Computational modelling of visual attention

By Laurent Itti, Christof Koch. 2001

4,770 citations recorded by the source corpus.

Subfields: Cognitive Neuroscience, Computer Vision and Pattern Recognition

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

Global-and-local attention networks for visual recognition (2018, methodology): “Decades of work on human attention have shown that our visual system uses at least two pathways to quickly guide attention to regions of interest [9]: A “global pathway” rapidly extracts a statistical summary of the whole scene in as little as a glance [10] while a complementary “local pathway” leve”
Residual Attention Network for Image Classification (2017, background): “The mixed nature of attention has been studied extensively in the previous literatures [34, 16, 23, 40].”
Evaluating the Visualization of What a Deep Neural Network Has Learned (2015, background): “In this paper, we refrain from mimicking the complex human heatmap evaluation process that includes attention, interest point models, and perception models of saliency [36]–[39] for the reason that we are interested in finding those regions that are relevant for a given classifier.”
The Frontoparietal Attention Network of the Human Brain (2012, background): “The term saliency is commonly applied to denote the physical intensity of signals in relation to surrounding stimuli (Itti and Koch 2001).”
Relative visual saliency differences induce sizable bias in consumer choice (2012, background): “Visual saliency then causes certain items to " pop out " of a visual scene, leading to automatic attention toward these items (Koch & Ullman, 1985; Itti & Koch, 2001; Mannan et al., 2009).”
Feature-based attention in visual cortex. (2006, background): “Such a representation of behaviorally relevant locations might be activated by knowledge of the environment, or by interactions between such knowledge and current sensory signals [ 46 ].”
Saliency Detection via Dense and Sparse Reconstruction (2013, background): “Numerous biologically plausible models have been developed to explain the cognitive process of humans and animals [12].”
The 35th Sir Frederick Bartlett Lecture: Eye movements and attention in reading, scene perception, and visual search (2009, background): “A fair number of computational models (Baddeley & Tatler, 2006; Itti & Koch, 2000, 2001; Parkhurst et al., 2002) use the concept of a saliency map (following from Findlay & Walker, 1999) to model eye fixation locations in scenes.”
Information Gaps: A Theory of Preferences Regarding the Presence and Absence of Information (2018, background): “Comparison and contrast generally increase a question’s salience (Duncan & Humphreys, 1989; Itti & Koch, 2001).”
What do eyes reveal about the mind?: Algorithmic inference of search targets from fixations (2015, background): “While the allocation of attention is often task-driven, it can also be guided by bottom-up and stimulusdriven cues [80,42,40,64,39,4,3,10].”
Components of bottom-up gaze allocation in natural images. (2005, positive): “Each model variant operates in the basic framework of a model of bottomup saliency-driven attention (Itti & Koch, 2001; Itti, Koch, & Niebur, 1998)—which we refer to here as the baseline salience model.”
Pyramid Dilated Deeper ConvLSTM for Video Salient Object Detection (2018, background): “Previous studies [18, 39] in cognitive psychology also emphasized the multi-scale nature as an essential element of visual saliency.”
Scene context guides eye movements during visual search. (2006, background): “Rather, we envision a common underlying search representation that integrates control signals from a wide variety of informational sources (see Itti & Koch, 2001; and Corbetta & Schulman, 2002, for possible brain areas responsible for this integration function).”
Quantitative Analysis of Human-Model Agreement in Visual Saliency Modeling: A Comparative Study (2013, background): “In [21], [60], authors enumerate and discuss features that influence attention.”