{"id":"https://openalex.org/W2095380808","doi":"https://doi.org/10.1145/1076034.1076097","title":"Automatic music video summarization based on audio-visual-text analysis and alignment","display_name":"Automatic music video summarization based on audio-visual-text analysis and alignment","publication_year":2005,"publication_date":"2005-08-15","ids":{"openalex":"https://openalex.org/W2095380808","doi":"https://doi.org/10.1145/1076034.1076097","mag":"2095380808"},"language":"en","primary_location":{"id":"doi:10.1145/1076034.1076097","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1076034.1076097","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th annual international ACM SIGIR conference on Research and development in information retrieval","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/A5022636178","display_name":"Changsheng Xu","orcid":"https://orcid.org/0000-0001-8343-9665"},"institutions":[{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Changsheng Xu","raw_affiliation_strings":["Institute for Infocomm Research, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research, Singapore","institution_ids":["https://openalex.org/I3005327000"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040075114","display_name":"Xi Shao","orcid":"https://orcid.org/0000-0002-2348-7515"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]},{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Xi Shao","raw_affiliation_strings":["Institute for Infocomm Research, Singapore and National University of Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research, Singapore and National University of Singapore, Singapore","institution_ids":["https://openalex.org/I3005327000","https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061102347","display_name":"Namunu C. Maddage","orcid":null},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]},{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Namunu C. Maddage","raw_affiliation_strings":["Institute for Infocomm Research, Singapore and National University of Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research, Singapore and National University of Singapore, Singapore","institution_ids":["https://openalex.org/I3005327000","https://openalex.org/I165932596"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016415049","display_name":"Mohan Kankanhalli","orcid":"https://orcid.org/0000-0002-4846-2015"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Mohan S. Kankanhalli","raw_affiliation_strings":["National University of Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":27,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"361","last_page":"368"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9991999864578247,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.9552000164985657,"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/lyrics","display_name":"Lyrics","score":0.9466272592544556},{"id":"https://openalex.org/keywords/automatic-summarization","display_name":"Automatic summarization","score":0.9097511172294617},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7993942499160767},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.7733813524246216},{"id":"https://openalex.org/keywords/audio-analyzer","display_name":"Audio analyzer","score":0.5991427898406982},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5660218000411987},{"id":"https://openalex.org/keywords/chorus","display_name":"Chorus","score":0.4948813319206238},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4764319062232971},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.4448445439338684},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.34965741634368896},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.2582331895828247},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.16961422562599182},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.07534188032150269},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.06829202175140381}],"concepts":[{"id":"https://openalex.org/C2776436406","wikidata":"https://www.wikidata.org/wiki/Q602446","display_name":"Lyrics","level":2,"score":0.9466272592544556},{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.9097511172294617},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7993942499160767},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.7733813524246216},{"id":"https://openalex.org/C160372630","wikidata":"https://www.wikidata.org/wiki/Q4819855","display_name":"Audio analyzer","level":5,"score":0.5991427898406982},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5660218000411987},{"id":"https://openalex.org/C2780832652","wikidata":"https://www.wikidata.org/wiki/Q5105266","display_name":"Chorus","level":2,"score":0.4948813319206238},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4764319062232971},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.4448445439338684},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.34965741634368896},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.2582331895828247},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.16961422562599182},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.07534188032150269},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.06829202175140381},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","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/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","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":3,"locations":[{"id":"doi:10.1145/1076034.1076097","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1076034.1076097","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th annual international ACM SIGIR conference on Research and development in information retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:scholarbank.nus.edu.sg:10635/78035","is_oa":false,"landing_page_url":"http://scholarbank.nus.edu.sg/handle/10635/78035","pdf_url":null,"source":{"id":"https://openalex.org/S7407052290","display_name":"National University of Singapore","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":"Scopus","raw_type":"Conference Paper"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.66.1178","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.66.1178","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.comp.nus.edu.sg/~mohan/papers/sigir2005.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5299999713897705,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W88081813","https://openalex.org/W1484280949","https://openalex.org/W1486089539","https://openalex.org/W1492953952","https://openalex.org/W1493163583","https://openalex.org/W1503560067","https://openalex.org/W1507782042","https://openalex.org/W1534221517","https://openalex.org/W1555563476","https://openalex.org/W1589182518","https://openalex.org/W1964150091","https://openalex.org/W1987827544","https://openalex.org/W2001496424","https://openalex.org/W2014411734","https://openalex.org/W2037057633","https://openalex.org/W2044916317","https://openalex.org/W2053836391","https://openalex.org/W2123603018","https://openalex.org/W2130976598","https://openalex.org/W2137542411","https://openalex.org/W2142575067","https://openalex.org/W2143235280","https://openalex.org/W2150231871","https://openalex.org/W2165297726","https://openalex.org/W2166275646","https://openalex.org/W2625477228","https://openalex.org/W4285719527","https://openalex.org/W6611528966"],"related_works":["https://openalex.org/W2809745188","https://openalex.org/W2494818933","https://openalex.org/W2475648064","https://openalex.org/W2349772854","https://openalex.org/W3152157429","https://openalex.org/W2364547139","https://openalex.org/W2139934687","https://openalex.org/W2154697232","https://openalex.org/W2559210633","https://openalex.org/W2075180943"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,47,64],"propose":[4],"a":[5],"novel":[6],"approach":[7],"for":[8],"automatic":[9],"music":[10,20,26,32,40,78,102,117],"video":[11,21,28,45,79],"summarization":[12,154],"based":[13,38,83,140],"on":[14,39,84,106,141],"audio-visual-text":[15],"analysis":[16],"and":[17,27,52,60,68,95,111,131,145],"alignment.":[18],"The":[19,77,104,135],"is":[22,36,81],"separated":[23],"into":[24,56],"the":[25,31,34,44,50,54,66,70,75,85,90,96,101,129,138,146,151,156],"tracks.":[29],"For":[30,43],"track,":[33,46],"chorus":[35,107],"detected":[37,91],"structure":[41],"analysis.":[42],"first":[48],"segment":[49],"shots":[51,55,59],"classify":[53],"close-up":[57],"face":[58],"non-face":[61],"shots,":[62],"then":[63],"extract":[65],"lyrics":[67,73,99,112],"detect":[69],"most":[71,97],"repeated":[72,98],"from":[74,100],"shots.":[76],"summary":[80],"generated":[82],"alignment":[86],"of":[87,89,133,153],"boundaries":[88],"chorus,":[92],"shot":[93,109],"class":[94],"video.":[103],"experiments":[105],"detection,":[108],"classification,":[110],"detection":[113],"using":[114,155],"20":[115],"English":[116],"videos":[118],"are":[119,159],"described.":[120],"Subjective":[121],"user":[122],"studies":[123],"have":[124],"been":[125],"conducted":[126],"to":[127],"evaluate":[128],"quality":[130],"effectiveness":[132],"summary.":[134],"comparisons":[136],"with":[137],"summaries":[139],"our":[142],"previous":[143],"method":[144,148,158],"manual":[147],"indicate":[149],"that":[150],"results":[152],"proposed":[157],"better":[160],"at":[161],"meeting":[162],"users'":[163],"expectations.":[164]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
