{"id":"https://openalex.org/W4393148499","doi":"https://doi.org/10.1609/aaai.v38i5.28299","title":"V2Meow: Meowing to the Visual Beat via Video-to-Music Generation","display_name":"V2Meow: Meowing to the Visual Beat via Video-to-Music Generation","publication_year":2024,"publication_date":"2024-03-24","ids":{"openalex":"https://openalex.org/W4393148499","doi":"https://doi.org/10.1609/aaai.v38i5.28299"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v38i5.28299","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v38i5.28299","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/28299/28588","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/28299/28588","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102890732","display_name":"Kun Su","orcid":"https://orcid.org/0000-0001-5014-6524"},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kun Su","raw_affiliation_strings":["University of Washington"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Washington","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071459336","display_name":"Judith Yue Li","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Judith Yue Li","raw_affiliation_strings":["Google Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103047819","display_name":"Qingqing Huang","orcid":"https://orcid.org/0000-0002-0837-4520"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qingqing Huang","raw_affiliation_strings":["ByteDance"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068428403","display_name":"Dima Kuzmin","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dima Kuzmin","raw_affiliation_strings":["Google Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101859889","display_name":"Joonseok Lee","orcid":"https://orcid.org/0000-0002-0786-8086"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR","US"],"is_corresponding":false,"raw_author_name":"Joonseok Lee","raw_affiliation_strings":["Google Research\nSeoul National University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research\nSeoul National University","institution_ids":["https://openalex.org/I1291425158","https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019674079","display_name":"Chris Donahue","orcid":"https://orcid.org/0009-0007-6825-6327"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I4210090411","display_name":"Google DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Chris Donahue","raw_affiliation_strings":["Google DeepMind\nCarnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google DeepMind\nCarnegie Mellon University","institution_ids":["https://openalex.org/I1291425158","https://openalex.org/I4210090411","https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101544732","display_name":"Fei Sha","orcid":"https://orcid.org/0000-0002-9382-0010"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fei Sha","raw_affiliation_strings":["Google Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103622427","display_name":"Aren Jansen","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aren Jansen","raw_affiliation_strings":["Google Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100445061","display_name":"Yu Wang","orcid":"https://orcid.org/0000-0001-6108-5157"},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yu Wang","raw_affiliation_strings":["New York University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New York University","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107858742","display_name":"M. Verzetti","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I4210090411","display_name":"Google DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Mauro Verzetti","raw_affiliation_strings":["Google DeepMind"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google DeepMind","institution_ids":["https://openalex.org/I1291425158","https://openalex.org/I4210090411"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038217434","display_name":"Timo I. Denk","orcid":"https://orcid.org/0009-0007-3727-6149"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I4210090411","display_name":"Google DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Timo Denk","raw_affiliation_strings":["Google DeepMind"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google DeepMind","institution_ids":["https://openalex.org/I1291425158","https://openalex.org/I4210090411"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.5527,"has_fulltext":true,"cited_by_count":15,"citation_normalized_percentile":{"value":0.81526104,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"38","issue":"5","first_page":"4952","last_page":"4960"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11349","display_name":"Music Technology and Sound Studies","score":0.9656000137329102,"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":0.9656000137329102,"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":0.9276999831199646,"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":0.9151999950408936,"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/beat","display_name":"Beat (acoustics)","score":0.724216103553772},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.10505422949790955}],"concepts":[{"id":"https://openalex.org/C189809214","wikidata":"https://www.wikidata.org/wiki/Q829522","display_name":"Beat (acoustics)","level":2,"score":0.724216103553772},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.10505422949790955},{"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:10.1609/aaai.v38i5.28299","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v38i5.28299","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/28299/28588","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:ojs.aaai.org:article/28299","is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/28299","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v38i5.28299","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v38i5.28299","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/28299/28588","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.5799999833106995,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G4700831490","display_name":null,"funder_award_id":"2022-","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"}],"funders":[{"id":"https://openalex.org/F4320335489","display_name":"Institute for Information and Communications Technology Promotion","ror":"https://ror.org/01g0hqq23"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4393148499.pdf"},"referenced_works_count":74,"referenced_works":["https://openalex.org/W1522734439","https://openalex.org/W2519091744","https://openalex.org/W2524365899","https://openalex.org/W2526050071","https://openalex.org/W2593116425","https://openalex.org/W2606176153","https://openalex.org/W2619082050","https://openalex.org/W2772474126","https://openalex.org/W2792210438","https://openalex.org/W2885835225","https://openalex.org/W2912947616","https://openalex.org/W2913302158","https://openalex.org/W2946521317","https://openalex.org/W2950547518","https://openalex.org/W2963066677","https://openalex.org/W2963408210","https://openalex.org/W2963524571","https://openalex.org/W2963807156","https://openalex.org/W2964345931","https://openalex.org/W2966220025","https://openalex.org/W2997367363","https://openalex.org/W3006926732","https://openalex.org/W3015538334","https://openalex.org/W3016096605","https://openalex.org/W3034572008","https://openalex.org/W3037391061","https://openalex.org/W3046715528","https://openalex.org/W3046890131","https://openalex.org/W3108240585","https://openalex.org/W3111853169","https://openalex.org/W3126721948","https://openalex.org/W3166396011","https://openalex.org/W3193521535","https://openalex.org/W3204221554","https://openalex.org/W3206395542","https://openalex.org/W3207290297","https://openalex.org/W3215615641","https://openalex.org/W4214612132","https://openalex.org/W4226033575","https://openalex.org/W4283022926","https://openalex.org/W4283074862","https://openalex.org/W4287372095","https://openalex.org/W4287802874","https://openalex.org/W4287995946","https://openalex.org/W4293575120","https://openalex.org/W4300936792","https://openalex.org/W4300980117","https://openalex.org/W4307323391","https://openalex.org/W4312319752","https://openalex.org/W4312814772","https://openalex.org/W4318351475","https://openalex.org/W4318718630","https://openalex.org/W4318718996","https://openalex.org/W4318719023","https://openalex.org/W4318752004","https://openalex.org/W4319989813","https://openalex.org/W4361807266","https://openalex.org/W4367359628","https://openalex.org/W4367860227","https://openalex.org/W4380136719","https://openalex.org/W4380551955","https://openalex.org/W4381786045","https://openalex.org/W4383993968","https://openalex.org/W4385245566","https://openalex.org/W4386071656","https://openalex.org/W6601851198","https://openalex.org/W6687537536","https://openalex.org/W6736965957","https://openalex.org/W6746008334","https://openalex.org/W6780316881","https://openalex.org/W6780770960","https://openalex.org/W6781345847","https://openalex.org/W6793119350","https://openalex.org/W6798098866"],"related_works":["https://openalex.org/W2090102624","https://openalex.org/W1490229056","https://openalex.org/W2009462014","https://openalex.org/W653810948","https://openalex.org/W4205930110","https://openalex.org/W1901050710","https://openalex.org/W2060714976","https://openalex.org/W2990609321","https://openalex.org/W1977400792","https://openalex.org/W2365261018"],"abstract_inverted_index":{"Video-to-music":[0],"generation":[1,18,75,166],"demands":[2],"both":[3,152],"a":[4,73,84,92,123],"temporally":[5],"localized":[6],"high-quality":[7,80],"listening":[8],"experience":[9],"and":[10,54,60,154,173],"globally":[11,49],"aligned":[12,50],"video-acoustic":[13,31],"signatures.":[14],"While":[15],"recent":[16],"music":[17,55,59,81,101,111,129,165],"models":[19,119],"excel":[20],"at":[21,180],"the":[22,28,45],"former":[23],"through":[24],"advanced":[25],"audio":[26,82,102,130,174],"codecs,":[27],"exploration":[29],"of":[30,47,78,87,100,170],"signatures":[32,51],"has":[33],"been":[34],"confined":[35],"to":[36],"specific":[37],"visual":[38,138],"scenarios.":[39],"In":[40],"contrast,":[41],"our":[42,160],"research":[43],"confronts":[44],"challenge":[46],"learning":[48],"between":[52],"video":[53,88,106,142],"directly":[56],"from":[57,109,141],"paired":[58,104],"videos,":[61,112],"without":[62],"explicitly":[63],"modeling":[64],"domain-specific":[65,118],"rhythmic":[66],"or":[67],"semantic":[68],"relationships.":[69],"We":[70],"propose":[71],"V2Meow,":[72],"video-to-music":[74],"system":[76],"capable":[77],"producing":[79],"for":[83],"diverse":[85],"range":[86],"input":[89],"types":[90],"using":[91],"multi-stage":[93],"autoregressive":[94],"model.":[95],"Trained":[96],"on":[97,135],"5k":[98],"hours":[99],"clips":[103],"with":[105,116,144],"frames":[107],"mined":[108],"in-the-wild":[110],"V2Meow":[113],"is":[114],"competitive":[115],"previous":[117],"when":[120],"evaluated":[121],"in":[122,168],"zero-shot":[124],"manner.":[125],"It":[126],"synthesizes":[127],"high-fidelity":[128],"waveforms":[131],"solely":[132],"by":[133],"conditioning":[134],"pre-trained":[136],"general-purpose":[137],"features":[139],"extracted":[140],"frames,":[143],"optional":[145],"style":[146],"control":[147],"via":[148],"text":[149],"prompts.":[150],"Through":[151],"qualitative":[153],"quantitative":[155],"evaluations,":[156],"we":[157],"demonstrate":[158],"that":[159],"model":[161],"outperforms":[162],"various":[163],"existing":[164],"systems":[167],"terms":[169],"visual-audio":[171],"correspondence":[172],"quality.":[175],"Music":[176],"samples":[177],"are":[178],"available":[179],"tinyurl.com/v2meow.":[181]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":5}],"updated_date":"2026-07-02T09:51:11.867554","created_date":"2025-10-10T00:00:00"}