An Attentional System Combining Top-Down and Bottom-Up Influences View Full Text


Ontology type: schema:Chapter     


Chapter Info

DATE

2007

AUTHORS

Babak Rasolzadeh , Alireza Tavakoli Targhi , Jan-Olof Eklundh

ABSTRACT

Attention plays an important role in human processing of sensory information as a mean of focusing resources toward the most important inputs at the moment. It has in particular been shown to be a key component of vision. In vision it has been argued that the attentional processes are crucial for dealing with the complexity of real world scenes. The problem has often been posed in terms of visual search tasks. It has been shown that both the use of prior task and context information - top-down influences - and favoring information that stands out clearly in the visual field - bottom-up influences - can make such search more efficient. In a generic scene analysis situation one presumably has a combination of these influences and a computational model for visual attention should therefore contain a mechanism for their integration. Such models are abundant for human vision, but relatively few attempts have been made to define any that apply to computer vision.In this article we describe a model that performs such a combination in a principled way. The system learns an optimal representation of the influences of task and context and thereby constructs a biased saliency map representing the top-down information. This map is combined with bottom-up saliency maps in a process evolving over time as a function over the input. The system is applied to search tasks in single images as well as in real scenes, in the latter case using an active vision system capable of shifting its gaze. The proposed model is shown to have desired qualities and to go beyond earlier proposed systems. More... »

PAGES

123-140

Book

TITLE

Attention in Cognitive Systems. Theories and Systems from an Interdisciplinary Viewpoint

ISBN

978-3-540-77342-9
978-3-540-77343-6

Identifiers

URI

http://scigraph.springernature.com/pub.10.1007/978-3-540-77343-6_8

DOI

http://dx.doi.org/10.1007/978-3-540-77343-6_8

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1010985193


Indexing Status Check whether this publication has been indexed by Scopus and Web Of Science using the SN Indexing Status Tool
Incoming Citations Browse incoming citations for this publication using opencitations.net

JSON-LD is the canonical representation for SciGraph data.

TIP: You can open this SciGraph record using an external JSON-LD service: JSON-LD Playground Google SDTT

[
  {
    "@context": "https://springernature.github.io/scigraph/jsonld/sgcontext.json", 
    "about": [
      {
        "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/08", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Information and Computing Sciences", 
        "type": "DefinedTerm"
      }, 
      {
        "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/17", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Psychology and Cognitive Sciences", 
        "type": "DefinedTerm"
      }, 
      {
        "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/0801", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Artificial Intelligence and Image Processing", 
        "type": "DefinedTerm"
      }, 
      {
        "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/1701", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Psychology", 
        "type": "DefinedTerm"
      }
    ], 
    "author": [
      {
        "affiliation": {
          "alternateName": "Computer Vision and Active Perception Laboratory, CSC, KTH, SE-100 44 Stockholm, Sweden", 
          "id": "http://www.grid.ac/institutes/grid.5037.1", 
          "name": [
            "Computer Vision and Active Perception Laboratory, CSC, KTH, SE-100 44 Stockholm, Sweden"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Rasolzadeh", 
        "givenName": "Babak", 
        "id": "sg:person.016000142445.55", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.016000142445.55"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Computer Vision and Active Perception Laboratory, CSC, KTH, SE-100 44 Stockholm, Sweden", 
          "id": "http://www.grid.ac/institutes/grid.5037.1", 
          "name": [
            "Computer Vision and Active Perception Laboratory, CSC, KTH, SE-100 44 Stockholm, Sweden"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Tavakoli Targhi", 
        "givenName": "Alireza", 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Computer Vision and Active Perception Laboratory, CSC, KTH, SE-100 44 Stockholm, Sweden", 
          "id": "http://www.grid.ac/institutes/grid.5037.1", 
          "name": [
            "Computer Vision and Active Perception Laboratory, CSC, KTH, SE-100 44 Stockholm, Sweden"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Eklundh", 
        "givenName": "Jan-Olof", 
        "id": "sg:person.014400652155.17", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.014400652155.17"
        ], 
        "type": "Person"
      }
    ], 
    "datePublished": "2007", 
    "datePublishedReg": "2007-01-01", 
    "description": "Attention plays an important role in human processing of sensory information as a mean of focusing resources toward the most important inputs at the moment. It has in particular been shown to be a key component of vision. In vision it has been argued that the attentional processes are crucial for dealing with the complexity of real world scenes. The problem has often been posed in terms of visual search tasks. It has been shown that both the use of prior task and context information - top-down influences - and favoring information that stands out clearly in the visual field - bottom-up influences - can make such search more efficient. In a generic scene analysis situation one presumably has a combination of these influences and a computational model for visual attention should therefore contain a mechanism for their integration. Such models are abundant for human vision, but relatively few attempts have been made to define any that apply to computer vision.In this article we describe a model that performs such a combination in a principled way. The system learns an optimal representation of the influences of task and context and thereby constructs a biased saliency map representing the top-down information. This map is combined with bottom-up saliency maps in a process evolving over time as a function over the input. The system is applied to search tasks in single images as well as in real scenes, in the latter case using an active vision system capable of shifting its gaze. The proposed model is shown to have desired qualities and to go beyond earlier proposed systems.", 
    "editor": [
      {
        "familyName": "Paletta", 
        "givenName": "Lucas", 
        "type": "Person"
      }, 
      {
        "familyName": "Rome", 
        "givenName": "Erich", 
        "type": "Person"
      }
    ], 
    "genre": "chapter", 
    "id": "sg:pub.10.1007/978-3-540-77343-6_8", 
    "isAccessibleForFree": false, 
    "isPartOf": {
      "isbn": [
        "978-3-540-77342-9", 
        "978-3-540-77343-6"
      ], 
      "name": "Attention in Cognitive Systems. Theories and Systems from an Interdisciplinary Viewpoint", 
      "type": "Book"
    }, 
    "keywords": [
      "search task", 
      "visual search task", 
      "saliency map", 
      "influence of task", 
      "active vision system", 
      "real-world scenes", 
      "attentional processes", 
      "attentional system", 
      "visual attention", 
      "human vision", 
      "computer vision", 
      "prior task", 
      "human processing", 
      "context information", 
      "vision system", 
      "real scenes", 
      "sensory information", 
      "single image", 
      "world scenes", 
      "principled way", 
      "task", 
      "computational model", 
      "Top-Down", 
      "such searches", 
      "optimal representation", 
      "situations one", 
      "vision", 
      "scene", 
      "information", 
      "such models", 
      "attention", 
      "gaze", 
      "system", 
      "maps", 
      "input", 
      "key component", 
      "processing", 
      "complexity", 
      "images", 
      "influence", 
      "model", 
      "representation", 
      "context", 
      "resources", 
      "search", 
      "integration", 
      "important input", 
      "process", 
      "way", 
      "quality", 
      "attempt", 
      "article", 
      "role", 
      "one", 
      "terms", 
      "important role", 
      "combination", 
      "time", 
      "problem", 
      "use", 
      "components", 
      "means", 
      "bottom", 
      "mechanism", 
      "function", 
      "latter case", 
      "moment", 
      "cases"
    ], 
    "name": "An Attentional System Combining Top-Down and Bottom-Up Influences", 
    "pagination": "123-140", 
    "productId": [
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1010985193"
        ]
      }, 
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1007/978-3-540-77343-6_8"
        ]
      }
    ], 
    "publisher": {
      "name": "Springer Nature", 
      "type": "Organisation"
    }, 
    "sameAs": [
      "https://doi.org/10.1007/978-3-540-77343-6_8", 
      "https://app.dimensions.ai/details/publication/pub.1010985193"
    ], 
    "sdDataset": "chapters", 
    "sdDatePublished": "2022-11-24T21:19", 
    "sdLicense": "https://scigraph.springernature.com/explorer/license/", 
    "sdPublisher": {
      "name": "Springer Nature - SN SciGraph project", 
      "type": "Organization"
    }, 
    "sdSource": "s3://com-springernature-scigraph/baseset/20221124/entities/gbq_results/chapter/chapter_64.jsonl", 
    "type": "Chapter", 
    "url": "https://doi.org/10.1007/978-3-540-77343-6_8"
  }
]
 

Download the RDF metadata as:  json-ld nt turtle xml License info

HOW TO GET THIS DATA PROGRAMMATICALLY:

JSON-LD is a popular format for linked data which is fully compatible with JSON.

curl -H 'Accept: application/ld+json' 'https://scigraph.springernature.com/pub.10.1007/978-3-540-77343-6_8'

N-Triples is a line-based linked data format ideal for batch operations.

curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1007/978-3-540-77343-6_8'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/978-3-540-77343-6_8'

RDF/XML is a standard XML format for linked data.

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/978-3-540-77343-6_8'


 

This table displays all metadata directly associated to this object as RDF triples.

153 TRIPLES      22 PREDICATES      95 URIs      86 LITERALS      7 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1007/978-3-540-77343-6_8 schema:about anzsrc-for:08
2 anzsrc-for:0801
3 anzsrc-for:17
4 anzsrc-for:1701
5 schema:author N657eaeeb67d34d9e8fe42d2288ec0675
6 schema:datePublished 2007
7 schema:datePublishedReg 2007-01-01
8 schema:description Attention plays an important role in human processing of sensory information as a mean of focusing resources toward the most important inputs at the moment. It has in particular been shown to be a key component of vision. In vision it has been argued that the attentional processes are crucial for dealing with the complexity of real world scenes. The problem has often been posed in terms of visual search tasks. It has been shown that both the use of prior task and context information - top-down influences - and favoring information that stands out clearly in the visual field - bottom-up influences - can make such search more efficient. In a generic scene analysis situation one presumably has a combination of these influences and a computational model for visual attention should therefore contain a mechanism for their integration. Such models are abundant for human vision, but relatively few attempts have been made to define any that apply to computer vision.In this article we describe a model that performs such a combination in a principled way. The system learns an optimal representation of the influences of task and context and thereby constructs a biased saliency map representing the top-down information. This map is combined with bottom-up saliency maps in a process evolving over time as a function over the input. The system is applied to search tasks in single images as well as in real scenes, in the latter case using an active vision system capable of shifting its gaze. The proposed model is shown to have desired qualities and to go beyond earlier proposed systems.
9 schema:editor N0af8660bd2ea426193f3ac61dc6c2ef3
10 schema:genre chapter
11 schema:isAccessibleForFree false
12 schema:isPartOf Nb5a6d25c61ad42fe846340958749fd62
13 schema:keywords Top-Down
14 active vision system
15 article
16 attempt
17 attention
18 attentional processes
19 attentional system
20 bottom
21 cases
22 combination
23 complexity
24 components
25 computational model
26 computer vision
27 context
28 context information
29 function
30 gaze
31 human processing
32 human vision
33 images
34 important input
35 important role
36 influence
37 influence of task
38 information
39 input
40 integration
41 key component
42 latter case
43 maps
44 means
45 mechanism
46 model
47 moment
48 one
49 optimal representation
50 principled way
51 prior task
52 problem
53 process
54 processing
55 quality
56 real scenes
57 real-world scenes
58 representation
59 resources
60 role
61 saliency map
62 scene
63 search
64 search task
65 sensory information
66 single image
67 situations one
68 such models
69 such searches
70 system
71 task
72 terms
73 time
74 use
75 vision
76 vision system
77 visual attention
78 visual search task
79 way
80 world scenes
81 schema:name An Attentional System Combining Top-Down and Bottom-Up Influences
82 schema:pagination 123-140
83 schema:productId Na1a08c4d0fa74771af721e02d399b4e2
84 Ncc91fff9fcf64115a940a81d4f7992a6
85 schema:publisher Nbecbccbc35be488ebfedaf989b2f7cd7
86 schema:sameAs https://app.dimensions.ai/details/publication/pub.1010985193
87 https://doi.org/10.1007/978-3-540-77343-6_8
88 schema:sdDatePublished 2022-11-24T21:19
89 schema:sdLicense https://scigraph.springernature.com/explorer/license/
90 schema:sdPublisher N4b06bce6296f4ef6ba0af71cb68f7dd1
91 schema:url https://doi.org/10.1007/978-3-540-77343-6_8
92 sgo:license sg:explorer/license/
93 sgo:sdDataset chapters
94 rdf:type schema:Chapter
95 N0af8660bd2ea426193f3ac61dc6c2ef3 rdf:first Ndb6e99ca643b4b6bb5b00226680728a6
96 rdf:rest N1e0322293d2e41f59c8f1cdea3825e97
97 N1e0322293d2e41f59c8f1cdea3825e97 rdf:first N6ee768d240db44ceb9266d5c050305c7
98 rdf:rest rdf:nil
99 N4b06bce6296f4ef6ba0af71cb68f7dd1 schema:name Springer Nature - SN SciGraph project
100 rdf:type schema:Organization
101 N657eaeeb67d34d9e8fe42d2288ec0675 rdf:first sg:person.016000142445.55
102 rdf:rest Ncc6e1d30f0104f498daf4ac4216465ef
103 N6ee768d240db44ceb9266d5c050305c7 schema:familyName Rome
104 schema:givenName Erich
105 rdf:type schema:Person
106 Na1a08c4d0fa74771af721e02d399b4e2 schema:name dimensions_id
107 schema:value pub.1010985193
108 rdf:type schema:PropertyValue
109 Na7a571ff2a22408f8d869ee73b15f142 rdf:first sg:person.014400652155.17
110 rdf:rest rdf:nil
111 Nb5a6d25c61ad42fe846340958749fd62 schema:isbn 978-3-540-77342-9
112 978-3-540-77343-6
113 schema:name Attention in Cognitive Systems. Theories and Systems from an Interdisciplinary Viewpoint
114 rdf:type schema:Book
115 Nbecbccbc35be488ebfedaf989b2f7cd7 schema:name Springer Nature
116 rdf:type schema:Organisation
117 Ncc6e1d30f0104f498daf4ac4216465ef rdf:first Nd98761dcba16453099ba9f45727556be
118 rdf:rest Na7a571ff2a22408f8d869ee73b15f142
119 Ncc91fff9fcf64115a940a81d4f7992a6 schema:name doi
120 schema:value 10.1007/978-3-540-77343-6_8
121 rdf:type schema:PropertyValue
122 Nd98761dcba16453099ba9f45727556be schema:affiliation grid-institutes:grid.5037.1
123 schema:familyName Tavakoli Targhi
124 schema:givenName Alireza
125 rdf:type schema:Person
126 Ndb6e99ca643b4b6bb5b00226680728a6 schema:familyName Paletta
127 schema:givenName Lucas
128 rdf:type schema:Person
129 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
130 schema:name Information and Computing Sciences
131 rdf:type schema:DefinedTerm
132 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
133 schema:name Artificial Intelligence and Image Processing
134 rdf:type schema:DefinedTerm
135 anzsrc-for:17 schema:inDefinedTermSet anzsrc-for:
136 schema:name Psychology and Cognitive Sciences
137 rdf:type schema:DefinedTerm
138 anzsrc-for:1701 schema:inDefinedTermSet anzsrc-for:
139 schema:name Psychology
140 rdf:type schema:DefinedTerm
141 sg:person.014400652155.17 schema:affiliation grid-institutes:grid.5037.1
142 schema:familyName Eklundh
143 schema:givenName Jan-Olof
144 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.014400652155.17
145 rdf:type schema:Person
146 sg:person.016000142445.55 schema:affiliation grid-institutes:grid.5037.1
147 schema:familyName Rasolzadeh
148 schema:givenName Babak
149 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.016000142445.55
150 rdf:type schema:Person
151 grid-institutes:grid.5037.1 schema:alternateName Computer Vision and Active Perception Laboratory, CSC, KTH, SE-100 44 Stockholm, Sweden
152 schema:name Computer Vision and Active Perception Laboratory, CSC, KTH, SE-100 44 Stockholm, Sweden
153 rdf:type schema:Organization
 




Preview window. Press ESC to close (or click here)


...