Enhancing Recognition of Visual Concepts with Primitive Color Histograms via Non-sparse Multiple Kernel Learning View Full Text


Ontology type: schema:Chapter     


Chapter Info

DATE

2010

AUTHORS

Alexander Binder , Motoaki Kawanabe

ABSTRACT

In order to achieve good performance in image annotation tasks, it is necessary to combine information from various image features. In recent competitions on photo annotation, many groups employed the bag-of-words (BoW) representations based on the SIFT descriptors over various color channels. In fact, it has been observed that adding other less informative features to the standard BoW degrades recognition performances. In this contribution, we will show that even primitive color histograms can enhance the standard classifiers in the ImageCLEF 2009 photo annotation task, if the feature weights are tuned optimally by non-sparse multiple kernel learning (MKL) proposed by Kloft et al.. Additionally, we will propose a sorting scheme of image subregions to deal with spatial variability within each visual concept. More... »

PAGES

269-276

References to SciGraph publications

  • 2010. Overview of the CLEF 2009 Large-Scale Visual Concept Detection and Annotation Task in MULTILINGUAL INFORMATION ACCESS EVALUATION II. MULTIMEDIA EXPERIMENTS
  • 2004-11. Distinctive Image Features from Scale-Invariant Keypoints in INTERNATIONAL JOURNAL OF COMPUTER VISION
  • 1995. The Nature of Statistical Learning Theory in NONE
  • Book

    TITLE

    Multilingual Information Access Evaluation II. Multimedia Experiments

    ISBN

    978-3-642-15750-9
    978-3-642-15751-6

    Identifiers

    URI

    http://scigraph.springernature.com/pub.10.1007/978-3-642-15751-6_33

    DOI

    http://dx.doi.org/10.1007/978-3-642-15751-6_33

    DIMENSIONS

    https://app.dimensions.ai/details/publication/pub.1004665961


    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/2008/0801", 
            "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/2008/08", 
            "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
            "name": "Information and Computing Sciences", 
            "type": "DefinedTerm"
          }
        ], 
        "author": [
          {
            "affiliation": {
              "alternateName": "Fraunhofer Institute for Process Engineering and Packaging", 
              "id": "https://www.grid.ac/institutes/grid.466709.a", 
              "name": [
                "Fraunhofer Institute FIRST, Kekul\u00e9str. 7, 12489, Berlin, Germany"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Binder", 
            "givenName": "Alexander", 
            "id": "sg:person.01062716467.33", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01062716467.33"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Technical University of Berlin", 
              "id": "https://www.grid.ac/institutes/grid.6734.6", 
              "name": [
                "Fraunhofer Institute FIRST, Kekul\u00e9str. 7, 12489, Berlin, Germany", 
                "TU Berlin, Franklinstr. 28/29, 10587, Berlin, Germany"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Kawanabe", 
            "givenName": "Motoaki", 
            "id": "sg:person.01264426371.28", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01264426371.28"
            ], 
            "type": "Person"
          }
        ], 
        "citation": [
          {
            "id": "sg:pub.10.1007/978-1-4757-2440-0", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1027312764", 
              "https://doi.org/10.1007/978-1-4757-2440-0"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-1-4757-2440-0", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1027312764", 
              "https://doi.org/10.1007/978-1-4757-2440-0"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1023/b:visi.0000029664.99615.94", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1052687286", 
              "https://doi.org/10.1023/b:visi.0000029664.99615.94"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-3-642-15751-6_10", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1052874237", 
              "https://doi.org/10.1007/978-3-642-15751-6_10"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-3-642-15751-6_10", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1052874237", 
              "https://doi.org/10.1007/978-3-642-15751-6_10"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/72.914517", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1061219539"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/tpami.2005.188", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1061742845"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/cvpr.2006.68", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1094512911"
            ], 
            "type": "CreativeWork"
          }
        ], 
        "datePublished": "2010", 
        "datePublishedReg": "2010-01-01", 
        "description": "In order to achieve good performance in image annotation tasks, it is necessary to combine information from various image features. In recent competitions on photo annotation, many groups employed the bag-of-words (BoW) representations based on the SIFT descriptors over various color channels. In fact, it has been observed that adding other less informative features to the standard BoW degrades recognition performances. In this contribution, we will show that even primitive color histograms can enhance the standard classifiers in the ImageCLEF 2009 photo annotation task, if the feature weights are tuned optimally by non-sparse multiple kernel learning (MKL) proposed by Kloft et al.. Additionally, we will propose a sorting scheme of image subregions to deal with spatial variability within each visual concept.", 
        "editor": [
          {
            "familyName": "Peters", 
            "givenName": "Carol", 
            "type": "Person"
          }, 
          {
            "familyName": "Caputo", 
            "givenName": "Barbara", 
            "type": "Person"
          }, 
          {
            "familyName": "Gonzalo", 
            "givenName": "Julio", 
            "type": "Person"
          }, 
          {
            "familyName": "Jones", 
            "givenName": "Gareth J. F.", 
            "type": "Person"
          }, 
          {
            "familyName": "Kalpathy-Cramer", 
            "givenName": "Jayashree", 
            "type": "Person"
          }, 
          {
            "familyName": "M\u00fcller", 
            "givenName": "Henning", 
            "type": "Person"
          }, 
          {
            "familyName": "Tsikrika", 
            "givenName": "Theodora", 
            "type": "Person"
          }
        ], 
        "genre": "chapter", 
        "id": "sg:pub.10.1007/978-3-642-15751-6_33", 
        "inLanguage": [
          "en"
        ], 
        "isAccessibleForFree": false, 
        "isPartOf": {
          "isbn": [
            "978-3-642-15750-9", 
            "978-3-642-15751-6"
          ], 
          "name": "Multilingual Information Access Evaluation II. Multimedia Experiments", 
          "type": "Book"
        }, 
        "name": "Enhancing Recognition of Visual Concepts with Primitive Color Histograms via Non-sparse Multiple Kernel Learning", 
        "pagination": "269-276", 
        "productId": [
          {
            "name": "dimensions_id", 
            "type": "PropertyValue", 
            "value": [
              "pub.1004665961"
            ]
          }, 
          {
            "name": "doi", 
            "type": "PropertyValue", 
            "value": [
              "10.1007/978-3-642-15751-6_33"
            ]
          }, 
          {
            "name": "readcube_id", 
            "type": "PropertyValue", 
            "value": [
              "163bcced0d3e2643d8623492c63b3b2732d26912fe1227579081fed5e3459013"
            ]
          }
        ], 
        "publisher": {
          "location": "Berlin, Heidelberg", 
          "name": "Springer Berlin Heidelberg", 
          "type": "Organisation"
        }, 
        "sameAs": [
          "https://doi.org/10.1007/978-3-642-15751-6_33", 
          "https://app.dimensions.ai/details/publication/pub.1004665961"
        ], 
        "sdDataset": "chapters", 
        "sdDatePublished": "2019-04-16T08:21", 
        "sdLicense": "https://scigraph.springernature.com/explorer/license/", 
        "sdPublisher": {
          "name": "Springer Nature - SN SciGraph project", 
          "type": "Organization"
        }, 
        "sdSource": "s3://com-uberresearch-data-dimensions-target-20181106-alternative/cleanup/v134/2549eaecd7973599484d7c17b260dba0a4ecb94b/merge/v9/a6c9fde33151104705d4d7ff012ea9563521a3ce/jats-lookup/v90/0000000363_0000000363/records_70028_00000000.jsonl", 
        "type": "Chapter", 
        "url": "https://link.springer.com/10.1007%2F978-3-642-15751-6_33"
      }
    ]
     

    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.10.1007/978-3-642-15751-6_33'

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

    curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1007/978-3-642-15751-6_33'

    Turtle is a human-readable linked data format.

    curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/978-3-642-15751-6_33'

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

    curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/978-3-642-15751-6_33'


     

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

    127 TRIPLES      23 PREDICATES      33 URIs      20 LITERALS      8 BLANK NODES

    Subject Predicate Object
    1 sg:pub.10.1007/978-3-642-15751-6_33 schema:about anzsrc-for:08
    2 anzsrc-for:0801
    3 schema:author N2fe16dae1a38426cb877a6a31fe6a2c4
    4 schema:citation sg:pub.10.1007/978-1-4757-2440-0
    5 sg:pub.10.1007/978-3-642-15751-6_10
    6 sg:pub.10.1023/b:visi.0000029664.99615.94
    7 https://doi.org/10.1109/72.914517
    8 https://doi.org/10.1109/cvpr.2006.68
    9 https://doi.org/10.1109/tpami.2005.188
    10 schema:datePublished 2010
    11 schema:datePublishedReg 2010-01-01
    12 schema:description In order to achieve good performance in image annotation tasks, it is necessary to combine information from various image features. In recent competitions on photo annotation, many groups employed the bag-of-words (BoW) representations based on the SIFT descriptors over various color channels. In fact, it has been observed that adding other less informative features to the standard BoW degrades recognition performances. In this contribution, we will show that even primitive color histograms can enhance the standard classifiers in the ImageCLEF 2009 photo annotation task, if the feature weights are tuned optimally by non-sparse multiple kernel learning (MKL) proposed by Kloft et al.. Additionally, we will propose a sorting scheme of image subregions to deal with spatial variability within each visual concept.
    13 schema:editor N2173817d5d6c44aa983b48a667525742
    14 schema:genre chapter
    15 schema:inLanguage en
    16 schema:isAccessibleForFree false
    17 schema:isPartOf N0684ba4fbc7d4b6e94115da09f756a70
    18 schema:name Enhancing Recognition of Visual Concepts with Primitive Color Histograms via Non-sparse Multiple Kernel Learning
    19 schema:pagination 269-276
    20 schema:productId N0a7fefc965a84e70ae192f6a3668830d
    21 N48567ff143af47b2901731a39dd830c3
    22 N8fc7244a7f814f8f9bdc3afa85e2a564
    23 schema:publisher N4e5fd8cc7ab84f398527a8dcc82cd4df
    24 schema:sameAs https://app.dimensions.ai/details/publication/pub.1004665961
    25 https://doi.org/10.1007/978-3-642-15751-6_33
    26 schema:sdDatePublished 2019-04-16T08:21
    27 schema:sdLicense https://scigraph.springernature.com/explorer/license/
    28 schema:sdPublisher Nb464fb8e4f1b43b6a01f203f340e8539
    29 schema:url https://link.springer.com/10.1007%2F978-3-642-15751-6_33
    30 sgo:license sg:explorer/license/
    31 sgo:sdDataset chapters
    32 rdf:type schema:Chapter
    33 N0684ba4fbc7d4b6e94115da09f756a70 schema:isbn 978-3-642-15750-9
    34 978-3-642-15751-6
    35 schema:name Multilingual Information Access Evaluation II. Multimedia Experiments
    36 rdf:type schema:Book
    37 N0a7fefc965a84e70ae192f6a3668830d schema:name readcube_id
    38 schema:value 163bcced0d3e2643d8623492c63b3b2732d26912fe1227579081fed5e3459013
    39 rdf:type schema:PropertyValue
    40 N13c7a8b45daa41b7b4464394da459638 rdf:first N327ac2a415d24def942b60893d70b849
    41 rdf:rest N300302e03ecc42aeb7ccce71872fed5b
    42 N1dc807904c824432b322ba5dfa4b4cd6 schema:familyName Tsikrika
    43 schema:givenName Theodora
    44 rdf:type schema:Person
    45 N2173817d5d6c44aa983b48a667525742 rdf:first N51565ea7b8ce48859f031f71e6df9dd2
    46 rdf:rest N13c7a8b45daa41b7b4464394da459638
    47 N2e0d8221497545cc93f6149faeb65d7a schema:familyName Jones
    48 schema:givenName Gareth J. F.
    49 rdf:type schema:Person
    50 N2fe16dae1a38426cb877a6a31fe6a2c4 rdf:first sg:person.01062716467.33
    51 rdf:rest Nd0b4ad0f56914257ac04e0c84d4b53bb
    52 N300302e03ecc42aeb7ccce71872fed5b rdf:first N50a487f8bf074aa8bb84eb8d354b6562
    53 rdf:rest Nddae7d5169f44aa6b4aef2a7cbe4778d
    54 N327ac2a415d24def942b60893d70b849 schema:familyName Caputo
    55 schema:givenName Barbara
    56 rdf:type schema:Person
    57 N427de3f0421946a7a63e86a3115b37c9 rdf:first N7c5c5f331e25451ba061e5631824b3df
    58 rdf:rest N49bdf8d338aa4bb597afae58fc825bbd
    59 N48567ff143af47b2901731a39dd830c3 schema:name doi
    60 schema:value 10.1007/978-3-642-15751-6_33
    61 rdf:type schema:PropertyValue
    62 N49bdf8d338aa4bb597afae58fc825bbd rdf:first N1dc807904c824432b322ba5dfa4b4cd6
    63 rdf:rest rdf:nil
    64 N4d1ef6c168d5498fae55d0ff6ea44824 schema:familyName Kalpathy-Cramer
    65 schema:givenName Jayashree
    66 rdf:type schema:Person
    67 N4e5fd8cc7ab84f398527a8dcc82cd4df schema:location Berlin, Heidelberg
    68 schema:name Springer Berlin Heidelberg
    69 rdf:type schema:Organisation
    70 N50a487f8bf074aa8bb84eb8d354b6562 schema:familyName Gonzalo
    71 schema:givenName Julio
    72 rdf:type schema:Person
    73 N51565ea7b8ce48859f031f71e6df9dd2 schema:familyName Peters
    74 schema:givenName Carol
    75 rdf:type schema:Person
    76 N7c5c5f331e25451ba061e5631824b3df schema:familyName Müller
    77 schema:givenName Henning
    78 rdf:type schema:Person
    79 N8fc7244a7f814f8f9bdc3afa85e2a564 schema:name dimensions_id
    80 schema:value pub.1004665961
    81 rdf:type schema:PropertyValue
    82 Na8db7b1091ce45b49657e780acbf3dbe rdf:first N4d1ef6c168d5498fae55d0ff6ea44824
    83 rdf:rest N427de3f0421946a7a63e86a3115b37c9
    84 Nb464fb8e4f1b43b6a01f203f340e8539 schema:name Springer Nature - SN SciGraph project
    85 rdf:type schema:Organization
    86 Nd0b4ad0f56914257ac04e0c84d4b53bb rdf:first sg:person.01264426371.28
    87 rdf:rest rdf:nil
    88 Nddae7d5169f44aa6b4aef2a7cbe4778d rdf:first N2e0d8221497545cc93f6149faeb65d7a
    89 rdf:rest Na8db7b1091ce45b49657e780acbf3dbe
    90 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
    91 schema:name Information and Computing Sciences
    92 rdf:type schema:DefinedTerm
    93 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
    94 schema:name Artificial Intelligence and Image Processing
    95 rdf:type schema:DefinedTerm
    96 sg:person.01062716467.33 schema:affiliation https://www.grid.ac/institutes/grid.466709.a
    97 schema:familyName Binder
    98 schema:givenName Alexander
    99 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01062716467.33
    100 rdf:type schema:Person
    101 sg:person.01264426371.28 schema:affiliation https://www.grid.ac/institutes/grid.6734.6
    102 schema:familyName Kawanabe
    103 schema:givenName Motoaki
    104 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01264426371.28
    105 rdf:type schema:Person
    106 sg:pub.10.1007/978-1-4757-2440-0 schema:sameAs https://app.dimensions.ai/details/publication/pub.1027312764
    107 https://doi.org/10.1007/978-1-4757-2440-0
    108 rdf:type schema:CreativeWork
    109 sg:pub.10.1007/978-3-642-15751-6_10 schema:sameAs https://app.dimensions.ai/details/publication/pub.1052874237
    110 https://doi.org/10.1007/978-3-642-15751-6_10
    111 rdf:type schema:CreativeWork
    112 sg:pub.10.1023/b:visi.0000029664.99615.94 schema:sameAs https://app.dimensions.ai/details/publication/pub.1052687286
    113 https://doi.org/10.1023/b:visi.0000029664.99615.94
    114 rdf:type schema:CreativeWork
    115 https://doi.org/10.1109/72.914517 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061219539
    116 rdf:type schema:CreativeWork
    117 https://doi.org/10.1109/cvpr.2006.68 schema:sameAs https://app.dimensions.ai/details/publication/pub.1094512911
    118 rdf:type schema:CreativeWork
    119 https://doi.org/10.1109/tpami.2005.188 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061742845
    120 rdf:type schema:CreativeWork
    121 https://www.grid.ac/institutes/grid.466709.a schema:alternateName Fraunhofer Institute for Process Engineering and Packaging
    122 schema:name Fraunhofer Institute FIRST, Kekuléstr. 7, 12489, Berlin, Germany
    123 rdf:type schema:Organization
    124 https://www.grid.ac/institutes/grid.6734.6 schema:alternateName Technical University of Berlin
    125 schema:name Fraunhofer Institute FIRST, Kekuléstr. 7, 12489, Berlin, Germany
    126 TU Berlin, Franklinstr. 28/29, 10587, Berlin, Germany
    127 rdf:type schema:Organization
     




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


    ...