Categorizing Visual Contents by Matching Visual “Keywords” View Full Text


Ontology type: schema:Chapter     


Chapter Info

DATE

2002-07-02

AUTHORS

Joo-Hwee Lim

ABSTRACT

In this paper, we propose a three-layer visual information processing architecture for extracting concise non-textual descriptions from visual contents. These coded descriptions capture both local saliencies and spatial configurations present in visual contents via prototypical visual tokens called visual “keywords”. Categorization of images and video shots represented by keyframes can be performed by comparing their coded descriptions. We demonstrate our proposed architecture in natural scene image categorization that outperforms methods which use aggregate measures of low-level features. More... »

PAGES

367-374

References to SciGraph publications

  • 1996-06. Photobook: Content-based manipulation of image databases in INTERNATIONAL JOURNAL OF COMPUTER VISION
  • Book

    TITLE

    Visual Information and Information Systems

    ISBN

    978-3-540-66079-8
    978-3-540-48762-3

    Identifiers

    URI

    http://scigraph.springernature.com/pub.10.1007/3-540-48762-x_46

    DOI

    http://dx.doi.org/10.1007/3-540-48762-x_46

    DIMENSIONS

    https://app.dimensions.ai/details/publication/pub.1042663072


    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": [
                "Information-Base Functions KRDL Lab, RWCP, 21 Heng Mui Kent Terrace, S(119613), Singapore"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Lim", 
            "givenName": "Joo-Hwee", 
            "id": "sg:person.0607463760.21", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0607463760.21"
            ], 
            "type": "Person"
          }
        ], 
        "citation": [
          {
            "id": "https://doi.org/10.1117/12.171772", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1001640412"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1002/(sici)1097-4571(199009)41:6<391::aid-asi1>3.0.co;2-9", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1012153938"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1117/12.143648", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1015213336"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/bf00123143", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1024066299", 
              "https://doi.org/10.1007/bf00123143"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/bf00123143", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1024066299", 
              "https://doi.org/10.1007/bf00123143"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1117/12.234785", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1042501265"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1145/243199.243276", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1044163989"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1145/218380.218454", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1046858645"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1147/rd.422.0233", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1063182324"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/iccv.1998.710772", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1094088849"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/cvpr.1997.609453", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1094877086"
            ], 
            "type": "CreativeWork"
          }
        ], 
        "datePublished": "2002-07-02", 
        "datePublishedReg": "2002-07-02", 
        "description": "In this paper, we propose a three-layer visual information processing architecture for extracting concise non-textual descriptions from visual contents. These coded descriptions capture both local saliencies and spatial configurations present in visual contents via prototypical visual tokens called visual \u201ckeywords\u201d. Categorization of images and video shots represented by keyframes can be performed by comparing their coded descriptions. We demonstrate our proposed architecture in natural scene image categorization that outperforms methods which use aggregate measures of low-level features.", 
        "editor": [
          {
            "familyName": "Huijsmans", 
            "givenName": "Dionysius P.", 
            "type": "Person"
          }, 
          {
            "familyName": "Smeulders", 
            "givenName": "Arnold W. M.", 
            "type": "Person"
          }
        ], 
        "genre": "chapter", 
        "id": "sg:pub.10.1007/3-540-48762-x_46", 
        "inLanguage": [
          "en"
        ], 
        "isAccessibleForFree": false, 
        "isPartOf": {
          "isbn": [
            "978-3-540-66079-8", 
            "978-3-540-48762-3"
          ], 
          "name": "Visual Information and Information Systems", 
          "type": "Book"
        }, 
        "name": "Categorizing Visual Contents by Matching Visual \u201cKeywords\u201d", 
        "pagination": "367-374", 
        "productId": [
          {
            "name": "doi", 
            "type": "PropertyValue", 
            "value": [
              "10.1007/3-540-48762-x_46"
            ]
          }, 
          {
            "name": "readcube_id", 
            "type": "PropertyValue", 
            "value": [
              "cb38d23d429f506690050bc5287afa4327a18e61a54ef9251de608eb564dc66b"
            ]
          }, 
          {
            "name": "dimensions_id", 
            "type": "PropertyValue", 
            "value": [
              "pub.1042663072"
            ]
          }
        ], 
        "publisher": {
          "location": "Berlin, Heidelberg", 
          "name": "Springer Berlin Heidelberg", 
          "type": "Organisation"
        }, 
        "sameAs": [
          "https://doi.org/10.1007/3-540-48762-x_46", 
          "https://app.dimensions.ai/details/publication/pub.1042663072"
        ], 
        "sdDataset": "chapters", 
        "sdDatePublished": "2019-04-16T05:47", 
        "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/v90/0000000347_0000000347/records_89814_00000001.jsonl", 
        "type": "Chapter", 
        "url": "https://link.springer.com/10.1007%2F3-540-48762-X_46"
      }
    ]
     

    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.10.1007/3-540-48762-x_46'

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

    curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1007/3-540-48762-x_46'

    Turtle is a human-readable linked data format.

    curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/3-540-48762-x_46'

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

    curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/3-540-48762-x_46'


     

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

    100 TRIPLES      23 PREDICATES      36 URIs      19 LITERALS      8 BLANK NODES

    Subject Predicate Object
    1 sg:pub.10.1007/3-540-48762-x_46 schema:about anzsrc-for:08
    2 anzsrc-for:0801
    3 schema:author N43180b3271aa499bafc35840c06d514b
    4 schema:citation sg:pub.10.1007/bf00123143
    5 https://doi.org/10.1002/(sici)1097-4571(199009)41:6<391::aid-asi1>3.0.co;2-9
    6 https://doi.org/10.1109/cvpr.1997.609453
    7 https://doi.org/10.1109/iccv.1998.710772
    8 https://doi.org/10.1117/12.143648
    9 https://doi.org/10.1117/12.171772
    10 https://doi.org/10.1117/12.234785
    11 https://doi.org/10.1145/218380.218454
    12 https://doi.org/10.1145/243199.243276
    13 https://doi.org/10.1147/rd.422.0233
    14 schema:datePublished 2002-07-02
    15 schema:datePublishedReg 2002-07-02
    16 schema:description In this paper, we propose a three-layer visual information processing architecture for extracting concise non-textual descriptions from visual contents. These coded descriptions capture both local saliencies and spatial configurations present in visual contents via prototypical visual tokens called visual “keywords”. Categorization of images and video shots represented by keyframes can be performed by comparing their coded descriptions. We demonstrate our proposed architecture in natural scene image categorization that outperforms methods which use aggregate measures of low-level features.
    17 schema:editor Nfc62d49716af43a3a8008bcec65d0d84
    18 schema:genre chapter
    19 schema:inLanguage en
    20 schema:isAccessibleForFree false
    21 schema:isPartOf Neafe4271480f4a748446e90e86e1edcd
    22 schema:name Categorizing Visual Contents by Matching Visual “Keywords”
    23 schema:pagination 367-374
    24 schema:productId N49a7af42eeab4376b12ec55fe5b38096
    25 N5e65b82c5d034de49167e7a416e2d6a2
    26 Nf7e9ac6a1ffc44978642fdc0d1a38b83
    27 schema:publisher N7bd892e4b576481b994d7b687594e5c2
    28 schema:sameAs https://app.dimensions.ai/details/publication/pub.1042663072
    29 https://doi.org/10.1007/3-540-48762-x_46
    30 schema:sdDatePublished 2019-04-16T05:47
    31 schema:sdLicense https://scigraph.springernature.com/explorer/license/
    32 schema:sdPublisher Nb3e10c8b3fba49668ba44104b90aec18
    33 schema:url https://link.springer.com/10.1007%2F3-540-48762-X_46
    34 sgo:license sg:explorer/license/
    35 sgo:sdDataset chapters
    36 rdf:type schema:Chapter
    37 N17d2bbc0ba2a427ea40fcf5b6cc5c354 rdf:first N67c78a27ee3446b2b799a91963cfbbd8
    38 rdf:rest rdf:nil
    39 N43180b3271aa499bafc35840c06d514b rdf:first sg:person.0607463760.21
    40 rdf:rest rdf:nil
    41 N49a7af42eeab4376b12ec55fe5b38096 schema:name readcube_id
    42 schema:value cb38d23d429f506690050bc5287afa4327a18e61a54ef9251de608eb564dc66b
    43 rdf:type schema:PropertyValue
    44 N4df05e468cbc4585b8c7256bfeab95b0 schema:name Information-Base Functions KRDL Lab, RWCP, 21 Heng Mui Kent Terrace, S(119613), Singapore
    45 rdf:type schema:Organization
    46 N5e65b82c5d034de49167e7a416e2d6a2 schema:name doi
    47 schema:value 10.1007/3-540-48762-x_46
    48 rdf:type schema:PropertyValue
    49 N67c78a27ee3446b2b799a91963cfbbd8 schema:familyName Smeulders
    50 schema:givenName Arnold W. M.
    51 rdf:type schema:Person
    52 N7bd892e4b576481b994d7b687594e5c2 schema:location Berlin, Heidelberg
    53 schema:name Springer Berlin Heidelberg
    54 rdf:type schema:Organisation
    55 Na017eb2352884a44a4024e4aa634b41e schema:familyName Huijsmans
    56 schema:givenName Dionysius P.
    57 rdf:type schema:Person
    58 Nb3e10c8b3fba49668ba44104b90aec18 schema:name Springer Nature - SN SciGraph project
    59 rdf:type schema:Organization
    60 Neafe4271480f4a748446e90e86e1edcd schema:isbn 978-3-540-48762-3
    61 978-3-540-66079-8
    62 schema:name Visual Information and Information Systems
    63 rdf:type schema:Book
    64 Nf7e9ac6a1ffc44978642fdc0d1a38b83 schema:name dimensions_id
    65 schema:value pub.1042663072
    66 rdf:type schema:PropertyValue
    67 Nfc62d49716af43a3a8008bcec65d0d84 rdf:first Na017eb2352884a44a4024e4aa634b41e
    68 rdf:rest N17d2bbc0ba2a427ea40fcf5b6cc5c354
    69 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
    70 schema:name Information and Computing Sciences
    71 rdf:type schema:DefinedTerm
    72 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
    73 schema:name Artificial Intelligence and Image Processing
    74 rdf:type schema:DefinedTerm
    75 sg:person.0607463760.21 schema:affiliation N4df05e468cbc4585b8c7256bfeab95b0
    76 schema:familyName Lim
    77 schema:givenName Joo-Hwee
    78 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0607463760.21
    79 rdf:type schema:Person
    80 sg:pub.10.1007/bf00123143 schema:sameAs https://app.dimensions.ai/details/publication/pub.1024066299
    81 https://doi.org/10.1007/bf00123143
    82 rdf:type schema:CreativeWork
    83 https://doi.org/10.1002/(sici)1097-4571(199009)41:6<391::aid-asi1>3.0.co;2-9 schema:sameAs https://app.dimensions.ai/details/publication/pub.1012153938
    84 rdf:type schema:CreativeWork
    85 https://doi.org/10.1109/cvpr.1997.609453 schema:sameAs https://app.dimensions.ai/details/publication/pub.1094877086
    86 rdf:type schema:CreativeWork
    87 https://doi.org/10.1109/iccv.1998.710772 schema:sameAs https://app.dimensions.ai/details/publication/pub.1094088849
    88 rdf:type schema:CreativeWork
    89 https://doi.org/10.1117/12.143648 schema:sameAs https://app.dimensions.ai/details/publication/pub.1015213336
    90 rdf:type schema:CreativeWork
    91 https://doi.org/10.1117/12.171772 schema:sameAs https://app.dimensions.ai/details/publication/pub.1001640412
    92 rdf:type schema:CreativeWork
    93 https://doi.org/10.1117/12.234785 schema:sameAs https://app.dimensions.ai/details/publication/pub.1042501265
    94 rdf:type schema:CreativeWork
    95 https://doi.org/10.1145/218380.218454 schema:sameAs https://app.dimensions.ai/details/publication/pub.1046858645
    96 rdf:type schema:CreativeWork
    97 https://doi.org/10.1145/243199.243276 schema:sameAs https://app.dimensions.ai/details/publication/pub.1044163989
    98 rdf:type schema:CreativeWork
    99 https://doi.org/10.1147/rd.422.0233 schema:sameAs https://app.dimensions.ai/details/publication/pub.1063182324
    100 rdf:type schema:CreativeWork
     




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


    ...