{"id":"https://openalex.org/W7213463527","doi":"https://doi.org/10.1016/j.jvcir.2026.104965","title":"DanceCrafter: A two-stage framework for high-quality music-driven image animation","display_name":"DanceCrafter: A two-stage framework for high-quality music-driven image animation","publication_year":2026,"publication_date":"2026-09-17","ids":{"openalex":"https://openalex.org/W7213463527","doi":"https://doi.org/10.1016/j.jvcir.2026.104965"},"language":"en","primary_location":{"id":"doi:10.1016/j.jvcir.2026.104965","doi":"https://doi.org/10.1016/j.jvcir.2026.104965","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.jvcir.2026.104965","pdf_url":null,"source":{"id":"https://openalex.org/S105424869","display_name":"Journal of Visual Communication and Image Representation","issn_l":"1047-3203","issn":["1047-3203","1095-9076"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","jufo-2","norway-2"],"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"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":"Journal of Visual Communication and Image Representation","raw_type":"journal-article"},"volume":null,"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1016/j.jvcir.2026.104965","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5151948901","display_name":"Yiwen Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiwen Wang","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, 200240, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, 200240, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138105823","display_name":"Ruiyan Wang","orcid":"https://orcid.org/0009-0002-0885-8311","observed_orcids":["https://orcid.org/0009-0002-0885-8311","https://orcid.org/0009-0007-8202-213X"]},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruiyan Wang","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, 200240, China"],"raw_orcid":"https://orcid.org/0009-0002-0885-8311","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, 200240, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065712326","display_name":"Zhengxue Cheng","orcid":"https://orcid.org/0009-0005-5364-7427","observed_orcids":["https://orcid.org/0009-0005-5364-7427"]},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhengxue Cheng","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, 200240, China"],"raw_orcid":"https://orcid.org/0009-0005-5364-7427","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, 200240, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002404808","display_name":"Li Song","orcid":"https://orcid.org/0000-0002-7124-5182","observed_orcids":["https://orcid.org/0000-0002-7124-5182"]},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Li Song","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, 200240, China"],"raw_orcid":"https://orcid.org/0000-0002-7124-5182","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, 200240, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5002404808","https://openalex.org/A5065712326"],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":{"value":2450,"currency":"USD","value_usd":2450},"apc_paid":{"value":2450,"currency":"USD","value_usd":2450},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.74857558,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"121","issue":null,"first_page":"104965","last_page":"104965"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9980000257492065,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9980000257492065,"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/T12290","display_name":"Human Motion and Animation","score":0.0015999999595806003,"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/T14254","display_name":"Digital Media and Visual Art","score":9.999999747378752e-05,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"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/vq-vae","display_name":"vector quantized variational autoencoder","score":0.7990000247955322},{"id":"https://openalex.org/keywords/identity-preservation","display_name":"identity preservation","score":0.6859999895095825},{"id":"https://openalex.org/keywords/human-motion-synthesis","display_name":"human motion synthesis","score":0.42399999499320984}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7098000049591064},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6690000295639038},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6068000197410583},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.600600004196167},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5375000238418579},{"id":"https://openalex.org/C502989409","wikidata":"https://www.wikidata.org/wiki/Q11425","display_name":"Animation","level":2,"score":0.42239999771118164},{"id":"https://openalex.org/C155650255","wikidata":"https://www.wikidata.org/wiki/Q259326","display_name":"Non-photorealistic rendering","level":5,"score":0.39989998936653137},{"id":"https://openalex.org/C44185422","wikidata":"https://www.wikidata.org/wiki/Q6002064","display_name":"Image-based modeling and rendering","level":3,"score":0.387800008058548},{"id":"https://openalex.org/C2989087649","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Image synthesis","level":3,"score":0.3353999853134155},{"id":"https://openalex.org/C138591656","wikidata":"https://www.wikidata.org/wiki/Q5157538","display_name":"Computer facial animation","level":4,"score":0.3273000121116638},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.31279999017715454},{"id":"https://openalex.org/C2987933465","wikidata":"https://www.wikidata.org/wiki/Q141130","display_name":"Image manipulation","level":3,"score":0.30070000886917114},{"id":"https://openalex.org/C13481523","wikidata":"https://www.wikidata.org/wiki/Q412438","display_name":"Image compression","level":4,"score":0.28060001134872437},{"id":"https://openalex.org/C55020928","wikidata":"https://www.wikidata.org/wiki/Q3813865","display_name":"Image quality","level":3,"score":0.2705000042915344},{"id":"https://openalex.org/C69369342","wikidata":"https://www.wikidata.org/wiki/Q1401416","display_name":"Computer animation","level":3,"score":0.2694999873638153},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.2646999955177307},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.259799987077713}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1016/j.jvcir.2026.104965","doi":"https://doi.org/10.1016/j.jvcir.2026.104965","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.jvcir.2026.104965","pdf_url":null,"source":{"id":"https://openalex.org/S105424869","display_name":"Journal of Visual Communication and Image Representation","issn_l":"1047-3203","issn":["1047-3203","1095-9076"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","jufo-2","norway-2"],"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"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":"Journal of Visual Communication and Image Representation","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1016/j.jvcir.2026.104965","doi":"https://doi.org/10.1016/j.jvcir.2026.104965","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.jvcir.2026.104965","pdf_url":null,"source":{"id":"https://openalex.org/S105424869","display_name":"Journal of Visual Communication and Image Representation","issn_l":"1047-3203","issn":["1047-3203","1095-9076"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","jufo-2","norway-2"],"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"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":"Journal of Visual Communication and Image Representation","raw_type":"journal-article"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321885","display_name":"Science and Technology Commission of Shanghai Municipality","ror":"https://ror.org/03kt66j61"},{"id":"https://openalex.org/F4320327718","display_name":"Shanghai Key Laboratory of Digital Media Processing and Transmission","ror":"https://ror.org/04gqa8725"},{"id":"https://openalex.org/F4320328119","display_name":"National University's Basic Research Foundation of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W2163301185","https://openalex.org/W2191779130","https://openalex.org/W3083173864","https://openalex.org/W3084572050","https://openalex.org/W3096831136","https://openalex.org/W3110017807","https://openalex.org/W3132524019","https://openalex.org/W3204221554","https://openalex.org/W4312671789","https://openalex.org/W4313167431","https://openalex.org/W4386065807","https://openalex.org/W4390190334","https://openalex.org/W4390871712","https://openalex.org/W4390873382","https://openalex.org/W4402704510","https://openalex.org/W4402716181","https://openalex.org/W4402727180","https://openalex.org/W4402754210","https://openalex.org/W4407947051","https://openalex.org/W4408459252","https://openalex.org/W4415537327","https://openalex.org/W4415539164","https://openalex.org/W6884306770"],"related_works":[],"abstract_inverted_index":{"Generating":[0],"dance":[1,122],"videos":[2],"from":[3,93],"music":[4],"and":[5,20,44,68,118,162,183],"a":[6,78,102,107,134,152],"single":[7],"reference":[8],"image":[9,109,147],"poses":[10],"significant":[11],"challenges,":[12,53],"including":[13],"realistic":[14],"motion":[15,34],"synthesis,":[16],"precise":[17],"rhythmic":[18,181],"alignment,":[19],"detailed":[21],"identity":[22,43,185],"preservation.":[23],"Existing":[24],"methods":[25],"often":[26],"fall":[27],"short":[28],"in":[29,115,180],"producing":[30],"long":[31],"yet":[32],"consistent":[33],"sequences":[35,91],"over":[36],"time,":[37],"while":[38],"also":[39],"preserving":[40],"the":[41,48,73,97,129,146,167],"visual":[42],"fine-grained":[45],"details":[46,168],"of":[47],"humans.":[49],"To":[50],"address":[51],"these":[52,111],"we":[54,76,100,132,150],"propose":[55,77],"DanceCrafter,":[56],"an":[57],"innovative":[58],"two-stage":[59],"framework":[60],"that":[61,85,156,174],"integrates":[62],"two":[63],"models":[64],"for":[65],"pose":[66,90],"generation":[67],"human":[69,108,121,184],"animation,":[70],"respectively.":[71],"In":[72,96],"first":[74],"stage,":[75,99],"Vector":[79],"Quantized":[80],"Variational":[81],"Autoencoder":[82],"(VQ-VAE)":[83],"model":[84],"generates":[86],"detailed,":[87],"rhythmically":[88],"aligned":[89],"directly":[92],"input":[94],"music.":[95],"second":[98],"employ":[101],"diffusion-based":[103],"approach":[104],"to":[105,125,160,165],"animate":[106],"with":[110,128,142],"synthesized":[112],"poses,":[113],"resulting":[114],"coherent,":[116],"realistic,":[117],"visually":[119],"appealing":[120],"videos.":[123],"Furthermore,":[124],"enhance":[126],"synchronization":[127],"musical":[130,143],"rhythm,":[131],"introduce":[133,151],"novel":[135],"beat":[136],"alignment":[137,141],"loss":[138],"ensuring":[139],"accurate":[140],"beats.":[144],"For":[145],"animation":[148],"model,":[149],"region":[153],"enhancement":[154],"strategy":[155],"assigns":[157],"greater":[158],"focus":[159],"hand":[161],"facial":[163],"areas":[164],"improve":[166],"generation.":[169],"Extensive":[170],"experimental":[171],"evaluations":[172],"demonstrate":[173],"our":[175],"method":[176],"outperforms":[177],"existing":[178],"approaches":[179],"coherence":[182],"consistency.":[186]},"counts_by_year":[],"updated_date":"2026-09-26T08:19:03.415552","created_date":"2026-09-17T00:00:00"}
