Modeling the role of salience in the allocation of overt visual attention.

By Derrick J. Parkhurst, Klinton Law, Ernst Niebur. Vision Research, 2002

1,511 citations recorded by the source corpus.

A biologically motivated computational model of bottom-up visual selective attention was used to examine the degree to which stimulus salience guides the allocation of attention. Human eye movements were recorded while participants viewed a series of digitized images of complex natural and artificial scenes. Stimulus dependence of attention, as measured by the correlation between computed stimulus salience and fixation locations, was found to be significantly greater than that expected by chance alone and furthermore was greatest for eye movements that immediately follow stimulus onset. The ability to guide attention of three modeled stimulus features (color, intensity and orientation) was examined and found to vary with image type. Additionally, the effect of the drop in visual sensitivity as a function of eccentricity on stimulus salience was examined, modeled, and shown to be an important determiner of attentional allocation. Overall, the results indicate that stimulus-driven, bottom-up mechanisms contribute significantly to attentional guidance under natural viewing conditions.

Subfields: Cognitive Neuroscience, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/fb19d28f3b0d96e65036fde8a0adc9bf1c4bbe46

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Cognitive Neuroscience

In Computer Vision and Pattern Recognition

Citations in the corpus

Deep Contrast Learning for Salient Object Detection (2016, background): “Results from perceptual research [12, 38] indicate that visual contrast is the most important factor in visual saliency.”
Human gaze control during real-world scene perception. (2003, background): “The salient points in the map serve as a prediction about the spatial distribution of gaze in a scene, and these points can be correlated with observed human fixations [23, 24 ].”
A Benchmark of Computational Models of Saliency to Predict Human Fixations (2012, background): “Several authors have shown that regions of interest found by computational model of visual attention correlate with eye fixations [59] [53] [19] [29] [52] [6] [33] [57] and the reported area under receiver operating characteristic (ROC) curve, which measures how well the two correlate, has increased”
Is bottom-up attention useful for object recognition? (2004, background): “While the model's usefulness has been demonstrated in various contexts (e.g. prediction of eye movements of humans [22]), its ability to serve as a front-end for object recognition is limited by the fact that its output is merely a pair of coordinates in the image corresponding to the most salient…”
Eye movements in natural behavior. (2005, background): “There are indeed some regularities in fixation patterns that can be explained by image properties [21-23].”
Components of bottom-up gaze allocation in natural images. (2005, methodology): “In general, our data agree with previous results (Parkhurst et al., 2002) showing that the baseline salience model was significantly above chance (p 10 À23 ) at predicting locations likely to be fixated by observers in a free-viewing task.”
Facilitation of return during scene viewing (2009, methodology): “…for computational models of attentional control All current computational models of attentional control during scene viewing require a mechanism for driving attention through conspicuous regions in a scene (Itti & Koch, 2001; Navalpakkam & Itti, 2005; Parkhurst et al., 2002; Sun et al., 2008).”
Tracking Restorative Components: Patterns in Eye Movements as a Consequence of a Restorative Rating Task (2013, background): “Top-down implies a goal-directed mechanism whereby semantic features influence view patterns (Parkhurst et al., 2002).”
Efficient Salient Region Detection with Soft Image Abstraction (2013, background): “Visual uniqueness in terms of high contrast to other image regions is believed to be the most important indicator of low-level visual saliency [21, 41].”
A coherent computational approach to model bottom-up visual attention (2006, neutral): “The collected data corresponds to the regular time sampling (20 ms) of eye gaze on the monitor.”
Years, Months, and Days versus 1, 12, and 365: The Influence of Units versus Numbers (2012, background): “As Pelham et al. (1994) discuss, because more pieces of something usually suggest a larger magnitude, people develop a numerosity heuristic.”
Shining in the Center: Central Gaze Cascade Effect on Product Choice (2012, background): “(2003), ―Biased Predecision Processing,‖ Psychological Bulletin, 129 (4), 545–68. Buswell, Guy Thomas (1935), How People Look at Pictures: A Study of the Psychology of Perception in Art, Chicago: University of Chicago Press.”
SuperCNN: A Superpixelwise Convolutional Neural Network for Salient Object Detection (2015, background): “Perceptual research (Itti and Koch 2001; Parkhurst et al. 2002) has shown that contrast is amajor factor to visual attention in the human visual system.”
What Do Different Evaluation Metrics Tell Us About Saliency Models? (2016, background): “The effect of center bias on model evaluation has received much attention [13], [22], [47], [60], [67], [78], [79], [93].”