Visual Attention. Itti, L. In The Handbook of Brain Theory and Neural Networks, pages 1196-1201. MIT Press, Jan, 2003. abstract bibtex Selective visual attention is the mechanism by which we can rapidly direct our gaze towards objects of interest in our visual environment. From an evolutionary viewpoint, this rapid orienting capability is critical in allowing living systems to quickly become aware of possible preys, mates or predators in their cluttered visual world. It has become clear that attention guides where to look next based on both bottom-up (image-based) and top-down (task-dependent) cues. As such, attention implements an information processing bottleneck, only allowing a small part of the incoming sensory information to reach short-term memory and visual awareness. That is, instead of attempting to fully process the massive sensory input in parallel, nature has devised a serial strategy to achieve near real-time performance despite limited computational capacity: Attention allows us to break down the problem of scene understanding into rapid series of computationally less demanding, localized visual analysis problems. These orienting and scene analysis functions of attention are complemented by a feedback modulation of neural activity at the location and for the visual attributes of the desired or selected targets. This feedback is believed to be essential for binding the different visual attributes of an object, such as color and form, into a unitary percept. That is, attention not only serves to select a location of interest, but also enhances the cortical representation at that location. As such, focal visual attention is often compared to a rapidly shiftable spotlight, which scans our visual environment both overtly (with accompanying eye movements) or covertly (with the eyes fixed). This spotlight has been shown to have variable size and shape depending on the target being attended to. Finally, attention is involved in triggering behavior, and consequently is intimately related to recognition, planning and motor control. Of course, not all of vision is attentional, as we can derive coarse understanding from presentations of visual scenes that are so brief that they do not leave time for attention to explore the scene. Vision thus appears to rely on sophisticated interactions between coarse, massively parallel, full-field pre-attentive analysis systems and the more detailed, circumscribed and sequential attentional analysis system. In what follows, we focus on several critical aspects of selective visual attention: First, the brain area involved in its control and deployment; second, the mechanisms by which attention is attracted in a bottom-up or image-based manner towards conspicuous or salient locations in our visual environment; third, the mechanisms by which attention modulates the early sensory representation of attended stimuli; fourth, the mechanisms for top-down or voluntary deployment of attention towards visual locations that may not necessarily be intrinsically conspicuous, but may be of interest in solving a given visual task; and fifth, the interaction between attention, object recognition and scene understanding.
@incollection{ Itti03hbtnn2e,
author = { L. Itti },
title = { Visual Attention },
year = {2003},
month = {Jan},
booktitle = { The Handbook of Brain Theory and Neural Networks },
publisher = {MIT Press},
abstract = {Selective visual attention is the mechanism by which we can
rapidly direct our gaze towards objects of interest in our visual
environment. From an evolutionary viewpoint, this rapid orienting
capability is critical in allowing living systems to quickly become
aware of possible preys, mates or predators in their cluttered visual
world. It has become clear that attention guides where to look next
based on both bottom-up (image-based) and top-down (task-dependent)
cues. As such, attention implements an information processing
bottleneck, only allowing a small part of the incoming sensory
information to reach short-term memory and visual awareness. That is,
instead of attempting to fully process the massive sensory input in
parallel, nature has devised a serial strategy to achieve near
real-time performance despite limited computational capacity:
Attention allows us to break down the problem of scene understanding
into rapid series of computationally less demanding, localized visual
analysis problems. These orienting and scene analysis functions of
attention are complemented by a feedback modulation of neural activity
at the location and for the visual attributes of the desired or
selected targets. This feedback is believed to be essential for
binding the different visual attributes of an object, such as color
and form, into a unitary percept. That is, attention not only serves
to select a location of interest, but also enhances the cortical
representation at that location. As such, focal visual attention is
often compared to a rapidly shiftable spotlight, which scans our
visual environment both overtly (with accompanying eye movements) or
covertly (with the eyes fixed). This spotlight has been shown to have
variable size and shape depending on the target being attended to.
Finally, attention is involved in triggering behavior, and
consequently is intimately related to recognition, planning and motor
control. Of course, not all of vision is attentional, as we can derive
coarse understanding from presentations of visual scenes that are so
brief that they do not leave time for attention to explore the
scene. Vision thus appears to rely on sophisticated interactions
between coarse, massively parallel, full-field pre-attentive analysis
systems and the more detailed, circumscribed and sequential
attentional analysis system. In what follows, we focus on several
critical aspects of selective visual attention: First, the brain area
involved in its control and deployment; second, the mechanisms by
which attention is attracted in a bottom-up or image-based manner
towards conspicuous or salient locations in our visual environment;
third, the mechanisms by which attention modulates the early sensory
representation of attended stimuli; fourth, the mechanisms for
top-down or voluntary deployment of attention towards visual locations
that may not necessarily be intrinsically conspicuous, but may be of
interest in solving a given visual task; and fifth, the interaction
between attention, object recognition and scene understanding.},
editor = {M. A. Arbib},
pages = {1196-1201},
file = { http://iLab.usc.edu/publications/doc/Itti02hbtnn2e.pdf },
type = {mod;bu;td;psy;rev;sc}
}
Downloads: 0
{"_id":{"_str":"5298a1a09eb585cc26000851"},"__v":0,"authorIDs":[],"author_short":["Itti, L."],"bibbaseid":"itti-visualattention-2003","bibdata":{"html":"<div class=\"bibbase_paper\"> \n\n\n<span class=\"bibbase_paper_titleauthoryear\">\n\t<span class=\"bibbase_paper_title\"><a name=\"Itti03hbtnn2e\"> </a>Visual Attention.</span>\n\t<span class=\"bibbase_paper_author\">\nItti, L.</span>\n\t<!-- <span class=\"bibbase_paper_year\">2003</span>. -->\n</span>\n\nIn\nArbib, M. A., editor, <i>The Handbook of Brain Theory and Neural Networks</i>, page 1196-1201.\nMIT Press, Jan 2003.\n\n\n\n<br class=\"bibbase_paper_content\"/>\n\n<span class=\"bibbase_paper_content\">\n \n \n \n <a href=\"javascript:showBib('Itti03hbtnn2e')\"\n class=\"bibbase link\">\n <!-- <img src=\"http://www.bibbase.org/img/filetypes/bib.png\" -->\n\t<!-- alt=\"Visual Attention [bib]\" -->\n\t<!-- class=\"bibbase_icon\" -->\n\t<!-- style=\"width: 24px; height: 24px; border: 0px; vertical-align: text-top\"><span class=\"bibbase_icon_text\">Bibtex</span> -->\n BibTeX\n <i class=\"fa fa-caret-down\"></i></a>\n \n \n \n <a class=\"bibbase_abstract_link bibbase link\"\n href=\"javascript:showAbstract('Itti03hbtnn2e')\">\n Abstract\n <i class=\"fa fa-caret-down\"></i></a>\n \n \n \n\n \n \n \n</span>\n\n<div class=\"well well-small bibbase\" id=\"bib_Itti03hbtnn2e\"\n style=\"display:none\">\n <pre>@incollection{ Itti03hbtnn2e,\n author = { L. Itti },\n title = { Visual Attention },\n year = {2003},\n month = {Jan},\n booktitle = { The Handbook of Brain Theory and Neural Networks },\n publisher = {MIT Press},\n abstract = {Selective visual attention is the mechanism by which we can\nrapidly direct our gaze towards objects of interest in our visual\nenvironment. From an evolutionary viewpoint, this rapid orienting\ncapability is critical in allowing living systems to quickly become\naware of possible preys, mates or predators in their cluttered visual\nworld. It has become clear that attention guides where to look next\nbased on both bottom-up (image-based) and top-down (task-dependent)\ncues. As such, attention implements an information processing\nbottleneck, only allowing a small part of the incoming sensory\ninformation to reach short-term memory and visual awareness. That is,\ninstead of attempting to fully process the massive sensory input in\nparallel, nature has devised a serial strategy to achieve near\nreal-time performance despite limited computational capacity:\nAttention allows us to break down the problem of scene understanding\ninto rapid series of computationally less demanding, localized visual\nanalysis problems. These orienting and scene analysis functions of\nattention are complemented by a feedback modulation of neural activity\nat the location and for the visual attributes of the desired or\nselected targets. This feedback is believed to be essential for\nbinding the different visual attributes of an object, such as color\nand form, into a unitary percept. That is, attention not only serves\nto select a location of interest, but also enhances the cortical\nrepresentation at that location. As such, focal visual attention is\noften compared to a rapidly shiftable spotlight, which scans our\nvisual environment both overtly (with accompanying eye movements) or\ncovertly (with the eyes fixed). This spotlight has been shown to have\nvariable size and shape depending on the target being attended to.\nFinally, attention is involved in triggering behavior, and\nconsequently is intimately related to recognition, planning and motor\ncontrol. Of course, not all of vision is attentional, as we can derive\ncoarse understanding from presentations of visual scenes that are so\nbrief that they do not leave time for attention to explore the\nscene. Vision thus appears to rely on sophisticated interactions\nbetween coarse, massively parallel, full-field pre-attentive analysis\nsystems and the more detailed, circumscribed and sequential\nattentional analysis system. In what follows, we focus on several\ncritical aspects of selective visual attention: First, the brain area\ninvolved in its control and deployment; second, the mechanisms by\nwhich attention is attracted in a bottom-up or image-based manner\ntowards conspicuous or salient locations in our visual environment;\nthird, the mechanisms by which attention modulates the early sensory\nrepresentation of attended stimuli; fourth, the mechanisms for\ntop-down or voluntary deployment of attention towards visual locations\nthat may not necessarily be intrinsically conspicuous, but may be of\ninterest in solving a given visual task; and fifth, the interaction\nbetween attention, object recognition and scene understanding.},\n editor = {M. A. Arbib},\n pages = {1196-1201},\n file = { http://iLab.usc.edu/publications/doc/Itti02hbtnn2e.pdf },\n type = {mod;bu;td;psy;rev;sc}\n}</pre>\n</div>\n\n\n<div class=\"well well-small bibbase\" id=\"abstract_Itti03hbtnn2e\"\n style=\"display:none\">\n Selective visual attention is the mechanism by which we can rapidly direct our gaze towards objects of interest in our visual environment. From an evolutionary viewpoint, this rapid orienting capability is critical in allowing living systems to quickly become aware of possible preys, mates or predators in their cluttered visual world. It has become clear that attention guides where to look next based on both bottom-up (image-based) and top-down (task-dependent) cues. As such, attention implements an information processing bottleneck, only allowing a small part of the incoming sensory information to reach short-term memory and visual awareness. That is, instead of attempting to fully process the massive sensory input in parallel, nature has devised a serial strategy to achieve near real-time performance despite limited computational capacity: Attention allows us to break down the problem of scene understanding into rapid series of computationally less demanding, localized visual analysis problems. These orienting and scene analysis functions of attention are complemented by a feedback modulation of neural activity at the location and for the visual attributes of the desired or selected targets. This feedback is believed to be essential for binding the different visual attributes of an object, such as color and form, into a unitary percept. That is, attention not only serves to select a location of interest, but also enhances the cortical representation at that location. As such, focal visual attention is often compared to a rapidly shiftable spotlight, which scans our visual environment both overtly (with accompanying eye movements) or covertly (with the eyes fixed). This spotlight has been shown to have variable size and shape depending on the target being attended to. Finally, attention is involved in triggering behavior, and consequently is intimately related to recognition, planning and motor control. Of course, not all of vision is attentional, as we can derive coarse understanding from presentations of visual scenes that are so brief that they do not leave time for attention to explore the scene. Vision thus appears to rely on sophisticated interactions between coarse, massively parallel, full-field pre-attentive analysis systems and the more detailed, circumscribed and sequential attentional analysis system. In what follows, we focus on several critical aspects of selective visual attention: First, the brain area involved in its control and deployment; second, the mechanisms by which attention is attracted in a bottom-up or image-based manner towards conspicuous or salient locations in our visual environment; third, the mechanisms by which attention modulates the early sensory representation of attended stimuli; fourth, the mechanisms for top-down or voluntary deployment of attention towards visual locations that may not necessarily be intrinsically conspicuous, but may be of interest in solving a given visual task; and fifth, the interaction between attention, object recognition and scene understanding.\n</div>\n\n\n</div>\n","downloads":0,"bibbaseid":"itti-visualattention-2003","role":"author","year":"2003","type":"mod;bu;td;psy;rev;sc","title":"Visual Attention","publisher":"MIT Press","pages":"1196-1201","month":"Jan","key":"Itti03hbtnn2e","id":"Itti03hbtnn2e","file":"http://iLab.usc.edu/publications/doc/Itti02hbtnn2e.pdf","editor_short":["Arbib, M.<nbsp>A."],"editor":["Arbib, M. A."],"booktitle":"The Handbook of Brain Theory and Neural Networks","bibtype":"incollection","bibtex":"@incollection{ Itti03hbtnn2e,\n author = { L. Itti },\n title = { Visual Attention },\n year = {2003},\n month = {Jan},\n booktitle = { The Handbook of Brain Theory and Neural Networks },\n publisher = {MIT Press},\n abstract = {Selective visual attention is the mechanism by which we can\nrapidly direct our gaze towards objects of interest in our visual\nenvironment. From an evolutionary viewpoint, this rapid orienting\ncapability is critical in allowing living systems to quickly become\naware of possible preys, mates or predators in their cluttered visual\nworld. It has become clear that attention guides where to look next\nbased on both bottom-up (image-based) and top-down (task-dependent)\ncues. As such, attention implements an information processing\nbottleneck, only allowing a small part of the incoming sensory\ninformation to reach short-term memory and visual awareness. That is,\ninstead of attempting to fully process the massive sensory input in\nparallel, nature has devised a serial strategy to achieve near\nreal-time performance despite limited computational capacity:\nAttention allows us to break down the problem of scene understanding\ninto rapid series of computationally less demanding, localized visual\nanalysis problems. These orienting and scene analysis functions of\nattention are complemented by a feedback modulation of neural activity\nat the location and for the visual attributes of the desired or\nselected targets. This feedback is believed to be essential for\nbinding the different visual attributes of an object, such as color\nand form, into a unitary percept. That is, attention not only serves\nto select a location of interest, but also enhances the cortical\nrepresentation at that location. As such, focal visual attention is\noften compared to a rapidly shiftable spotlight, which scans our\nvisual environment both overtly (with accompanying eye movements) or\ncovertly (with the eyes fixed). This spotlight has been shown to have\nvariable size and shape depending on the target being attended to.\nFinally, attention is involved in triggering behavior, and\nconsequently is intimately related to recognition, planning and motor\ncontrol. Of course, not all of vision is attentional, as we can derive\ncoarse understanding from presentations of visual scenes that are so\nbrief that they do not leave time for attention to explore the\nscene. Vision thus appears to rely on sophisticated interactions\nbetween coarse, massively parallel, full-field pre-attentive analysis\nsystems and the more detailed, circumscribed and sequential\nattentional analysis system. In what follows, we focus on several\ncritical aspects of selective visual attention: First, the brain area\ninvolved in its control and deployment; second, the mechanisms by\nwhich attention is attracted in a bottom-up or image-based manner\ntowards conspicuous or salient locations in our visual environment;\nthird, the mechanisms by which attention modulates the early sensory\nrepresentation of attended stimuli; fourth, the mechanisms for\ntop-down or voluntary deployment of attention towards visual locations\nthat may not necessarily be intrinsically conspicuous, but may be of\ninterest in solving a given visual task; and fifth, the interaction\nbetween attention, object recognition and scene understanding.},\n editor = {M. A. Arbib},\n pages = {1196-1201},\n file = { http://iLab.usc.edu/publications/doc/Itti02hbtnn2e.pdf },\n type = {mod;bu;td;psy;rev;sc}\n}","author_short":["Itti, L."],"author":["Itti, L."],"abstract":"Selective visual attention is the mechanism by which we can rapidly direct our gaze towards objects of interest in our visual environment. From an evolutionary viewpoint, this rapid orienting capability is critical in allowing living systems to quickly become aware of possible preys, mates or predators in their cluttered visual world. It has become clear that attention guides where to look next based on both bottom-up (image-based) and top-down (task-dependent) cues. As such, attention implements an information processing bottleneck, only allowing a small part of the incoming sensory information to reach short-term memory and visual awareness. That is, instead of attempting to fully process the massive sensory input in parallel, nature has devised a serial strategy to achieve near real-time performance despite limited computational capacity: Attention allows us to break down the problem of scene understanding into rapid series of computationally less demanding, localized visual analysis problems. These orienting and scene analysis functions of attention are complemented by a feedback modulation of neural activity at the location and for the visual attributes of the desired or selected targets. This feedback is believed to be essential for binding the different visual attributes of an object, such as color and form, into a unitary percept. That is, attention not only serves to select a location of interest, but also enhances the cortical representation at that location. As such, focal visual attention is often compared to a rapidly shiftable spotlight, which scans our visual environment both overtly (with accompanying eye movements) or covertly (with the eyes fixed). This spotlight has been shown to have variable size and shape depending on the target being attended to. Finally, attention is involved in triggering behavior, and consequently is intimately related to recognition, planning and motor control. Of course, not all of vision is attentional, as we can derive coarse understanding from presentations of visual scenes that are so brief that they do not leave time for attention to explore the scene. Vision thus appears to rely on sophisticated interactions between coarse, massively parallel, full-field pre-attentive analysis systems and the more detailed, circumscribed and sequential attentional analysis system. In what follows, we focus on several critical aspects of selective visual attention: First, the brain area involved in its control and deployment; second, the mechanisms by which attention is attracted in a bottom-up or image-based manner towards conspicuous or salient locations in our visual environment; third, the mechanisms by which attention modulates the early sensory representation of attended stimuli; fourth, the mechanisms for top-down or voluntary deployment of attention towards visual locations that may not necessarily be intrinsically conspicuous, but may be of interest in solving a given visual task; and fifth, the interaction between attention, object recognition and scene understanding."},"bibtype":"incollection","biburl":"http://ilab.usc.edu/publications/src/ilab.bib","downloads":0,"search_terms":["visual","attention","itti"],"title":"Visual Attention","year":2003,"dataSources":["wedBDxEpNXNCLZ2sZ"]}