{"id":"https://openalex.org/W4385681340","doi":"https://doi.org/10.1145/3581783.3612307","title":"DiffDance: Cascaded Human Motion Diffusion Model for Dance Generation","display_name":"DiffDance: Cascaded Human Motion Diffusion Model for Dance Generation","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4385681340","doi":"https://doi.org/10.1145/3581783.3612307"},"language":"en","primary_location":{"id":"doi:10.1145/3581783.3612307","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3581783.3612307","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3612307","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3612307","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5091480702","display_name":"Qiaosong Qi","orcid":"https://orcid.org/0000-0002-9977-967X"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Qiaosong Qi","raw_affiliation_strings":["Alibaba Group, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Alibaba Group, Beijing, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089348549","display_name":"Le Zhuo","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":"Le Zhuo","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/A5049610245","display_name":"Aixi Zhang","orcid":"https://orcid.org/0000-0001-9863-0091"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Aixi Zhang","raw_affiliation_strings":["Alibaba Group, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Alibaba Group, Beijing, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002061412","display_name":"Yue Liao","orcid":"https://orcid.org/0000-0002-2671-0655"},"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":"Yue Liao","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/A5100688786","display_name":"Fei Fang","orcid":null},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fei Fang","raw_affiliation_strings":["Alibaba Group, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Alibaba Group, Beijing, China","institution_ids":["https://openalex.org/I45928872"]}]},{"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":"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":["BAAI & Skyworks, Beijing, China"],"affiliations":[{"raw_affiliation_string":"BAAI & Skyworks, Beijing, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5091480702"],"corresponding_institution_ids":["https://openalex.org/I45928872"],"apc_list":null,"apc_paid":null,"fwci":3.9832,"has_fulltext":true,"cited_by_count":22,"citation_normalized_percentile":{"value":0.94231617,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1374","last_page":"1382"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12290","display_name":"Human Motion and Animation","score":0.9987000226974487,"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"}},"topics":[{"id":"https://openalex.org/T12290","display_name":"Human Motion and Animation","score":0.9987000226974487,"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"}},{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.998199999332428,"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":0.9958000183105469,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/dance","display_name":"Dance","score":0.740959107875824},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7195000648498535},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.606794536113739},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5949558019638062},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5486144423484802},{"id":"https://openalex.org/keywords/motion-capture","display_name":"Motion capture","score":0.5462093949317932},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.5091297030448914},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.5036165118217468},{"id":"https://openalex.org/keywords/rhythm","display_name":"Rhythm","score":0.5030998587608337},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.49780917167663574},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.4324200749397278},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4130907356739044},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.38037967681884766},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17392468452453613},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.15998592972755432}],"concepts":[{"id":"https://openalex.org/C147446459","wikidata":"https://www.wikidata.org/wiki/Q11639","display_name":"Dance","level":2,"score":0.740959107875824},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7195000648498535},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.606794536113739},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5949558019638062},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5486144423484802},{"id":"https://openalex.org/C48007421","wikidata":"https://www.wikidata.org/wiki/Q676252","display_name":"Motion capture","level":3,"score":0.5462093949317932},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.5091297030448914},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.5036165118217468},{"id":"https://openalex.org/C135343436","wikidata":"https://www.wikidata.org/wiki/Q170406","display_name":"Rhythm","level":2,"score":0.5030998587608337},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.49780917167663574},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.4324200749397278},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4130907356739044},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.38037967681884766},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17392468452453613},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.15998592972755432},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3581783.3612307","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3581783.3612307","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3612307","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2308.02915","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2308.02915","pdf_url":"https://arxiv.org/pdf/2308.02915","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":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1145/3581783.3612307","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3581783.3612307","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3612307","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1121271761","display_name":null,"funder_award_id":"Program","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1231421488","display_name":null,"funder_award_id":"under","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2087396116","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2802911279","display_name":null,"funder_award_id":"Young","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G391238517","display_name":null,"funder_award_id":", and","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5696407354","display_name":null,"funder_award_id":"62122010","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5994120800","display_name":null,"funder_award_id":"Natural","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":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385681340.pdf","grobid_xml":"https://content.openalex.org/works/W4385681340.grobid-xml"},"referenced_works_count":51,"referenced_works":["https://openalex.org/W1967554269","https://openalex.org/W2028605775","https://openalex.org/W2129069237","https://openalex.org/W2191779130","https://openalex.org/W2257663825","https://openalex.org/W2594167370","https://openalex.org/W2780124704","https://openalex.org/W2899129842","https://openalex.org/W2908510526","https://openalex.org/W2949924544","https://openalex.org/W2953267996","https://openalex.org/W2959300817","https://openalex.org/W2977816919","https://openalex.org/W2993797559","https://openalex.org/W3002101995","https://openalex.org/W3035486405","https://openalex.org/W3035551320","https://openalex.org/W3036167779","https://openalex.org/W3037309139","https://openalex.org/W3037374099","https://openalex.org/W3068510429","https://openalex.org/W3083132452","https://openalex.org/W3093390323","https://openalex.org/W3102619627","https://openalex.org/W3129651364","https://openalex.org/W3153832461","https://openalex.org/W3162926177","https://openalex.org/W3166396011","https://openalex.org/W3175528029","https://openalex.org/W3190716692","https://openalex.org/W3201409833","https://openalex.org/W3204221554","https://openalex.org/W4226125322","https://openalex.org/W4238826863","https://openalex.org/W4281485151","https://openalex.org/W4281690218","https://openalex.org/W4281720387","https://openalex.org/W4284898017","https://openalex.org/W4286418703","https://openalex.org/W4288099666","https://openalex.org/W4298186886","https://openalex.org/W4303440777","https://openalex.org/W4303519914","https://openalex.org/W4306310244","https://openalex.org/W4313145975","https://openalex.org/W4313167431","https://openalex.org/W4320085220","https://openalex.org/W4385489997","https://openalex.org/W6687152286","https://openalex.org/W6779823529","https://openalex.org/W6795288823"],"related_works":["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","https://openalex.org/W2762501427","https://openalex.org/W2039848376"],"abstract_inverted_index":{"When":[0],"hearing":[1],"music,":[2],"it":[3],"is":[4,17,169],"natural":[5],"for":[6,67,93],"people":[7],"to":[8,10,22,45,104,114,131,136,152,187],"dance":[9,14,51,70,174],"its":[11,111],"rhythm.":[12],"Automatic":[13],"generation,":[15,95],"however,":[16],"a":[18,59,75,80,98,142],"challenging":[19],"task":[20],"due":[21],"the":[23,47,87,133,161,180],"physical":[24],"constraints":[25],"of":[26,50,171],"human":[27],"motion":[28,62,92,115],"and":[29,43,79,91,108,140],"rhythmic":[30],"alignment":[31],"with":[32,179],"target":[33],"music.":[34,182],"Conventional":[35],"autoregressive":[36,192],"methods":[37],"introduce":[38],"compounding":[39],"errors":[40],"during":[41],"sampling":[42],"struggle":[44],"capture":[46],"long-term":[48],"structure":[49],"sequences.":[52],"To":[53,85],"address":[54],"these":[55],"limitations,":[56],"we":[57,125,165],"present":[58],"novel":[60],"cascaded":[61,122],"diffusion":[63,77,83,123,150],"model,":[64,124],"DiffDance,":[65],"designed":[66],"high-resolution,":[68],"long-form":[69],"generation.":[71],"This":[72],"model":[73,78,103,134],"comprises":[74],"music-to-dance":[76],"sequence":[81],"super-resolution":[82],"model.":[84],"bridge":[86],"gap":[88],"between":[89],"music":[90,106],"conditional":[94],"DiffDance":[96,168],"employs":[97],"pretrained":[99],"audio":[100],"representation":[101],"learning":[102],"extract":[105],"embeddings":[107],"further":[109],"align":[110,177],"embedding":[112],"space":[113],"via":[116],"contrastive":[117],"loss.":[118],"During":[119],"training":[120],"our":[121],"also":[126],"incorporate":[127],"multiple":[128],"geometric":[129],"losses":[130],"constrain":[132],"outputs":[135],"be":[137],"physically":[138],"plausible":[139],"add":[141],"dynamic":[143],"loss":[144],"weight":[145],"that":[146,167,176],"adaptively":[147],"changes":[148],"over":[149],"timesteps":[151],"facilitate":[153],"sample":[154],"diversity.":[155],"Through":[156],"comprehensive":[157],"experiments":[158],"performed":[159],"on":[160],"benchmark":[162],"dataset":[163],"AIST++,":[164],"demonstrate":[166],"capable":[170],"generating":[172],"realistic":[173],"sequences":[175],"effectively":[178],"input":[181],"These":[183],"results":[184],"are":[185],"comparable":[186],"those":[188],"achieved":[189],"by":[190],"state-of-the-art":[191],"methods.":[193]},"counts_by_year":[{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":10}],"updated_date":"2026-04-13T07:58:08.660418","created_date":"2025-10-10T00:00:00"}