{"id":"https://openalex.org/W2000636201","doi":"https://doi.org/10.1145/1101149.1101154","title":"Joint visual-text modeling for automatic retrieval of multimedia documents","display_name":"Joint visual-text modeling for automatic retrieval of multimedia documents","publication_year":2005,"publication_date":"2005-11-06","ids":{"openalex":"https://openalex.org/W2000636201","doi":"https://doi.org/10.1145/1101149.1101154","mag":"2000636201"},"language":"en","primary_location":{"id":"doi:10.1145/1101149.1101154","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1101149.1101154","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 13th annual ACM international conference on Multimedia","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://works.bepress.com/r_manmatha/35/download/","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5022650481","display_name":"Giridharan Iyengar","orcid":null},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"G. Iyengar","raw_affiliation_strings":["IBM TJ Watson Research Center","IBM TJ Watson Research Center,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM TJ Watson Research Center","institution_ids":["https://openalex.org/I1341412227"]},{"raw_affiliation_string":"IBM TJ Watson Research Center,","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048195433","display_name":"P\u0131nar Duygulu","orcid":"https://orcid.org/0000-0002-6420-2838"},"institutions":[{"id":"https://openalex.org/I168864056","display_name":"Bilkent University","ror":"https://ror.org/02vh8a032","country_code":"TR","type":"education","lineage":["https://openalex.org/I168864056"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"P. Duygulu","raw_affiliation_strings":["Bilkent University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bilkent University","institution_ids":["https://openalex.org/I168864056"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071639289","display_name":"Siwei Feng","orcid":"https://orcid.org/0000-0002-4286-4793"},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"S. Feng","raw_affiliation_strings":["University of Massachusetts, Amherst","University of Massachusetts: Amherst#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Massachusetts, Amherst","institution_ids":["https://openalex.org/I24603500"]},{"raw_affiliation_string":"University of Massachusetts: Amherst#TAB#","institution_ids":["https://openalex.org/I24603500"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047784245","display_name":"Pavel Ircing","orcid":"https://orcid.org/0000-0001-6967-1687"},"institutions":[{"id":"https://openalex.org/I110263422","display_name":"University West","ror":"https://ror.org/0257kt353","country_code":"SE","type":"education","lineage":["https://openalex.org/I110263422"]},{"id":"https://openalex.org/I92715842","display_name":"University of West Bohemia in Pilsen","ror":"https://ror.org/040t43x18","country_code":"CZ","type":"education","lineage":["https://openalex.org/I92715842"]}],"countries":["CZ","SE"],"is_corresponding":false,"raw_author_name":"P. Ircing","raw_affiliation_strings":["Univ. West Bohemia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Univ. West Bohemia","institution_ids":["https://openalex.org/I92715842","https://openalex.org/I110263422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014580424","display_name":"Sanjeev Khudanpur","orcid":"https://orcid.org/0000-0001-5976-0897"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"S. P. Khudanpur","raw_affiliation_strings":["Johns Hopkins University","Johns Hopkins University ("],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Johns Hopkins University (","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008875255","display_name":"Dietrich Klakow","orcid":"https://orcid.org/0000-0002-4147-9690"},"institutions":[{"id":"https://openalex.org/I91712215","display_name":"Saarland University","ror":"https://ror.org/01jdpyv68","country_code":"DE","type":"education","lineage":["https://openalex.org/I91712215"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"D. Klakow","raw_affiliation_strings":["Saarland University","saarland university"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Saarland University","institution_ids":["https://openalex.org/I91712215"]},{"raw_affiliation_string":"saarland university","institution_ids":["https://openalex.org/I91712215"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070661197","display_name":"Matthew R. Krause","orcid":"https://orcid.org/0000-0002-1837-687X"},"institutions":[{"id":"https://openalex.org/I184565670","display_name":"Georgetown University","ror":"https://ror.org/05vzafd60","country_code":"US","type":"education","lineage":["https://openalex.org/I184565670"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"M. R. Krause","raw_affiliation_strings":["Georgetown University","GEORGETOWN UNIVERSITY"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgetown University","institution_ids":["https://openalex.org/I184565670"]},{"raw_affiliation_string":"GEORGETOWN UNIVERSITY","institution_ids":["https://openalex.org/I184565670"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055459215","display_name":"R. Manmatha","orcid":"https://orcid.org/0000-0003-2315-8583"},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"R. Manmatha","raw_affiliation_strings":["University of Massachusetts, Amherst","University of Massachusetts: Amherst#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Massachusetts, Amherst","institution_ids":["https://openalex.org/I24603500"]},{"raw_affiliation_string":"University of Massachusetts: Amherst#TAB#","institution_ids":["https://openalex.org/I24603500"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108291571","display_name":"Harriet J. Nock","orcid":null},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"H. J. Nock","raw_affiliation_strings":["IBM TJ Watson Research Center","IBM TJ Watson Research Center,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM TJ Watson Research Center","institution_ids":["https://openalex.org/I1341412227"]},{"raw_affiliation_string":"IBM TJ Watson Research Center,","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110535912","display_name":"Desislava Petkova","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"D. Petkova","raw_affiliation_strings":["Mt. Holyoke College"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mt. Holyoke College","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040183398","display_name":"Brock Pytlik","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"B. Pytlik","raw_affiliation_strings":["Johns Hopkins University","Johns Hopkins University ("],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Johns Hopkins University (","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036221896","display_name":"Paola Virga","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"P. Virga","raw_affiliation_strings":["Johns Hopkins University","Johns Hopkins University ("],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Johns Hopkins University (","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":5,"institutions_distinct_count":12,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.9818,"has_fulltext":true,"cited_by_count":44,"citation_normalized_percentile":{"value":0.9664798,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"21","last_page":"30"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8725779056549072},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.7045168280601501},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.6178695559501648},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.6169671416282654},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.5745334625244141},{"id":"https://openalex.org/keywords/text-retrieval","display_name":"Text retrieval","score":0.5467450022697449},{"id":"https://openalex.org/keywords/visual-word","display_name":"Visual Word","score":0.46431398391723633},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3781188726425171},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.332943856716156},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.32181334495544434},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.28213149309158325},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.16525089740753174}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8725779056549072},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.7045168280601501},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.6178695559501648},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.6169671416282654},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.5745334625244141},{"id":"https://openalex.org/C2985933255","wikidata":"https://www.wikidata.org/wiki/Q1638872","display_name":"Text retrieval","level":2,"score":0.5467450022697449},{"id":"https://openalex.org/C189391414","wikidata":"https://www.wikidata.org/wiki/Q7936579","display_name":"Visual Word","level":4,"score":0.46431398391723633},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3781188726425171},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.332943856716156},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.32181334495544434},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.28213149309158325},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.16525089740753174},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1145/1101149.1101154","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1101149.1101154","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 13th annual ACM international conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:works.bepress.com:r_manmatha-1069","is_oa":true,"landing_page_url":"https://works.bepress.com/r_manmatha/35","pdf_url":"https://works.bepress.com/r_manmatha/35/download/","source":{"id":"https://openalex.org/S4306402240","display_name":"ScholarWorks@UMassAmherst (University of Massachusetts Amherst)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I24603500","host_organization_name":"University of Massachusetts Amherst","host_organization_lineage":["https://openalex.org/I24603500"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"R. Manmatha","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.152.3748","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.152.3748","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://ciir.cs.umass.edu/pubfiles/mm-397.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.214.9842","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.214.9842","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.clsp.jhu.edu/ws2004/groups/ws04vstxt/documents/ACMpaper.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.65.3741","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.65.3741","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.bilkent.edu.tr/~duygulu/papers/ACM-MM2005.pdf","raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:works.bepress.com:r_manmatha-1069","is_oa":true,"landing_page_url":"https://works.bepress.com/r_manmatha/35","pdf_url":"https://works.bepress.com/r_manmatha/35/download/","source":{"id":"https://openalex.org/S4306402240","display_name":"ScholarWorks@UMassAmherst (University of Massachusetts Amherst)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I24603500","host_organization_name":"University of Massachusetts Amherst","host_organization_lineage":["https://openalex.org/I24603500"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"R. Manmatha","raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7699999809265137}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2000636201.pdf","grobid_xml":"https://content.openalex.org/works/W2000636201.grobid-xml"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W4508078","https://openalex.org/W98731357","https://openalex.org/W1531474894","https://openalex.org/W1590275315","https://openalex.org/W1666447063","https://openalex.org/W1671203680","https://openalex.org/W1773803948","https://openalex.org/W2001792610","https://openalex.org/W2006969979","https://openalex.org/W2018560257","https://openalex.org/W2068905009","https://openalex.org/W2081580037","https://openalex.org/W2093390569","https://openalex.org/W2106129249","https://openalex.org/W2123504579","https://openalex.org/W2129664360","https://openalex.org/W2137918516","https://openalex.org/W2141080726","https://openalex.org/W2141159588","https://openalex.org/W2156336347","https://openalex.org/W2160657477","https://openalex.org/W2979454998","https://openalex.org/W2998215494","https://openalex.org/W4206765718","https://openalex.org/W4243333943","https://openalex.org/W4285719527","https://openalex.org/W6635389295","https://openalex.org/W6637108112","https://openalex.org/W6637852806"],"related_works":["https://openalex.org/W73545470","https://openalex.org/W4224266612","https://openalex.org/W2383394264","https://openalex.org/W4320153225","https://openalex.org/W4293261942","https://openalex.org/W3125968744","https://openalex.org/W203959209","https://openalex.org/W2167701463","https://openalex.org/W2110287964","https://openalex.org/W204730171"],"abstract_inverted_index":{"In":[0,52],"this":[1,170],"paper":[2],"we":[3],"describe":[4],"a":[5,28,48,56,114],"novel":[6,29],"approach":[7],"for":[8,20],"jointly":[9],"modeling":[10],"the":[11,14,21,53,66,73,76,85,89,95,118,135,157,165],"text":[12,67,86,102],"and":[13,42,44,72,162],"visual":[15,77],"components":[16,33],"of":[17,23,69,97,142],"multimedia":[18],"documents":[19,41],"purpose":[22],"information":[24,106],"retrieval(IR).":[25],"We":[26,130],"propose":[27],"framework":[30],"where":[31],"individual":[32],"are":[34],"developed":[35],"to":[36],"model":[37],"different":[38],"relationships":[39],"between":[40,59,117],"queries":[43],"then":[45],"combined":[46],"into":[47],"joint":[49],"retrieval":[50,107],"framework.":[51],"state-of-the-art":[54],"systems,":[55,62],"late":[57],"combination":[58],"two":[60],"independent":[61],"one":[63],"analyzing":[64,75],"just":[65],"part":[68,78],"such":[70],"documents,":[71],"other":[74],"without":[79],"leveraging":[80],"any":[81,98,127],"knowledge":[82],"acquired":[83],"in":[84,105,121,124,153],"processing,":[87],"is":[88],"norm.":[90],"Such":[91],"systems":[92],"rarely":[93],"exceed":[94],"performance":[96,125,155],"single":[99,128],"modality":[100],"(i.e.":[101],"or":[103],"video)":[104],"tasks.":[108],"Our":[109,146],"experiments":[110],"indicate":[111],"that":[112],"allowing":[113],"rich":[115],"interaction":[116],"modalities":[119],"results":[120,133,147,167],"significant":[122],"improvement":[123,152],"over":[126,149,156],"modality.":[129],"demonstrate":[131,148],"these":[132],"using":[134],"TRECVID03":[136],"corpus,":[137],"which":[138],"comprises":[139],"120":[140],"hours":[141],"broadcast":[143],"news":[144],"videos.":[145],"14":[150],"%":[151],"IR":[154],"best":[158,166],"reported":[159,168],"text-only":[160],"baseline":[161],"ranks":[163],"amongst":[164],"on":[169],"corpus.":[171]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
