{"id":"https://openalex.org/W7160325522","doi":"https://doi.org/10.1109/wacv61042.2026.00391","title":"Efficient Text-Guided Convolutional Adapter for the Diffusion Model","display_name":"Efficient Text-Guided Convolutional Adapter for the Diffusion Model","publication_year":2026,"publication_date":"2026-03-06","ids":{"openalex":"https://openalex.org/W7160325522","doi":"https://doi.org/10.1109/wacv61042.2026.00391"},"language":null,"primary_location":{"id":"doi:10.1109/wacv61042.2026.00391","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00391","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","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/A5126178467","display_name":"Aryan Das","orcid":null},"institutions":[{"id":"https://openalex.org/I4210097295","display_name":"Vital Research","ror":"https://ror.org/00svqj211","country_code":"US","type":"facility","lineage":["https://openalex.org/I4210097295"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aryan Das","raw_affiliation_strings":["VIT,Bhopal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"VIT,Bhopal","institution_ids":["https://openalex.org/I4210097295"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010852509","display_name":"Koushik Biswas","orcid":"https://orcid.org/0000-0002-9818-8966"},"institutions":[{"id":"https://openalex.org/I119939252","display_name":"Indraprastha Institute of Information Technology Delhi","ror":"https://ror.org/03vfp4g33","country_code":"IN","type":"education","lineage":["https://openalex.org/I119939252"]},{"id":"https://openalex.org/I68891433","display_name":"Indian Institute of Technology Delhi","ror":"https://ror.org/049tgcd06","country_code":"IN","type":"education","lineage":["https://openalex.org/I68891433"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Koushik Biswas","raw_affiliation_strings":["IIIT,Delhi"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IIIT,Delhi","institution_ids":["https://openalex.org/I119939252","https://openalex.org/I68891433"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087427076","display_name":"Swalpa Kumar Roy","orcid":"https://orcid.org/0000-0002-6580-3977"},"institutions":[{"id":"https://openalex.org/I126601174","display_name":"Tezpur University","ror":"https://ror.org/005x56091","country_code":"IN","type":"education","lineage":["https://openalex.org/I126601174"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Swalpa Kumar Roy","raw_affiliation_strings":["Tezpur University,Assam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tezpur University,Assam","institution_ids":["https://openalex.org/I126601174"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035714586","display_name":"Badri N. Patro","orcid":"https://orcid.org/0000-0002-2585-7014"},"institutions":[{"id":"https://openalex.org/I94234084","display_name":"Indian Institute of Technology Kanpur","ror":"https://ror.org/05pjsgx75","country_code":"IN","type":"education","lineage":["https://openalex.org/I94234084"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Badri Narayana Patro","raw_affiliation_strings":["IIT,Kanpur"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IIT,Kanpur","institution_ids":["https://openalex.org/I94234084"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101744115","display_name":"Vinay Kumar Verma","orcid":"https://orcid.org/0000-0002-6532-2997"},"institutions":[{"id":"https://openalex.org/I94234084","display_name":"Indian Institute of Technology Kanpur","ror":"https://ror.org/05pjsgx75","country_code":"IN","type":"education","lineage":["https://openalex.org/I94234084"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Vinay Kumar Verma","raw_affiliation_strings":["IIT,Kanpur"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IIT,Kanpur","institution_ids":["https://openalex.org/I94234084"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"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":"4015","last_page":"4024"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.14090000092983246,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.14090000092983246,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.11990000307559967,"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":0.10499999672174454,"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/diffusion","display_name":"Diffusion","score":0.3790999948978424},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.32850000262260437},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.24619999527931213},{"id":"https://openalex.org/keywords/convolutional-code","display_name":"Convolutional code","score":0.24410000443458557}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5493999719619751},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5045999884605408},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.3790999948978424},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3337000012397766},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.32850000262260437},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2946999967098236},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.262800008058548},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.24619999527931213},{"id":"https://openalex.org/C157899210","wikidata":"https://www.wikidata.org/wiki/Q1395022","display_name":"Convolutional code","level":3,"score":0.24410000443458557},{"id":"https://openalex.org/C24326235","wikidata":"https://www.wikidata.org/wiki/Q126095","display_name":"Electronic engineering","level":1,"score":0.2328999936580658}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/wacv61042.2026.00391","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00391","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2765811365","https://openalex.org/W2955639361","https://openalex.org/W2962974533","https://openalex.org/W2963073614","https://openalex.org/W2963800363","https://openalex.org/W4214774769","https://openalex.org/W4312529868","https://openalex.org/W4312933868","https://openalex.org/W4390873054","https://openalex.org/W4393148714","https://openalex.org/W4413156575","https://openalex.org/W7133185348","https://openalex.org/W7137915226"],"related_works":[],"abstract_inverted_index":{"We":[0,168],"introduce":[1],"the":[2,10,14,62,66,76,79,87,95,101,110,116,121,153,161,166,173,179,193,210],"Nexus":[3,129,142,180,202],"Adapters,":[4],"novel":[5],"text-guided":[6],"efficient":[7,127],"adapters":[8],"to":[9,65,74,147,192],"diffusion-based":[11],"framework":[12],"for":[13,36,42,109,115],"Structure":[15],"Preserving":[16],"Conditional":[17],"Generation":[18],"(SPCG).":[19],"Recently,":[20],"structure-preserving":[21],"methods":[22],"have":[23],"achieved":[24,214],"promising":[25],"results":[26],"in":[27,61],"conditional":[28],"image":[29],"generation":[30],"by":[31,136],"using":[32],"a":[33,157,200],"base":[34,67],"model":[35,77,81],"prompt":[37,163],"conditioning":[38],"and":[39,56,85,131,138,176],"an":[40],"adapter":[41,63,96,155,182,204],"structure":[43],"input,":[44],"such":[45],"as":[46],"sketches":[47],"or":[48],"depth":[49],"maps.":[50],"These":[51],"approaches":[52],"are":[53,134],"highly":[54,90],"inefficient":[55],"sometimes":[57],"require":[58],"equal":[59],"parameters":[60,190,208],"compared":[64,191],"architecture.":[68],"It":[69],"is":[70,82,89,97,106],"not":[71,98,114],"always":[72],"possible":[73],"train":[75],"since":[78],"diffusion":[80],"itself":[83],"costly,":[84],"doubling":[86],"parameter":[88],"inefficient.":[91],"In":[92],"these":[93],"approaches,":[94],"aware":[99],"of":[100,160],"input":[102,112,117,162],"prompt;":[103],"therefore,":[104],"it":[105],"optimal":[107],"only":[108,187],"structural":[111,139],"but":[113],"prompt.":[118],"To":[119],"overcome":[120],"above":[122],"challenges,":[123],"we":[124,197],"proposed":[125,154,174],"two":[126],"adapters,":[128],"Prime":[130,181],"Slim,":[132],"which":[133,212],"guided":[135],"prompts":[137],"inputs.":[140],"Each":[141],"Block":[143],"incorporates":[144],"cross-attention":[145],"mechanisms":[146],"enable":[148],"rich":[149],"multimodal":[150],"conditioning.":[151],"Therefore,":[152],"has":[156],"better":[158],"understanding":[159],"while":[164],"preserving":[165],"structure.":[167],"conducted":[169],"extensive":[170],"experiments":[171],"on":[172],"models":[175],"demonstrated":[177],"that":[178],"significantly":[183],"enhances":[184],"performance,":[185],"requiring":[186],"8M":[188],"additional":[189],"baseline,":[194],"T2I-Adapter.":[195],"Furthermore,":[196],"also":[198],"introduced":[199],"lightweight":[201],"Slim":[203],"with":[205],"18M":[206],"fewer":[207],"than":[209],"T2I-Adapter,":[211],"still":[213],"state-of-the-art":[215],"results.":[216],"Code:":[217],"https://github.com/arya-domain/Nexus-Adapters":[218]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-05-06T00:00:00"}