Ontology type: schema:ScholarlyArticle
2019-02
AUTHORSZhineng Chen, Wei Zhang, Bin Deng, Hongtao Xie, Xiaoyan Gu
ABSTRACTThis paper describes methods for automatically associating faces detected from multimedia documents with their names presented in the surrounding metadata. We consider the task in the image matching (IM) framework, where external Web facial images are automatically retrieved as the gallery face set of the names in advance, and a detected face is assigned to one of the names, or none of them, according to the association score between the two kinds of faces and constraints. Several important issues are investigated within the IM framework. In collecting Web facial images, beyond the basic scheme that use a celebrity name purely as the query to crawl facial images, a context-assisted image search method is proposed to enhance the relevance and discriminability of the retrieved faces. In constraint formulation, we propose an assigning-thresholding (AT) pipeline to uniformly ensure that the name-face correspondence is strictly one-to-one, and set low confidence associations as null assignments. In association score computation, we propose methods that jointly consider IM with the well-established graph-based association (GA) method at different stages, aiming at producing more accurate scores to benefit the association. Based on these efforts, an Accu-IM method performing the association as accurate as possible and a Fast-IM method performing the association in real-time are respective proposed. Extensive experiments on datasets of captioned News images and Web videos both demonstrate the advantages of the proposed efforts individually and jointly, which consistently provide improvement gains under different settings when compared with state-of-the-art methods. More... »
PAGES1-20
http://scigraph.springernature.com/pub.10.1007/s00530-017-0544-y
DOIhttp://dx.doi.org/10.1007/s00530-017-0544-y
DIMENSIONShttps://app.dimensions.ai/details/publication/pub.1084022569
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": "Institute of Automation",
"id": "https://www.grid.ac/institutes/grid.429126.a",
"name": [
"Institute of Automation, Chinese Academy of Sciences, 100190, Beijing, China"
],
"type": "Organization"
},
"familyName": "Chen",
"givenName": "Zhineng",
"id": "sg:person.012273373467.30",
"sameAs": [
"https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.012273373467.30"
],
"type": "Person"
},
{
"affiliation": {
"alternateName": "Institute of Information Engineering",
"id": "https://www.grid.ac/institutes/grid.458480.5",
"name": [
"Institute of Information Engineering, Chinese Academy of Sciences, 100093, Beijing, China"
],
"type": "Organization"
},
"familyName": "Zhang",
"givenName": "Wei",
"id": "sg:person.011075166225.46",
"sameAs": [
"https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.011075166225.46"
],
"type": "Person"
},
{
"affiliation": {
"alternateName": "Hunan University of Technology",
"id": "https://www.grid.ac/institutes/grid.411431.2",
"name": [
"School of Computer Science, Hunan University of Technology, 412007, Hunan, China"
],
"type": "Organization"
},
"familyName": "Deng",
"givenName": "Bin",
"id": "sg:person.010010301573.93",
"sameAs": [
"https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010010301573.93"
],
"type": "Person"
},
{
"affiliation": {
"alternateName": "Institute of Information Engineering",
"id": "https://www.grid.ac/institutes/grid.458480.5",
"name": [
"Institute of Information Engineering, Chinese Academy of Sciences, 100093, Beijing, China"
],
"type": "Organization"
},
"familyName": "Xie",
"givenName": "Hongtao",
"id": "sg:person.013416520456.02",
"sameAs": [
"https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.013416520456.02"
],
"type": "Person"
},
{
"affiliation": {
"alternateName": "Institute of Information Engineering",
"id": "https://www.grid.ac/institutes/grid.458480.5",
"name": [
"Institute of Information Engineering, Chinese Academy of Sciences, 100093, Beijing, China"
],
"type": "Organization"
},
"familyName": "Gu",
"givenName": "Xiaoyan",
"id": "sg:person.013471271203.97",
"sameAs": [
"https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.013471271203.97"
],
"type": "Person"
}
],
"citation": [
{
"id": "sg:pub.10.1007/978-3-319-04114-8_6",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1001243168",
"https://doi.org/10.1007/978-3-319-04114-8_6"
],
"type": "CreativeWork"
},
{
"id": "sg:pub.10.1007/s11263-011-0447-x",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1003839794",
"https://doi.org/10.1007/s11263-011-0447-x"
],
"type": "CreativeWork"
},
{
"id": "https://doi.org/10.1145/2072298.2071909",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1004907968"
],
"type": "CreativeWork"
},
{
"id": "https://doi.org/10.1145/1027527.1027666",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1008627092"
],
"type": "CreativeWork"
},
{
"id": "https://doi.org/10.1145/2072298.2072021",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1010863565"
],
"type": "CreativeWork"
},
{
"id": "https://doi.org/10.1016/j.patcog.2009.10.015",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1012125792"
],
"type": "CreativeWork"
},
{
"id": "https://doi.org/10.1145/2009916.2009989",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1014918028"
],
"type": "CreativeWork"
},
{
"id": "https://doi.org/10.1145/2488388.2488515",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1017435325"
],
"type": "CreativeWork"
},
{
"id": "https://doi.org/10.1145/1991996.1992038",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1018451511"
],
"type": "CreativeWork"
},
{
"id": "sg:pub.10.1007/s11390-014-1468-z",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1020853577",
"https://doi.org/10.1007/s11390-014-1468-z"
],
"type": "CreativeWork"
},
{
"id": "https://doi.org/10.1145/2600428.2609568",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1022304122"
],
"type": "CreativeWork"
},
{
"id": "https://doi.org/10.1145/954339.954342",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1024296753"
],
"type": "CreativeWork"
},
{
"id": "https://doi.org/10.1145/1459359.1459468",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1027779072"
],
"type": "CreativeWork"
},
{
"id": "https://doi.org/10.1145/2671188.2749401",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1028529103"
],
"type": "CreativeWork"
},
{
"id": "https://doi.org/10.1016/j.patcog.2011.12.018",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1032116297"
],
"type": "CreativeWork"
},
{
"id": "https://doi.org/10.1145/2647868.2654942",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1037093687"
],
"type": "CreativeWork"
},
{
"id": "https://doi.org/10.1145/2393347.2393383",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1037167092"
],
"type": "CreativeWork"
},
{
"id": "https://doi.org/10.1016/j.jvcir.2013.04.012",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1039974890"
],
"type": "CreativeWork"
},
{
"id": "https://doi.org/10.1145/1101149.1101155",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1041022634"
],
"type": "CreativeWork"
},
{
"id": "sg:pub.10.1007/978-3-319-48896-7_62",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1043016895",
"https://doi.org/10.1007/978-3-319-48896-7_62"
],
"type": "CreativeWork"
},
{
"id": "https://doi.org/10.1145/2461466.2461477",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1044261422"
],
"type": "CreativeWork"
},
{
"id": "https://doi.org/10.1145/1873951.1874162",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1044931210"
],
"type": "CreativeWork"
},
{
"id": "sg:pub.10.1007/s11042-010-0604-1",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1045673257",
"https://doi.org/10.1007/s11042-010-0604-1"
],
"type": "CreativeWork"
},
{
"id": "https://doi.org/10.1016/j.jvcir.2013.06.009",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1047336599"
],
"type": "CreativeWork"
},
{
"id": "https://doi.org/10.1109/93.752960",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1061248890"
],
"type": "CreativeWork"
},
{
"id": "https://doi.org/10.1109/jproc.2010.2044551",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1061297237"
],
"type": "CreativeWork"
},
{
"id": "https://doi.org/10.1109/mmul.2011.22",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1061410255"
],
"type": "CreativeWork"
},
{
"id": "https://doi.org/10.1109/tcsvt.2011.2148470",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1061575798"
],
"type": "CreativeWork"
},
{
"id": "https://doi.org/10.1109/tcsvt.2014.2319671",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1061576315"
],
"type": "CreativeWork"
},
{
"id": "https://doi.org/10.1109/tcsvt.2015.2504738",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1061576664"
],
"type": "CreativeWork"
},
{
"id": "https://doi.org/10.1109/tie.2012.2216237",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1061625777"
],
"type": "CreativeWork"
},
{
"id": "https://doi.org/10.1109/tip.2012.2236341",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1061643453"
],
"type": "CreativeWork"
},
{
"id": "https://doi.org/10.1109/tip.2016.2590321",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1061645118"
],
"type": "CreativeWork"
},
{
"id": "https://doi.org/10.1109/tip.2016.2601491",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1061645175"
],
"type": "CreativeWork"
},
{
"id": "https://doi.org/10.1109/tmm.2009.2030629",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1061697674"
],
"type": "CreativeWork"
},
{
"id": "https://doi.org/10.1109/tmm.2009.2036232",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1061697694"
],
"type": "CreativeWork"
},
{
"id": "https://doi.org/10.1109/tmm.2010.2050651",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1061697725"
],
"type": "CreativeWork"
},
{
"id": "https://doi.org/10.1109/tmm.2011.2165053",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1061697866"
],
"type": "CreativeWork"
},
{
"id": "https://doi.org/10.1109/tmm.2011.2167224",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1061697878"
],
"type": "CreativeWork"
},
{
"id": "https://doi.org/10.1109/tmm.2012.2186121",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1061697937"
],
"type": "CreativeWork"
},
{
"id": "https://doi.org/10.1109/tmm.2012.2188784",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1061697957"
],
"type": "CreativeWork"
},
{
"id": "https://doi.org/10.1109/tmm.2014.2305909",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1061698280"
],
"type": "CreativeWork"
},
{
"id": "https://doi.org/10.1109/tmm.2014.2306392",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1061698286"
],
"type": "CreativeWork"
},
{
"id": "https://doi.org/10.1109/tmm.2015.2419452",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1061698452"
],
"type": "CreativeWork"
},
{
"id": "https://doi.org/10.1109/tmm.2015.2440997",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1061698484"
],
"type": "CreativeWork"
},
{
"id": "https://doi.org/10.1109/tpami.2008.79",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1061743675"
],
"type": "CreativeWork"
},
{
"id": "https://doi.org/10.1109/tpami.2013.145",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1061744459"
],
"type": "CreativeWork"
},
{
"id": "https://doi.org/10.1109/iccv.2011.6126415",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1093226224"
],
"type": "CreativeWork"
},
{
"id": "https://doi.org/10.1109/cvpr.2013.462",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1093289883"
],
"type": "CreativeWork"
},
{
"id": "https://doi.org/10.1109/cvpr.2013.462",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1093289883"
],
"type": "CreativeWork"
},
{
"id": "https://doi.org/10.1109/iccv.2015.12",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1093359952"
],
"type": "CreativeWork"
},
{
"id": "https://doi.org/10.1109/iccv.2009.5459197",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1093361768"
],
"type": "CreativeWork"
},
{
"id": "https://doi.org/10.1109/iccv.2007.4409012",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1093419161"
],
"type": "CreativeWork"
},
{
"id": "https://doi.org/10.1109/icdm.2008.47",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1093446545"
],
"type": "CreativeWork"
},
{
"id": "https://doi.org/10.1109/cvpr.2004.1315253",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1093697819"
],
"type": "CreativeWork"
},
{
"id": "https://doi.org/10.1109/cvpr.2011.5995566",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1093814890"
],
"type": "CreativeWork"
},
{
"id": "https://doi.org/10.1109/icassp.2009.4959999",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1094419800"
],
"type": "CreativeWork"
},
{
"id": "https://doi.org/10.1109/afgr.2008.4813463",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1094556306"
],
"type": "CreativeWork"
},
{
"id": "https://doi.org/10.1109/fg.2015.7163083",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1094735660"
],
"type": "CreativeWork"
},
{
"id": "https://doi.org/10.1109/afgr.2008.4813381",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1095083975"
],
"type": "CreativeWork"
},
{
"id": "https://doi.org/10.1109/cvpr.2017.111",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1095851665"
],
"type": "CreativeWork"
},
{
"id": "https://doi.org/10.5244/c.20.92",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1099325911"
],
"type": "CreativeWork"
},
{
"id": "https://doi.org/10.1109/iccv.2017.524",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1100060531"
],
"type": "CreativeWork"
}
],
"datePublished": "2019-02",
"datePublishedReg": "2019-02-01",
"description": "This paper describes methods for automatically associating faces detected from multimedia documents with their names presented in the surrounding metadata. We consider the task in the image matching (IM) framework, where external Web facial images are automatically retrieved as the gallery face set of the names in advance, and a detected face is assigned to one of the names, or none of them, according to the association score between the two kinds of faces and constraints. Several important issues are investigated within the IM framework. In collecting Web facial images, beyond the basic scheme that use a celebrity name purely as the query to crawl facial images, a context-assisted image search method is proposed to enhance the relevance and discriminability of the retrieved faces. In constraint formulation, we propose an assigning-thresholding (AT) pipeline to uniformly ensure that the name-face correspondence is strictly one-to-one, and set low confidence associations as null assignments. In association score computation, we propose methods that jointly consider IM with the well-established graph-based association (GA) method at different stages, aiming at producing more accurate scores to benefit the association. Based on these efforts, an Accu-IM method performing the association as accurate as possible and a Fast-IM method performing the association in real-time are respective proposed. Extensive experiments on datasets of captioned News images and Web videos both demonstrate the advantages of the proposed efforts individually and jointly, which consistently provide improvement gains under different settings when compared with state-of-the-art methods.",
"genre": "research_article",
"id": "sg:pub.10.1007/s00530-017-0544-y",
"inLanguage": [
"en"
],
"isAccessibleForFree": false,
"isFundedItemOf": [
{
"id": "sg:grant.7201554",
"type": "MonetaryGrant"
},
{
"id": "sg:grant.7176731",
"type": "MonetaryGrant"
}
],
"isPartOf": [
{
"id": "sg:journal.1284647",
"issn": [
"0942-4962",
"1432-1882"
],
"name": "Multimedia Systems",
"type": "Periodical"
},
{
"issueNumber": "1",
"type": "PublicationIssue"
},
{
"type": "PublicationVolume",
"volumeNumber": "25"
}
],
"name": "Name-face association with web facial image supervision",
"pagination": "1-20",
"productId": [
{
"name": "readcube_id",
"type": "PropertyValue",
"value": [
"d19ca031eb85c6afa1ab4bd03d2b81c714d09595e695c84423a409b43ff77bcf"
]
},
{
"name": "doi",
"type": "PropertyValue",
"value": [
"10.1007/s00530-017-0544-y"
]
},
{
"name": "dimensions_id",
"type": "PropertyValue",
"value": [
"pub.1084022569"
]
}
],
"sameAs": [
"https://doi.org/10.1007/s00530-017-0544-y",
"https://app.dimensions.ai/details/publication/pub.1084022569"
],
"sdDataset": "articles",
"sdDatePublished": "2019-04-11T09:41",
"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/v90/0000000346_0000000346/records_99841_00000003.jsonl",
"type": "ScholarlyArticle",
"url": "https://link.springer.com/10.1007%2Fs00530-017-0544-y"
}
]Download the RDF metadata as: json-ld nt turtle xml License info
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/s00530-017-0544-y'
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/s00530-017-0544-y'
Turtle is a human-readable linked data format.
curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/s00530-017-0544-y'
RDF/XML is a standard XML format for linked data.
curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/s00530-017-0544-y'
This table displays all metadata directly associated to this object as RDF triples.
290 TRIPLES
21 PREDICATES
89 URIs
19 LITERALS
7 BLANK NODES