{"id":"https://openalex.org/W2056952330","doi":"https://doi.org/10.1145/1027527.1027665","title":"Optimal multimodal fusion for multimedia data analysis","display_name":"Optimal multimodal fusion for multimedia data analysis","publication_year":2004,"publication_date":"2004-10-10","ids":{"openalex":"https://openalex.org/W2056952330","doi":"https://doi.org/10.1145/1027527.1027665","mag":"2056952330"},"language":"en","primary_location":{"id":"doi:10.1145/1027527.1027665","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1027527.1027665","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 12th annual ACM international conference on Multimedia","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101541675","display_name":"Yi Wu","orcid":"https://orcid.org/0000-0001-6731-1346"},"institutions":[{"id":"https://openalex.org/I154570441","display_name":"University of California, Santa Barbara","ror":"https://ror.org/02t274463","country_code":"US","type":"education","lineage":["https://openalex.org/I154570441"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yi Wu","raw_affiliation_strings":["University of California Santa Barbara, Santa Barbara, CA","University of California, Santa Barbara Santa Barbara, CA#TAB#"],"affiliations":[{"raw_affiliation_string":"University of California Santa Barbara, Santa Barbara, CA","institution_ids":["https://openalex.org/I154570441"]},{"raw_affiliation_string":"University of California, Santa Barbara Santa Barbara, CA#TAB#","institution_ids":["https://openalex.org/I154570441"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013545831","display_name":"Edward Yi Chang","orcid":"https://orcid.org/0000-0003-1616-5240"},"institutions":[{"id":"https://openalex.org/I154570441","display_name":"University of California, Santa Barbara","ror":"https://ror.org/02t274463","country_code":"US","type":"education","lineage":["https://openalex.org/I154570441"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Edward Y. Chang","raw_affiliation_strings":["University of California Santa Barbara, Santa Barbara, CA","University of California, Santa Barbara Santa Barbara, CA#TAB#"],"affiliations":[{"raw_affiliation_string":"University of California Santa Barbara, Santa Barbara, CA","institution_ids":["https://openalex.org/I154570441"]},{"raw_affiliation_string":"University of California, Santa Barbara Santa Barbara, CA#TAB#","institution_ids":["https://openalex.org/I154570441"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101880377","display_name":"Kevin Chen\u2013Chuan Chang","orcid":"https://orcid.org/0000-0003-0997-6803"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kevin Chen-Chuan Chang","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, Urbana, IL","[University of Illinois at Urbana-Champaign,Urbana,IL]"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, Urbana, IL","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"[University of Illinois at Urbana-Champaign,Urbana,IL]","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5105523625","display_name":"John R. Smith","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":"John R. Smith","raw_affiliation_strings":["IBM T.J. Watson Research Center, Hawthorne, NY"],"affiliations":[{"raw_affiliation_string":"IBM T.J. Watson Research Center, Hawthorne, NY","institution_ids":["https://openalex.org/I1341412227"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101541675"],"corresponding_institution_ids":["https://openalex.org/I154570441"],"apc_list":null,"apc_paid":null,"fwci":16.2845,"has_fulltext":false,"cited_by_count":226,"citation_normalized_percentile":{"value":0.99477752,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"572","last_page":"579"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11309","display_name":"Music and Audio Processing","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.9902999997138977,"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/T10860","display_name":"Speech and Audio Processing","score":0.9891999959945679,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.8286718130111694},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.8047362565994263},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.5479405522346497},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.528829038143158},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5124555230140686},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.49272897839546204},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.47401127219200134},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4694727659225464},{"id":"https://openalex.org/keywords/curse-of-dimensionality","display_name":"Curse of dimensionality","score":0.4491528868675232},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.34892672300338745}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8286718130111694},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.8047362565994263},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.5479405522346497},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.528829038143158},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5124555230140686},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.49272897839546204},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.47401127219200134},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4694727659225464},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.4491528868675232},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.34892672300338745},{"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/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/1027527.1027665","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1027527.1027665","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 12th annual ACM international conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.800.5292","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.800.5292","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://oak.cs.ucla.edu/%7Emjwelch/multimedia/papers/p572-wu.pdf","raw_type":"text"},{"id":"pmh:oai:eprints.ucl.ac.uk.OAI2:1397998","is_oa":false,"landing_page_url":"http://discovery.ucl.ac.uk/1397998/","pdf_url":null,"source":{"id":"https://openalex.org/S4306400024","display_name":"UCL Discovery (University College London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I45129253","host_organization_name":"University College London","host_organization_lineage":["https://openalex.org/I45129253"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"     In: Schulzrinne, H and Dimitrova, N and Sasse, MA and Moon, SB and Lienhart, R, (eds.)   (pp. pp. 572-579).  ACM (2004)     ","raw_type":"Proceedings paper"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4099999964237213,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332178","display_name":"National Institute of Standards and Technology","ror":"https://ror.org/05xpvk416"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W1505600378","https://openalex.org/W1532684463","https://openalex.org/W1548950020","https://openalex.org/W1618905105","https://openalex.org/W1654865708","https://openalex.org/W1663369658","https://openalex.org/W1672197616","https://openalex.org/W1676820704","https://openalex.org/W1980048347","https://openalex.org/W2002505231","https://openalex.org/W2002604768","https://openalex.org/W2019502123","https://openalex.org/W2035782554","https://openalex.org/W2103110216","https://openalex.org/W2103116581","https://openalex.org/W2106488367","https://openalex.org/W2108384452","https://openalex.org/W2117086609","https://openalex.org/W2124101779","https://openalex.org/W2125972593","https://openalex.org/W2129927672","https://openalex.org/W2133069808","https://openalex.org/W2134206624","https://openalex.org/W2134737843","https://openalex.org/W2148694408","https://openalex.org/W2157236054","https://openalex.org/W2160066518","https://openalex.org/W2164899449","https://openalex.org/W2168818958","https://openalex.org/W2296661036","https://openalex.org/W3100344990","https://openalex.org/W4237171445","https://openalex.org/W4285719527","https://openalex.org/W4292023222","https://openalex.org/W6631862205","https://openalex.org/W6679756777","https://openalex.org/W6681538531","https://openalex.org/W6684447540","https://openalex.org/W7066396194"],"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/W2110287964","https://openalex.org/W2167701463","https://openalex.org/W4307407935"],"abstract_inverted_index":{"Considerable":[0],"research":[1,17],"has":[2,60],"been":[3,22,61],"devoted":[4],"to":[5,69,71,99],"utilizing":[6],"multimodal":[7],"features":[8,30],"for":[9],"better":[10],"understanding":[11],"multimedia":[12],"data.":[13],"However,":[14],"two":[15],"core":[16],"issues":[18],"have":[19],"not":[20],"yet":[21],"adequately":[23],"addressed.":[24],"First,":[25],"given":[26],"a":[27,56,78,141],"set":[28,57],"of":[29,45,58,104,123,144],"extracted":[31,37],"from":[32,38,88],"multiple":[33],"media":[34],"sources":[35],"(e.g.,":[36],"the":[39,51,92,101,110,145],"visual,":[40],"audio,":[41],"and":[42,125,130],"caption":[43],"track":[44],"videos),":[46],"how":[47,63],"do":[48,64],"we":[49,65,76,95,133],"determine":[50,100],"best":[52,66],"modalities?":[53],"Second,":[54],"once":[55],"modal-ities":[59],"identified,":[62],"fuse":[67],"them":[68],"map":[70],"se-mantics?":[72],"In":[73,91],"this":[74],"paper,":[75],"propose":[77],"two-step":[79,137],"approach.":[80],"The":[81],"first":[82],"step":[83],"finds":[84],"statistically":[85],"independent":[86],"modalities":[87],"raw":[89],"features.":[90],"second":[93],"step,":[94],"use":[96],"super-kernel":[97],"fusion":[98,118],"optimal":[102],"combination":[103],"individual":[105],"modalities.":[106],"We":[107],"carefully":[108],"ana-lyze":[109],"tradeoffs":[111],"between":[112],"three":[113,146],"design":[114,147],"factors":[115],"that":[116,135],"affect":[117],"performance:":[119],"modality":[120],"independence,":[121],"curse":[122],"dimensionality,":[124],"fusion-model":[126],"complexity.":[127],"Through":[128],"analytical":[129],"empirical":[131],"studies,":[132],"demonstrate":[134],"our":[136],"approach,":[138],"which":[139],"achieves":[140],"care-ful":[142],"balance":[143],"factors,":[148],"can":[149],"improve":[150],"class-prediction":[151],"accuracy":[152],"over":[153],"traditional":[154],"techniques.":[155]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":6},{"year":2016,"cited_by_count":7},{"year":2015,"cited_by_count":9},{"year":2014,"cited_by_count":12},{"year":2013,"cited_by_count":15},{"year":2012,"cited_by_count":24}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}