Graph-Based Visual Saliency
Jonathan Harel, Christof Koch, Pietro Perona · The MIT Press eBooks · 2007
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 \nchannels, and then normalizing them in a way which highlights conspicuity and admits combination with other maps. The model is simple, and biologically plausible \ninsofar as it is naturally parallelized. This model powerfully predicts human fixations on 749 variations of 108 natural images, achieving 98% of the ROC area \nof a human-based control, whereas the classical algorithms of Itti & Koch ([2], [3], [4]) achieve only 84%.
Cited by 3,439 works. doi:10.7551/mitpress/7503.003.0073
Authors
References
- A model of saliency-based visual attention for rapid scene analysis
- Preattentive texture discrimination with early vision mechanisms
- A saliency-based search mechanism for overt and covert shifts of visual attention
- Saliency Based on Information Maximization
- Modeling the role of salience in the allocation of overt visual attention
- Is bottom-up attention useful for object recognition?
- Visual correlates of fixation selection: effects of scale and time
- Attention activates winner-take-all competition among visual filters
- Does luminance‐contrast contribute to a saliency map for overt visual attention?
- Differences of monkey and human overt attention under natural conditions