{"id":"https://openalex.org/W2063049279","doi":"https://doi.org/10.1145/1014052.1014135","title":"Automatic multimedia cross-modal correlation discovery","display_name":"Automatic multimedia cross-modal correlation discovery","publication_year":2004,"publication_date":"2004-08-22","ids":{"openalex":"https://openalex.org/W2063049279","doi":"https://doi.org/10.1145/1014052.1014135","mag":"2063049279"},"language":"en","primary_location":{"id":"doi:10.1145/1014052.1014135","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1014052.1014135","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the tenth ACM SIGKDD international conference on Knowledge discovery and data mining","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://repository.bilkent.edu.tr/bitstreams/abae85d8-966e-4ab5-b7b4-feb1362370b7/download","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5083649006","display_name":"Jia-Yu Pan","orcid":"https://orcid.org/0009-0005-6700-908X"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jia-Yu Pan","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA","Carnegie-Mellon University, Pittsburgh, PA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie-Mellon University, Pittsburgh, PA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087619194","display_name":"Hyung-Jeong Yang","orcid":"https://orcid.org/0000-0003-3024-5060"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hyung-Jeong Yang","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA","Carnegie-Mellon University, Pittsburgh, PA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie-Mellon University, Pittsburgh, PA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035605036","display_name":"Christos Faloutsos","orcid":"https://orcid.org/0000-0003-2996-9790"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Christos Faloutsos","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA","Carnegie-Mellon University, Pittsburgh, PA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie-Mellon University, Pittsburgh, PA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048195433","display_name":"P\u0131nar Duygulu","orcid":"https://orcid.org/0000-0002-6420-2838"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pinar Duygulu","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA","Carnegie-Mellon University, Pittsburgh, PA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie-Mellon University, Pittsburgh, PA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5083649006"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":10.219,"has_fulltext":true,"cited_by_count":488,"citation_normalized_percentile":{"value":0.98545523,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"653","last_page":"658"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9994000196456909,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9994000196456909,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9988999962806702,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9987000226974487,"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":0.833984911441803},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.7332963347434998},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.5541313886642456},{"id":"https://openalex.org/keywords/scripting-language","display_name":"Scripting language","score":0.5457630753517151},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4783850908279419},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46948203444480896},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.4660687744617462},{"id":"https://openalex.org/keywords/clips","display_name":"CLIPS","score":0.4467869997024536},{"id":"https://openalex.org/keywords/spectral-clustering","display_name":"Spectral clustering","score":0.4207395315170288},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.35626861453056335},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.33463722467422485},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3324376046657562},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.31809014081954956}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.833984911441803},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.7332963347434998},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5541313886642456},{"id":"https://openalex.org/C61423126","wikidata":"https://www.wikidata.org/wiki/Q187432","display_name":"Scripting language","level":2,"score":0.5457630753517151},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4783850908279419},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46948203444480896},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.4660687744617462},{"id":"https://openalex.org/C2778739407","wikidata":"https://www.wikidata.org/wiki/Q165372","display_name":"CLIPS","level":2,"score":0.4467869997024536},{"id":"https://openalex.org/C105611402","wikidata":"https://www.wikidata.org/wiki/Q2976589","display_name":"Spectral clustering","level":3,"score":0.4207395315170288},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.35626861453056335},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.33463722467422485},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3324376046657562},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.31809014081954956},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.1145/1014052.1014135","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1014052.1014135","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the tenth ACM SIGKDD international conference on Knowledge discovery and data mining","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.bilkent.edu.tr:11693/27429","is_oa":true,"landing_page_url":"http://hdl.handle.net/11693/27429","pdf_url":"https://repository.bilkent.edu.tr/bitstreams/abae85d8-966e-4ab5-b7b4-feb1362370b7/download","source":{"id":"https://openalex.org/S4306400079","display_name":"Bilkent University Institutional Repository (Bilkent University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I168864056","host_organization_name":"Bilkent University","host_organization_lineage":["https://openalex.org/I168864056"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"KDD-2004 - Proceedings of the Tenth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining","raw_type":"Conference Paper"},{"id":"pmh:oai:repository.cmu.edu:compsci-1539","is_oa":false,"landing_page_url":"http://repository.cmu.edu/compsci/538","pdf_url":null,"source":{"id":"https://openalex.org/S4306400668","display_name":"Research Showcase @ Carnegie Mellon University (Carnegie Mellon University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I74973139","host_organization_name":"Carnegie Mellon University","host_organization_lineage":["https://openalex.org/I74973139"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Computer Science Department","raw_type":"text"},{"id":"pmh:doi:10.1184/r1/6603758","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Journal contribution"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.58.3860","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.58.3860","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/%7Eduygulu/papers/KDD2004.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.72.4131","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.72.4131","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.cmu.edu/~christos/PUBLICATIONS/kdd04-gCap.pdf","raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:repository.bilkent.edu.tr:11693/27429","is_oa":true,"landing_page_url":"http://hdl.handle.net/11693/27429","pdf_url":"https://repository.bilkent.edu.tr/bitstreams/abae85d8-966e-4ab5-b7b4-feb1362370b7/download","source":{"id":"https://openalex.org/S4306400079","display_name":"Bilkent University Institutional Repository (Bilkent University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I168864056","host_organization_name":"Bilkent University","host_organization_lineage":["https://openalex.org/I168864056"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"KDD-2004 - Proceedings of the Tenth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining","raw_type":"Conference Paper"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6800000071525574}],"awards":[{"id":"https://openalex.org/G1042556623","display_name":"Collaborative Research: NetMine: Finding Patterns in Network Data","funder_award_id":"0209107","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G1915539989","display_name":"U.S.-Japan Joint Seminar: A Data Mining-Based Approach to Semantic Integration of Stream Data","funder_award_id":"0318547","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3938009581","display_name":"ITR:    Providing Intuitive Access to Human Motion Databases","funder_award_id":"0205224","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6681146981","display_name":"ITR Collaborative Research: Indexing, Retrieval, and Use of Large Motion Databases","funder_award_id":"0326322","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G695767982","display_name":"SENSORS:    Placement and Operation of an Environmental Sensor Network to Facilitate Decision Making Regarding Drinking Water Quality and Security","funder_award_id":"0329549","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7027821119","display_name":"ITR/IM: Capturing, Coordinating and Remembering Human Experience","funder_award_id":"0121641","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8700874257","display_name":"Information Technology Research (ITR):  Next-Generation Bio-Molecular Imaging and Information Discovery","funder_award_id":"0331657","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320322348","display_name":"Korea Science and Engineering Foundation","ror":"https://ror.org/013aysd81"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W2063049279.pdf"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W79946180","https://openalex.org/W1487950779","https://openalex.org/W1514107797","https://openalex.org/W1536481811","https://openalex.org/W1540386283","https://openalex.org/W1555118771","https://openalex.org/W1575084925","https://openalex.org/W1666447063","https://openalex.org/W1934863104","https://openalex.org/W1969228515","https://openalex.org/W1981202432","https://openalex.org/W2062170755","https://openalex.org/W2063392856","https://openalex.org/W2066636486","https://openalex.org/W2080051508","https://openalex.org/W2121947440","https://openalex.org/W2131620262","https://openalex.org/W2137918516","https://openalex.org/W2148512378","https://openalex.org/W2150692003","https://openalex.org/W2167064216","https://openalex.org/W2170344111","https://openalex.org/W2293605478","https://openalex.org/W2769133055","https://openalex.org/W4285719527","https://openalex.org/W6603267525","https://openalex.org/W6630727257","https://openalex.org/W6679274366","https://openalex.org/W6684913354"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W3088136942","https://openalex.org/W2949362007","https://openalex.org/W2775506363","https://openalex.org/W4290852288","https://openalex.org/W4388893791","https://openalex.org/W4283207562","https://openalex.org/W2963177403","https://openalex.org/W2330246314","https://openalex.org/W2949522393"],"abstract_inverted_index":{"Given":[0],"an":[1],"image":[2,102],"(or":[3],"video":[4,34],"clip,":[5],"or":[6],"audio":[7],"song),":[8],"how":[9],"do":[10],"we":[11,78],"automatically":[12],"assign":[13],"keywords":[14],"to":[15,21,52,71,116],"it?":[16],"The":[17],"general":[18],"problem":[19],"is":[20],"find":[22],"correlations":[23],"across":[24],"the":[25,91,99],"media":[26],"in":[27,120],"a":[28,47,80],"collection":[29],"of":[30,104],"multimedia":[31,73],"objects":[32],"like":[33],"clips,":[35],"with":[36,90],"colors,":[37],"and/or":[38,40,42],"motion,":[39],"audio,":[41],"text":[43],"scripts.":[44],"We":[45,94],"propose":[46],"novel,":[48],"graph-based":[49],"approach,":[50],"\"MMG\",":[51],"discover":[53],"such":[54],"cross-modal":[55],"correlations.Our":[56],"\"MMG\"":[57],"method":[58],"requires":[59],"no":[60,62,64],"tuning,":[61],"clustering,":[63],"user-determined":[65],"constants;":[66],"it":[67,87,108],"can":[68],"be":[69],"applied":[70],"any":[72],"collection,":[74],"as":[75,77],"long":[76],"have":[79],"similarity":[81],"function":[82],"for":[83],"each":[84],"medium;":[85],"and":[86],"scales":[88],"linearly":[89],"database":[92,103],"size.":[93],"report":[95],"auto-captioning":[96],"experiments":[97],"on":[98],"\"standard\"":[100],"Corel":[101],"680":[105],"MB,":[106],"where":[107],"outperforms":[109],"domain":[110],"specific,":[111],"fine-tuned":[112],"methods":[113],"by":[114],"up":[115],"10":[117],"percentage":[118],"points":[119],"captioning":[121],"accuracy":[122],"(50%":[123],"relative":[124],"improvement).":[125]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":18},{"year":2022,"cited_by_count":12},{"year":2021,"cited_by_count":16},{"year":2020,"cited_by_count":20},{"year":2019,"cited_by_count":21},{"year":2018,"cited_by_count":25},{"year":2017,"cited_by_count":34},{"year":2016,"cited_by_count":31},{"year":2015,"cited_by_count":31},{"year":2014,"cited_by_count":33},{"year":2013,"cited_by_count":33},{"year":2012,"cited_by_count":40}],"updated_date":"2026-04-29T09:16:38.111599","created_date":"2025-10-10T00:00:00"}