Reinforcement Learning for Decision Making in Sequential Visual Attention View Full Text


Ontology type: schema:Chapter      Open Access: True


Chapter Info

DATE

2007

AUTHORS

Lucas Paletta , Gerald Fritz

ABSTRACT

The innovation of this work is the provision of a system that learns visual encodings of attention patterns and that enables sequential attention for object detection in real world environments. The system embeds the saccadic decision procedure in a cascaded process where visual evidence is probed at the most informative image locations. It is based on the extraction of information theoretic saliency by determining informative local image descriptors that provide selected foci of interest. Both the local information in terms of code book vector responses, and the geometric information in the shift of attention contribute to the recognition state of a Markov decision process. A Q-learner performs then explorative search on useful actions towards salient locations, developing a strategy of useful action sequences being directed in state space towards the optimization of information maximization. The method is evaluated in experiments on real world object recognition and demonstrates efficient performance in outdoor tasks. More... »

PAGES

293-306

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_19

DOI

http://dx.doi.org/10.1007/978-3-540-77343-6_19

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1044765831


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/2008/17", 
        "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/2008/1701", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Psychology", 
        "type": "DefinedTerm"
      }
    ], 
    "author": [
      {
        "affiliation": {
          "alternateName": "JOANNEUM RESEARCH Forschungsgesellschaft mbH, Institute of Digital Image Processing, Computational Perception Group, Wastiangasse 6, 8010 Graz, Austria", 
          "id": "http://www.grid.ac/institutes/grid.8684.2", 
          "name": [
            "JOANNEUM RESEARCH Forschungsgesellschaft mbH, Institute of Digital Image Processing, Computational Perception Group, Wastiangasse 6, 8010 Graz, Austria"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Paletta", 
        "givenName": "Lucas", 
        "id": "sg:person.010060055125.29", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010060055125.29"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "JOANNEUM RESEARCH Forschungsgesellschaft mbH, Institute of Digital Image Processing, Computational Perception Group, Wastiangasse 6, 8010 Graz, Austria", 
          "id": "http://www.grid.ac/institutes/grid.8684.2", 
          "name": [
            "JOANNEUM RESEARCH Forschungsgesellschaft mbH, Institute of Digital Image Processing, Computational Perception Group, Wastiangasse 6, 8010 Graz, Austria"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Fritz", 
        "givenName": "Gerald", 
        "id": "sg:person.011015636117.31", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.011015636117.31"
        ], 
        "type": "Person"
      }
    ], 
    "datePublished": "2007", 
    "datePublishedReg": "2007-01-01", 
    "description": "The innovation of this work is the provision of a system that learns visual encodings of attention patterns and that enables sequential attention for object detection in real world environments. The system embeds the saccadic decision procedure in a cascaded process where visual evidence is probed at the most informative image locations. It is based on the extraction of information theoretic saliency by determining informative local image descriptors that provide selected foci of interest. Both the local information in terms of code book vector responses, and the geometric information in the shift of attention contribute to the recognition state of a Markov decision process. A Q-learner performs then explorative search on useful actions towards salient locations, developing a strategy of useful action sequences being directed in state space towards the optimization of information maximization. The method is evaluated in experiments on real world object recognition and demonstrates efficient performance in outdoor tasks.", 
    "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_19", 
    "inLanguage": "en", 
    "isAccessibleForFree": true, 
    "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": [
      "useful action sequences", 
      "real world environment", 
      "attention contributes", 
      "local image descriptors", 
      "visual attention", 
      "attention patterns", 
      "sequential attention", 
      "visual encoding", 
      "salient locations", 
      "action sequences", 
      "object recognition", 
      "Markov decision process", 
      "object detection", 
      "image descriptors", 
      "world environment", 
      "explorative search", 
      "information maximization", 
      "recognition state", 
      "image location", 
      "geometric information", 
      "local information", 
      "outdoor tasks", 
      "useful actions", 
      "efficient performance", 
      "decision procedure", 
      "decision process", 
      "state space", 
      "attention", 
      "focus of interest", 
      "encoding", 
      "saliency", 
      "task", 
      "learners", 
      "information", 
      "visual evidence", 
      "system", 
      "descriptors", 
      "recognition", 
      "maximization", 
      "optimization", 
      "environment", 
      "search", 
      "performance", 
      "decisions", 
      "extraction", 
      "detection", 
      "location", 
      "process", 
      "space", 
      "focus", 
      "evidence", 
      "work", 
      "contributes", 
      "action", 
      "strategies", 
      "method", 
      "experiments", 
      "innovation", 
      "patterns", 
      "interest", 
      "terms", 
      "response", 
      "vector response", 
      "sequence", 
      "provision", 
      "state", 
      "shift", 
      "procedure", 
      "saccadic decision procedure", 
      "informative image locations", 
      "information theoretic saliency", 
      "theoretic saliency", 
      "informative local image descriptors", 
      "code book vector responses", 
      "book vector responses", 
      "real world object recognition", 
      "world object recognition", 
      "Sequential Visual Attention"
    ], 
    "name": "Reinforcement Learning for Decision Making in Sequential Visual Attention", 
    "pagination": "293-306", 
    "productId": [
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1044765831"
        ]
      }, 
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1007/978-3-540-77343-6_19"
        ]
      }
    ], 
    "publisher": {
      "name": "Springer Nature", 
      "type": "Organisation"
    }, 
    "sameAs": [
      "https://doi.org/10.1007/978-3-540-77343-6_19", 
      "https://app.dimensions.ai/details/publication/pub.1044765831"
    ], 
    "sdDataset": "chapters", 
    "sdDatePublished": "2022-01-01T19:25", 
    "sdLicense": "https://scigraph.springernature.com/explorer/license/", 
    "sdPublisher": {
      "name": "Springer Nature - SN SciGraph project", 
      "type": "Organization"
    }, 
    "sdSource": "s3://com-springernature-scigraph/baseset/20220101/entities/gbq_results/chapter/chapter_446.jsonl", 
    "type": "Chapter", 
    "url": "https://doi.org/10.1007/978-3-540-77343-6_19"
  }
]
 

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_19'

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_19'

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_19'

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_19'


 

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

150 TRIPLES      23 PREDICATES      104 URIs      97 LITERALS      7 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1007/978-3-540-77343-6_19 schema:about anzsrc-for:17
2 anzsrc-for:1701
3 schema:author Neee8d82eec6e48b69186d66340ce6c1a
4 schema:datePublished 2007
5 schema:datePublishedReg 2007-01-01
6 schema:description The innovation of this work is the provision of a system that learns visual encodings of attention patterns and that enables sequential attention for object detection in real world environments. The system embeds the saccadic decision procedure in a cascaded process where visual evidence is probed at the most informative image locations. It is based on the extraction of information theoretic saliency by determining informative local image descriptors that provide selected foci of interest. Both the local information in terms of code book vector responses, and the geometric information in the shift of attention contribute to the recognition state of a Markov decision process. A Q-learner performs then explorative search on useful actions towards salient locations, developing a strategy of useful action sequences being directed in state space towards the optimization of information maximization. The method is evaluated in experiments on real world object recognition and demonstrates efficient performance in outdoor tasks.
7 schema:editor N4b4e134265484c6193c7a4f25e21d610
8 schema:genre chapter
9 schema:inLanguage en
10 schema:isAccessibleForFree true
11 schema:isPartOf N6f8a9e981c6a4b96ad09293339aa53e9
12 schema:keywords Markov decision process
13 Sequential Visual Attention
14 action
15 action sequences
16 attention
17 attention contributes
18 attention patterns
19 book vector responses
20 code book vector responses
21 contributes
22 decision procedure
23 decision process
24 decisions
25 descriptors
26 detection
27 efficient performance
28 encoding
29 environment
30 evidence
31 experiments
32 explorative search
33 extraction
34 focus
35 focus of interest
36 geometric information
37 image descriptors
38 image location
39 information
40 information maximization
41 information theoretic saliency
42 informative image locations
43 informative local image descriptors
44 innovation
45 interest
46 learners
47 local image descriptors
48 local information
49 location
50 maximization
51 method
52 object detection
53 object recognition
54 optimization
55 outdoor tasks
56 patterns
57 performance
58 procedure
59 process
60 provision
61 real world environment
62 real world object recognition
63 recognition
64 recognition state
65 response
66 saccadic decision procedure
67 saliency
68 salient locations
69 search
70 sequence
71 sequential attention
72 shift
73 space
74 state
75 state space
76 strategies
77 system
78 task
79 terms
80 theoretic saliency
81 useful action sequences
82 useful actions
83 vector response
84 visual attention
85 visual encoding
86 visual evidence
87 work
88 world environment
89 world object recognition
90 schema:name Reinforcement Learning for Decision Making in Sequential Visual Attention
91 schema:pagination 293-306
92 schema:productId N86652371dfdc460181b6d0131ca9cd0d
93 Nfe12a5be3c0549bdad4bffa43b677ef6
94 schema:publisher Nbb5d1322b91d46039364bfbd5c91827e
95 schema:sameAs https://app.dimensions.ai/details/publication/pub.1044765831
96 https://doi.org/10.1007/978-3-540-77343-6_19
97 schema:sdDatePublished 2022-01-01T19:25
98 schema:sdLicense https://scigraph.springernature.com/explorer/license/
99 schema:sdPublisher N83e37f8a098a4f0e94c04028f4ea024f
100 schema:url https://doi.org/10.1007/978-3-540-77343-6_19
101 sgo:license sg:explorer/license/
102 sgo:sdDataset chapters
103 rdf:type schema:Chapter
104 N3e72d62c1281434fb66982e8abf8c1c0 schema:familyName Paletta
105 schema:givenName Lucas
106 rdf:type schema:Person
107 N433a7aade10b4ee998daee0640b206d9 rdf:first N7a470e69c65044b6b3910aead313b553
108 rdf:rest rdf:nil
109 N484f8e88bffa412e9b82e676673400b4 rdf:first sg:person.011015636117.31
110 rdf:rest rdf:nil
111 N4b4e134265484c6193c7a4f25e21d610 rdf:first N3e72d62c1281434fb66982e8abf8c1c0
112 rdf:rest N433a7aade10b4ee998daee0640b206d9
113 N6f8a9e981c6a4b96ad09293339aa53e9 schema:isbn 978-3-540-77342-9
114 978-3-540-77343-6
115 schema:name Attention in Cognitive Systems. Theories and Systems from an Interdisciplinary Viewpoint
116 rdf:type schema:Book
117 N7a470e69c65044b6b3910aead313b553 schema:familyName Rome
118 schema:givenName Erich
119 rdf:type schema:Person
120 N83e37f8a098a4f0e94c04028f4ea024f schema:name Springer Nature - SN SciGraph project
121 rdf:type schema:Organization
122 N86652371dfdc460181b6d0131ca9cd0d schema:name doi
123 schema:value 10.1007/978-3-540-77343-6_19
124 rdf:type schema:PropertyValue
125 Nbb5d1322b91d46039364bfbd5c91827e schema:name Springer Nature
126 rdf:type schema:Organisation
127 Neee8d82eec6e48b69186d66340ce6c1a rdf:first sg:person.010060055125.29
128 rdf:rest N484f8e88bffa412e9b82e676673400b4
129 Nfe12a5be3c0549bdad4bffa43b677ef6 schema:name dimensions_id
130 schema:value pub.1044765831
131 rdf:type schema:PropertyValue
132 anzsrc-for:17 schema:inDefinedTermSet anzsrc-for:
133 schema:name Psychology and Cognitive Sciences
134 rdf:type schema:DefinedTerm
135 anzsrc-for:1701 schema:inDefinedTermSet anzsrc-for:
136 schema:name Psychology
137 rdf:type schema:DefinedTerm
138 sg:person.010060055125.29 schema:affiliation grid-institutes:grid.8684.2
139 schema:familyName Paletta
140 schema:givenName Lucas
141 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010060055125.29
142 rdf:type schema:Person
143 sg:person.011015636117.31 schema:affiliation grid-institutes:grid.8684.2
144 schema:familyName Fritz
145 schema:givenName Gerald
146 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.011015636117.31
147 rdf:type schema:Person
148 grid-institutes:grid.8684.2 schema:alternateName JOANNEUM RESEARCH Forschungsgesellschaft mbH, Institute of Digital Image Processing, Computational Perception Group, Wastiangasse 6, 8010 Graz, Austria
149 schema:name JOANNEUM RESEARCH Forschungsgesellschaft mbH, Institute of Digital Image Processing, Computational Perception Group, Wastiangasse 6, 8010 Graz, Austria
150 rdf:type schema:Organization
 




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


...