A saliency-based search mechanism for overt and covert shifts of visual attention.

By Laurent Itti, Christof Koch. Vision Research, 2000

3,313 citations recorded by the source corpus.

Subfields: Cognitive Neuroscience, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/7b4b801de1ba8a4456adcde7b1a9c5bc5cf09fc3

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

The central fixation bias in scene viewing: selecting an optimal viewing position independently of motor biases and image feature distributions. (2007, background): “…popular weighted salience account of selection, in which the top down modulation can be manifest in terms of selectively weighting the feature maps (Itti & Koch, 2000; Peters et al., 2005), fails to account for certain aspects of human performance (Vincent, Troscianko, & Gilchrist, 2007): For…”
Object-based visual attention for computer vision (2003, background): “Future research will consider overt eye movements such as saccades and how saliency is integrated with overt multiple fixations.”
A coherent computational approach to model bottom-up visual attention (2006, positive): “The second category consists of models [6], [7], [8], [9], [10], [11] built around two important concepts: the Feature Integration Theory (FIT) from Treisman and Gelade [12] and a neurally plausible architecture proposed by Koch and Ullman [13].”
Dynamic Eye Movement Datasets and Learnt Saliency Models for Visual Action Recognition (2012, methodology): “The problem of visual attention and the prediction of visual saliency have long been of interest in the human vision community[16, 10, 18].”
Clustering of Gaze During Dynamic Scene Viewing is Predicted by Motion (2011, methodology): “The widely used computational model of visual saliency developed by Itti and Koch [19] [28] has been shown to predict fixation locations better than chance under some conditions [21] [28].”
Edge and line oriented contour detection: State of the art (2011, background): “In particular, much research has been made to distinguish from long chains of collinear edges and randomly scattered oriented stimuli [136,137,291].”
An Integrated Model of Top-Down and Bottom-Up Attention for Optimizing Detection Speed (2006, methodology): “T0D0, the naive, bottom-up model [9] does not know T or D (hence, uses default top-down weights of 1).”
TRoPICALS: a computational embodied neuroscience model of compatibility effects. (2010, background): “…processes would guide attention based on the perceptual saliency of the various regions of the scene and objects (cf. Wheeler & Treisman, 2002, and Itti & Koch, 2000, Knudsen, 2007, on this; see Ognibene, Balkenius, & Baldassarre, 2008, for the proposal of an architecture that integrates…”
Modeling the influence of task on attention. (2005, methodology): “To further explore the validity of such a mechanism, we compared our biased modelÕs predictions with existing psychophysical data and other models such as a random model, the bottom-up or unbiased model (Itti & Koch, 2000), and the top-down search model proposed by Rao et al. (2002).”
Interesting objects are visually salient. (2008, background): “Since we define interesting objects as objects that people choose to label , we hypothesize that one such distinguishing visual property is low - level visual saliency , as approximated by saliency map models ( Itti et al .”
The Neural Basis of Selective Attention (2008, background): “Itti and Koch (2000) proposed a model of stimulus-driven capture of Address correspondence to Steven Yantis, Department of Psycho logical and Brain Sciences, Johns Hopkins University, 3400 N.”
Visual Fixation Durations and Saccade Amplitudes: Shifting Relationship in a Variety of Conditions (2008, neutral): “It has often been suggested that eye guidance is mainly controlled by stimulus properties (Engel, 1977; Godijn & Theeuwes, 2002; Itti & Koch, 2000; Kramer, Irwin, Theeuwes, & Hahn, 1999; Parkhurst, Law, & Niebur, 2002; Torralba, Oliva, Castelhano, & Henderson, 2006).”
Creativity, attention and the memory for brands: an outdoor advertising field study (2015, methodology): “…grouped together because these items represent the best approximation of the visual features that are detected early in human visual search, and humans tend to respond collectively to these factors rather than individually (Borji, Sihite, and Itti 2013; Itti and Koch 2000; Le Meur and Chevet 2010).”
Optimal scanning for faster object detection (2009, background): “Models of visual saliency [13, 8 , 18] have been shown to provide a useful way to improve the search efficiency of specific object detectors, i.e., most regions without objects tend to have low visual saliency [5].”
Task and context determine where you look. (2016, methodology): “The parameters were adjusted to match the values mentioned in Itti ( 2000 ) and Itti and Koch ( 2000 ) .”
How are eye fixation durations controlled during scene viewing? Further evidence from a scene onset delay paradigm (2009, methodology): “…http://www.psypress.com/viscog DOI: 10.1080/13506280802685552 the processes that determine fixation locations (e.g., Baddeley & Tatler, 2006; Itti & Koch, 2000; Parkhurst & Neibur, 2003; Reinagel & Zador, 1999; Tatler, Baddeley, & Gilchrist, 2005; Torralba, Oliva, Castelhano, & Henderson,…”
Saliency Detection: A Spectral Residual Approach (2007, methodology): “Based on Treisman’s integration theory [24], Itti and Koch proposed a saliency model that simulates the visual search process of human [8, 6, 7].”
Attentional Selection for Object Recognition - A Gentle Way (2002, methodology): “Our model combines a saliency-based attention system [2, 8, 9] with a hierarchical recognition system [10, 11].”