A feature-integration theory of attention.

By Anne Treisman, Garry A. Gelade. 1980

How researchers see this paper

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

Citations in the corpus

On the Binding Problem in Artificial Neural Networks (2020, background): “Another important empirical finding occurs when attention is overloaded (or directed elsewhere), which sometimes causes humans to perceive illusory conjunctions: illusory objects that are the result of wrongly combining features from other objects (Treisman and Gelade, 1980; Figure 23c).”
Top-Down Neural Attention by Excitation Backprop (2016, background): “Top-down task-driven attention is an important mechanism for efficient visual search (Usher and Niebur 1996; Wolfe et al. 2003). Various top-down attention models have been proposed, e.g. Koch andUllman (1987), Anderson and Essen (1987), Tsotsos et al.”
Scene segmentation by spike synchronization in reciprocally connected visual areas. II. Global assemblies and synchronization on larger space and time scales (2002, background): “The same effect may be responsible for the psychological finding ( Treisman and Gelade 1980; Treisman 1998) that some tasks can be done in parallel (search within one feature dimension, e.g., a red letter within green distractors), while other tasks need serial attention switching (e.g., search for”
Bottom-up priming of top-down attentional control settings (2008, background): “Theoretical accounts of such intertrial priming of features and dimensions have centred on the notion that pre-attentive processing produces activity in spatiotopically organized feature maps (Treisman & Gelade, 1980).”
A Stagewise Refinement Model for Detecting Salient Objects in Images (2017, background): “Early saliency models mainly concentrated on the lowlevel features dating back to the feature integration theory [44].”
The development of visual attention in infancy. (2001, background): “…(form and color are those usually put forth as examples, although size and texture are also sometimes mentioned; Robertson 1998) that are apparently processed independently are re-integrated or “bound” together to form a coherent percept (Treisman & Gelade 1980; but see Duncan & Humphreys 1989).”
Automatic foveation for video compression using a neurobiological model of visual attention (2004, background): “The extent to which the low-level features used here attract attention in humans and monkeys has been previously investigated in details [29], [44], [62].”
Why Look? Reasons for Eye Movements Related to Language Production. (2004, background): “It is generally believed that one function of attention is to combine separate features (e.g., color, shape) that appear at the same spatial location into an integrated whole or object (e.g., Treisman & Gelade, 1980 ); in the absence of attention, illusory conjunctions, or incorrect combinations of”
Modeling attention to salient proto-objects (2006, unknown): “Attention as a selective gating mechanism is often compared to a spotlight (Posner, 1980; Treisman & Gelade, 1980), enhancing visual processing in the attended ( " illuminated " ) region of a few degrees of visual angle (Sagi & Julesz, 1986).”
Context-aware saliency detection (2010, background): “Our context-aware saliency follows four basic principles of human visual attention, which are supported by psychological evidence [22, 26, 10, 11]:”
The “Physics” of Notations: Toward a Scientific Basis for Constructing Visual Notations in Software Engineering (2009, background): “Perceptual discrimination : Features of the retinal image (color, shape, etc.) are detected by specialized feature detectors [72], [131].”
Attention, please! A survey of neural attention models in deep learning (2021, background): “Treisman’s Feature Integration Theory (FIT) (Treisman and Gelade 1980), Wolfe’s Guides Search (Wolfe et al.”
Top-down modulation of preattentive processing: Testing the recovery account of contingent capture (2006, background): “…model’’, preattentive processing is a preliminary stage of analysis that provides a quick representation of the visual field in terms of ‘‘simple’’ or ‘‘basic’’ visual features such as colour, orientation, shape, brightness, etc. (Treisman & Gelade, 1980; Treisman & Souther, 1995; Wolfe, 1994).”