{"id":"https://openalex.org/W4414565121","doi":"https://doi.org/10.1109/iccv51701.2025.01597","title":"VACE: All-in-One Video Creation and Editing","display_name":"VACE: All-in-One Video Creation and Editing","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4414565121","doi":"https://doi.org/10.1109/iccv51701.2025.01597"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01597","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01597","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2503.07598","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5036869159","display_name":"Zeyinzi Jiang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Zeyinzi Jiang","raw_affiliation_strings":["Tongyi Lab, Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tongyi Lab, Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100748570","display_name":"Zhen Han","orcid":"https://orcid.org/0000-0002-9547-9063"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhen Han","raw_affiliation_strings":["Tongyi Lab, Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tongyi Lab, Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049980050","display_name":"Chaojie Mao","orcid":null},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chaojie Mao","raw_affiliation_strings":["Tongyi Lab, Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tongyi Lab, Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100749004","display_name":"Jingfeng Zhang","orcid":"https://orcid.org/0000-0003-3491-8074"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jingfeng Zhang","raw_affiliation_strings":["Tongyi Lab, Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tongyi Lab, Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101339698","display_name":"Yulin Pan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yulin Pan","raw_affiliation_strings":["Tongyi Lab, Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tongyi Lab, Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004545610","display_name":"Yu Liu","orcid":"https://orcid.org/0000-0002-2399-2829"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yu Liu","raw_affiliation_strings":["Tongyi Lab, Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tongyi Lab, Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5036869159"],"corresponding_institution_ids":["https://openalex.org/I4210095624"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.33832075,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"17191","last_page":"17202"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10758","display_name":"Cinema and Media Studies","score":0.1451999992132187,"subfield":{"id":"https://openalex.org/subfields/2002","display_name":"Economics and Econometrics"},"field":{"id":"https://openalex.org/fields/20","display_name":"Economics, Econometrics and Finance"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10758","display_name":"Cinema and Media Studies","score":0.1451999992132187,"subfield":{"id":"https://openalex.org/subfields/2002","display_name":"Economics and Econometrics"},"field":{"id":"https://openalex.org/fields/20","display_name":"Economics, Econometrics and Finance"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.534600019454956},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4973999857902527},{"id":"https://openalex.org/keywords/unification","display_name":"Unification","score":0.44920000433921814},{"id":"https://openalex.org/keywords/video-tracking","display_name":"Video tracking","score":0.41449999809265137},{"id":"https://openalex.org/keywords/adapter","display_name":"Adapter (computing)","score":0.4047999978065491},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.3806999921798706},{"id":"https://openalex.org/keywords/context-model","display_name":"Context model","score":0.353300005197525},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.3479999899864197}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8410000205039978},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.534600019454956},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4973999857902527},{"id":"https://openalex.org/C96146094","wikidata":"https://www.wikidata.org/wiki/Q609057","display_name":"Unification","level":2,"score":0.44920000433921814},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.41449999809265137},{"id":"https://openalex.org/C177284502","wikidata":"https://www.wikidata.org/wiki/Q1005390","display_name":"Adapter (computing)","level":2,"score":0.4047999978065491},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3959999978542328},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.3806999921798706},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.353300005197525},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.3479999899864197},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34060001373291016},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.328900009393692},{"id":"https://openalex.org/C2776449333","wikidata":"https://www.wikidata.org/wiki/Q7928781","display_name":"View synthesis","level":3,"score":0.31949999928474426},{"id":"https://openalex.org/C65483669","wikidata":"https://www.wikidata.org/wiki/Q3536669","display_name":"Video processing","level":2,"score":0.29840001463890076},{"id":"https://openalex.org/C2780310081","wikidata":"https://www.wikidata.org/wiki/Q1154312","display_name":"Video editing","level":2,"score":0.2978000044822693},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.29190000891685486},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.28600001335144043},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.2777999937534332},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.27489998936653137},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.2556999921798706},{"id":"https://openalex.org/C108803254","wikidata":"https://www.wikidata.org/wiki/Q857512","display_name":"Smacker video","level":4,"score":0.2513999938964844}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.01597","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01597","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2503.07598","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.07598","pdf_url":"https://arxiv.org/pdf/2503.07598","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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.2503.07598","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2503.07598","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":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2503.07598","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.07598","pdf_url":"https://arxiv.org/pdf/2503.07598","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Diffusion":[0],"Transformer":[1],"has":[2,23],"demonstrated":[3],"powerful":[4],"capability":[5],"and":[6,12,20,45,73,82,104,138],"scalability":[7],"in":[8,27],"generating":[9],"high-quality":[10],"images":[11],"videos.":[13],"Further":[14],"pursuing":[15],"the":[16,28,37,90,113,131,154],"unification":[17],"of":[18,30,92,136,157],"generation":[19],"editing":[21],"tasks":[22,66,76,94,148],"yielded":[24],"significant":[25],"progress":[26],"domain":[29],"image":[31],"content":[32],"creation.":[33],"However,":[34],"due":[35],"to":[36,63,111,143],"intrinsic":[38],"demands":[39],"for":[40,52,71],"consistency":[41],"across":[42,166],"both":[43],"temporal":[44,137],"spatial":[46,139],"dynamics,":[47],"achieving":[48],"a":[49,107,121],"unified":[50,108,155],"approach":[51],"video":[53,97,146],"synthesis":[54,147],"remains":[55],"challenging.":[56],"We":[57],"introduce":[58],"VACE,":[59],"which":[60],"enables":[61,171],"users":[62],"perform":[64],"Video":[65,114],"within":[67],"an":[68],"All-in-one":[69],"framework":[70],"Creation":[72],"Editing.":[74],"These":[75],"include":[77],"reference-to-video":[78],"generation,":[79],"video-to-video":[80,84],"editing,":[81,102],"masked":[83],"editing.":[85],"Specifically,":[86],"we":[87,125],"effectively":[88],"integrate":[89],"requirements":[91],"various":[93,167],"by":[95,119],"organizing":[96],"task":[98,128,176],"inputs,":[99],"such":[100],"as":[101,112],"reference,":[103],"masking,":[105],"into":[106,130],"interface":[109],"referred":[110],"Condition":[115],"Unit":[116],"(VCU).":[117],"Furthermore,":[118],"utilizing":[120],"Context":[122],"Adapter":[123],"structure,":[124],"inject":[126],"different":[127],"concepts":[129],"model":[132,156],"using":[133],"formalized":[134],"representations":[135],"dimensions,":[140],"allowing":[141],"it":[142,170],"handle":[144],"arbitrary":[145],"flexibly.":[149],"Extensive":[150],"experiments":[151],"demonstrate":[152],"that":[153],"VACE":[158],"achieves":[159],"performance":[160],"on":[161],"par":[162],"with":[163],"task-specific":[164],"models":[165],"subtasks.":[168],"Simultaneously,":[169],"diverse":[172],"applications":[173],"through":[174],"versatile":[175],"combinations.":[177],"Project":[178],"page:":[179],"https://ali-vilab.github.io/VACE-Page/.":[180]},"counts_by_year":[],"updated_date":"2026-05-06T06:03:25.996018","created_date":"2025-10-10T00:00:00"}
