{"id":"https://openalex.org/W2141713975","doi":"https://doi.org/10.1109/icme.2002.1035607","title":"Semantic indexing of multimedia using audio, text and visual cues","display_name":"Semantic indexing of multimedia using audio, text and visual cues","publication_year":2003,"publication_date":"2003-06-25","ids":{"openalex":"https://openalex.org/W2141713975","doi":"https://doi.org/10.1109/icme.2002.1035607","mag":"2141713975"},"language":"en","primary_location":{"id":"doi:10.1109/icme.2002.1035607","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme.2002.1035607","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings. IEEE International Conference on Multimedia and Expo","raw_type":"proceedings-article"},"type":"conference-paper","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/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"]},{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"G. Iyengar","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","IBM TJ Watson Research Center; Yorktown Heights, NY USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]},{"raw_affiliation_string":"IBM TJ Watson Research Center; Yorktown Heights, NY USA","institution_ids":["https://openalex.org/I1341412227"]}]},{"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"]},{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"H. Nock","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","IBM TJ Watson Research Center; Yorktown Heights, NY USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]},{"raw_affiliation_string":"IBM TJ Watson Research Center; Yorktown Heights, NY USA","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111579153","display_name":"C. Neti","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"]},{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"C. Neti","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","IBM TJ Watson Research Center; Yorktown Heights, NY USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]},{"raw_affiliation_string":"IBM TJ Watson Research Center; Yorktown Heights, NY USA","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071900309","display_name":"Martin Franz","orcid":"https://orcid.org/0000-0001-6697-3022"},"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"]},{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"M. Franz","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","IBM TJ Watson Research Center; Yorktown Heights, NY USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]},{"raw_affiliation_string":"IBM TJ Watson Research Center; Yorktown Heights, NY USA","institution_ids":["https://openalex.org/I1341412227"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.1789,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":{"value":0.93219018,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"2","issue":null,"first_page":"369","last_page":"372"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":1.0,"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":1.0,"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":0.9995999932289124,"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":0.996399998664856,"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":0.8630846738815308},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.792631983757019},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.7081618905067444},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.51112300157547},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4660288989543915},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.42574232816696167},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3653465509414673},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.334133505821228}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8630846738815308},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.792631983757019},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.7081618905067444},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.51112300157547},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4660288989543915},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.42574232816696167},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3653465509414673},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.334133505821228},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"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/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme.2002.1035607","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme.2002.1035607","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings. IEEE International Conference on Multimedia and Expo","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6800000071525574}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306101","display_name":"National Aeronautics and Space Administration","ror":"https://ror.org/027ka1x80"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W3158926","https://openalex.org/W1513593019","https://openalex.org/W1545046063","https://openalex.org/W1931334728","https://openalex.org/W2020387553","https://openalex.org/W2038721957","https://openalex.org/W2057613716","https://openalex.org/W2120912160","https://openalex.org/W2128838222","https://openalex.org/W2136846563","https://openalex.org/W2138043589","https://openalex.org/W2343867458","https://openalex.org/W6630573528","https://openalex.org/W6664934753"],"related_works":["https://openalex.org/W154501238","https://openalex.org/W1568422127","https://openalex.org/W2043194666","https://openalex.org/W2083498763","https://openalex.org/W1993625798","https://openalex.org/W2118916824","https://openalex.org/W2008725429","https://openalex.org/W2145203730","https://openalex.org/W2008019426","https://openalex.org/W2547724331","https://openalex.org/W2131193678","https://openalex.org/W2132488042","https://openalex.org/W2184650817","https://openalex.org/W2168322624","https://openalex.org/W2154218008","https://openalex.org/W3143239048","https://openalex.org/W2166853537","https://openalex.org/W2117278977","https://openalex.org/W2061163603","https://openalex.org/W2389798139"],"abstract_inverted_index":{"We":[0],"describe":[1],"methods":[2],"for":[3,62],"automatic":[4,63],"labeling":[5,64],"of":[6,16,44,65],"high-level":[7],"semantic":[8,47],"concepts":[9,48],"in":[10],"documentary":[11],"style":[12],"videos.":[13],"The":[14,30],"emphasis":[15],"this":[17],"paper":[18],"is":[19],"on":[20,24],"audio":[21],"processing":[22],"and":[23,56],"fusing":[25],"information":[26,58],"from":[27,59],"multiple":[28],"modalities.":[29],"work":[31,35],"described":[32],"represents":[33],"initial":[34],"towards":[36],"a":[37,42,66,76],"trainable":[38],"system":[39],"that":[40,72],"acquires":[41],"collection":[43],"generic":[45],"\"intermediate\"":[46],"across":[49],"modalities":[50,61],"(such":[51],"as":[52],"audio,":[53],"video,":[54],"text)":[55],"combines":[57],"these":[60],"\"high-level\"":[67],"concept.":[68],"Initial":[69],"results":[70],"suggest":[71],"multi-modal":[73],"fusion":[74],"achieves":[75],"12.5%":[77],"relative":[78],"improvement":[79],"over":[80],"the":[81],"best":[82],"unimodal":[83],"model.":[84]},"counts_by_year":[{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
