{"id":"https://openalex.org/W4393154259","doi":"https://doi.org/10.1609/aaai.v38i4.28111","title":"Multi-Region Text-Driven Manipulation of Diffusion Imagery","display_name":"Multi-Region Text-Driven Manipulation of Diffusion Imagery","publication_year":2024,"publication_date":"2024-03-24","ids":{"openalex":"https://openalex.org/W4393154259","doi":"https://doi.org/10.1609/aaai.v38i4.28111"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v38i4.28111","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v38i4.28111","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/28111/28226","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/28111/28226","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100346332","display_name":"Yiming Li","orcid":"https://orcid.org/0000-0002-2258-265X"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiming Li","raw_affiliation_strings":["Shanghai Key Lab of Digital Media Processing and Transmission, Shanghai Jiao Tong University\nMoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Key Lab of Digital Media Processing and Transmission, Shanghai Jiao Tong University\nMoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038636096","display_name":"Peng Zhou","orcid":"https://orcid.org/0000-0003-4726-3054"},"institutions":[{"id":"https://openalex.org/I180662265","display_name":"China Mobile (China)","ror":"https://ror.org/05gftfe97","country_code":"CN","type":"company","lineage":["https://openalex.org/I180662265"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng Zhou","raw_affiliation_strings":["China Mobile (Suzhou) Software Technology Co., Ltd, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China Mobile (Suzhou) Software Technology Co., Ltd, China","institution_ids":["https://openalex.org/I180662265"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100327203","display_name":"Jun Sun","orcid":"https://orcid.org/0000-0002-9824-4294"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Sun","raw_affiliation_strings":["Shanghai Key Lab of Digital Media Processing and Transmission, Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Key Lab of Digital Media Processing and Transmission, Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018343158","display_name":"Yi Xu","orcid":"https://orcid.org/0000-0003-2126-6054"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Xu","raw_affiliation_strings":["Shanghai Key Lab of Digital Media Processing and Transmission, Shanghai Jiao Tong University\nMoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Key Lab of Digital Media Processing and Transmission, Shanghai Jiao Tong University\nMoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"38","issue":"4","first_page":"3261","last_page":"3269"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13523","display_name":"Mathematics, Computing, and Information Processing","score":0.6420000195503235,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T13523","display_name":"Mathematics, Computing, and Information Processing","score":0.6420000195503235,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T14339","display_name":"Image Processing and 3D Reconstruction","score":0.6035000085830688,"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":0.5982999801635742,"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/diffusion","display_name":"Diffusion","score":0.6287493705749512},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.49247512221336365},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3735727071762085},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.35553255677223206},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.3372114300727844},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.3331448435783386},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.2578851580619812},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.10914796590805054}],"concepts":[{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.6287493705749512},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.49247512221336365},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3735727071762085},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.35553255677223206},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.3372114300727844},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.3331448435783386},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.2578851580619812},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.10914796590805054},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1609/aaai.v38i4.28111","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v38i4.28111","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/28111/28226","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:ojs.aaai.org:article/28111","is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/28111","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v38i4.28111","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v38i4.28111","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/28111/28226","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4393154259.pdf"},"referenced_works_count":80,"referenced_works":["https://openalex.org/W2916671372","https://openalex.org/W2965289598","https://openalex.org/W2970562079","https://openalex.org/W2972328244","https://openalex.org/W2982450728","https://openalex.org/W3013504650","https://openalex.org/W3013944633","https://openalex.org/W3035515747","https://openalex.org/W3036167779","https://openalex.org/W3102061158","https://openalex.org/W3121370741","https://openalex.org/W3122887982","https://openalex.org/W3162926177","https://openalex.org/W3163884521","https://openalex.org/W3165647589","https://openalex.org/W3166396011","https://openalex.org/W3168053944","https://openalex.org/W3173102319","https://openalex.org/W3178406257","https://openalex.org/W3216352822","https://openalex.org/W4200633008","https://openalex.org/W4200634729","https://openalex.org/W4220968945","https://openalex.org/W4221152065","https://openalex.org/W4221159622","https://openalex.org/W4223418030","https://openalex.org/W4224035735","https://openalex.org/W4224951336","https://openalex.org/W4225744354","https://openalex.org/W4226125322","https://openalex.org/W4226175584","https://openalex.org/W4226317937","https://openalex.org/W4287029626","https://openalex.org/W4288099666","https://openalex.org/W4289785045","https://openalex.org/W4289785095","https://openalex.org/W4293342478","https://openalex.org/W4297808394","https://openalex.org/W4306177323","https://openalex.org/W4306809142","https://openalex.org/W4306809168","https://openalex.org/W4307073290","https://openalex.org/W4309398423","https://openalex.org/W4309398467","https://openalex.org/W4312282373","https://openalex.org/W4312680947","https://openalex.org/W4312740349","https://openalex.org/W4312872987","https://openalex.org/W4312931308","https://openalex.org/W4312933868","https://openalex.org/W4312995674","https://openalex.org/W4318203092","https://openalex.org/W4319299843","https://openalex.org/W4319300158","https://openalex.org/W4319452911","https://openalex.org/W4321276804","https://openalex.org/W4321854185","https://openalex.org/W4327525621","https://openalex.org/W4327673614","https://openalex.org/W4360884927","https://openalex.org/W4361865933","https://openalex.org/W4363671612","https://openalex.org/W4364383299","https://openalex.org/W4365600729","https://openalex.org/W4385271281","https://openalex.org/W4385537492","https://openalex.org/W4385682474","https://openalex.org/W4386057725","https://openalex.org/W4386072096","https://openalex.org/W4386076215","https://openalex.org/W4386076403","https://openalex.org/W4386076532","https://openalex.org/W6767384525","https://openalex.org/W6776111094","https://openalex.org/W6779823529","https://openalex.org/W6790577477","https://openalex.org/W6795288823","https://openalex.org/W6797469170","https://openalex.org/W6838178482","https://openalex.org/W6842465419"],"related_works":["https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2772917594","https://openalex.org/W2775347418","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Text-guided":[0],"image":[1,12,46,183],"manipulation":[2,47,50],"has":[3],"attracted":[4],"significant":[5],"attention":[6],"recently.":[7],"Prevailing":[8],"techniques":[9],"concentrate":[10],"on":[11,36,99,122],"attribute":[13],"editing":[14],"for":[15,126,146,152,171],"individual":[16],"objects,":[17],"however,":[18],"encountering":[19],"challenges":[20],"when":[21,103],"it":[22],"comes":[23],"to":[24,63,94,105],"multi-object":[25,70,100],"editing.":[26],"The":[27],"main":[28],"reason":[29],"is":[30,150,168,187],"the":[31,37,64,106,108,117],"lack":[32],"of":[33,67,110,143,164],"consistency":[34],"constraints":[35],"spatial":[38,71,97],"layout.":[39],"This":[40],"work":[41],"presents":[42],"a":[43,58,68,79,133,140],"multi-region":[44,147],"guided":[45],"framework,":[48],"enabling":[49],"through":[51],"region-level":[52],"textual":[53],"prompts.":[54],"With":[55],"MultiDiffusion":[56],"as":[57,78],"baseline,":[59],"we":[60,88,131,138],"are":[61,76],"dedicated":[62],"automatic":[65],"generation":[66],"rational":[69],"distribution,":[72],"where":[73],"disparate":[74],"regions":[75],"fused":[77],"unified":[80],"entity.":[81],"To":[82,119],"mitigate":[83],"interference":[84],"from":[85],"regional":[86],"fusion,":[87],"employ":[89],"an":[90],"off-the-shelf":[91],"model":[92],"(CLIP)":[93],"impose":[95],"region-aware":[96],"guidance":[98,128],"manipulation.":[101,118],"Moreover,":[102],"applied":[104],"StableDiffusion,":[107],"presence":[109],"quality-related":[111],"yet":[112],"object-agnostic":[113],"lengthy":[114],"words":[115,125],"hampers":[116],"ensure":[120],"focus":[121],"meaningful":[123],"object-specific":[124],"efficient":[127],"and":[129],"generation,":[130,180],"introduce":[132],"keyword":[134],"selection":[135],"method.":[136],"Furthermore,":[137],"demonstrate":[139],"downstream":[141],"application":[142],"our":[144],"method":[145],"inversion,":[148],"which":[149],"tailored":[151],"manipulating":[153,172],"multiple":[154],"objects":[155,174],"in":[156,175],"real":[157],"images.":[158],"Our":[159],"approach,":[160],"compatible":[161],"with":[162,178],"variants":[163],"Stable":[165],"Diffusion":[166],"models,":[167],"readily":[169],"applicable":[170],"diverse":[173],"extensive":[176],"images":[177],"high-quality":[179],"showing":[181],"superb":[182],"control":[184],"capabilities.":[185],"Code":[186],"available":[188],"at":[189],"https://github.com/liyiming09/multi-region-guided-diffusion.":[190]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}
