{"id":"https://openalex.org/W4414360374","doi":"https://doi.org/10.24963/ijcai.2025/1131","title":"AdaptEdit: An Adaptive Correspondence Guidance Framework for Reference-Based Video Editing","display_name":"AdaptEdit: An Adaptive Correspondence Guidance Framework for Reference-Based Video Editing","publication_year":2025,"publication_date":"2025-09-01","ids":{"openalex":"https://openalex.org/W4414360374","doi":"https://doi.org/10.24963/ijcai.2025/1131"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2025/1131","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/1131","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5054602568","display_name":"Tongtong Su","orcid":"https://orcid.org/0000-0003-4021-6466"},"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"]},{"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":"Tongtong Su","raw_affiliation_strings":["Alibaba Cloud Computing","Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Cloud Computing","institution_ids":["https://openalex.org/I45928872"]},{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100373451","display_name":"Chengyu Wang","orcid":"https://orcid.org/0000-0003-1010-9678"},"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":"Chengyu Wang","raw_affiliation_strings":["Alibaba Cloud Computing"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Cloud Computing","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101497182","display_name":"Bingyan Liu","orcid":"https://orcid.org/0000-0003-2613-9863"},"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"]},{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bingyan Liu","raw_affiliation_strings":["Alibaba Cloud Computing","South China University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Cloud Computing","institution_ids":["https://openalex.org/I45928872"]},{"raw_affiliation_string":"South China University of Technology","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059743923","display_name":"Jun Huang","orcid":"https://orcid.org/0000-0001-9207-8953"},"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":"Jun Huang","raw_affiliation_strings":["Alibaba Cloud Computing"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Cloud Computing","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050960677","display_name":"Dongming Lu","orcid":"https://orcid.org/0000-0002-7228-0887"},"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":"Dongming Lu","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"10180","last_page":"10188"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.991599977016449,"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/T11439","display_name":"Video Analysis and Summarization","score":0.991599977016449,"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/T12720","display_name":"Multimedia Communication and Technology","score":0.9753999710083008,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","score":0.9419000148773193,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/image-editing","display_name":"Image editing","score":0.6987000107765198},{"id":"https://openalex.org/keywords/video-editing","display_name":"Video editing","score":0.6715999841690063},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5396999716758728},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.5040000081062317},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.49639999866485596},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.44600000977516174},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4072999954223633},{"id":"https://openalex.org/keywords/video-tracking","display_name":"Video tracking","score":0.39329999685287476}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8661999702453613},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.6987000107765198},{"id":"https://openalex.org/C2780310081","wikidata":"https://www.wikidata.org/wiki/Q1154312","display_name":"Video editing","level":2,"score":0.6715999841690063},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5896999835968018},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5396999716758728},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5097000002861023},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5040000081062317},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.49639999866485596},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.44600000977516174},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4072999954223633},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.39329999685287476},{"id":"https://openalex.org/C155542232","wikidata":"https://www.wikidata.org/wiki/Q736111","display_name":"Optical flow","level":3,"score":0.383899986743927},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.3659000098705292},{"id":"https://openalex.org/C172849965","wikidata":"https://www.wikidata.org/wiki/Q3148875","display_name":"Reference frame","level":3,"score":0.3305000066757202},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.31700000166893005},{"id":"https://openalex.org/C2780967703","wikidata":"https://www.wikidata.org/wiki/Q2571389","display_name":"Collaborative editing","level":2,"score":0.31209999322891235},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3093999922275543},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.30160000920295715},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2921999990940094},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.2863999903202057},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.26350000500679016},{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.2624000012874603},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2597000002861023},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.25519999861717224}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2025/1131","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/1131","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Video":[0],"editing":[1,30,52,56,63,167],"is":[2],"a":[3,42,64,135,178,193],"pivotal":[4],"process":[5],"for":[6,29,141],"customizing":[7],"video":[8,51,79,95],"content":[9],"according":[10],"to":[11,20,76,120,138,151],"user":[12,23],"needs.":[13],"However,":[14],"existing":[15],"text-guided":[16],"methods":[17],"often":[18],"lead":[19],"ambiguities":[21],"regarding":[22],"intentions":[24],"and":[25,67,89,102],"restrict":[26],"fine-grained":[27],"control":[28],"specific":[31],"aspects":[32],"in":[33,129],"videos.":[34],"To":[35,163],"overcome":[36],"these":[37],"limitations,":[38],"this":[39,60],"paper":[40],"introduces":[41],"novel":[43],"approach":[44],"named":[45],"\\emph{AdaptEdit},":[46],"which":[47,182],"focuses":[48],"on":[49],"reference-based":[50],"that":[53,111],"disentangles":[54],"the":[55,78,90,114,117,121,130,149,153,169,189],"process.":[57],"It":[58],"achieves":[59],"by":[61,124,173],"first":[62],"reference":[65,118],"image":[66,142],"then":[68],"adaptively":[69],"propagating":[70],"its":[71],"appearance":[72,115],"across":[73],"other":[74],"frames":[75,123],"complete":[77],"editing.":[80],"While":[81],"previous":[82],"propagation":[83],"methods,":[84],"such":[85],"as":[86],"optical":[87],"flow":[88],"temporal":[91],"modules":[92],"of":[93,160,197],"recent":[94],"generative":[96],"models,":[97,175],"struggle":[98],"with":[99,192],"object":[100],"deformations":[101],"large":[103],"motions,":[104],"we":[105,176],"propose":[106],"an":[107],"adaptive":[108],"correspondence":[109],"strategy":[110],"accurately":[112,165],"transfers":[113],"from":[116],"frame":[119],"target":[122,154],"leveraging":[125],"inter-frame":[126],"semantic":[127],"correspondences":[128],"original":[131],"video.":[132],"By":[133],"implementing":[134],"proxy-editing":[136],"task":[137],"optimize":[139],"hyperparameters":[140],"token-level":[143],"correspondence,":[144],"our":[145],"method":[146,187],"effectively":[147],"balances":[148],"need":[150],"maintain":[152],"frame's":[155],"structure":[156],"while":[157],"preventing":[158],"leakage":[159],"irrelevant":[161],"appearance.":[162],"more":[164],"evaluate":[166],"beyond":[168],"semantic-level":[170],"consistency":[171],"provided":[172],"CLIP-style":[174],"introduce":[177],"new":[179],"dataset,":[180],"PVA,":[181],"supports":[183],"pixel-level":[184],"evaluation.":[185],"Our":[186],"outperforms":[188],"best-performing":[190],"baseline":[191],"clear":[194],"PSNR":[195],"improvement":[196],"3.6":[198],"dB.":[199]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
