{"id":"https://openalex.org/W4414359976","doi":"https://doi.org/10.24963/ijcai.2025/244","title":"AttentionDrag: Exploiting Latent Correlation Knowledge in Pre-trained Diffusion Models for Image Editing","display_name":"AttentionDrag: Exploiting Latent Correlation Knowledge in Pre-trained Diffusion Models for Image Editing","publication_year":2025,"publication_date":"2025-09-01","ids":{"openalex":"https://openalex.org/W4414359976","doi":"https://doi.org/10.24963/ijcai.2025/244"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2025/244","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/244","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/A5085793821","display_name":"Biao Yang","orcid":"https://orcid.org/0000-0002-3630-1169"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Biao Yang","raw_affiliation_strings":["Shanghai Key Laboratory of Data Science, School of Computer Science, Fudan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Key Laboratory of Data Science, School of Computer Science, Fudan University","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Muqi Huang","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":"Muqi Huang","raw_affiliation_strings":["Rajax Network Technology (ele.me), Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Rajax Network Technology (ele.me), Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100624911","display_name":"Yuhui Zhang","orcid":"https://orcid.org/0000-0001-7171-4009"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuhui Zhang","raw_affiliation_strings":["Shanghai Key Laboratory of Data Science, School of Computer Science, Fudan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Key Laboratory of Data Science, School of Computer Science, Fudan University","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001877137","display_name":"Yun Xiong","orcid":"https://orcid.org/0000-0002-8575-5415"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yun Xiong","raw_affiliation_strings":["Shanghai Key Laboratory of Data Science, School of Computer Science, Fudan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Key Laboratory of Data Science, School of Computer Science, Fudan University","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Kun Zhou","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":"Kun Zhou","raw_affiliation_strings":["Rajax Network Technology (ele.me), Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Rajax Network Technology (ele.me), Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030297934","display_name":"Xi Chen","orcid":"https://orcid.org/0009-0003-6156-4811"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xi Chen","raw_affiliation_strings":["Shanghai Key Laboratory of Data Science, School of Computer Science, Fudan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Key Laboratory of Data Science, School of Computer Science, Fudan University","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113147221","display_name":"Shiyang Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shiyang Zhou","raw_affiliation_strings":["Shanghai Key Laboratory of Data Science, School of Computer Science, Fudan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Key Laboratory of Data Science, School of Computer Science, Fudan University","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114189868","display_name":"H. -R. Bao","orcid":"https://orcid.org/0000-0001-5706-2155"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huishuai Bao","raw_affiliation_strings":["Shanghai Key Laboratory of Data Science, School of Computer Science, Fudan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Key Laboratory of Data Science, School of Computer Science, Fudan University","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100404427","display_name":"Chuan Li","orcid":"https://orcid.org/0000-0003-0004-1497"},"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":"Chuan Li","raw_affiliation_strings":["Rajax Network Technology (ele.me), Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Rajax Network Technology (ele.me), Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044868467","display_name":"Feng Shi","orcid":"https://orcid.org/0000-0003-1522-9943"},"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":"Feng Shi","raw_affiliation_strings":["Rajax Network Technology (ele.me), Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Rajax Network Technology (ele.me), Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075745968","display_name":"Hualei Liu","orcid":"https://orcid.org/0000-0002-7680-1854"},"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":"Hualei Liu","raw_affiliation_strings":["Rajax Network Technology (ele.me), Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Rajax Network Technology (ele.me), Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"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":"2188","last_page":"2196"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12422","display_name":"Radiomics and Machine Learning in Medical Imaging","score":0.9656999707221985,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T12422","display_name":"Radiomics and Machine Learning in Medical Imaging","score":0.9656999707221985,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10862","display_name":"AI in cancer detection","score":0.9625999927520752,"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"}},{"id":"https://openalex.org/T10552","display_name":"Colorectal Cancer Screening and Detection","score":0.9621999859809875,"subfield":{"id":"https://openalex.org/subfields/2730","display_name":"Oncology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/image-editing","display_name":"Image editing","score":0.8522999882698059},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5497000217437744},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.47269999980926514},{"id":"https://openalex.org/keywords/image-processing","display_name":"Image processing","score":0.4260999858379364},{"id":"https://openalex.org/keywords/latent-semantic-analysis","display_name":"Latent semantic analysis","score":0.4097000062465668},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.40799999237060547},{"id":"https://openalex.org/keywords/latent-image","display_name":"Latent image","score":0.40549999475479126},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.3873000144958496}],"concepts":[{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.8522999882698059},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8036999702453613},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5626000165939331},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5497000217437744},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.47269999980926514},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.4260999858379364},{"id":"https://openalex.org/C170133592","wikidata":"https://www.wikidata.org/wiki/Q1806883","display_name":"Latent semantic analysis","level":2,"score":0.4097000062465668},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.40799999237060547},{"id":"https://openalex.org/C205372313","wikidata":"https://www.wikidata.org/wiki/Q355645","display_name":"Latent image","level":3,"score":0.40549999475479126},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3873000144958496},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3723999857902527},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.367900013923645},{"id":"https://openalex.org/C2780310081","wikidata":"https://www.wikidata.org/wiki/Q1154312","display_name":"Video editing","level":2,"score":0.3431999981403351},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3391000032424927},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3147999942302704},{"id":"https://openalex.org/C2780967703","wikidata":"https://www.wikidata.org/wiki/Q2571389","display_name":"Collaborative editing","level":2,"score":0.3027999997138977},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.2915000021457672},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.28380000591278076},{"id":"https://openalex.org/C143587482","wikidata":"https://www.wikidata.org/wiki/Q1543216","display_name":"Iterative and incremental development","level":2,"score":0.2831999957561493},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.26489999890327454},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.25540000200271606},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.25529998540878296},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.2540000081062317}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2025/244","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/244","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Traditional":[0],"point-based":[1,54,168],"image":[2,38,55,74,120,169],"editing":[3,39,56,75,135,170],"methods":[4,31,154],"rely":[5],"on":[6],"iterative":[7],"latent":[8,64,97],"optimization":[9],"or":[10,20,91],"geometric":[11],"transformations,":[12],"which":[13,60],"are":[14],"either":[15],"inefficient":[16],"in":[17,42,105],"their":[18],"processing":[19],"fail":[21],"to":[22,114,132],"capture":[23],"the":[24,28,34,62,86,96,102,106,110,134],"semantic":[25,80,123],"relationships":[26],"within":[27,69],"image.":[29],"These":[30],"often":[32],"overlook":[33],"powerful":[35],"yet":[36],"underutilized":[37],"capabilities":[40],"inherent":[41,63],"pre-trained":[43,70],"diffusion":[44,71],"models.":[45],"In":[46],"this":[47],"work,":[48],"we":[49,94],"propose":[50],"a":[51,148,160],"novel":[52],"one-step":[53],"method,":[57],"named":[58],"\\textbf{AttentionDrag},":[59],"leverages":[61],"knowledge":[65,99],"and":[66,82,117,125,139,163],"feature":[67],"correlations":[68,98],"models":[72],"for":[73,88,167],"tasks.":[76,171],"This":[77],"framework":[78],"enables":[79],"consistency":[81],"high-quality":[83],"manipulation":[84],"without":[85],"need":[87],"extensive":[89],"re-optimization":[90],"retraining.":[92],"Specifically,":[93],"reutilize":[95],"learned":[100],"by":[101],"self-attention":[103],"mechanism":[104],"U-Net":[107],"module":[108],"during":[109],"DDIM":[111],"inversion":[112],"process":[113],"automatically":[115],"identify":[116],"adjust":[118],"relevant":[119],"regions,":[121],"ensuring":[122],"validity":[124],"consistency.":[126],"Additionally,":[127],"AttentionDrag":[128],"adaptively":[129],"generates":[130],"masks":[131],"guide":[133],"process,":[136],"enabling":[137],"precise":[138],"context-aware":[140],"modifications":[141],"with":[142,155],"friendly":[143],"interaction.":[144],"Our":[145],"results":[146],"demonstrate":[147],"performance":[149],"that":[150],"surpasses":[151],"most":[152],"state-of-the-art":[153],"significantly":[156],"faster":[157],"speeds,":[158],"showing":[159],"more":[161],"efficient":[162],"semantically":[164],"coherent":[165],"solution":[166],"Code":[172],"is":[173],"released":[174],"at:":[175],"https://github.com/GPlaying/AttentionDrag.":[176]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}