Towards Unsupervised Discovery of Visual Categories View Full Text


Ontology type: schema:Chapter     


Chapter Info

DATE

2006

AUTHORS

Mario Fritz , Bernt Schiele

ABSTRACT

Recently, many approaches have been proposed for visual object category detection. They vary greatly in terms of how much supervision is needed. High performance object detection methods tend to be trained in a supervised manner from relatively clean data. In order to deal with a large number of object classes and large amounts of training data, there is a clear desire to use as little supervision as possible. This paper proposes a new approach for unsupervised learning of visual categories based on a scheme to detect reoccurring structure in sets of images. The approach finds the locations as well as the scales of such reoccurring structures in an unsupervised manner. In the experiments those reoccurring structures correspond to object categories which can be used to directly learn object category models. Experimental results show the effectiveness of the new approach and compare the performance to previous fully-supervised methods. More... »

PAGES

232-241

Book

TITLE

Pattern Recognition

ISBN

978-3-540-44412-1
978-3-540-44414-5

Identifiers

URI

http://scigraph.springernature.com/pub.10.1007/11861898_24

DOI

http://dx.doi.org/10.1007/11861898_24

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1039354510


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/2008/0801", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Artificial Intelligence and Image Processing", 
        "type": "DefinedTerm"
      }
    ], 
    "author": [
      {
        "affiliation": {
          "alternateName": "Multimodal Interactive Systems, TU-Darmstadt, Germany", 
          "id": "http://www.grid.ac/institutes/grid.6546.1", 
          "name": [
            "Multimodal Interactive Systems, TU-Darmstadt, Germany"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Fritz", 
        "givenName": "Mario", 
        "id": "sg:person.013361072755.17", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.013361072755.17"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Multimodal Interactive Systems, TU-Darmstadt, Germany", 
          "id": "http://www.grid.ac/institutes/grid.6546.1", 
          "name": [
            "Multimodal Interactive Systems, TU-Darmstadt, Germany"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Schiele", 
        "givenName": "Bernt", 
        "id": "sg:person.01174260421.90", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01174260421.90"
        ], 
        "type": "Person"
      }
    ], 
    "datePublished": "2006", 
    "datePublishedReg": "2006-01-01", 
    "description": "Recently, many approaches have been proposed for visual object category detection. They vary greatly in terms of how much supervision is needed. High performance object detection methods tend to be trained in a supervised manner from relatively clean data. In order to deal with a large number of object classes and large amounts of training data, there is a clear desire to use as little supervision as possible. This paper proposes a new approach for unsupervised learning of visual categories based on a scheme to detect reoccurring structure in sets of images. The approach finds the locations as well as the scales of such reoccurring structures in an unsupervised manner. In the experiments those reoccurring structures correspond to object categories which can be used to directly learn object category models. Experimental results show the effectiveness of the new approach and compare the performance to previous fully-supervised methods.", 
    "editor": [
      {
        "familyName": "Franke", 
        "givenName": "Katrin", 
        "type": "Person"
      }, 
      {
        "familyName": "M\u00fcller", 
        "givenName": "Klaus-Robert", 
        "type": "Person"
      }, 
      {
        "familyName": "Nickolay", 
        "givenName": "Bertram", 
        "type": "Person"
      }, 
      {
        "familyName": "Sch\u00e4fer", 
        "givenName": "Ralf", 
        "type": "Person"
      }
    ], 
    "genre": "chapter", 
    "id": "sg:pub.10.1007/11861898_24", 
    "isAccessibleForFree": false, 
    "isPartOf": {
      "isbn": [
        "978-3-540-44412-1", 
        "978-3-540-44414-5"
      ], 
      "name": "Pattern Recognition", 
      "type": "Book"
    }, 
    "keywords": [
      "object category models", 
      "new approach", 
      "category model", 
      "unsupervised learning", 
      "clean data", 
      "unsupervised manner", 
      "training data", 
      "large number", 
      "experimental results", 
      "approach", 
      "scheme", 
      "class", 
      "unsupervised discovery", 
      "structure", 
      "object classes", 
      "set", 
      "supervised manner", 
      "model", 
      "terms", 
      "visual categories", 
      "set of images", 
      "order", 
      "effectiveness", 
      "number", 
      "performance", 
      "object category detection", 
      "data", 
      "experiments", 
      "results", 
      "large amount", 
      "object detection method", 
      "manner", 
      "detection method", 
      "category detection", 
      "scale", 
      "categories", 
      "location", 
      "little supervision", 
      "learning", 
      "images", 
      "supervision", 
      "discovery", 
      "detection", 
      "amount", 
      "desire", 
      "clear desire", 
      "paper", 
      "method"
    ], 
    "name": "Towards Unsupervised Discovery of Visual Categories", 
    "pagination": "232-241", 
    "productId": [
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1039354510"
        ]
      }, 
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1007/11861898_24"
        ]
      }
    ], 
    "publisher": {
      "name": "Springer Nature", 
      "type": "Organisation"
    }, 
    "sameAs": [
      "https://doi.org/10.1007/11861898_24", 
      "https://app.dimensions.ai/details/publication/pub.1039354510"
    ], 
    "sdDataset": "chapters", 
    "sdDatePublished": "2022-11-24T21:18", 
    "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_427.jsonl", 
    "type": "Chapter", 
    "url": "https://doi.org/10.1007/11861898_24"
  }
]
 

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.10.1007/11861898_24'

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

curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1007/11861898_24'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/11861898_24'

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

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/11861898_24'


 

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

129 TRIPLES      22 PREDICATES      73 URIs      66 LITERALS      7 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1007/11861898_24 schema:about anzsrc-for:08
2 anzsrc-for:0801
3 schema:author N73bd3fcf3dae4654826b5e09e1620402
4 schema:datePublished 2006
5 schema:datePublishedReg 2006-01-01
6 schema:description Recently, many approaches have been proposed for visual object category detection. They vary greatly in terms of how much supervision is needed. High performance object detection methods tend to be trained in a supervised manner from relatively clean data. In order to deal with a large number of object classes and large amounts of training data, there is a clear desire to use as little supervision as possible. This paper proposes a new approach for unsupervised learning of visual categories based on a scheme to detect reoccurring structure in sets of images. The approach finds the locations as well as the scales of such reoccurring structures in an unsupervised manner. In the experiments those reoccurring structures correspond to object categories which can be used to directly learn object category models. Experimental results show the effectiveness of the new approach and compare the performance to previous fully-supervised methods.
7 schema:editor N2ff8e196cc5444559ac94a444976a312
8 schema:genre chapter
9 schema:isAccessibleForFree false
10 schema:isPartOf N3cd76f61be1b49d18ccd41b784476577
11 schema:keywords amount
12 approach
13 categories
14 category detection
15 category model
16 class
17 clean data
18 clear desire
19 data
20 desire
21 detection
22 detection method
23 discovery
24 effectiveness
25 experimental results
26 experiments
27 images
28 large amount
29 large number
30 learning
31 little supervision
32 location
33 manner
34 method
35 model
36 new approach
37 number
38 object category detection
39 object category models
40 object classes
41 object detection method
42 order
43 paper
44 performance
45 results
46 scale
47 scheme
48 set
49 set of images
50 structure
51 supervised manner
52 supervision
53 terms
54 training data
55 unsupervised discovery
56 unsupervised learning
57 unsupervised manner
58 visual categories
59 schema:name Towards Unsupervised Discovery of Visual Categories
60 schema:pagination 232-241
61 schema:productId N56697818c47d428da8ac19a560eb0ef5
62 Nb7cf58dd1d6d406e9d6b0ed0b939fb7e
63 schema:publisher N20b2d6e8328b49f9b1867f1c1e16c930
64 schema:sameAs https://app.dimensions.ai/details/publication/pub.1039354510
65 https://doi.org/10.1007/11861898_24
66 schema:sdDatePublished 2022-11-24T21:18
67 schema:sdLicense https://scigraph.springernature.com/explorer/license/
68 schema:sdPublisher N730ebb8cee0841699419433bee8d8bb5
69 schema:url https://doi.org/10.1007/11861898_24
70 sgo:license sg:explorer/license/
71 sgo:sdDataset chapters
72 rdf:type schema:Chapter
73 N20b2d6e8328b49f9b1867f1c1e16c930 schema:name Springer Nature
74 rdf:type schema:Organisation
75 N2ff8e196cc5444559ac94a444976a312 rdf:first N41e4f0309bf84091a50a9c8acc622db6
76 rdf:rest Nc246a25bff684c60950a64cf55cde2f6
77 N3cd76f61be1b49d18ccd41b784476577 schema:isbn 978-3-540-44412-1
78 978-3-540-44414-5
79 schema:name Pattern Recognition
80 rdf:type schema:Book
81 N41e4f0309bf84091a50a9c8acc622db6 schema:familyName Franke
82 schema:givenName Katrin
83 rdf:type schema:Person
84 N56697818c47d428da8ac19a560eb0ef5 schema:name doi
85 schema:value 10.1007/11861898_24
86 rdf:type schema:PropertyValue
87 N676c50d861d747bb9e5fcd79378f765f rdf:first Nc61643bdd5c043379241d364c5a992f1
88 rdf:rest N79042d0a51bb48dcbea31cdf4bd37cbb
89 N730ebb8cee0841699419433bee8d8bb5 schema:name Springer Nature - SN SciGraph project
90 rdf:type schema:Organization
91 N73bd3fcf3dae4654826b5e09e1620402 rdf:first sg:person.013361072755.17
92 rdf:rest Ne70e0530125d4a7585e78361f81e645a
93 N79042d0a51bb48dcbea31cdf4bd37cbb rdf:first N830818d5b91e41b2ae05412ec8e156db
94 rdf:rest rdf:nil
95 N830818d5b91e41b2ae05412ec8e156db schema:familyName Schäfer
96 schema:givenName Ralf
97 rdf:type schema:Person
98 N9afa1c527eba46548c0fd264ebc8d5df schema:familyName Müller
99 schema:givenName Klaus-Robert
100 rdf:type schema:Person
101 Nb7cf58dd1d6d406e9d6b0ed0b939fb7e schema:name dimensions_id
102 schema:value pub.1039354510
103 rdf:type schema:PropertyValue
104 Nc246a25bff684c60950a64cf55cde2f6 rdf:first N9afa1c527eba46548c0fd264ebc8d5df
105 rdf:rest N676c50d861d747bb9e5fcd79378f765f
106 Nc61643bdd5c043379241d364c5a992f1 schema:familyName Nickolay
107 schema:givenName Bertram
108 rdf:type schema:Person
109 Ne70e0530125d4a7585e78361f81e645a rdf:first sg:person.01174260421.90
110 rdf:rest rdf:nil
111 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
112 schema:name Information and Computing Sciences
113 rdf:type schema:DefinedTerm
114 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
115 schema:name Artificial Intelligence and Image Processing
116 rdf:type schema:DefinedTerm
117 sg:person.01174260421.90 schema:affiliation grid-institutes:grid.6546.1
118 schema:familyName Schiele
119 schema:givenName Bernt
120 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01174260421.90
121 rdf:type schema:Person
122 sg:person.013361072755.17 schema:affiliation grid-institutes:grid.6546.1
123 schema:familyName Fritz
124 schema:givenName Mario
125 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.013361072755.17
126 rdf:type schema:Person
127 grid-institutes:grid.6546.1 schema:alternateName Multimodal Interactive Systems, TU-Darmstadt, Germany
128 schema:name Multimodal Interactive Systems, TU-Darmstadt, Germany
129 rdf:type schema:Organization
 




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


...