{"id":"https://openalex.org/W4415536828","doi":"https://doi.org/10.1145/3746027.3755429","title":"Prompt-Softbox-Prompt: A Free-Text Embedding Control for Image Editing","display_name":"Prompt-Softbox-Prompt: A Free-Text Embedding Control for Image Editing","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415536828","doi":"https://doi.org/10.1145/3746027.3755429"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3755429","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755429","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd 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":"https://openalex.org/A5019452865","display_name":"Yitong Yang","orcid":"https://orcid.org/0000-0001-5855-7248"},"institutions":[{"id":"https://openalex.org/I181679659","display_name":"Shanghai University of Finance and Economics","ror":"https://ror.org/00wtvfq62","country_code":"CN","type":"education","lineage":["https://openalex.org/I181679659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yitong Yang","raw_affiliation_strings":["Shanghai University of Finance and Economics, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-5855-7248","affiliations":[{"raw_affiliation_string":"Shanghai University of Finance and Economics, Shanghai, China","institution_ids":["https://openalex.org/I181679659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030131997","display_name":"Yinglin Wang","orcid":"https://orcid.org/0000-0002-0276-5029"},"institutions":[{"id":"https://openalex.org/I181679659","display_name":"Shanghai University of Finance and Economics","ror":"https://ror.org/00wtvfq62","country_code":"CN","type":"education","lineage":["https://openalex.org/I181679659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yinglin Wang","raw_affiliation_strings":["School of Computing and Aritificial Intelligence, Shanghai University of Finance and Economics, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-0276-5029","affiliations":[{"raw_affiliation_string":"School of Computing and Aritificial Intelligence, Shanghai University of Finance and Economics, Shanghai, China","institution_ids":["https://openalex.org/I181679659"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Tian Zhang","orcid":"https://orcid.org/0009-0004-9507-3049"},"institutions":[{"id":"https://openalex.org/I181679659","display_name":"Shanghai University of Finance and Economics","ror":"https://ror.org/00wtvfq62","country_code":"CN","type":"education","lineage":["https://openalex.org/I181679659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tian Zhang","raw_affiliation_strings":["Shanghai University of Finance and Economics, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0004-9507-3049","affiliations":[{"raw_affiliation_string":"Shanghai University of Finance and Economics, Shanghai, China","institution_ids":["https://openalex.org/I181679659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100378503","display_name":"Jing Wang","orcid":"https://orcid.org/0000-0002-3941-2147"},"institutions":[{"id":"https://openalex.org/I181679659","display_name":"Shanghai University of Finance and Economics","ror":"https://ror.org/00wtvfq62","country_code":"CN","type":"education","lineage":["https://openalex.org/I181679659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Wang","raw_affiliation_strings":["Shanghai University of Finance and Economics, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-3941-2147","affiliations":[{"raw_affiliation_string":"Shanghai University of Finance and Economics, Shanghai, China","institution_ids":["https://openalex.org/I181679659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085200012","display_name":"Shuting He","orcid":"https://orcid.org/0000-0002-1582-5684"},"institutions":[{"id":"https://openalex.org/I181679659","display_name":"Shanghai University of Finance and Economics","ror":"https://ror.org/00wtvfq62","country_code":"CN","type":"education","lineage":["https://openalex.org/I181679659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuting He","raw_affiliation_strings":["MoE Key Laboratory of Interdisciplinary Research of Computation and Economics, Shanghai University of Finance and Economics, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-1582-5684","affiliations":[{"raw_affiliation_string":"MoE Key Laboratory of Interdisciplinary Research of Computation and Economics, Shanghai University of Finance and Economics, Shanghai, China","institution_ids":["https://openalex.org/I181679659"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I181679659"],"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":"10132","last_page":"10141"},"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":0.9959999918937683,"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":0.9959999918937683,"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/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.9627000093460083,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"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/T11439","display_name":"Video Analysis and Summarization","score":0.9562000036239624,"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/embedding","display_name":"Embedding","score":0.8130000233650208},{"id":"https://openalex.org/keywords/image-editing","display_name":"Image editing","score":0.6248000264167786},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.6065999865531921},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5717999935150146},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5685999989509583},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5680999755859375},{"id":"https://openalex.org/keywords/ambiguity","display_name":"Ambiguity","score":0.5428000092506409}],"concepts":[{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.8130000233650208},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.732699990272522},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.6248000264167786},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.6065999865531921},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5717999935150146},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5685999989509583},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5680999755859375},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.5428000092506409},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5045999884605408},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4767000079154968},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.44029998779296875},{"id":"https://openalex.org/C2777462759","wikidata":"https://www.wikidata.org/wiki/Q18395344","display_name":"Word embedding","level":3,"score":0.43209999799728394},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3781999945640564},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.36010000109672546},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.3531999886035919},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3255000114440918},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3124000132083893},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.31029999256134033},{"id":"https://openalex.org/C86034646","wikidata":"https://www.wikidata.org/wiki/Q474311","display_name":"Semantic gap","level":4,"score":0.2922999858856201},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.28870001435279846}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3755429","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755429","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7344333925","display_name":null,"funder_award_id":"25ZR1402138","funder_id":"https://openalex.org/F4320309612","funder_display_name":"Natural Science Foundation of Shanghai"}],"funders":[{"id":"https://openalex.org/F4320309612","display_name":"Natural Science Foundation of Shanghai","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W2962785568","https://openalex.org/W2963966654","https://openalex.org/W2964024144","https://openalex.org/W4312740349","https://openalex.org/W4312933868","https://openalex.org/W4386057777","https://openalex.org/W4386071604","https://openalex.org/W4386072096","https://openalex.org/W4386076215","https://openalex.org/W4386076532","https://openalex.org/W4386083141","https://openalex.org/W4386083151","https://openalex.org/W4386113271","https://openalex.org/W4390872205","https://openalex.org/W4390873054","https://openalex.org/W4390873195","https://openalex.org/W4390874265","https://openalex.org/W4390874575","https://openalex.org/W4393147759","https://openalex.org/W4394625750","https://openalex.org/W4400582187","https://openalex.org/W4400818431","https://openalex.org/W4402667906","https://openalex.org/W4402716004"],"related_works":[],"abstract_inverted_index":{"While":[0],"text-driven":[1],"diffusion":[2],"models":[3],"demonstrate":[4],"remarkable":[5],"performance":[6],"in":[7,42,218],"image":[8,81,152,162],"editing,":[9],"the":[10,60,64,69,89,117,136,169,177,186,197],"critical":[11],"components":[12],"of":[13,23,39,63,120,139,190,196],"their":[14],"text":[15,40,66,92,166,208],"embeddings":[16,25,41,167],"remain":[17],"underexplored.":[18],"The":[19],"ambiguity":[20],"and":[21,105,123,131,172,188,226],"entanglement":[22],"these":[24,144],"pose":[26],"challenges":[27],"for":[28,180],"precise":[29,161],"editing.":[30],"In":[31],"this":[32],"paper,":[33],"we":[34,146],"provide":[35],"a":[36,150],"comprehensive":[37],"analysis":[38],"Stable":[43],"Diffusion":[44],"XL,":[45],"offering":[46],"three":[47],"key":[48],"insights:":[49],"(1)":[50],"aug":[51,54],"embedding":[52,55,107,128],"~.":[53],"is":[56,85,129,231],"obtained":[57],"by":[58,164,205],"combining":[59],"pooled":[61],"output":[62],"final":[65],"encoder":[67],"with":[68,135],"timestep":[70],"embeddings.":[71,141,209],"https://github.com/huggingface/diffusers":[72],"retains":[73],"complete":[74],"textual":[75],"semantics":[76,97],"but":[77],"contributes":[78],"minimally":[79],"to":[80,175],"generation":[82],"as":[83,221],"it":[84],"only":[86],"fused":[87],"via":[88],"ResBlocks.":[90],"More":[91],"information":[93,119],"weakens":[94],"its":[95],"local":[96],"while":[98],"preserving":[99],"most":[100],"global":[101],"semantics.":[102],"(2)":[103],"BOS":[104],"padding":[106],"do":[108],"not":[109,133],"contain":[110],"any":[111],"semantic":[112,118,137,181],"information.":[113,125],"(3)":[114],"EOS":[115],"holds":[116],"all":[121],"words":[122],"stylistic":[124],"Each":[126],"word":[127],"important":[130],"does":[132],"interfere":[134],"injection":[138],"other":[140,194],"Based":[142],"on":[143],"insights,":[145],"propose":[147],"PSP":[148,159,200,214],"(Prompt-Softbox-Prompt),":[149],"training-free":[151],"editing":[153,163],"method":[154],"that":[155,213],"leverages":[156],"free-text":[157],"embedding.":[158],"enables":[160,185],"modifying":[165],"within":[168],"cross-attention":[170],"layers":[171],"using":[173],"Softbox":[174],"control":[176],"specific":[178],"area":[179],"injection.":[182],"This":[183],"technique":[184],"addition":[187],"replacement":[189],"objects":[191],"without":[192],"affecting":[193],"areas":[195],"image.":[198],"Additionally,":[199],"can":[201],"achieve":[202],"style":[203,227],"transfer":[204],"simply":[206],"replacing":[207],"Extensive":[210],"experiments":[211],"show":[212],"performs":[215],"remarkably":[216],"well":[217],"tasks":[219],"such":[220],"object":[222,224],"replacement,":[223],"addition,":[225],"transfer.":[228],"Our":[229],"code":[230],"available":[232],"at":[233],"https://github.com/yangyt46/PSP.":[234]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-25T00:00:00"}
