{"id":"https://openalex.org/W2095005467","doi":"https://doi.org/10.1145/1027527.1027641","title":"Automatic music video generation based on temporal pattern analysis","display_name":"Automatic music video generation based on temporal pattern analysis","publication_year":2004,"publication_date":"2004-10-10","ids":{"openalex":"https://openalex.org/W2095005467","doi":"https://doi.org/10.1145/1027527.1027641","mag":"2095005467"},"language":"en","primary_location":{"id":"doi:10.1145/1027527.1027641","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1027527.1027641","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/A5024965898","display_name":"Xian\u2010Sheng Hua","orcid":"https://orcid.org/0000-0002-8232-5049"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xian-Sheng HUA","raw_affiliation_strings":["Microsoft Research Asia","Microsoft Research Asia,"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Microsoft Research Asia,","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110491600","display_name":"Lie Lu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lie LU","raw_affiliation_strings":["Microsoft Research Asia","Microsoft Research Asia,"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Microsoft Research Asia,","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100397026","display_name":"Hao Zhang","orcid":"https://orcid.org/0000-0003-1991-119X"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hong-Jiang ZHANG","raw_affiliation_strings":["Microsoft Research Asia","Microsoft Research Asia,"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Microsoft Research Asia,","institution_ids":["https://openalex.org/I4210113369"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5024965898"],"corresponding_institution_ids":["https://openalex.org/I4210113369"],"apc_list":null,"apc_paid":null,"fwci":2.207,"has_fulltext":false,"cited_by_count":60,"citation_normalized_percentile":{"value":0.88557758,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"472","last_page":"475"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","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/T11439","display_name":"Video Analysis and Summarization","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/T11309","display_name":"Music and Audio Processing","score":0.9979000091552734,"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/T12720","display_name":"Multimedia Communication and Technology","score":0.9786999821662903,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7562735080718994},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.594112753868103},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5689905285835266},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5036322474479675},{"id":"https://openalex.org/keywords/video-processing","display_name":"Video processing","score":0.46840259432792664},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43195223808288574},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4223499298095703},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4084850549697876},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.33931541442871094}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7562735080718994},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.594112753868103},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5689905285835266},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5036322474479675},{"id":"https://openalex.org/C65483669","wikidata":"https://www.wikidata.org/wiki/Q3536669","display_name":"Video processing","level":2,"score":0.46840259432792664},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43195223808288574},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4223499298095703},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4084850549697876},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.33931541442871094},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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:10.1145/1027527.1027641","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1027527.1027641","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:10.1.1.146.2785","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.146.2785","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://research.microsoft.com/~xshua/publications/pdf/2004_ACMMM_MusicVideo.pdf","raw_type":"text"},{"id":"pmh:oai:eprints.ucl.ac.uk.OAI2:1398096","is_oa":false,"landing_page_url":"http://discovery.ucl.ac.uk/1398096/","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. 472-475).  ACM (2004)     ","raw_type":"Proceedings paper"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W2006180404","https://openalex.org/W2047094503","https://openalex.org/W2053836391","https://openalex.org/W2120194878","https://openalex.org/W2165578912","https://openalex.org/W3152412763"],"related_works":["https://openalex.org/W1972035260","https://openalex.org/W2062195135","https://openalex.org/W4301594054","https://openalex.org/W2794488505","https://openalex.org/W2795079307","https://openalex.org/W3125889879","https://openalex.org/W2793058541","https://openalex.org/W3124422538","https://openalex.org/W2295467472","https://openalex.org/W2365286546"],"abstract_inverted_index":{"Music":[0],"video":[1,54,62,72,100,121,129],"(MV)":[2],"is":[3,122],"a":[4,10,14,23,51,91],"short":[5],"film":[6],"meant":[7],"to":[8,86],"present":[9,22],"visual":[11,43,108],"representation":[12],"of":[13,53,70,93],"popular":[15],"music":[16,56,61,120],"song.":[17],"In":[18],"this":[19],"paper,":[20],"we":[21],"system":[24,65],"that":[25,37,141],"automatically":[26,66],"generates":[27],"MV-like":[28],"videos":[29,33],"from":[30,96],"personal":[31],"home":[32,99],"based":[34],"on":[35,50],"observations":[36],"generally":[38],"there":[39],"are":[40,102,144],"obvious":[41],"repetitive":[42,78],"and":[44,55,73,89,114,146],"aural":[45,112],"patterns":[46,79],"in":[47,80],"MVs.":[48],"Based":[49],"set":[52,92],"analysis":[57],"algorithms,":[58],"the":[59,71,81,87,97,107,111,118,126,137,142],"automatic":[60],"(AMV)":[63],"generation":[64],"extracts":[67],"temporal":[68],"structures":[69],"music,":[74],"as":[75,77],"well":[76],"music.":[82,138],"And":[83,116],"then,":[84],"according":[85],"structure":[88,113],"patterns,":[90],"highlight":[94,128],"segments":[95,130],"raw":[98],"footage":[101],"selected,":[103],"aiming":[104],"at":[105],"matching":[106],"content":[109],"with":[110,131,136],"pattern.":[115],"last,":[117],"output":[119],"rendered":[123],"by":[124],"connecting":[125],"selected":[127],"appropriate":[132],"transition":[133],"effects,":[134],"accompanied":[135],"Experiments":[139],"show":[140],"results":[143],"compelling":[145],"promising.":[147]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":2},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":2}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
