{"id":"https://openalex.org/W3207290297","doi":"https://doi.org/10.1145/3474085.3475195","title":"Video Background Music Generation with Controllable Music Transformer","display_name":"Video Background Music Generation with Controllable Music Transformer","publication_year":2021,"publication_date":"2021-10-17","ids":{"openalex":"https://openalex.org/W3207290297","doi":"https://doi.org/10.1145/3474085.3475195","mag":"3207290297"},"language":"en","primary_location":{"id":"doi:10.1145/3474085.3475195","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3474085.3475195","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2111.08380","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5007532959","display_name":"Shangzhe Di","orcid":"https://orcid.org/0009-0005-6977-4332"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Shangzhe Di","raw_affiliation_strings":["Beihang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066892877","display_name":"Zeren Jiang","orcid":null},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zeren Jiang","raw_affiliation_strings":["Beihang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100330138","display_name":"Si Liu","orcid":"https://orcid.org/0000-0002-9180-2935"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Si Liu","raw_affiliation_strings":["Beihang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060872432","display_name":"Zhaokai Wang","orcid":"https://orcid.org/0009-0007-4357-7802"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhaokai Wang","raw_affiliation_strings":["Beihang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055939118","display_name":"Leyan Zhu","orcid":"https://orcid.org/0000-0002-3273-5269"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Leyan Zhu","raw_affiliation_strings":["Beihang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100676068","display_name":"Zexin He","orcid":"https://orcid.org/0000-0002-2698-6627"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zexin He","raw_affiliation_strings":["Beihang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100369963","display_name":"Hongming Liu","orcid":"https://orcid.org/0000-0003-2256-765X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hongming Liu","raw_affiliation_strings":["Charterhouse School, Godalming, Surrey, United Kingdom"],"affiliations":[{"raw_affiliation_string":"Charterhouse School, Godalming, Surrey, United Kingdom","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100381753","display_name":"Shuicheng Yan","orcid":"https://orcid.org/0000-0001-8906-3777"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shuicheng Yan","raw_affiliation_strings":["Sea AI Lab, singapore city, Singapore"],"affiliations":[{"raw_affiliation_string":"Sea AI Lab, singapore city, Singapore","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5007532959"],"corresponding_institution_ids":["https://openalex.org/I82880672"],"apc_list":null,"apc_paid":null,"fwci":4.6612,"has_fulltext":false,"cited_by_count":74,"citation_normalized_percentile":{"value":0.96072508,"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":"2037","last_page":"2045"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11349","display_name":"Music Technology and Sound Studies","score":0.9977999925613403,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.9977999925613403,"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":0.9968000054359436,"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/T12290","display_name":"Human Motion and Animation","score":0.9825999736785889,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6994238495826721},{"id":"https://openalex.org/keywords/rhythm","display_name":"Rhythm","score":0.6649035215377808},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4900730848312378},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4645620882511139},{"id":"https://openalex.org/keywords/beat","display_name":"Beat (acoustics)","score":0.4322768449783325},{"id":"https://openalex.org/keywords/popular-music","display_name":"Popular music","score":0.431282639503479},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.39187583327293396},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.13518878817558289},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.09856531023979187},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09296262264251709},{"id":"https://openalex.org/keywords/visual-arts","display_name":"Visual arts","score":0.0826827883720398},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.07586345076560974},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.06843280792236328}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6994238495826721},{"id":"https://openalex.org/C135343436","wikidata":"https://www.wikidata.org/wiki/Q170406","display_name":"Rhythm","level":2,"score":0.6649035215377808},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4900730848312378},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4645620882511139},{"id":"https://openalex.org/C189809214","wikidata":"https://www.wikidata.org/wiki/Q829522","display_name":"Beat (acoustics)","level":2,"score":0.4322768449783325},{"id":"https://openalex.org/C114611597","wikidata":"https://www.wikidata.org/wiki/Q373342","display_name":"Popular music","level":2,"score":0.431282639503479},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.39187583327293396},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.13518878817558289},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.09856531023979187},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09296262264251709},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0826827883720398},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.07586345076560974},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.06843280792236328},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3474085.3475195","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3474085.3475195","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2111.08380","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2111.08380","pdf_url":"https://arxiv.org/pdf/2111.08380","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2111.08380","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2111.08380","pdf_url":"https://arxiv.org/pdf/2111.08380","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7834498664","display_name":null,"funder_award_id":"61876177","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W2403342846","https://openalex.org/W2475687244","https://openalex.org/W2524365899","https://openalex.org/W2584032004","https://openalex.org/W2626778328","https://openalex.org/W2746068898","https://openalex.org/W2772474126","https://openalex.org/W2792210438","https://openalex.org/W2811167645","https://openalex.org/W2898148140","https://openalex.org/W2902968583","https://openalex.org/W2910577860","https://openalex.org/W2919624000","https://openalex.org/W2938704169","https://openalex.org/W2949382160","https://openalex.org/W2950547518","https://openalex.org/W2959020461","https://openalex.org/W2962981281","https://openalex.org/W2963032576","https://openalex.org/W2963403868","https://openalex.org/W2963681776","https://openalex.org/W3034573343","https://openalex.org/W3037798801","https://openalex.org/W3045082460","https://openalex.org/W3046715528","https://openalex.org/W3047325651","https://openalex.org/W3049174246","https://openalex.org/W3077305422","https://openalex.org/W3090740343","https://openalex.org/W3092850823","https://openalex.org/W3092879656","https://openalex.org/W3103837916","https://openalex.org/W3111853169","https://openalex.org/W3173531154"],"related_works":["https://openalex.org/W2072492413","https://openalex.org/W2997159972","https://openalex.org/W4296378967","https://openalex.org/W2064134577","https://openalex.org/W2373995729","https://openalex.org/W3203096336","https://openalex.org/W2157038729","https://openalex.org/W2393707162","https://openalex.org/W2242088654","https://openalex.org/W2951162327"],"abstract_inverted_index":{"In":[0,61],"this":[1],"work,":[2],"we":[3,50,63],"address":[4],"the":[5,36,42,47,53,93,97,104,108,112,124,133,138],"task":[6],"of":[7,33,96,107],"video":[8,57,72],"background":[9,43,59,126],"music":[10,17,25,44,109,127,142],"generation.":[11],"Some":[12],"previous":[13],"works":[14],"achieve":[15],"effective":[16],"generation":[18],"but":[19],"are":[20],"unable":[21],"to":[22],"generate":[23,41],"melodious":[24],"specifically":[26],"for":[27],"a":[28,87],"given":[29,48],"video,":[30,49],"and":[31,58,68,77,111,119,136],"none":[32],"them":[34],"considers":[35],"video-music":[37],"rhythmic":[38,54,99],"consistency.":[39],"To":[40],"that":[45,91,123],"matches":[46],"first":[51],"establish":[52],"relationships":[55],"between":[56],"music.":[60],"particular,":[62],"connect":[64],"timing,":[65],"motion":[66,69],"speed,":[67],"saliency":[70],"from":[71,80],"with":[73,132],"beat,":[74],"simu-note":[75,78],"density,":[76],"strength":[79],"music,":[81],"respectively.":[82],"We":[83],"then":[84],"propose":[85],"CMT,":[86],"Controllable":[88],"Music":[89],"Transformer":[90],"enables":[92],"local":[94],"control":[95,106],"aforementioned":[98],"features,":[100],"as":[101,103],"well":[102],"global":[105],"genre":[110],"used":[113],"instrument":[114],"specified":[115],"by":[116],"users.":[117],"Objective":[118],"subjective":[120],"evaluations":[121],"show":[122],"generated":[125],"has":[128],"achieved":[129],"satisfactory":[130],"compatibility":[131],"input":[134],"videos,":[135],"at":[137],"same":[139],"time,":[140],"impressive":[141],"quality.":[143]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":24},{"year":2024,"cited_by_count":25},{"year":2023,"cited_by_count":15},{"year":2022,"cited_by_count":8}],"updated_date":"2026-04-14T08:04:32.555800","created_date":"2025-10-10T00:00:00"}
