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", 
      "multi-stage processing", 
      "relevant information", 
      "object databases", 
      "visual object recognition", 
      "object search", 
      "object detection", 
      "robust recognition", 
      "feature extraction", 
      "visual features", 
      "generic tasks", 
      "severe occlusion", 
      "saliency measure", 
      "decision tree", 
      "partial occlusion", 
      "specific objects", 
      "specific tasks", 
      "processing chain", 
      "object representations", 
      "appearance patterns", 
      "performance evaluation", 
      "image noise", 
      "task relevant information", 
      "image analysis", 
      "different scopes", 
      "efficient recognition", 
      "task", 
      "recognition", 
      "information", 
      "noise effects", 
      "processing", 
      "focus of attention", 
      "performance", 
      "objects", 
      "features", 
      "database", 
      "representation", 
      "task performance", 
      "search", 
      "major goal", 
      "noise", 
      "extraction", 
      "filter", 
      "mapping", 
      "detection", 
      "goal", 
      "trees", 
      "evaluation", 
      "attention", 
      "example", 
      "kind", 
      "scope", 
      "occlusion", 
      "specific interpretation", 
      "experiments", 
      "patterns", 
      "focus", 
      "means", 
      "measures", 
      "analysis", 
      "selective attention", 
      "interpretation", 
      "chain", 
      "addition", 
      "impact", 
      "degree", 
      "appearance", 
      "region", 
      "specific responses", 
      "early feature", 
      "presence", 
      "response", 
      "effect", 
      "specificity", 
      "robust task performance", 
      "attentive visual object recognition", 
      "generic visual feature extraction", 
      "object specific interpretation", 
      "select task relevant information", 
      "sparse object representation", 
      "rapid object specific responses", 
      "object specific responses", 
      "single appearance patterns", 
      "public available reference object database", 
      "available reference object database", 
      "reference object database", 
      "Attentive Object Detection", 
      "Information Theoretic Saliency Measure", 
      "Theoretic Saliency Measure"
    ], 
    "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": "2022-01-01T19:17", 
    "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_292.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.

199 TRIPLES      23 PREDICATES      120 URIs      111 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 N987c643f6b9d4e289670bd4161a7dbf3
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 Nb9ffd7f4a2d3412e8d547565115de4a0
10 schema:genre chapter
11 schema:inLanguage en
12 schema:isAccessibleForFree false
13 schema:isPartOf N471d0c5d20ef406fa19a4fe631d94fa6
14 schema:keywords Attentive Object Detection
15 Information Theoretic Saliency Measure
16 Theoretic Saliency Measure
17 addition
18 analysis
19 appearance
20 appearance patterns
21 attention
22 attentive visual object recognition
23 available reference object database
24 chain
25 complete image analysis
26 database
27 decision tree
28 degree
29 detection
30 different scopes
31 discriminative patterns
32 early feature
33 effect
34 efficient recognition
35 evaluation
36 example
37 experiments
38 extraction
39 feature extraction
40 features
41 filter
42 focus
43 focus of attention
44 generic tasks
45 generic visual feature extraction
46 goal
47 image analysis
48 image noise
49 impact
50 information
51 interpretation
52 kind
53 major goal
54 mapping
55 means
56 measures
57 multi-stage processing
58 noise
59 noise effects
60 object databases
61 object detection
62 object recognition
63 object representations
64 object search
65 object specific interpretation
66 object specific responses
67 objects
68 occlusion
69 partial occlusion
70 patterns
71 performance
72 performance evaluation
73 presence
74 processing
75 processing chain
76 public available reference object database
77 rapid object specific responses
78 recognition
79 reference object database
80 region
81 relevant information
82 representation
83 response
84 robust recognition
85 robust task performance
86 saliency measure
87 scope
88 search
89 select task relevant information
90 selective attention
91 severe occlusion
92 single appearance patterns
93 sparse object representation
94 specific interpretation
95 specific objects
96 specific responses
97 specific tasks
98 specificity
99 task
100 task performance
101 task relevant information
102 trees
103 visual feature extraction
104 visual features
105 visual object recognition
106 schema:name Attentive Object Detection Using an Information Theoretic Saliency Measure
107 schema:pagination 29-41
108 schema:productId N272f8d8a66704a619c091a2942058344
109 N9cb88e319e374dd0821492e240c5692a
110 schema:publisher N604d2235264548478303c7a39b97dfd6
111 schema:sameAs https://app.dimensions.ai/details/publication/pub.1032169666
112 https://doi.org/10.1007/978-3-540-30572-9_3
113 schema:sdDatePublished 2022-01-01T19:17
114 schema:sdLicense https://scigraph.springernature.com/explorer/license/
115 schema:sdPublisher Nc3c78fbda49343c78e7841277103c6a8
116 schema:url https://doi.org/10.1007/978-3-540-30572-9_3
117 sgo:license sg:explorer/license/
118 sgo:sdDataset chapters
119 rdf:type schema:Chapter
120 N1e0ef623d4e945ebb4141316189043d0 schema:familyName Tsotsos
121 schema:givenName John K.
122 rdf:type schema:Person
123 N272f8d8a66704a619c091a2942058344 schema:name dimensions_id
124 schema:value pub.1032169666
125 rdf:type schema:PropertyValue
126 N471d0c5d20ef406fa19a4fe631d94fa6 schema:isbn 978-3-540-24421-9
127 978-3-540-30572-9
128 schema:name Attention and Performance in Computational Vision
129 rdf:type schema:Book
130 N51a6ae1091824e29b8edd10fbb617d60 rdf:first N1e0ef623d4e945ebb4141316189043d0
131 rdf:rest N971f9fee2d734407866e8ab56be8d247
132 N53854e8b3e434a139262039175859e97 rdf:first sg:person.010257616672.34
133 rdf:rest Nbfee310faeb348dc865cc850d6d7d1f6
134 N567b58a2a4ec4b46aa68266ffad71ac7 schema:familyName Paletta
135 schema:givenName Lucas
136 rdf:type schema:Person
137 N604d2235264548478303c7a39b97dfd6 schema:name Springer Nature
138 rdf:type schema:Organisation
139 N83d81d9ceea14d62bca73dd71718994c rdf:first N93c5722f07484f338ad5e9c6acd340b5
140 rdf:rest rdf:nil
141 N93c5722f07484f338ad5e9c6acd340b5 schema:familyName Humphreys
142 schema:givenName Glyn
143 rdf:type schema:Person
144 N971f9fee2d734407866e8ab56be8d247 rdf:first Nf64707ec8be64541ba7fd25a1fc8b77f
145 rdf:rest N83d81d9ceea14d62bca73dd71718994c
146 N987c643f6b9d4e289670bd4161a7dbf3 rdf:first sg:person.011015636117.31
147 rdf:rest N53854e8b3e434a139262039175859e97
148 N9cb88e319e374dd0821492e240c5692a schema:name doi
149 schema:value 10.1007/978-3-540-30572-9_3
150 rdf:type schema:PropertyValue
151 Nb9ffd7f4a2d3412e8d547565115de4a0 rdf:first N567b58a2a4ec4b46aa68266ffad71ac7
152 rdf:rest N51a6ae1091824e29b8edd10fbb617d60
153 Nbc02018104d448bfb61d8d5d8db3a3db rdf:first sg:person.013002347027.27
154 rdf:rest rdf:nil
155 Nbfee310faeb348dc865cc850d6d7d1f6 rdf:first sg:person.010060055125.29
156 rdf:rest Nbc02018104d448bfb61d8d5d8db3a3db
157 Nc3c78fbda49343c78e7841277103c6a8 schema:name Springer Nature - SN SciGraph project
158 rdf:type schema:Organization
159 Nf64707ec8be64541ba7fd25a1fc8b77f schema:familyName Rome
160 schema:givenName Erich
161 rdf:type schema:Person
162 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
163 schema:name Information and Computing Sciences
164 rdf:type schema:DefinedTerm
165 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
166 schema:name Artificial Intelligence and Image Processing
167 rdf:type schema:DefinedTerm
168 anzsrc-for:17 schema:inDefinedTermSet anzsrc-for:
169 schema:name Psychology and Cognitive Sciences
170 rdf:type schema:DefinedTerm
171 anzsrc-for:1701 schema:inDefinedTermSet anzsrc-for:
172 schema:name Psychology
173 rdf:type schema:DefinedTerm
174 sg:person.010060055125.29 schema:affiliation grid-institutes:grid.8684.2
175 schema:familyName Paletta
176 schema:givenName Lucas
177 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010060055125.29
178 rdf:type schema:Person
179 sg:person.010257616672.34 schema:affiliation grid-institutes:grid.8684.2
180 schema:familyName Seifert
181 schema:givenName Christin
182 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010257616672.34
183 rdf:type schema:Person
184 sg:person.011015636117.31 schema:affiliation grid-institutes:grid.8684.2
185 schema:familyName Fritz
186 schema:givenName Gerald
187 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.011015636117.31
188 rdf:type schema:Person
189 sg:person.013002347027.27 schema:affiliation grid-institutes:grid.410413.3
190 schema:familyName Bischof
191 schema:givenName Horst
192 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.013002347027.27
193 rdf:type schema:Person
194 grid-institutes:grid.410413.3 schema:alternateName Institute for Computer Graphics and Vision, Graz University of Technology, Inffeldgasse 16/II, A-8010, Graz, Austria
195 schema:name Institute for Computer Graphics and Vision, Graz University of Technology, Inffeldgasse 16/II, A-8010, Graz, Austria
196 rdf:type schema:Organization
197 grid-institutes:grid.8684.2 schema:alternateName Institute of Digital Image Processing, JOANNEUM RESEARCH, Forschungsgesellschaft mbH, Wastiangasse 6, A-8010, Graz, Austria
198 schema:name Institute of Digital Image Processing, JOANNEUM RESEARCH, Forschungsgesellschaft mbH, Wastiangasse 6, A-8010, Graz, Austria
199 rdf:type schema:Organization
 




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


...