additional Information:||© 2007 Massachusetts Institute of Technology. The authors express sincere gratitude to Wolfgang Einhäuser for his offering of natural images, and the fixation data associated with them from a study with seven human subjects. We also acknowledge NSF, NIH, DARPA, and ONR for their generous support of our research.|
|Group:||KLAB, Koch Laboratory|
|Usage Policy:||No commercial reproduction, distribution, display or performance rights in this work are provided.|
|Deposited By:||Kristin Buxton|
|Deposited On:||30 Mar 2016 23:40|
|Last Modified:||30 Mar 2016 23:40|
Repository Staff Only: item control page