{"id":"https://openalex.org/W7164837429","doi":"https://doi.org/10.1145/3805622.3810691","title":"Asymmetric Pipeline for Dataset Construction and Situation-aware Generative Outfit Retrieval Leveraging Differences in Task Difficulty","display_name":"Asymmetric Pipeline for Dataset Construction and Situation-aware Generative Outfit Retrieval Leveraging Differences in Task Difficulty","publication_year":2026,"publication_date":"2026-06-15","ids":{"openalex":"https://openalex.org/W7164837429","doi":"https://doi.org/10.1145/3805622.3810691"},"language":null,"primary_location":{"id":"doi:10.1145/3805622.3810691","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810691","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3805622.3810691","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5110466909","display_name":"Yuma Oe","orcid":null},"institutions":[{"id":"https://openalex.org/I1298590031","display_name":"Shizuoka University","ror":"https://ror.org/01w6wtk13","country_code":"JP","type":"education","lineage":["https://openalex.org/I1298590031"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yuma Oe","raw_affiliation_strings":["Faculty of Informatics, Shizuoka University, Hamamatsu, Shizuoka, Japan"],"raw_orcid":"https://orcid.org/0009-0001-1346-2752","affiliations":[{"raw_affiliation_string":"Faculty of Informatics, Shizuoka University, Hamamatsu, Shizuoka, Japan","institution_ids":["https://openalex.org/I1298590031"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044349986","display_name":"Katsumi Tanaka","orcid":"https://orcid.org/0009-0002-8372-5308"},"institutions":[{"id":"https://openalex.org/I206011266","display_name":"Kwansei Gakuin University","ror":"https://ror.org/02qf2tx24","country_code":"JP","type":"education","lineage":["https://openalex.org/I206011266"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Katsumi Tanaka","raw_affiliation_strings":["Kwansei Gakuin University, Sanda, Hyogo, Japan"],"raw_orcid":"https://orcid.org/0009-0002-8372-5308","affiliations":[{"raw_affiliation_string":"Kwansei Gakuin University, Sanda, Hyogo, Japan","institution_ids":["https://openalex.org/I206011266"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103036803","display_name":"Yoshiyuki Shoji","orcid":"https://orcid.org/0000-0002-7405-9270"},"institutions":[{"id":"https://openalex.org/I1298590031","display_name":"Shizuoka University","ror":"https://ror.org/01w6wtk13","country_code":"JP","type":"education","lineage":["https://openalex.org/I1298590031"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yoshiyuki Shoji","raw_affiliation_strings":["Faculty of Informatics, Shizuoka University, Hamamatsu, Shizuoka, Japan"],"raw_orcid":"https://orcid.org/0000-0002-7405-9270","affiliations":[{"raw_affiliation_string":"Faculty of Informatics, Shizuoka University, Hamamatsu, Shizuoka, Japan","institution_ids":["https://openalex.org/I1298590031"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.76998953,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2607","last_page":"2615"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.7027999758720398,"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":0.7027999758720398,"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":0.1315000057220459,"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/T13310","display_name":"Subtitles and Audiovisual Media","score":0.012799999676644802,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.7516999840736389},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.6646000146865845},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.6480000019073486},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6459000110626221},{"id":"https://openalex.org/keywords/subject","display_name":"Subject (documents)","score":0.37380000948905945},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.3264999985694885}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7781000137329102},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.7516999840736389},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.6646000146865845},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.6480000019073486},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6459000110626221},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.507099986076355},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3991999924182892},{"id":"https://openalex.org/C2777855551","wikidata":"https://www.wikidata.org/wiki/Q12310021","display_name":"Subject (documents)","level":2,"score":0.37380000948905945},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3441999852657318},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.3264999985694885},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.31679999828338623},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.30379998683929443},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.28049999475479126},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.2782999873161316},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2623000144958496},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.25}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3805622.3810691","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810691","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3805622.3810691","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810691","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W2130660124","https://openalex.org/W2136340547","https://openalex.org/W2737102415","https://openalex.org/W2753004958","https://openalex.org/W2769033722","https://openalex.org/W2883309205","https://openalex.org/W2964050021","https://openalex.org/W3173998882","https://openalex.org/W4292794082","https://openalex.org/W4312394910","https://openalex.org/W4367046921","https://openalex.org/W4381804476","https://openalex.org/W4386076406","https://openalex.org/W4387801427","https://openalex.org/W4390873520","https://openalex.org/W4392271057","https://openalex.org/W4394625835","https://openalex.org/W4396821179","https://openalex.org/W4402671829","https://openalex.org/W4407953194","https://openalex.org/W4408326921","https://openalex.org/W4409917706","https://openalex.org/W4412394857","https://openalex.org/W4415537201","https://openalex.org/W7133208667","https://openalex.org/W7133233472"],"related_works":[],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"a":[3,92,127],"method":[4],"to":[5,64,90,109,126],"verbalize":[6],"and":[7,32,55,76,160,176],"generate":[8],"corresponding":[9],"outfit":[10,35,66,75,82,115,119,132,141,145],"images":[11,52,146,161],"based":[12],"on":[13,105],"natural":[14],"language":[15],"inputs":[16],"describing":[17],"everyday":[18],"situations.":[19],"To":[20],"achieve":[21],"this,":[22],"an":[23],"asymmetric":[24],"pipeline":[25,41],"is":[26,42,62],"constructed":[27,174],"for":[28,162],"both":[29,69,169],"dataset":[30,95,107,175],"construction":[31],"situation-aware":[33,140],"generative":[34],"retrieval.":[36],"The":[37,100,117,154],"design":[38],"of":[39,73,156],"this":[40,106,135],"grounded":[43],"in":[44,47,79],"the":[45,70,74,77,81,137,150,157,173],"difference":[46],"task":[48],"difficulty":[49],"between":[50],"generating":[51,144],"from":[53],"situations":[54,78,165],"captioning":[56],"images.":[57,133],"A":[58],"Vision-Language":[59],"Model":[60],"(VLM)":[61],"employed":[63],"caption":[65],"images,":[67],"producing":[68],"constituent":[71],"elements":[72],"which":[80,130],"might":[83],"be":[84],"worn.":[85],"These":[86],"outputs":[87],"are":[88,121],"paired":[89],"construct":[91],"situation\u2013outfit":[93],"description":[94],"named":[96],"OOTM":[97],"(Outfit":[98],"Of":[99],"Moment).":[101],"An":[102],"LLM":[103],"trained":[104],"learns":[108],"transform":[110],"situation":[111],"descriptions":[112,120],"into":[113],"appropriate":[114],"descriptions.":[116],"generated":[118,158],"then":[122],"provided":[123],"as":[124],"input":[125],"text-to-image":[128],"model,":[129],"synthesizes":[131],"Through":[134],"process,":[136],"framework":[138],"enables":[139],"retrieval":[142],"by":[143],"that":[147],"align":[148],"with":[149],"given":[151],"situational":[152],"query.":[153],"appropriateness":[155],"text":[159],"their":[163],"respective":[164],"was":[166],"evaluated":[167],"through":[168],"automatic":[170],"evaluation":[171],"using":[172],"human":[177],"subject":[178],"experiments.":[179]},"counts_by_year":[],"updated_date":"2026-06-16T07:37:23.134862","created_date":"2026-06-16T00:00:00"}