Image Classification Using Super-Vector Coding of Local Image Descriptors View Full Text


Ontology type: schema:Chapter      Open Access: True


Chapter Info

DATE

2010

AUTHORS

Xi Zhou , Kai Yu , Tong Zhang , Thomas S. Huang

ABSTRACT

This paper introduces a new framework for image classification using local visual descriptors. The pipeline first performs a nonlinear feature transformation on descriptors, then aggregates the results together to form image-level representations, and finally applies a classification model. For all the three steps we suggest novel solutions which make our approach appealing in theory, more scalable in computation, and transparent in classification. Our experiments demonstrate that the proposed classification method achieves state-of-the-art accuracy on the well-known PASCAL benchmarks. More... »

PAGES

141-154

References to SciGraph publications

  • 2003. Bhattacharyya and Expected Likelihood Kernels in LEARNING THEORY AND KERNEL MACHINES
  • 2010-06. The Pascal Visual Object Classes (VOC) Challenge in INTERNATIONAL JOURNAL OF COMPUTER VISION
  • 2008. A New Baseline for Image Annotation in COMPUTER VISION – ECCV 2008
  • Book

    TITLE

    Computer Vision – ECCV 2010

    ISBN

    978-3-642-15554-3
    978-3-642-15555-0

    Author Affiliations

    Identifiers

    URI

    http://scigraph.springernature.com/pub.10.1007/978-3-642-15555-0_11

    DOI

    http://dx.doi.org/10.1007/978-3-642-15555-0_11

    DIMENSIONS

    https://app.dimensions.ai/details/publication/pub.1044213993


    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": {
              "name": [
                "Dept. of ECE, University of Illnois at Urbana-Champaign"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Zhou", 
            "givenName": "Xi", 
            "id": "sg:person.013513202775.26", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.013513202775.26"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "name": [
                "NEC Laboratories America, Cupertino, CA"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Yu", 
            "givenName": "Kai", 
            "id": "sg:person.015365401647.88", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.015365401647.88"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Rutgers University", 
              "id": "https://www.grid.ac/institutes/grid.430387.b", 
              "name": [
                "Department of Statistics, Rutgers University"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Zhang", 
            "givenName": "Tong", 
            "id": "sg:person.015165710332.53", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.015165710332.53"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "name": [
                "Dept. of ECE, University of Illnois at Urbana-Champaign"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Huang", 
            "givenName": "Thomas S.", 
            "id": "sg:person.011374774067.03", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.011374774067.03"
            ], 
            "type": "Person"
          }
        ], 
        "citation": [
          {
            "id": "https://doi.org/10.1016/j.cviu.2005.09.012", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1004784969"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-3-540-88690-7_24", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1009765396", 
              "https://doi.org/10.1007/978-3-540-88690-7_24"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-3-540-88690-7_24", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1009765396", 
              "https://doi.org/10.1007/978-3-540-88690-7_24"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-3-540-45167-9_6", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1013863491", 
              "https://doi.org/10.1007/978-3-540-45167-9_6"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/s11263-009-0275-4", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1014796149", 
              "https://doi.org/10.1007/s11263-009-0275-4"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/s11263-009-0275-4", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1014796149", 
              "https://doi.org/10.1007/s11263-009-0275-4"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1145/1282280.1282340", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1033635059"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1145/1273496.1273592", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1052861703"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/5.726791", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1061179979"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/cvpr.2008.4587633", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1093176609"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/cvpr.2006.301", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1093880961"
            ], 
            "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.2009.5459435", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1094696425"
            ], 
            "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.2005.16", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1095244523"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/cvpr.2005.16", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1095244523"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/iccv.2007.4408875", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1095251623"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/cvpr.2005.254", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1095271325"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/cvpr.2005.254", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1095271325"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/cvpr.2007.383266", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1095559903"
            ], 
            "type": "CreativeWork"
          }
        ], 
        "datePublished": "2010", 
        "datePublishedReg": "2010-01-01", 
        "description": "This paper introduces a new framework for image classification using local visual descriptors. The pipeline first performs a nonlinear feature transformation on descriptors, then aggregates the results together to form image-level representations, and finally applies a classification model. For all the three steps we suggest novel solutions which make our approach appealing in theory, more scalable in computation, and transparent in classification. Our experiments demonstrate that the proposed classification method achieves state-of-the-art accuracy on the well-known PASCAL benchmarks.", 
        "editor": [
          {
            "familyName": "Daniilidis", 
            "givenName": "Kostas", 
            "type": "Person"
          }, 
          {
            "familyName": "Maragos", 
            "givenName": "Petros", 
            "type": "Person"
          }, 
          {
            "familyName": "Paragios", 
            "givenName": "Nikos", 
            "type": "Person"
          }
        ], 
        "genre": "chapter", 
        "id": "sg:pub.10.1007/978-3-642-15555-0_11", 
        "inLanguage": [
          "en"
        ], 
        "isAccessibleForFree": true, 
        "isPartOf": {
          "isbn": [
            "978-3-642-15554-3", 
            "978-3-642-15555-0"
          ], 
          "name": "Computer Vision \u2013 ECCV 2010", 
          "type": "Book"
        }, 
        "name": "Image Classification Using Super-Vector Coding of Local Image Descriptors", 
        "pagination": "141-154", 
        "productId": [
          {
            "name": "dimensions_id", 
            "type": "PropertyValue", 
            "value": [
              "pub.1044213993"
            ]
          }, 
          {
            "name": "doi", 
            "type": "PropertyValue", 
            "value": [
              "10.1007/978-3-642-15555-0_11"
            ]
          }, 
          {
            "name": "readcube_id", 
            "type": "PropertyValue", 
            "value": [
              "d29af1b681c14b39bdc2d58bd39f0f343d77ff3c9d4ab569393ba8991cc78551"
            ]
          }
        ], 
        "publisher": {
          "location": "Berlin, Heidelberg", 
          "name": "Springer Berlin Heidelberg", 
          "type": "Organisation"
        }, 
        "sameAs": [
          "https://doi.org/10.1007/978-3-642-15555-0_11", 
          "https://app.dimensions.ai/details/publication/pub.1044213993"
        ], 
        "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%2F978-3-642-15555-0_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.10.1007/978-3-642-15555-0_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.10.1007/978-3-642-15555-0_11'

    Turtle is a human-readable linked data format.

    curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/978-3-642-15555-0_11'

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

    curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/978-3-642-15555-0_11'


     

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

    153 TRIPLES      23 PREDICATES      43 URIs      20 LITERALS      8 BLANK NODES

    Subject Predicate Object
    1 sg:pub.10.1007/978-3-642-15555-0_11 schema:about anzsrc-for:08
    2 anzsrc-for:0801
    3 schema:author N2f35fb32ef7e45f480a84f2768b6a29e
    4 schema:citation sg:pub.10.1007/978-3-540-45167-9_6
    5 sg:pub.10.1007/978-3-540-88690-7_24
    6 sg:pub.10.1007/s11263-009-0275-4
    7 https://doi.org/10.1016/j.cviu.2005.09.012
    8 https://doi.org/10.1109/5.726791
    9 https://doi.org/10.1109/cvpr.2005.16
    10 https://doi.org/10.1109/cvpr.2005.254
    11 https://doi.org/10.1109/cvpr.2006.301
    12 https://doi.org/10.1109/cvpr.2006.68
    13 https://doi.org/10.1109/cvpr.2007.383266
    14 https://doi.org/10.1109/cvpr.2008.4587633
    15 https://doi.org/10.1109/cvpr.2009.5206757
    16 https://doi.org/10.1109/iccv.2007.4408875
    17 https://doi.org/10.1109/iccv.2009.5459435
    18 https://doi.org/10.1145/1273496.1273592
    19 https://doi.org/10.1145/1282280.1282340
    20 schema:datePublished 2010
    21 schema:datePublishedReg 2010-01-01
    22 schema:description This paper introduces a new framework for image classification using local visual descriptors. The pipeline first performs a nonlinear feature transformation on descriptors, then aggregates the results together to form image-level representations, and finally applies a classification model. For all the three steps we suggest novel solutions which make our approach appealing in theory, more scalable in computation, and transparent in classification. Our experiments demonstrate that the proposed classification method achieves state-of-the-art accuracy on the well-known PASCAL benchmarks.
    23 schema:editor Nc48b09b11f8e4793a595b30e6a59c27b
    24 schema:genre chapter
    25 schema:inLanguage en
    26 schema:isAccessibleForFree true
    27 schema:isPartOf N964154158fd1420e9ec521d6b7e56d48
    28 schema:name Image Classification Using Super-Vector Coding of Local Image Descriptors
    29 schema:pagination 141-154
    30 schema:productId N11c0d22e0c4b4e5f90c21a042fda69ab
    31 N25739bd6ca3b438692876f620f03a11f
    32 N4b561978900f41d1aaac7f73ef6a39b1
    33 schema:publisher N5ff4258e302048c794a305ef4460ece7
    34 schema:sameAs https://app.dimensions.ai/details/publication/pub.1044213993
    35 https://doi.org/10.1007/978-3-642-15555-0_11
    36 schema:sdDatePublished 2019-04-16T08:20
    37 schema:sdLicense https://scigraph.springernature.com/explorer/license/
    38 schema:sdPublisher N5f972bd8bb064628b91f75ec99bf949c
    39 schema:url https://link.springer.com/10.1007%2F978-3-642-15555-0_11
    40 sgo:license sg:explorer/license/
    41 sgo:sdDataset chapters
    42 rdf:type schema:Chapter
    43 N0e0bed466453444580b62e5d1d322281 rdf:first N709ad79baa7e42bbbdcb62993f84d997
    44 rdf:rest rdf:nil
    45 N11c0d22e0c4b4e5f90c21a042fda69ab schema:name dimensions_id
    46 schema:value pub.1044213993
    47 rdf:type schema:PropertyValue
    48 N25739bd6ca3b438692876f620f03a11f schema:name doi
    49 schema:value 10.1007/978-3-642-15555-0_11
    50 rdf:type schema:PropertyValue
    51 N2ec42387342b4c838cf4c6a9ac0c12ca schema:name NEC Laboratories America, Cupertino, CA
    52 rdf:type schema:Organization
    53 N2f35fb32ef7e45f480a84f2768b6a29e rdf:first sg:person.013513202775.26
    54 rdf:rest Nc982d664f9cf45dd91ac0b90275b48cb
    55 N33bb475d5b6c471cb54c54f937278d03 schema:name Dept. of ECE, University of Illnois at Urbana-Champaign
    56 rdf:type schema:Organization
    57 N4b561978900f41d1aaac7f73ef6a39b1 schema:name readcube_id
    58 schema:value d29af1b681c14b39bdc2d58bd39f0f343d77ff3c9d4ab569393ba8991cc78551
    59 rdf:type schema:PropertyValue
    60 N5f972bd8bb064628b91f75ec99bf949c schema:name Springer Nature - SN SciGraph project
    61 rdf:type schema:Organization
    62 N5ff4258e302048c794a305ef4460ece7 schema:location Berlin, Heidelberg
    63 schema:name Springer Berlin Heidelberg
    64 rdf:type schema:Organisation
    65 N663829b62b334d1b97b8f7955699019d rdf:first sg:person.011374774067.03
    66 rdf:rest rdf:nil
    67 N680ee8b404cc4dfc97c758a7cfa008b7 schema:familyName Daniilidis
    68 schema:givenName Kostas
    69 rdf:type schema:Person
    70 N709ad79baa7e42bbbdcb62993f84d997 schema:familyName Paragios
    71 schema:givenName Nikos
    72 rdf:type schema:Person
    73 N7984326eae6b44f08db9b82ac5d7ea5e schema:familyName Maragos
    74 schema:givenName Petros
    75 rdf:type schema:Person
    76 N964154158fd1420e9ec521d6b7e56d48 schema:isbn 978-3-642-15554-3
    77 978-3-642-15555-0
    78 schema:name Computer Vision – ECCV 2010
    79 rdf:type schema:Book
    80 N9ed1476af74845789de20d28d80d618e rdf:first N7984326eae6b44f08db9b82ac5d7ea5e
    81 rdf:rest N0e0bed466453444580b62e5d1d322281
    82 Nb7c868ea4445461287f68f55c68254d5 rdf:first sg:person.015165710332.53
    83 rdf:rest N663829b62b334d1b97b8f7955699019d
    84 Nc48b09b11f8e4793a595b30e6a59c27b rdf:first N680ee8b404cc4dfc97c758a7cfa008b7
    85 rdf:rest N9ed1476af74845789de20d28d80d618e
    86 Nc982d664f9cf45dd91ac0b90275b48cb rdf:first sg:person.015365401647.88
    87 rdf:rest Nb7c868ea4445461287f68f55c68254d5
    88 Nd0c96993ac864859b67384da460ce8fc schema:name Dept. of ECE, University of Illnois at Urbana-Champaign
    89 rdf:type schema:Organization
    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.011374774067.03 schema:affiliation Nd0c96993ac864859b67384da460ce8fc
    97 schema:familyName Huang
    98 schema:givenName Thomas S.
    99 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.011374774067.03
    100 rdf:type schema:Person
    101 sg:person.013513202775.26 schema:affiliation N33bb475d5b6c471cb54c54f937278d03
    102 schema:familyName Zhou
    103 schema:givenName Xi
    104 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.013513202775.26
    105 rdf:type schema:Person
    106 sg:person.015165710332.53 schema:affiliation https://www.grid.ac/institutes/grid.430387.b
    107 schema:familyName Zhang
    108 schema:givenName Tong
    109 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.015165710332.53
    110 rdf:type schema:Person
    111 sg:person.015365401647.88 schema:affiliation N2ec42387342b4c838cf4c6a9ac0c12ca
    112 schema:familyName Yu
    113 schema:givenName Kai
    114 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.015365401647.88
    115 rdf:type schema:Person
    116 sg:pub.10.1007/978-3-540-45167-9_6 schema:sameAs https://app.dimensions.ai/details/publication/pub.1013863491
    117 https://doi.org/10.1007/978-3-540-45167-9_6
    118 rdf:type schema:CreativeWork
    119 sg:pub.10.1007/978-3-540-88690-7_24 schema:sameAs https://app.dimensions.ai/details/publication/pub.1009765396
    120 https://doi.org/10.1007/978-3-540-88690-7_24
    121 rdf:type schema:CreativeWork
    122 sg:pub.10.1007/s11263-009-0275-4 schema:sameAs https://app.dimensions.ai/details/publication/pub.1014796149
    123 https://doi.org/10.1007/s11263-009-0275-4
    124 rdf:type schema:CreativeWork
    125 https://doi.org/10.1016/j.cviu.2005.09.012 schema:sameAs https://app.dimensions.ai/details/publication/pub.1004784969
    126 rdf:type schema:CreativeWork
    127 https://doi.org/10.1109/5.726791 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061179979
    128 rdf:type schema:CreativeWork
    129 https://doi.org/10.1109/cvpr.2005.16 schema:sameAs https://app.dimensions.ai/details/publication/pub.1095244523
    130 rdf:type schema:CreativeWork
    131 https://doi.org/10.1109/cvpr.2005.254 schema:sameAs https://app.dimensions.ai/details/publication/pub.1095271325
    132 rdf:type schema:CreativeWork
    133 https://doi.org/10.1109/cvpr.2006.301 schema:sameAs https://app.dimensions.ai/details/publication/pub.1093880961
    134 rdf:type schema:CreativeWork
    135 https://doi.org/10.1109/cvpr.2006.68 schema:sameAs https://app.dimensions.ai/details/publication/pub.1094512911
    136 rdf:type schema:CreativeWork
    137 https://doi.org/10.1109/cvpr.2007.383266 schema:sameAs https://app.dimensions.ai/details/publication/pub.1095559903
    138 rdf:type schema:CreativeWork
    139 https://doi.org/10.1109/cvpr.2008.4587633 schema:sameAs https://app.dimensions.ai/details/publication/pub.1093176609
    140 rdf:type schema:CreativeWork
    141 https://doi.org/10.1109/cvpr.2009.5206757 schema:sameAs https://app.dimensions.ai/details/publication/pub.1095180230
    142 rdf:type schema:CreativeWork
    143 https://doi.org/10.1109/iccv.2007.4408875 schema:sameAs https://app.dimensions.ai/details/publication/pub.1095251623
    144 rdf:type schema:CreativeWork
    145 https://doi.org/10.1109/iccv.2009.5459435 schema:sameAs https://app.dimensions.ai/details/publication/pub.1094696425
    146 rdf:type schema:CreativeWork
    147 https://doi.org/10.1145/1273496.1273592 schema:sameAs https://app.dimensions.ai/details/publication/pub.1052861703
    148 rdf:type schema:CreativeWork
    149 https://doi.org/10.1145/1282280.1282340 schema:sameAs https://app.dimensions.ai/details/publication/pub.1033635059
    150 rdf:type schema:CreativeWork
    151 https://www.grid.ac/institutes/grid.430387.b schema:alternateName Rutgers University
    152 schema:name Department of Statistics, Rutgers University
    153 rdf:type schema:Organization
     




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


    ...