Improving the Fisher Kernel for Large-Scale Image Classification View Full Text


Ontology type: schema:Chapter      Open Access: True


Chapter Info

DATE

2010

AUTHORS

Florent Perronnin , Jorge Sánchez , Thomas Mensink

ABSTRACT

The Fisher kernel (FK) is a generic framework which combines the benefits of generative and discriminative approaches. In the context of image classification the FK was shown to extend the popular bag-of-visual-words (BOV) by going beyond count statistics. However, in practice, this enriched representation has not yet shown its superiority over the BOV. In the first part we show that with several well-motivated modifications over the original framework we can boost the accuracy of the FK. On PASCAL VOC 2007 we increase the Average Precision (AP) from 47.9% to 58.3%. Similarly, we demonstrate state-of-the-art accuracy on CalTech 256. A major advantage is that these results are obtained using only SIFT descriptors and costless linear classifiers. Equipped with this representation, we can now explore image classification on a larger scale. In the second part, as an application, we compare two abundant resources of labeled images to learn classifiers: ImageNet and Flickr groups. In an evaluation involving hundreds of thousands of training images we show that classifiers learned on Flickr groups perform surprisingly well (although they were not intended for this purpose) and that they can complement classifiers learned on more carefully annotated datasets. More... »

PAGES

143-156

References to SciGraph publications

  • 2004-11. Distinctive Image Features from Scale-Invariant Keypoints in INTERNATIONAL JOURNAL OF COMPUTER VISION
  • 2007-06. Local Features and Kernels for Classification of Texture and Object Categories: A Comprehensive Study in INTERNATIONAL JOURNAL OF COMPUTER VISION
  • 2011-03. Pegasos: primal estimated sub-gradient solver for SVM in MATHEMATICAL PROGRAMMING
  • Book

    TITLE

    Computer Vision – ECCV 2010

    ISBN

    978-3-642-15560-4
    978-3-642-15561-1

    Identifiers

    URI

    http://scigraph.springernature.com/pub.10.1007/978-3-642-15561-1_11

    DOI

    http://dx.doi.org/10.1007/978-3-642-15561-1_11

    DIMENSIONS

    https://app.dimensions.ai/details/publication/pub.1045344996


    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/2008/1701", 
            "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
            "name": "Psychology", 
            "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"
          }
        ], 
        "author": [
          {
            "affiliation": {
              "name": [
                "Xerox Research Centre Europe (XRCE)"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Perronnin", 
            "givenName": "Florent", 
            "id": "sg:person.01320142425.13", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01320142425.13"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "name": [
                "Xerox Research Centre Europe (XRCE)"
              ], 
              "type": "Organization"
            }, 
            "familyName": "S\u00e1nchez", 
            "givenName": "Jorge", 
            "id": "sg:person.01136743706.30", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01136743706.30"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "name": [
                "Xerox Research Centre Europe (XRCE)"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Mensink", 
            "givenName": "Thomas", 
            "id": "sg:person.010600141141.73", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010600141141.73"
            ], 
            "type": "Person"
          }
        ], 
        "citation": [
          {
            "id": "sg:pub.10.1007/s11263-006-9794-4", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1008205152", 
              "https://doi.org/10.1007/s11263-006-9794-4"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1145/1150402.1150429", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1044904927"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/s10107-010-0420-4", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1050541291", 
              "https://doi.org/10.1007/s10107-010-0420-4"
            ], 
            "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": "https://doi.org/10.1109/tpami.2008.128", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1061743490"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/tpami.2009.132", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1061743716"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/cvpr.2006.264", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1093301542"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/iccv.2009.5459432", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1093378856"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/iccvw.2009.5457703", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1093567598"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/cvpr.2008.4587598", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1093888066"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/iccv.2009.5459354", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1094040462"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/cvpr.2009.5206663", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1094077345"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/iccv.2009.5459203", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1094402362"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/cvpr.2010.5539914", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1094512169"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/cvpr.2006.68", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1094512911"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/iccv.2009.5459167", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1094765820"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/cvpr.2010.5539949", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1094875983"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/iccv.2009.5459257", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1094965859"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/cvpr.2009.5206757", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1095180230"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/cvpr.2007.383266", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1095559903"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/cvpr.2009.5206848", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1095689025"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/iccv.2009.5459172", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1095690739"
            ], 
            "type": "CreativeWork"
          }
        ], 
        "datePublished": "2010", 
        "datePublishedReg": "2010-01-01", 
        "description": "The Fisher kernel (FK) is a generic framework which combines the benefits of generative and discriminative approaches. In the context of image classification the FK was shown to extend the popular bag-of-visual-words (BOV) by going beyond count statistics. However, in practice, this enriched representation has not yet shown its superiority over the BOV. In the first part we show that with several well-motivated modifications over the original framework we can boost the accuracy of the FK. On PASCAL VOC 2007 we increase the Average Precision (AP) from 47.9% to 58.3%. Similarly, we demonstrate state-of-the-art accuracy on CalTech 256. A major advantage is that these results are obtained using only SIFT descriptors and costless linear classifiers. Equipped with this representation, we can now explore image classification on a larger scale. In the second part, as an application, we compare two abundant resources of labeled images to learn classifiers: ImageNet and Flickr groups. In an evaluation involving hundreds of thousands of training images we show that classifiers learned on Flickr groups perform surprisingly well (although they were not intended for this purpose) and that they can complement classifiers learned on more carefully annotated datasets.", 
        "editor": [
          {
            "familyName": "Daniilidis", 
            "givenName": "Kostas", 
            "type": "Person"
          }, 
          {
            "familyName": "Maragos", 
            "givenName": "Petros", 
            "type": "Person"
          }, 
          {
            "familyName": "Paragios", 
            "givenName": "Nikos", 
            "type": "Person"
          }
        ], 
        "genre": "chapter", 
        "id": "sg:pub.10.1007/978-3-642-15561-1_11", 
        "inLanguage": [
          "en"
        ], 
        "isAccessibleForFree": true, 
        "isPartOf": {
          "isbn": [
            "978-3-642-15560-4", 
            "978-3-642-15561-1"
          ], 
          "name": "Computer Vision \u2013 ECCV 2010", 
          "type": "Book"
        }, 
        "name": "Improving the Fisher Kernel for Large-Scale Image Classification", 
        "pagination": "143-156", 
        "productId": [
          {
            "name": "dimensions_id", 
            "type": "PropertyValue", 
            "value": [
              "pub.1045344996"
            ]
          }, 
          {
            "name": "doi", 
            "type": "PropertyValue", 
            "value": [
              "10.1007/978-3-642-15561-1_11"
            ]
          }, 
          {
            "name": "readcube_id", 
            "type": "PropertyValue", 
            "value": [
              "d7ff81f0b91c3b8508969016ab9e383f75c9bcce2090b1a1da386c1049bd2bbc"
            ]
          }
        ], 
        "publisher": {
          "location": "Berlin, Heidelberg", 
          "name": "Springer Berlin Heidelberg", 
          "type": "Organisation"
        }, 
        "sameAs": [
          "https://doi.org/10.1007/978-3-642-15561-1_11", 
          "https://app.dimensions.ai/details/publication/pub.1045344996"
        ], 
        "sdDataset": "chapters", 
        "sdDatePublished": "2019-04-16T08:20", 
        "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/v90/0000000362_0000000362/records_87117_00000001.jsonl", 
        "type": "Chapter", 
        "url": "https://link.springer.com/10.1007%2F978-3-642-15561-1_11"
      }
    ]
     

    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.10.1007/978-3-642-15561-1_11'

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

    curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1007/978-3-642-15561-1_11'

    Turtle is a human-readable linked data format.

    curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/978-3-642-15561-1_11'

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

    curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/978-3-642-15561-1_11'


     

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

    161 TRIPLES      23 PREDICATES      49 URIs      20 LITERALS      8 BLANK NODES

    Subject Predicate Object
    1 sg:pub.10.1007/978-3-642-15561-1_11 schema:about anzsrc-for:17
    2 anzsrc-for:1701
    3 schema:author Nac906efe206141619188ae3169bbcfd1
    4 schema:citation sg:pub.10.1007/s10107-010-0420-4
    5 sg:pub.10.1007/s11263-006-9794-4
    6 sg:pub.10.1023/b:visi.0000029664.99615.94
    7 https://doi.org/10.1109/cvpr.2006.264
    8 https://doi.org/10.1109/cvpr.2006.68
    9 https://doi.org/10.1109/cvpr.2007.383266
    10 https://doi.org/10.1109/cvpr.2008.4587598
    11 https://doi.org/10.1109/cvpr.2009.5206663
    12 https://doi.org/10.1109/cvpr.2009.5206757
    13 https://doi.org/10.1109/cvpr.2009.5206848
    14 https://doi.org/10.1109/cvpr.2010.5539914
    15 https://doi.org/10.1109/cvpr.2010.5539949
    16 https://doi.org/10.1109/iccv.2009.5459167
    17 https://doi.org/10.1109/iccv.2009.5459172
    18 https://doi.org/10.1109/iccv.2009.5459203
    19 https://doi.org/10.1109/iccv.2009.5459257
    20 https://doi.org/10.1109/iccv.2009.5459354
    21 https://doi.org/10.1109/iccv.2009.5459432
    22 https://doi.org/10.1109/iccvw.2009.5457703
    23 https://doi.org/10.1109/tpami.2008.128
    24 https://doi.org/10.1109/tpami.2009.132
    25 https://doi.org/10.1145/1150402.1150429
    26 schema:datePublished 2010
    27 schema:datePublishedReg 2010-01-01
    28 schema:description The Fisher kernel (FK) is a generic framework which combines the benefits of generative and discriminative approaches. In the context of image classification the FK was shown to extend the popular bag-of-visual-words (BOV) by going beyond count statistics. However, in practice, this enriched representation has not yet shown its superiority over the BOV. In the first part we show that with several well-motivated modifications over the original framework we can boost the accuracy of the FK. On PASCAL VOC 2007 we increase the Average Precision (AP) from 47.9% to 58.3%. Similarly, we demonstrate state-of-the-art accuracy on CalTech 256. A major advantage is that these results are obtained using only SIFT descriptors and costless linear classifiers. Equipped with this representation, we can now explore image classification on a larger scale. In the second part, as an application, we compare two abundant resources of labeled images to learn classifiers: ImageNet and Flickr groups. In an evaluation involving hundreds of thousands of training images we show that classifiers learned on Flickr groups perform surprisingly well (although they were not intended for this purpose) and that they can complement classifiers learned on more carefully annotated datasets.
    29 schema:editor Nf6a25b1eba244db5b41735876db318a7
    30 schema:genre chapter
    31 schema:inLanguage en
    32 schema:isAccessibleForFree true
    33 schema:isPartOf N7888fb0c31594b9ebafd34c7c6afa237
    34 schema:name Improving the Fisher Kernel for Large-Scale Image Classification
    35 schema:pagination 143-156
    36 schema:productId N1493ecc63a4744119d5d2216fea273cf
    37 N74e5c9e7dbea42829fb4848d1b8b2ce8
    38 Na296ba50a38f4c06b1a3c3c61c720ea2
    39 schema:publisher N5cf37266ccd548c7a0746cee6d643da3
    40 schema:sameAs https://app.dimensions.ai/details/publication/pub.1045344996
    41 https://doi.org/10.1007/978-3-642-15561-1_11
    42 schema:sdDatePublished 2019-04-16T08:20
    43 schema:sdLicense https://scigraph.springernature.com/explorer/license/
    44 schema:sdPublisher N0334429d097448c39add07afc08230bb
    45 schema:url https://link.springer.com/10.1007%2F978-3-642-15561-1_11
    46 sgo:license sg:explorer/license/
    47 sgo:sdDataset chapters
    48 rdf:type schema:Chapter
    49 N0334429d097448c39add07afc08230bb schema:name Springer Nature - SN SciGraph project
    50 rdf:type schema:Organization
    51 N1493ecc63a4744119d5d2216fea273cf schema:name dimensions_id
    52 schema:value pub.1045344996
    53 rdf:type schema:PropertyValue
    54 N22356bd7b70f48dfb8c7ec94e588b072 schema:name Xerox Research Centre Europe (XRCE)
    55 rdf:type schema:Organization
    56 N2c22ce48f5ac4526a59e7e93ed748825 schema:name Xerox Research Centre Europe (XRCE)
    57 rdf:type schema:Organization
    58 N465add12c9bb408383e8cc1b928f7047 rdf:first sg:person.010600141141.73
    59 rdf:rest rdf:nil
    60 N50749ee269a4401f830f7d56e5252ac9 rdf:first Nbc86c62eaacd433a9bd654da13229c2f
    61 rdf:rest N80cf873523f04d0ab8153d7be0ef84d0
    62 N5cf37266ccd548c7a0746cee6d643da3 schema:location Berlin, Heidelberg
    63 schema:name Springer Berlin Heidelberg
    64 rdf:type schema:Organisation
    65 N6f2eb9fbd4af4405924a7cc31c6f32f5 schema:familyName Daniilidis
    66 schema:givenName Kostas
    67 rdf:type schema:Person
    68 N74e5c9e7dbea42829fb4848d1b8b2ce8 schema:name readcube_id
    69 schema:value d7ff81f0b91c3b8508969016ab9e383f75c9bcce2090b1a1da386c1049bd2bbc
    70 rdf:type schema:PropertyValue
    71 N7888fb0c31594b9ebafd34c7c6afa237 schema:isbn 978-3-642-15560-4
    72 978-3-642-15561-1
    73 schema:name Computer Vision – ECCV 2010
    74 rdf:type schema:Book
    75 N80cf873523f04d0ab8153d7be0ef84d0 rdf:first Nbb02c91e57b3474995bfb5612fea9d7f
    76 rdf:rest rdf:nil
    77 Na296ba50a38f4c06b1a3c3c61c720ea2 schema:name doi
    78 schema:value 10.1007/978-3-642-15561-1_11
    79 rdf:type schema:PropertyValue
    80 Nac906efe206141619188ae3169bbcfd1 rdf:first sg:person.01320142425.13
    81 rdf:rest Nc67edde0f9e54c62b0bb622c715c1887
    82 Nbb02c91e57b3474995bfb5612fea9d7f schema:familyName Paragios
    83 schema:givenName Nikos
    84 rdf:type schema:Person
    85 Nbc86c62eaacd433a9bd654da13229c2f schema:familyName Maragos
    86 schema:givenName Petros
    87 rdf:type schema:Person
    88 Nc67edde0f9e54c62b0bb622c715c1887 rdf:first sg:person.01136743706.30
    89 rdf:rest N465add12c9bb408383e8cc1b928f7047
    90 Nf6a25b1eba244db5b41735876db318a7 rdf:first N6f2eb9fbd4af4405924a7cc31c6f32f5
    91 rdf:rest N50749ee269a4401f830f7d56e5252ac9
    92 Nff04bbf0aa6541ee8d7be492d599027b schema:name Xerox Research Centre Europe (XRCE)
    93 rdf:type schema:Organization
    94 anzsrc-for:17 schema:inDefinedTermSet anzsrc-for:
    95 schema:name Psychology and Cognitive Sciences
    96 rdf:type schema:DefinedTerm
    97 anzsrc-for:1701 schema:inDefinedTermSet anzsrc-for:
    98 schema:name Psychology
    99 rdf:type schema:DefinedTerm
    100 sg:person.010600141141.73 schema:affiliation N22356bd7b70f48dfb8c7ec94e588b072
    101 schema:familyName Mensink
    102 schema:givenName Thomas
    103 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010600141141.73
    104 rdf:type schema:Person
    105 sg:person.01136743706.30 schema:affiliation Nff04bbf0aa6541ee8d7be492d599027b
    106 schema:familyName Sánchez
    107 schema:givenName Jorge
    108 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01136743706.30
    109 rdf:type schema:Person
    110 sg:person.01320142425.13 schema:affiliation N2c22ce48f5ac4526a59e7e93ed748825
    111 schema:familyName Perronnin
    112 schema:givenName Florent
    113 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01320142425.13
    114 rdf:type schema:Person
    115 sg:pub.10.1007/s10107-010-0420-4 schema:sameAs https://app.dimensions.ai/details/publication/pub.1050541291
    116 https://doi.org/10.1007/s10107-010-0420-4
    117 rdf:type schema:CreativeWork
    118 sg:pub.10.1007/s11263-006-9794-4 schema:sameAs https://app.dimensions.ai/details/publication/pub.1008205152
    119 https://doi.org/10.1007/s11263-006-9794-4
    120 rdf:type schema:CreativeWork
    121 sg:pub.10.1023/b:visi.0000029664.99615.94 schema:sameAs https://app.dimensions.ai/details/publication/pub.1052687286
    122 https://doi.org/10.1023/b:visi.0000029664.99615.94
    123 rdf:type schema:CreativeWork
    124 https://doi.org/10.1109/cvpr.2006.264 schema:sameAs https://app.dimensions.ai/details/publication/pub.1093301542
    125 rdf:type schema:CreativeWork
    126 https://doi.org/10.1109/cvpr.2006.68 schema:sameAs https://app.dimensions.ai/details/publication/pub.1094512911
    127 rdf:type schema:CreativeWork
    128 https://doi.org/10.1109/cvpr.2007.383266 schema:sameAs https://app.dimensions.ai/details/publication/pub.1095559903
    129 rdf:type schema:CreativeWork
    130 https://doi.org/10.1109/cvpr.2008.4587598 schema:sameAs https://app.dimensions.ai/details/publication/pub.1093888066
    131 rdf:type schema:CreativeWork
    132 https://doi.org/10.1109/cvpr.2009.5206663 schema:sameAs https://app.dimensions.ai/details/publication/pub.1094077345
    133 rdf:type schema:CreativeWork
    134 https://doi.org/10.1109/cvpr.2009.5206757 schema:sameAs https://app.dimensions.ai/details/publication/pub.1095180230
    135 rdf:type schema:CreativeWork
    136 https://doi.org/10.1109/cvpr.2009.5206848 schema:sameAs https://app.dimensions.ai/details/publication/pub.1095689025
    137 rdf:type schema:CreativeWork
    138 https://doi.org/10.1109/cvpr.2010.5539914 schema:sameAs https://app.dimensions.ai/details/publication/pub.1094512169
    139 rdf:type schema:CreativeWork
    140 https://doi.org/10.1109/cvpr.2010.5539949 schema:sameAs https://app.dimensions.ai/details/publication/pub.1094875983
    141 rdf:type schema:CreativeWork
    142 https://doi.org/10.1109/iccv.2009.5459167 schema:sameAs https://app.dimensions.ai/details/publication/pub.1094765820
    143 rdf:type schema:CreativeWork
    144 https://doi.org/10.1109/iccv.2009.5459172 schema:sameAs https://app.dimensions.ai/details/publication/pub.1095690739
    145 rdf:type schema:CreativeWork
    146 https://doi.org/10.1109/iccv.2009.5459203 schema:sameAs https://app.dimensions.ai/details/publication/pub.1094402362
    147 rdf:type schema:CreativeWork
    148 https://doi.org/10.1109/iccv.2009.5459257 schema:sameAs https://app.dimensions.ai/details/publication/pub.1094965859
    149 rdf:type schema:CreativeWork
    150 https://doi.org/10.1109/iccv.2009.5459354 schema:sameAs https://app.dimensions.ai/details/publication/pub.1094040462
    151 rdf:type schema:CreativeWork
    152 https://doi.org/10.1109/iccv.2009.5459432 schema:sameAs https://app.dimensions.ai/details/publication/pub.1093378856
    153 rdf:type schema:CreativeWork
    154 https://doi.org/10.1109/iccvw.2009.5457703 schema:sameAs https://app.dimensions.ai/details/publication/pub.1093567598
    155 rdf:type schema:CreativeWork
    156 https://doi.org/10.1109/tpami.2008.128 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061743490
    157 rdf:type schema:CreativeWork
    158 https://doi.org/10.1109/tpami.2009.132 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061743716
    159 rdf:type schema:CreativeWork
    160 https://doi.org/10.1145/1150402.1150429 schema:sameAs https://app.dimensions.ai/details/publication/pub.1044904927
    161 rdf:type schema:CreativeWork
     




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


    ...