Welcome to the new version of CaltechAUTHORS. Login is currently restricted to library staff. If you notice any issues, please email coda@library.caltech.edu
Published 2007 | Published
Book Section - Chapter Open

Graph-Based Visual Saliency

Abstract

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 ([2], [3], [4]) achieve only 84%.

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.

Attached Files

Published - 3095-graph-based-visual-saliency.pdf

Files

3095-graph-based-visual-saliency.pdf
Files (232.3 kB)
Name Size Download all
md5:fa1b04316ead0954aa7accc8790c5865
232.3 kB Preview Download

Additional details

Created:
September 15, 2023
Modified:
January 13, 2024