Attentive Object Detection Using an Information Theoretic Saliency Measure View Full Text


Ontology type: schema:Chapter     


Chapter Info

DATE

2005

AUTHORS

Gerald Fritz , Christin Seifert , Lucas Paletta , Horst Bischof

ABSTRACT

A major goal of selective attention is to focus processing on relevant information to enable rapid and robust task performance. For the example of attentive visual object recognition, we investigate here the impact of top-down information on multi-stage processing, instead of integrating generic visual feature extraction into object specific interpretation. We discriminate between generic and specific task based filters that select task relevant information of different scope and specificity within a processing chain. Attention is applied by tuned early features to selectively respond to generic task related visual features, i.e., to information that is in general locally relevant for any kind of object search. The mapping from appearances to discriminative regions is then modeled using decision trees to accelerate processing. The focus of attention on discriminative patterns enables efficient recognition of specific objects, by means of a sparse object representation that enables selective, task relevant, and rapid object specific responses. In the experiments the performance in object recognition from single appearance patterns dramatically increased considering only discriminative patterns, and evaluation of complete image analysis under various degrees of partial occlusion and image noise resulted in highly robust recognition, even in the presence of severe occlusion and noise effects. In addition, we present performance evaluation on our public available reference object database (TSG-20). More... »

PAGES

29-41

Identifiers

URI

http://scigraph.springernature.com/pub.10.1007/978-3-540-30572-9_3

DOI

http://dx.doi.org/10.1007/978-3-540-30572-9_3

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1032169666


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": "Institute of Digital Image Processing, JOANNEUM RESEARCH, Forschungsgesellschaft mbH, Wastiangasse 6, A-8010, Graz, Austria", 
          "id": "http://www.grid.ac/institutes/grid.8684.2", 
          "name": [
            "Institute of Digital Image Processing, JOANNEUM RESEARCH, Forschungsgesellschaft mbH, Wastiangasse 6, A-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"
      }, 
      {
        "affiliation": {
          "alternateName": "Institute of Digital Image Processing, JOANNEUM RESEARCH, Forschungsgesellschaft mbH, Wastiangasse 6, A-8010, Graz, Austria", 
          "id": "http://www.grid.ac/institutes/grid.8684.2", 
          "name": [
            "Institute of Digital Image Processing, JOANNEUM RESEARCH, Forschungsgesellschaft mbH, Wastiangasse 6, A-8010, Graz, Austria"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Seifert", 
        "givenName": "Christin", 
        "id": "sg:person.010257616672.34", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010257616672.34"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Institute of Digital Image Processing, JOANNEUM RESEARCH, Forschungsgesellschaft mbH, Wastiangasse 6, A-8010, Graz, Austria", 
          "id": "http://www.grid.ac/institutes/grid.8684.2", 
          "name": [
            "Institute of Digital Image Processing, JOANNEUM RESEARCH, Forschungsgesellschaft mbH, Wastiangasse 6, A-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": "Institute for Computer Graphics and Vision, Graz University of Technology, Inffeldgasse 16/II, A-8010, Graz, Austria", 
          "id": "http://www.grid.ac/institutes/grid.410413.3", 
          "name": [
            "Institute for Computer Graphics and Vision, Graz University of Technology, Inffeldgasse 16/II, A-8010, Graz, Austria"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Bischof", 
        "givenName": "Horst", 
        "id": "sg:person.013002347027.27", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.013002347027.27"
        ], 
        "type": "Person"
      }
    ], 
    "datePublished": "2005", 
    "datePublishedReg": "2005-01-01", 
    "description": "A major goal of selective attention is to focus processing on relevant information to enable rapid and robust task performance. For the example of attentive visual object recognition, we investigate here the impact of top-down information on multi-stage processing, instead of integrating generic visual feature extraction into object specific interpretation. We discriminate between generic and specific task based filters that select task relevant information of different scope and specificity within a processing chain. Attention is applied by tuned early features to selectively respond to generic task related visual features, i.e., to information that is in general locally relevant for any kind of object search. The mapping from appearances to discriminative regions is then modeled using decision trees to accelerate processing. The focus of attention on discriminative patterns enables efficient recognition of specific objects, by means of a sparse object representation that enables selective, task relevant, and rapid object specific responses. In the experiments the performance in object recognition from single appearance patterns dramatically increased considering only discriminative patterns, and evaluation of complete image analysis under various degrees of partial occlusion and image noise resulted in highly robust recognition, even in the presence of severe occlusion and noise effects. In addition, we present performance evaluation on our public available reference object database (TSG-20).", 
    "editor": [
      {
        "familyName": "Paletta", 
        "givenName": "Lucas", 
        "type": "Person"
      }, 
      {
        "familyName": "Tsotsos", 
        "givenName": "John K.", 
        "type": "Person"
      }, 
      {
        "familyName": "Rome", 
        "givenName": "Erich", 
        "type": "Person"
      }, 
      {
        "familyName": "Humphreys", 
        "givenName": "Glyn", 
        "type": "Person"
      }
    ], 
    "genre": "chapter", 
    "id": "sg:pub.10.1007/978-3-540-30572-9_3", 
    "inLanguage": "en", 
    "isAccessibleForFree": false, 
    "isPartOf": {
      "isbn": [
        "978-3-540-24421-9", 
        "978-3-540-30572-9"
      ], 
      "name": "Attention and Performance in Computational Vision", 
      "type": "Book"
    }, 
    "keywords": [
      "object recognition", 
      "discriminative patterns", 
      "visual feature extraction", 
      "complete image analysis", 
      "relevant information", 
      "visual object recognition", 
      "object search", 
      "object databases", 
      "object detection", 
      "multi-stage processing", 
      "robust recognition", 
      "generic tasks", 
      "feature extraction", 
      "visual features", 
      "severe occlusion", 
      "decision tree", 
      "specific tasks", 
      "specific objects", 
      "partial occlusion", 
      "processing chain", 
      "saliency measure", 
      "appearance patterns", 
      "object representations", 
      "performance evaluation", 
      "image analysis", 
      "efficient recognition", 
      "image noise", 
      "task", 
      "different scopes", 
      "recognition", 
      "information", 
      "processing", 
      "task-relevant information", 
      "focus of attention", 
      "noise effects", 
      "performance", 
      "features", 
      "task performance", 
      "objects", 
      "representation", 
      "database", 
      "major goal", 
      "search", 
      "extraction", 
      "detection", 
      "trees", 
      "attention", 
      "mapping", 
      "noise", 
      "goal", 
      "evaluation", 
      "filter", 
      "kind", 
      "example", 
      "occlusion", 
      "scope", 
      "experiments", 
      "patterns", 
      "specific interpretation", 
      "focus", 
      "means", 
      "measures", 
      "interpretation", 
      "analysis", 
      "chain", 
      "addition", 
      "impact", 
      "selective attention", 
      "appearance", 
      "degree", 
      "region", 
      "specificity", 
      "presence", 
      "response", 
      "effect", 
      "early feature", 
      "specific responses"
    ], 
    "name": "Attentive Object Detection Using an Information Theoretic Saliency Measure", 
    "pagination": "29-41", 
    "productId": [
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1032169666"
        ]
      }, 
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1007/978-3-540-30572-9_3"
        ]
      }
    ], 
    "publisher": {
      "name": "Springer Nature", 
      "type": "Organisation"
    }, 
    "sameAs": [
      "https://doi.org/10.1007/978-3-540-30572-9_3", 
      "https://app.dimensions.ai/details/publication/pub.1032169666"
    ], 
    "sdDataset": "chapters", 
    "sdDatePublished": "2022-05-20T07:43", 
    "sdLicense": "https://scigraph.springernature.com/explorer/license/", 
    "sdPublisher": {
      "name": "Springer Nature - SN SciGraph project", 
      "type": "Organization"
    }, 
    "sdSource": "s3://com-springernature-scigraph/baseset/20220519/entities/gbq_results/chapter/chapter_210.jsonl", 
    "type": "Chapter", 
    "url": "https://doi.org/10.1007/978-3-540-30572-9_3"
  }
]
 

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.10.1007/978-3-540-30572-9_3'

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

curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1007/978-3-540-30572-9_3'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/978-3-540-30572-9_3'

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

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/978-3-540-30572-9_3'


 

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

184 TRIPLES      23 PREDICATES      105 URIs      96 LITERALS      7 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1007/978-3-540-30572-9_3 schema:about anzsrc-for:08
2 anzsrc-for:0801
3 anzsrc-for:17
4 anzsrc-for:1701
5 schema:author Ncff81d5e02b447ce88bb1b86e83200f7
6 schema:datePublished 2005
7 schema:datePublishedReg 2005-01-01
8 schema:description A major goal of selective attention is to focus processing on relevant information to enable rapid and robust task performance. For the example of attentive visual object recognition, we investigate here the impact of top-down information on multi-stage processing, instead of integrating generic visual feature extraction into object specific interpretation. We discriminate between generic and specific task based filters that select task relevant information of different scope and specificity within a processing chain. Attention is applied by tuned early features to selectively respond to generic task related visual features, i.e., to information that is in general locally relevant for any kind of object search. The mapping from appearances to discriminative regions is then modeled using decision trees to accelerate processing. The focus of attention on discriminative patterns enables efficient recognition of specific objects, by means of a sparse object representation that enables selective, task relevant, and rapid object specific responses. In the experiments the performance in object recognition from single appearance patterns dramatically increased considering only discriminative patterns, and evaluation of complete image analysis under various degrees of partial occlusion and image noise resulted in highly robust recognition, even in the presence of severe occlusion and noise effects. In addition, we present performance evaluation on our public available reference object database (TSG-20).
9 schema:editor N2f66717c997e459c91a6be90aa862bf4
10 schema:genre chapter
11 schema:inLanguage en
12 schema:isAccessibleForFree false
13 schema:isPartOf N434f9825d09f42dba3c2dd0c1eb09971
14 schema:keywords addition
15 analysis
16 appearance
17 appearance patterns
18 attention
19 chain
20 complete image analysis
21 database
22 decision tree
23 degree
24 detection
25 different scopes
26 discriminative patterns
27 early feature
28 effect
29 efficient recognition
30 evaluation
31 example
32 experiments
33 extraction
34 feature extraction
35 features
36 filter
37 focus
38 focus of attention
39 generic tasks
40 goal
41 image analysis
42 image noise
43 impact
44 information
45 interpretation
46 kind
47 major goal
48 mapping
49 means
50 measures
51 multi-stage processing
52 noise
53 noise effects
54 object databases
55 object detection
56 object recognition
57 object representations
58 object search
59 objects
60 occlusion
61 partial occlusion
62 patterns
63 performance
64 performance evaluation
65 presence
66 processing
67 processing chain
68 recognition
69 region
70 relevant information
71 representation
72 response
73 robust recognition
74 saliency measure
75 scope
76 search
77 selective attention
78 severe occlusion
79 specific interpretation
80 specific objects
81 specific responses
82 specific tasks
83 specificity
84 task
85 task performance
86 task-relevant information
87 trees
88 visual feature extraction
89 visual features
90 visual object recognition
91 schema:name Attentive Object Detection Using an Information Theoretic Saliency Measure
92 schema:pagination 29-41
93 schema:productId N05fd100a84394885b7f35bc167f08571
94 Nda079a540d734ba28094bc9bd3af8fb1
95 schema:publisher N3db687d336604d4b8592eb907b6f801f
96 schema:sameAs https://app.dimensions.ai/details/publication/pub.1032169666
97 https://doi.org/10.1007/978-3-540-30572-9_3
98 schema:sdDatePublished 2022-05-20T07:43
99 schema:sdLicense https://scigraph.springernature.com/explorer/license/
100 schema:sdPublisher Ne2c920d0d66d4194a39dd15f2c18e970
101 schema:url https://doi.org/10.1007/978-3-540-30572-9_3
102 sgo:license sg:explorer/license/
103 sgo:sdDataset chapters
104 rdf:type schema:Chapter
105 N0360eef51dd64d3494ba4c9d98ddd506 schema:familyName Tsotsos
106 schema:givenName John K.
107 rdf:type schema:Person
108 N05fd100a84394885b7f35bc167f08571 schema:name dimensions_id
109 schema:value pub.1032169666
110 rdf:type schema:PropertyValue
111 N0f11d52d3a2846fb904e031e67a76011 rdf:first sg:person.013002347027.27
112 rdf:rest rdf:nil
113 N14bfee51a20644658c23fdaeba1ec090 schema:familyName Humphreys
114 schema:givenName Glyn
115 rdf:type schema:Person
116 N2b1072304ab245b39c525b41fe1b6ade rdf:first N0360eef51dd64d3494ba4c9d98ddd506
117 rdf:rest N34255b67fdf9446a99b7c15a2b7f5947
118 N2f66717c997e459c91a6be90aa862bf4 rdf:first Nf41c30250deb481d8ae6a5b994c1bc43
119 rdf:rest N2b1072304ab245b39c525b41fe1b6ade
120 N34255b67fdf9446a99b7c15a2b7f5947 rdf:first N6f66066d0ba34189acfcf01d55781ec5
121 rdf:rest Na8bbd9f2b9744723aac7e2ec3780c333
122 N3db687d336604d4b8592eb907b6f801f schema:name Springer Nature
123 rdf:type schema:Organisation
124 N434f9825d09f42dba3c2dd0c1eb09971 schema:isbn 978-3-540-24421-9
125 978-3-540-30572-9
126 schema:name Attention and Performance in Computational Vision
127 rdf:type schema:Book
128 N6f66066d0ba34189acfcf01d55781ec5 schema:familyName Rome
129 schema:givenName Erich
130 rdf:type schema:Person
131 Na8bbd9f2b9744723aac7e2ec3780c333 rdf:first N14bfee51a20644658c23fdaeba1ec090
132 rdf:rest rdf:nil
133 Ncff81d5e02b447ce88bb1b86e83200f7 rdf:first sg:person.011015636117.31
134 rdf:rest Nd5738d33b86d4afab3c3d54ae582b499
135 Nd5738d33b86d4afab3c3d54ae582b499 rdf:first sg:person.010257616672.34
136 rdf:rest Nfa9dad0ee7ff4b9489573fc732b563fa
137 Nda079a540d734ba28094bc9bd3af8fb1 schema:name doi
138 schema:value 10.1007/978-3-540-30572-9_3
139 rdf:type schema:PropertyValue
140 Ne2c920d0d66d4194a39dd15f2c18e970 schema:name Springer Nature - SN SciGraph project
141 rdf:type schema:Organization
142 Nf41c30250deb481d8ae6a5b994c1bc43 schema:familyName Paletta
143 schema:givenName Lucas
144 rdf:type schema:Person
145 Nfa9dad0ee7ff4b9489573fc732b563fa rdf:first sg:person.010060055125.29
146 rdf:rest N0f11d52d3a2846fb904e031e67a76011
147 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
148 schema:name Information and Computing Sciences
149 rdf:type schema:DefinedTerm
150 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
151 schema:name Artificial Intelligence and Image Processing
152 rdf:type schema:DefinedTerm
153 anzsrc-for:17 schema:inDefinedTermSet anzsrc-for:
154 schema:name Psychology and Cognitive Sciences
155 rdf:type schema:DefinedTerm
156 anzsrc-for:1701 schema:inDefinedTermSet anzsrc-for:
157 schema:name Psychology
158 rdf:type schema:DefinedTerm
159 sg:person.010060055125.29 schema:affiliation grid-institutes:grid.8684.2
160 schema:familyName Paletta
161 schema:givenName Lucas
162 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010060055125.29
163 rdf:type schema:Person
164 sg:person.010257616672.34 schema:affiliation grid-institutes:grid.8684.2
165 schema:familyName Seifert
166 schema:givenName Christin
167 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010257616672.34
168 rdf:type schema:Person
169 sg:person.011015636117.31 schema:affiliation grid-institutes:grid.8684.2
170 schema:familyName Fritz
171 schema:givenName Gerald
172 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.011015636117.31
173 rdf:type schema:Person
174 sg:person.013002347027.27 schema:affiliation grid-institutes:grid.410413.3
175 schema:familyName Bischof
176 schema:givenName Horst
177 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.013002347027.27
178 rdf:type schema:Person
179 grid-institutes:grid.410413.3 schema:alternateName Institute for Computer Graphics and Vision, Graz University of Technology, Inffeldgasse 16/II, A-8010, Graz, Austria
180 schema:name Institute for Computer Graphics and Vision, Graz University of Technology, Inffeldgasse 16/II, A-8010, Graz, Austria
181 rdf:type schema:Organization
182 grid-institutes:grid.8684.2 schema:alternateName Institute of Digital Image Processing, JOANNEUM RESEARCH, Forschungsgesellschaft mbH, Wastiangasse 6, A-8010, Graz, Austria
183 schema:name Institute of Digital Image Processing, JOANNEUM RESEARCH, Forschungsgesellschaft mbH, Wastiangasse 6, A-8010, Graz, Austria
184 rdf:type schema:Organization
 




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


...