scispace - formally typeset
Search or ask a question
Journal ArticleDOI

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

01 Jun 2000-Vision Research (Elsevier)-Vol. 40, Iss: 10, pp 1489-1506
TL;DR: A detailed computer implementation of a saliency map scheme is described, focusing on the problem of combining information across modalities, here orientation, intensity and color information, in a purely stimulus-driven manner, which is applied to common psychophysical stimuli as well as to a very demanding visual search task.
About: This article is published in Vision Research.The article was published on 2000-06-01 and is currently open access. It has received 3105 citations till now. The article focuses on the topics: Visual search & Gaze-contingency paradigm.
Citations
More filters
Journal ArticleDOI
TL;DR: Five important trends have emerged from recent work on computational models of focal visual attention that emphasize the bottom-up, image-based control of attentional deployment, providing a framework for a computational and neurobiological understanding of visual attention.
Abstract: Five important trends have emerged from recent work on computational models of focal visual attention that emphasize the bottom-up, image-based control of attentional deployment. First, the perceptual saliency of stimuli critically depends on the surrounding context. Second, a unique 'saliency map' that topographically encodes for stimulus conspicuity over the visual scene has proved to be an efficient and plausible bottom-up control strategy. Third, inhibition of return, the process by which the currently attended location is prevented from being attended again, is a crucial element of attentional deployment. Fourth, attention and eye movements tightly interplay, posing computational challenges with respect to the coordinate system used to control attention. And last, scene understanding and object recognition strongly constrain the selection of attended locations. Insights from these five key areas provide a framework for a computational and neurobiological understanding of visual attention.

4,485 citations

Proceedings Article
04 Dec 2006
TL;DR: A new bottom-up visual saliency model, Graph-Based Visual Saliency (GBVS), is proposed, which 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 achieve only 84%.
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%

3,475 citations


Cites methods or result from "A saliency-based search mechanism f..."

  • ...The parameters of this were checked against the literature [2] and [ 3 ], and were found to be almost identical, with a few slight alterations that actually improved performance relative to the published parameters....

    [...]

  • ...graph (ii) graph (iv) 0.981148 graph (i) graph (iv) 0.975313 graph (ii) I 0.974592 graph (ii) ave-max 0.974578 graph (ii) graph (iii) 0.974227 graph (i) graph (iii) 0.968414 self-info I 0.841054 *Bruce & Tsotsos [5] c-s DoG 0.840968 *Itti & Koch [ 3 ] c-s ave-max 0.840725 *Itti, Koch, &...

    [...]

  • ...This model powerfully predicts human �xations 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%....

    [...]

Proceedings ArticleDOI
17 Jun 2007
TL;DR: A simple method for the visual saliency detection is presented, independent of features, categories, or other forms of prior knowledge of the objects, and a fast method to construct the corresponding saliency map in spatial domain is proposed.
Abstract: The ability of human visual system to detect visual saliency is extraordinarily fast and reliable. However, computational modeling of this basic intelligent behavior still remains a challenge. This paper presents a simple method for the visual saliency detection. Our model is independent of features, categories, or other forms of prior knowledge of the objects. By analyzing the log-spectrum of an input image, we extract the spectral residual of an image in spectral domain, and propose a fast method to construct the corresponding saliency map in spatial domain. We test this model on both natural pictures and artificial images such as psychological patterns. The result indicate fast and robust saliency detection of our method.

3,464 citations


Cites methods from "A saliency-based search mechanism f..."

  • ...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]....

    [...]

Proceedings ArticleDOI
01 Sep 2009
TL;DR: This paper collects eye tracking data of 15 viewers on 1003 images and uses this database as training and testing examples to learn a model of saliency based on low, middle and high-level image features.
Abstract: For many applications in graphics, design, and human computer interaction, it is essential to understand where humans look in a scene Where eye tracking devices are not a viable option, models of saliency can be used to predict fixation locations Most saliency approaches are based on bottom-up computation that does not consider top-down image semantics and often does not match actual eye movements To address this problem, we collected eye tracking data of 15 viewers on 1003 images and use this database as training and testing examples to learn a model of saliency based on low, middle and high-level image features This large database of eye tracking data is publicly available with this paper

2,093 citations


Cites background or methods from "A saliency-based search mechanism f..."

  • ...We include the three channels corresponding to these image features as calculated by Itti and Koch’s saliency method [9]....

    [...]

  • ...Most models of saliency [9] [13] [8] are biologically Figure 1....

    [...]

Journal ArticleDOI
TL;DR: Research on the following topics is reviewed with respect to reading: (a) the perceptual span, (or span of effective vision), (b) preview benefit, (c) eye movement control, and (d) models of eye movements.
Abstract: Eye movements are now widely used to investigate cognitive processes during reading, scene perception, and visual search. In this article, research on the following topics is reviewed with respect to reading: (a) the perceptual span (or span of effective vision), (b) preview benefit, (c) eye movement control, and (d) models of eye movements. Related issues with respect to eye movements during scene perception and visual search are also reviewed. It is argued that research on eye movements during reading has been somewhat advanced over research on eye movements in scene perception and visual search and that some of the paradigms developed to study reading should be more widely adopted in the study of scene perception and visual search. Research dealing with "real-world" tasks and research utilizing the visual-world paradigm are also briefly discussed.

2,033 citations


Cites background from "A saliency-based search mechanism f..."

  • ...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....

    [...]

  • ...…recently been devoted to understanding the factors that govern fixation position in scenes (Foulsham, Kingstone, & Underwood, 2008; Henderson, 2003; Itti & Koch, 2000; Melcher & Kowler, 2001; Parkhurst, Law, & Niebur, 2002; Rutishauser & Koch, 2007; Tatler, Baddeley, & Vincent, 2006; Underwood,…...

    [...]

References
More filters
Book
01 Jan 1890
TL;DR: For instance, the authors discusses the multiplicity of the consciousness of self in the form of the stream of thought and the perception of space in the human brain, which is the basis for our work.
Abstract: Arguably the greatest single work in the history of psychology. James's analyses of habit, the nature of emotion, the phenomenology of attention, the stream of thought, the perception of space, and the multiplicity of the consciousness of self are still widely cited and incorporated into contemporary theoretical accounts of these phenomena.

14,049 citations

Journal ArticleDOI
TL;DR: A new hypothesis about the role of focused attention is proposed, which offers a new set of criteria for distinguishing separable from integral features and a new rationale for predicting which tasks will show attention limits and which will not.

11,452 citations


"A saliency-based search mechanism f..." refers background in this paper

  • ...…has accumulated in favor of a twocomponent framework for the control of where in a visual scene attention is deployed (James, 1890/1981; Treisman & Gelade, 1980; Bergen & Julesz, 1983; Treisman, 1988; Nakayama & Mackeben, 1989; Braun & Sagi, 1990; Hikosaka, Miyauchi & Shimojo, 1996; Braun, 1998;…...

    [...]

  • ...In contrast, search times for targets which differ from distractors by a combination of features (a so-called ‘conjunctive task’) are typically proportional to the number of distractors (Treisman & Gelade, 1980)....

    [...]

Journal ArticleDOI
TL;DR: In this article, a visual attention system inspired by the behavior and the neuronal architecture of the early primate visual system is presented, where multiscale image features are combined into a single topographical saliency map.
Abstract: A visual attention system, inspired by the behavior and the neuronal architecture of the early primate visual system, is presented. Multiscale image features are combined into a single topographical saliency map. A dynamical neural network then selects attended locations in order of decreasing saliency. The system breaks down the complex problem of scene understanding by rapidly selecting, in a computationally efficient manner, conspicuous locations to be analyzed in detail.

10,525 citations

Book
01 Jan 2010

8,181 citations

Journal ArticleDOI
TL;DR: The two basic phenomena that define the problem of visual attention can be illustrated in a simple example and selectivity-the ability to filter out un­ wanted information is illustrated.
Abstract: The two basic phenomena that define the problem of visual attention can be illustrated in a simple example. Consider the arrays shown in each panel of Figure 1. In a typical experiment, before the arrays were presented, subjects would be asked to report letters appearing in one color (targets, here black letters), and to disregard letters in the other color (nontargets, here white letters). The array would then be briefly flashed, and the subjects, without any opportunity for eye movements, would give their report. The display mimics our. usual cluttered visual environment: It contains one or more objects that are relevant to current behavior, along with others that are irrelevant. The first basic phenomenon is limited capacity for processing information. At any given time, only a small amount of the information available on the retina can be processed and used in the control of behavior. Subjectively, giving attention to any one target leaves less available for others. In Figure 1, the probability of reporting the target letter N is much lower with two accompa­ nying targets (Figure la) than with none (Figure Ib). The second basic phenomenon is selectivity-the ability to filter out un­ wanted information. Subjectively, one is aware of attended stimuli and largely unaware of unattended ones. Correspondingly, accuracy in identifying an attended stimulus may be independent of the number of nontargets in a display (Figure la vs Ie) (see Bundesen 1990, Duncan 1980).

7,642 citations


"A saliency-based search mechanism f..." refers background in this paper

  • ...In particular, Desimone and Duncan (1995) postulate that selective attention is a consequence of interactions among feature maps, each of which encodes in an implicit fashion, the saliency of a stimulus in that particular feature....

    [...]

  • ...Alternatively, it is possible that stimulus saliency is not expressed independently of feature dimensions but is encoded implicitly within each specific feature map as proposed by Desimone and Duncan, (1995) ....

    [...]

  • ...In particular, Desimone and Duncan (1995) postulate that selective attention is a consequence of interactions among feature maps, each of which encodes in an implicit fashion, the saliency of a stimulus in that particular feature....

    [...]