{"id":"https://openalex.org/W4403780757","doi":"https://doi.org/10.1145/3664647.3680594","title":"Attentive Linguistic Tracking in Diffusion Models for Training-free Text-guided Image Editing","display_name":"Attentive Linguistic Tracking in Diffusion Models for Training-free Text-guided Image Editing","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403780757","doi":"https://doi.org/10.1145/3664647.3680594"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3680594","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3680594","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","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":null,"display_name":"Bingyan Liu","orcid":"https://orcid.org/0009-0005-5820-0704"},"institutions":[{"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":["South China University of Technology, Guangzhou, China"],"raw_orcid":"https://orcid.org/0009-0005-5820-0704","affiliations":[{"raw_affiliation_string":"South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"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 Group, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-1010-9678","affiliations":[{"raw_affiliation_string":"Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054621636","display_name":"Jun Huang","orcid":"https://orcid.org/0000-0002-7706-7081"},"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 Group, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-7706-7081","affiliations":[{"raw_affiliation_string":"Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101849748","display_name":"Kui Jia","orcid":"https://orcid.org/0000-0003-4748-5298"},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kui Jia","raw_affiliation_strings":["The Chinese University of Hong Kong, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0003-4748-5298","affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Shenzhen, China","institution_ids":["https://openalex.org/I4210116924"]}]}],"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":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4158","last_page":"4166"},"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":0.9987000226974487,"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":0.9987000226974487,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9818999767303467,"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/T10028","display_name":"Topic Modeling","score":0.9596999883651733,"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/computer-science","display_name":"Computer science","score":0.6964297294616699},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.572944700717926},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.5523633360862732},{"id":"https://openalex.org/keywords/image-editing","display_name":"Image editing","score":0.5459765791893005},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.5354118347167969},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.45953914523124695},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44794678688049316},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.44500917196273804},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.34335485100746155},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3406186103820801},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.3324757218360901},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.14819630980491638},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.06651481986045837},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.05819544196128845}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6964297294616699},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.572944700717926},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.5523633360862732},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.5459765791893005},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5354118347167969},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.45953914523124695},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44794678688049316},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.44500917196273804},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.34335485100746155},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3406186103820801},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.3324757218360901},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.14819630980491638},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.06651481986045837},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.05819544196128845},{"id":"https://openalex.org/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","level":1,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3664647.3680594","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3680594","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5299999713897705,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W569478347","https://openalex.org/W2962770929","https://openalex.org/W4214926101","https://openalex.org/W4281485151","https://openalex.org/W4281758439","https://openalex.org/W4286611278","https://openalex.org/W4312933868","https://openalex.org/W4385270985","https://openalex.org/W4385527149","https://openalex.org/W4385569875","https://openalex.org/W4386057725","https://openalex.org/W4386072096","https://openalex.org/W4386076215","https://openalex.org/W4386076532","https://openalex.org/W4386113271","https://openalex.org/W4389524329","https://openalex.org/W4390873054","https://openalex.org/W4390873195","https://openalex.org/W4394597404","https://openalex.org/W4402775818"],"related_works":["https://openalex.org/W4319453795","https://openalex.org/W4205104112","https://openalex.org/W1974870326","https://openalex.org/W2770776392","https://openalex.org/W3176454756","https://openalex.org/W2772330423","https://openalex.org/W3163523050","https://openalex.org/W3006381446","https://openalex.org/W4386301887","https://openalex.org/W3015353979"],"abstract_inverted_index":{"Building":[0],"on":[1,91,188],"recent":[2],"breakthroughs":[3],"in":[4,61,141,146,178],"diffusion-based":[5],"text-to-image":[6],"synthesis":[7],"(TIS),":[8],"training-free":[9],"text-guided":[10],"image":[11,22,51,87],"editing":[12,23,52,58,125],"(TIE)":[13],"has":[14],"emerged":[15],"as":[16],"an":[17,62],"indispensable":[18],"aspect":[19],"of":[20,30,83,127,144,175,182],"modern":[21],"practices.":[24],"This":[25],"technique":[26,138],"involves":[27],"the":[28,44,81,124,142,170,180],"modification":[29],"features":[31],"within":[32,41,93],"attention":[33,84],"layers":[34,95],"to":[35,96,150],"alter":[36],"objects":[37,60],"or":[38],"their":[39,117],"attributes":[40],"images":[42],"during":[43,86],"generation":[45],"process.":[46],"Despite":[47],"its":[48],"utility,":[49],"current":[50],"algorithms":[53],"face":[54],"challenges,":[55],"particularly":[56],"when":[57],"multiple":[59,128],"image.":[63],"In":[64],"this":[65],"paper,":[66],"we":[67,106],"introduce":[68],"VICTORIA,":[69],"a":[70,108,134,185],"novel":[71,109],"approach":[72],"that":[73,112,139,159],"augments":[74],"TIE":[75],"by":[76],"incorporating":[77],"linguistic":[78,120,135,176],"knowledge":[79],"into":[80],"manipulation":[82],"maps":[85],"generation.":[88],"VICTORIA":[89,160],"capitalizes":[90],"mechanisms":[92],"self-attention":[94],"ensure":[97],"spatial":[98],"consistency":[99],"between":[100],"source":[101],"and":[102,173],"target":[103,129],"images.":[104],"Further,":[105],"design":[107],"loss":[110],"function":[111],"refines":[113],"cross-attention":[114],"maps,":[115],"ensuring":[116],"alignment":[118],"with":[119,184],"constraints,":[121],"thereby":[122],"enhancing":[123],"precision":[126],"objects.":[130],"We":[131],"also":[132],"present":[133],"mask":[136],"blending":[137],"aids":[140],"retention":[143],"information":[145],"regions":[147],"not":[148],"subjected":[149],"modification.":[151],"Experimental":[152],"results":[153],"across":[154],"seven":[155],"diverse":[156],"datasets":[157],"show":[158],"achieves":[161],"significant":[162],"improvements":[163],"over":[164],"state-of-the-art":[165],"methods.":[166],"Our":[167],"work":[168],"underscores":[169],"critical":[171],"role":[172],"effectiveness":[174],"analysis":[177],"elevating":[179],"performance":[181],"TIE,":[183],"specific":[186],"emphasis":[187],"multi-object":[189],"scenarios.":[190],"The":[191],"code":[192],"is":[193],"available":[194],"at":[195],"https://github.com/alibaba/EasyNLP/tree/master/diffusion/VICTORIA.":[196]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}