{"id":"https://openalex.org/W4415537039","doi":"https://doi.org/10.1145/3746027.3755462","title":"UniEdit: A Unified Tuning-Free Framework for Video Motion and Appearance Editing","display_name":"UniEdit: A Unified Tuning-Free Framework for Video Motion and Appearance Editing","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415537039","doi":"https://doi.org/10.1145/3746027.3755462"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3755462","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3755462","pdf_url":null,"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 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3746027.3755462","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5104207086","display_name":"Jianhong Bai","orcid":"https://orcid.org/0000-0002-3121-7259"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianhong Bai","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-3121-7259","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013117915","display_name":"Tianyu He","orcid":"https://orcid.org/0000-0002-4828-3228"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianyu He","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-4828-3228","affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yuchi Wang","orcid":"https://orcid.org/0009-0000-1906-8820"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuchi Wang","raw_affiliation_strings":["Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0000-1906-8820","affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055122985","display_name":"Junliang Guo","orcid":"https://orcid.org/0000-0001-8360-5483"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junliang Guo","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-8360-5483","affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017732456","display_name":"Haoji Hu","orcid":"https://orcid.org/0000-0001-6048-6549"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoji Hu","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-6048-6549","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024343415","display_name":"Zuozhu Liu","orcid":"https://orcid.org/0000-0002-7816-502X"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zuozhu Liu","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-7816-502X","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101544241","display_name":"Jiang Bian","orcid":"https://orcid.org/0000-0002-9472-600X"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiang Bian","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-9472-600X","affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":7.0681,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.97415997,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"10171","last_page":"10180"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9994999766349792,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9994999766349792,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9991000294685364,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.9988999962806702,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.44679999351501465},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.3328000009059906},{"id":"https://openalex.org/keywords/video-tracking","display_name":"Video tracking","score":0.3075999915599823},{"id":"https://openalex.org/keywords/motion-estimation","display_name":"Motion estimation","score":0.2870999872684479},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.26190000772476196}],"concepts":[{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6733999848365784},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6503000259399414},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6186000108718872},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.44679999351501465},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.38519999384880066},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3328000009059906},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.3075999915599823},{"id":"https://openalex.org/C10161872","wikidata":"https://www.wikidata.org/wiki/Q557891","display_name":"Motion estimation","level":2,"score":0.2870999872684479},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.26190000772476196},{"id":"https://openalex.org/C95020103","wikidata":"https://www.wikidata.org/wiki/Q1813492","display_name":"Match moving","level":3,"score":0.25060001015663147}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3755462","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3755462","pdf_url":null,"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 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3746027.3755462","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3755462","pdf_url":null,"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 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W2964245526","https://openalex.org/W4312933868","https://openalex.org/W4386071957","https://openalex.org/W4386076215","https://openalex.org/W4386076280","https://openalex.org/W4386113271","https://openalex.org/W4390871782","https://openalex.org/W4390871980","https://openalex.org/W4390872862","https://openalex.org/W4390873054","https://openalex.org/W4390874575","https://openalex.org/W4390874580","https://openalex.org/W4391940619","https://openalex.org/W4402660110"],"related_works":[],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2,10,19],"text-guided":[3,100],"video":[4,16,30,49,74,148],"editing":[5,12,18,31,53,70,115,150,154],"have":[6],"showcased":[7],"promising":[8],"results":[9],"appearance":[11,52,153],"(e.g.,":[13,23],"stylization).":[14],"However,":[15],"motion":[17,50,69,101,149],"the":[20,56,78,113,126,158],"temporal":[21,81,118],"dimension":[22],"from":[24,32],"eating":[25],"to":[26,98],"waving),":[27],"which":[28],"distinguishes":[29],"image":[33],"editing,":[34],"is":[35,163],"underexplored.":[36],"In":[37],"this":[38],"work,":[39],"we":[40,91],"present":[41],"UniEdit,":[42],"a":[43,59],"tuning-free":[44],"framework":[45],"that":[46,80,145],"supports":[47],"both":[48],"and":[51,82,88,95,102,119,128,151,156],"by":[54,132],"harnessing":[55],"power":[57],"of":[58,130],"pre-trained":[60],"text-to-video":[61],"generator":[62],"within":[63],"an":[64],"inversion-then-generation":[65],"framework.":[66],"To":[67],"realize":[68],"while":[71],"preserving":[72],"source":[73,103],"content,":[75],"based":[76],"on":[77,135],"insights":[79],"spatial":[83,120],"self-attention":[84,121],"layers":[85],"encode":[86],"inter-frame":[87],"intra-frame":[89],"dependency,":[90],"introduce":[92],"auxiliary":[93],"motion-reference":[94],"reconstruction":[96],"branches":[97],"produce":[99],"features":[104,108],"respectively.":[105],"The":[106],"obtained":[107],"are":[109],"then":[110],"injected":[111],"into":[112],"main":[114],"path":[116],"via":[117],"layers.":[122],"We":[123],"also":[124],"validate":[125],"effectiveness":[127],"flexibility":[129],"UniEdit":[131,146],"deploying":[133],"it":[134],"three":[136],"T2V":[137],"generative":[138],"models":[139],"with":[140],"different":[141],"architectures.":[142],"Experiments":[143],"demonstrate":[144],"covers":[147],"various":[152],"scenarios,":[155],"surpasses":[157],"state-of-the-art":[159],"methods.":[160],"Our":[161],"code":[162],"publicly":[164],"available.":[165]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-25T00:00:00"}