{"id":"https://openalex.org/W4407759530","doi":"https://doi.org/10.1145/3816020","title":"A Comprehensive Survey on Generative AI for Video-to-Music Generation","display_name":"A Comprehensive Survey on Generative AI for Video-to-Music Generation","publication_year":2026,"publication_date":"2026-06-24","ids":{"openalex":"https://openalex.org/W4407759530","doi":"https://doi.org/10.1145/3816020"},"language":"en","primary_location":{"id":"doi:10.1145/3816020","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3816020","pdf_url":null,"source":{"id":"https://openalex.org/S157921468","display_name":"ACM Computing Surveys","issn_l":"0360-0300","issn":["0360-0300","1557-7341"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Computing Surveys","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1145/3816020","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5007662123","display_name":"Shulei Ji","orcid":"https://orcid.org/0000-0002-9908-136X"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shulei Ji","raw_affiliation_strings":["Innovation Center of Yangtze River Delta, Zhejiang University","Zhejiang University"],"raw_orcid":"https://orcid.org/0000-0002-9908-136X","affiliations":[{"raw_affiliation_string":"Innovation Center of Yangtze River Delta, Zhejiang University","institution_ids":["https://openalex.org/I76130692"]},{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002666984","display_name":"Songruoyao Wu","orcid":"https://orcid.org/0000-0002-0760-6289"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Songruoyao Wu","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":"https://orcid.org/0000-0002-0760-6289","affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100413100","display_name":"Zihao Wang","orcid":"https://orcid.org/0000-0002-9217-3720"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zihao Wang","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":"https://orcid.org/0000-0002-5613-3262","affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100733004","display_name":"Shuyu Li","orcid":"https://orcid.org/0000-0002-7586-0430"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuyu Li","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":"https://orcid.org/0009-0009-3452-1641","affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101577175","display_name":"Kejun Zhang","orcid":"https://orcid.org/0000-0002-0778-2303"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kejun Zhang","raw_affiliation_strings":["Innovation Center of Yangtze River Delta, Zhejiang University","Zhejiang University"],"raw_orcid":"https://orcid.org/0000-0002-0778-2303","affiliations":[{"raw_affiliation_string":"Innovation Center of Yangtze River Delta, Zhejiang University","institution_ids":["https://openalex.org/I76130692"]},{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I76130692"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.00698047,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"58","issue":"13","first_page":"1","last_page":"36"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11349","display_name":"Music Technology and Sound Studies","score":0.9836000204086304,"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":0.9836000204086304,"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":0.9832000136375427,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9276000261306763,"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/generative-grammar","display_name":"Generative grammar","score":0.722176194190979},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4180659353733063},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.34835392236709595},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2764279842376709}],"concepts":[{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.722176194190979},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4180659353733063},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.34835392236709595},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2764279842376709}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3816020","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3816020","pdf_url":null,"source":{"id":"https://openalex.org/S157921468","display_name":"ACM Computing Surveys","issn_l":"0360-0300","issn":["0360-0300","1557-7341"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Computing Surveys","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2502.12489","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2502.12489","pdf_url":"https://arxiv.org/pdf/2502.12489","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"},{"id":"doi:10.48550/arxiv.2502.12489","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2502.12489","pdf_url":null,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.1145/3816020","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3816020","pdf_url":null,"source":{"id":"https://openalex.org/S157921468","display_name":"ACM Computing Surveys","issn_l":"0360-0300","issn":["0360-0300","1557-7341"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Computing Surveys","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G111693571","display_name":null,"funder_award_id":"62272409","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2380075625","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890"],"abstract_inverted_index":{"The":[0],"burgeoning":[1],"growth":[2],"of":[3,12,21,42,78,88,100],"video-to-music":[4,43],"generation":[5,44,62,104],"can":[6],"be":[7],"attributed":[8],"to":[9],"the":[10,27,76,98,103,120],"ascendancy":[11],"multimodal":[13,110],"generative":[14,47],"models.":[15],"However,":[16],"there":[17],"is":[18],"a":[19,39,85],"lack":[20],"literature":[22],"that":[23],"comprehensively":[24],"combs":[25],"through":[26],"work":[28],"in":[29,119],"this":[30,34,36],"field.":[31,121],"To":[32],"fill":[33],"gap,":[35],"article":[37],"presents":[38],"comprehensive":[40],"review":[41],"using":[45],"deep":[46],"AI":[48],"techniques,":[49],"focusing":[50],"on":[51,69],"three":[52],"key":[53],"components:":[54],"conditioning":[55,58],"input":[56],"construction,":[57],"mechanism,":[59],"and":[60,90,112],"music":[61,91],"frameworks.":[63],"We":[64],"categorize":[65],"existing":[66],"approaches":[67],"based":[68],"their":[70],"designs":[71],"for":[72],"each":[73],"component,":[74],"clarifying":[75],"roles":[77],"different":[79,95],"strategies.":[80],"Preceding":[81],"this,":[82],"we":[83,107],"provide":[84],"fine-grained":[86],"categorization":[87],"video":[89],"modalities,":[92],"illustrating":[93],"how":[94],"categories":[96],"influence":[97],"design":[99],"components":[101],"within":[102],"pipelines.":[105],"Furthermore,":[106],"summarize":[108],"available":[109],"datasets":[111],"evaluation":[113],"metrics":[114],"while":[115],"highlighting":[116],"ongoing":[117],"challenges":[118]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}