{"id":"https://openalex.org/W7131126688","doi":"https://doi.org/10.1109/iccvw69036.2025.00206","title":"StyleBooth: Image Style Editing with Multimodal Instruction","display_name":"StyleBooth: Image Style Editing with Multimodal Instruction","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W7131126688","doi":"https://doi.org/10.1109/iccvw69036.2025.00206"},"language":null,"primary_location":{"id":"doi:10.1109/iccvw69036.2025.00206","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccvw69036.2025.00206","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW)","raw_type":"proceedings-article"},"type":"article","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/A5126625354","display_name":"Zhen Han","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"]},{"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","US"],"is_corresponding":true,"raw_author_name":"Zhen Han","raw_affiliation_strings":["Alibaba Group,Tongyi Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group,Tongyi Lab","institution_ids":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124255825","display_name":"Chaojie Mao","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"]},{"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","US"],"is_corresponding":false,"raw_author_name":"Chaojie Mao","raw_affiliation_strings":["Alibaba Group,Tongyi Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group,Tongyi Lab","institution_ids":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036869159","display_name":"Zeyinzi Jiang","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"]},{"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","US"],"is_corresponding":false,"raw_author_name":"Zeyinzi Jiang","raw_affiliation_strings":["Alibaba Group,Tongyi Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group,Tongyi Lab","institution_ids":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126609439","display_name":"Yulin Pan","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"]},{"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","US"],"is_corresponding":false,"raw_author_name":"Yulin Pan","raw_affiliation_strings":["Alibaba Group,Tongyi Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group,Tongyi Lab","institution_ids":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5126635954","display_name":"Jingfeng Zhang","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"]},{"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","US"],"is_corresponding":false,"raw_author_name":"Jingfeng Zhang","raw_affiliation_strings":["Alibaba Group,Tongyi Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group,Tongyi Lab","institution_ids":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5126625354"],"corresponding_institution_ids":["https://openalex.org/I4210095624","https://openalex.org/I45928872"],"apc_list":null,"apc_paid":null,"fwci":1.1092,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.85295897,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1968","last_page":"1978"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.32260000705718994,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.32260000705718994,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.13850000500679016,"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":0.06849999725818634,"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/image-editing","display_name":"Image editing","score":0.9039999842643738},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.7333999872207642},{"id":"https://openalex.org/keywords/usability","display_name":"Usability","score":0.5978999733924866},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5489000082015991},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5292999744415283},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.4894999861717224},{"id":"https://openalex.org/keywords/style","display_name":"Style (visual arts)","score":0.4747999906539917}],"concepts":[{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.9039999842643738},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7904999852180481},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.7333999872207642},{"id":"https://openalex.org/C170130773","wikidata":"https://www.wikidata.org/wiki/Q216378","display_name":"Usability","level":2,"score":0.5978999733924866},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5489000082015991},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5292999744415283},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.4894999861717224},{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.4747999906539917},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.428600013256073},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.42480000853538513},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3896999955177307},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.374099999666214},{"id":"https://openalex.org/C2780967703","wikidata":"https://www.wikidata.org/wiki/Q2571389","display_name":"Collaborative editing","level":2,"score":0.3361000120639801},{"id":"https://openalex.org/C2780310081","wikidata":"https://www.wikidata.org/wiki/Q1154312","display_name":"Video editing","level":2,"score":0.33550000190734863},{"id":"https://openalex.org/C2987933465","wikidata":"https://www.wikidata.org/wiki/Q141130","display_name":"Image manipulation","level":3,"score":0.2922999858856201},{"id":"https://openalex.org/C55020928","wikidata":"https://www.wikidata.org/wiki/Q3813865","display_name":"Image quality","level":3,"score":0.28459998965263367},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2678000032901764},{"id":"https://openalex.org/C109747225","wikidata":"https://www.wikidata.org/wiki/Q815758","display_name":"Scarcity","level":2,"score":0.2639000117778778},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.25360000133514404}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iccvw69036.2025.00206","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccvw69036.2025.00206","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5290699601173401,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W2145023731","https://openalex.org/W2550673061","https://openalex.org/W2955639361","https://openalex.org/W2962770929","https://openalex.org/W2963073614","https://openalex.org/W2963767194","https://openalex.org/W3183252420","https://openalex.org/W4286611278","https://openalex.org/W4312872987","https://openalex.org/W4312933868","https://openalex.org/W4385801729","https://openalex.org/W4386071613","https://openalex.org/W4386076215","https://openalex.org/W4386076532","https://openalex.org/W4390871982","https://openalex.org/W4390872351","https://openalex.org/W4390873054","https://openalex.org/W4390873195","https://openalex.org/W4390873331","https://openalex.org/W4394625831","https://openalex.org/W4402716004","https://openalex.org/W4402753379","https://openalex.org/W4402753750","https://openalex.org/W4404526287","https://openalex.org/W4413146222"],"related_works":[],"abstract_inverted_index":{"Given":[0],"an":[1,9],"original":[2,98],"image,":[3],"image":[4,10,38,52,66,85,99,119],"editing":[5,54,67,77,96,109,145,177],"aims":[6],"to":[7,20,165],"generate":[8],"that":[11,60,153],"align":[12],"with":[13],"the":[14,95,113,128,154,163,170],"provided":[15],"instruction.":[16],"The":[17,150],"challenges":[18],"are":[19],"accept":[21],"multimodal":[22,41,101],"inputs":[23],"as":[24,87,139],"instructions":[25],"and":[26,40,43,55,68,84,108,110,146,156,168],"a":[27,58,62,69,74,88],"scarcity":[28],"of":[29,36,97,124,130,158,173],"high-quality":[30,75],"training":[31,159],"data,":[32],"including":[33],"crucial":[34],"triplets":[35],"source/target":[37],"pairs":[39,120],"(text":[42],"image)":[44],"instructions.":[45,102],"In":[46],"this":[47],"paper,":[48],"we":[49,132],"focus":[50],"on":[51,135],"style":[53,76,141,144,148],"present":[56],"StyleBooth,":[57],"method":[59],"proposes":[61],"comprehensive":[63],"framework":[64],"for":[65,72,91],"feasible":[70],"strategy":[71],"building":[73],"dataset.":[78],"We":[79],"integrate":[80],"encoded":[81],"textual":[82],"instruction":[83],"exemplar":[86],"unified":[89],"condition":[90],"diffusion":[92],"model,":[93],"enabling":[94],"following":[100],"Furthermore,":[103],"by":[104],"iterative":[105],"style-destyle":[106],"tuning":[107],"usability":[111],"filtering,":[112],"StyleBooth":[114],"dataset":[115],"provides":[116],"content-consistent":[117],"stylized/plain":[118],"in":[121,176],"various":[122],"categories":[123],"styles.":[125],"To":[126],"show":[127],"flexibility":[129],"Style-Booth,":[131],"conduct":[133],"experiments":[134],"diverse":[136],"tasks,":[137],"such":[138],"text-based":[140],"editing,":[142],"exemplar-based":[143],"compositional":[147],"editing.":[149],"results":[151],"demonstrate":[152],"quality":[155,172],"variety":[157],"data":[160],"significantly":[161],"enhance":[162],"ability":[164],"preserve":[166],"content":[167],"improve":[169],"overall":[171],"generated":[174],"images":[175],"tasks.":[178],"Project":[179],"page":[180],"can":[181],"be":[182],"found":[183],"at":[184],"https://ali-vilab.github.io/stylebooth-page/":[185]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-05-03T08:25:01.440150","created_date":"2026-02-24T00:00:00"}
