{"id":"https://openalex.org/W4402987512","doi":"https://doi.org/10.1186/s13636-024-00370-6","title":"Dance2Music-Diffusion: leveraging latent diffusion models for music generation from dance videos","display_name":"Dance2Music-Diffusion: leveraging latent diffusion models for music generation from dance videos","publication_year":2024,"publication_date":"2024-09-30","ids":{"openalex":"https://openalex.org/W4402987512","doi":"https://doi.org/10.1186/s13636-024-00370-6"},"language":"en","primary_location":{"id":"doi:10.1186/s13636-024-00370-6","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-024-00370-6","pdf_url":"https://link.springer.com/content/pdf/10.1186/s13636-024-00370-6.pdf","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722","3091-4523"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"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":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://link.springer.com/content/pdf/10.1186/s13636-024-00370-6.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100603447","display_name":"Chaoyang Zhang","orcid":"https://orcid.org/0000-0003-3634-7324"},"institutions":[{"id":"https://openalex.org/I75689368","display_name":"Communication University of China","ror":"https://ror.org/04facbs33","country_code":"CN","type":"education","lineage":["https://openalex.org/I75689368"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chaoyang Zhang","raw_affiliation_strings":["School of Information and Communication Engineering, Communication University of China, 1 Dingfuzhuang East St, Chaoyang District, Beijing, 100024, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information and Communication Engineering, Communication University of China, 1 Dingfuzhuang East St, Chaoyang District, Beijing, 100024, China","institution_ids":["https://openalex.org/I75689368"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101585024","display_name":"Hua Yan","orcid":"https://orcid.org/0000-0001-5845-1857"},"institutions":[{"id":"https://openalex.org/I75689368","display_name":"Communication University of China","ror":"https://ror.org/04facbs33","country_code":"CN","type":"education","lineage":["https://openalex.org/I75689368"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yan Hua","raw_affiliation_strings":["School of Information and Communication Engineering, Communication University of China, 1 Dingfuzhuang East St, Chaoyang District, Beijing, 100024, China"],"raw_orcid":"https://orcid.org/0000-0001-5845-1857","affiliations":[{"raw_affiliation_string":"School of Information and Communication Engineering, Communication University of China, 1 Dingfuzhuang East St, Chaoyang District, Beijing, 100024, China","institution_ids":["https://openalex.org/I75689368"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5101585024"],"corresponding_institution_ids":["https://openalex.org/I75689368"],"apc_list":{"value":1635,"currency":"USD","value_usd":1635},"apc_paid":{"value":1635,"currency":"USD","value_usd":1635},"fwci":0.8527,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.708376,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":"2024","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":1.0,"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":1.0,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.9994000196456909,"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/T10788","display_name":"Neuroscience and Music Perception","score":0.9919000267982483,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.9089385271072388},{"id":"https://openalex.org/keywords/dance","display_name":"Dance","score":0.7503734827041626},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.6771682500839233},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.3576448857784271},{"id":"https://openalex.org/keywords/visual-arts","display_name":"Visual arts","score":0.1705627739429474},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.09539154171943665}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9089385271072388},{"id":"https://openalex.org/C147446459","wikidata":"https://www.wikidata.org/wiki/Q11639","display_name":"Dance","level":2,"score":0.7503734827041626},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.6771682500839233},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.3576448857784271},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.1705627739429474},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.09539154171943665},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1186/s13636-024-00370-6","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-024-00370-6","pdf_url":"https://link.springer.com/content/pdf/10.1186/s13636-024-00370-6.pdf","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722","3091-4523"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"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":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:e8a6c1ff84c34ba1ad43e07379299666","is_oa":true,"landing_page_url":"https://doaj.org/article/e8a6c1ff84c34ba1ad43e07379299666","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing, Vol 2024, Iss 1, Pp 1-12 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1186/s13636-024-00370-6","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-024-00370-6","pdf_url":"https://link.springer.com/content/pdf/10.1186/s13636-024-00370-6.pdf","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722","3091-4523"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"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":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5659406121","display_name":null,"funder_award_id":"61702466","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6066285843","display_name":null,"funder_award_id":"CUC230B028","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G6882236828","display_name":null,"funder_award_id":"CUCAI24002","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"}],"funders":[{"id":"https://openalex.org/F4320311508","display_name":"National Institute of Advanced Industrial Science and Technology","ror":"https://ror.org/01703db54"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4402987512.pdf","grobid_xml":"https://content.openalex.org/works/W4402987512.grobid-xml"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W1971928988","https://openalex.org/W2191779130","https://openalex.org/W3085146247","https://openalex.org/W3100204393","https://openalex.org/W3108240585","https://openalex.org/W3204221554","https://openalex.org/W3207290297","https://openalex.org/W3213549365","https://openalex.org/W4281485151","https://openalex.org/W4312814772","https://openalex.org/W4312933868","https://openalex.org/W4385489997","https://openalex.org/W4388994500","https://openalex.org/W4390873054","https://openalex.org/W4400965626","https://openalex.org/W6600297362","https://openalex.org/W6600319451","https://openalex.org/W6601215536","https://openalex.org/W6602344735","https://openalex.org/W6605269899","https://openalex.org/W6702248584","https://openalex.org/W6758535090","https://openalex.org/W6813391973"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W597595235","https://openalex.org/W3200585538","https://openalex.org/W2357651146","https://openalex.org/W1574267311","https://openalex.org/W2501127304","https://openalex.org/W3209785493","https://openalex.org/W3120492113","https://openalex.org/W2299690913"],"abstract_inverted_index":{"With":[0],"the":[1,122,130,156,159],"rapid":[2],"development":[3],"of":[4,14,48,121,140,158,186],"social":[5],"networks,":[6],"short":[7],"videos":[8,29,67,185],"have":[9],"become":[10],"a":[11,59,75,84],"popular":[12],"form":[13],"content,":[15],"especially":[16],"dance":[17,28,51,66,96,113,151,166,182,191],"videos.":[18],"In":[19,53],"this":[20,54],"context,":[21],"research":[22],"on":[23,129],"automatically":[24],"generating":[25,90,109],"music":[26,44,63,85,92,163,189],"for":[27,62,79,89,175],"shows":[30,135],"significant":[31],"practical":[32],"value.":[33],"However,":[34],"existing":[35,106,127],"studies":[36],"face":[37],"challenges":[38],"such":[39],"as":[40],"limited":[41],"richness":[42],"in":[43,108,138,161],"timbre":[45],"and":[46,83,99,111,118,148,172,179,190],"lack":[47],"synchronization":[49],"with":[50,145,150],"movements.":[52,152],"paper,":[55],"we":[56],"propose":[57],"Dance2Music-Diffusion,":[58],"novel":[60],"framework":[61,104,134],"generation":[64,87,164],"from":[65,165],"using":[68],"latent":[69,91,100],"diffusion":[70,86,101],"models.":[71],"Our":[72,133],"approach":[73],"includes":[74],"motion":[76,81],"encoder":[77],"module":[78,88],"extracting":[80],"features":[82],"representations.":[93],"By":[94],"integrating":[95],"type":[97],"monitoring":[98],"techniques,":[102],"our":[103,187],"outperforms":[105],"methods":[107],"complex":[110],"rich":[112],"music.":[114],"We":[115],"conducted":[116],"objective":[117],"subjective":[119],"evaluations":[120],"results":[123],"produced":[124],"by":[125],"various":[126],"models":[128],"AIST++":[131],"dataset.":[132],"outstanding":[136],"performance":[137],"terms":[139],"beat":[141],"recall":[142],"rate,":[143],"consistency":[144],"GT":[146],"beats,":[147],"coordination":[149],"This":[153],"work":[154],"represents":[155],"state":[157],"art":[160],"automatic":[162],"videos,":[167],"is":[168,200],"easy":[169],"to":[170],"train,":[171],"has":[173],"implications":[174],"enhancing":[176],"entertainment":[177],"experiences":[178],"inspiring":[180],"innovative":[181],"productions.":[183],"Sample":[184],"generated":[188],"can":[192],"be":[193],"viewed":[194],"at":[195,202],"https://youtu.be/eCvLdLdkX-Y":[196],".":[197,204],"The":[198],"code":[199],"available":[201],"https://github.com/hellto/dance2music-diffusion":[203]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2025-10-10T00:00:00"}
