{"id":"https://openalex.org/W4296591846","doi":"https://doi.org/10.1145/3523227.3546774","title":"Multi-Modal Dialog State Tracking for Interactive Fashion Recommendation","display_name":"Multi-Modal Dialog State Tracking for Interactive Fashion Recommendation","publication_year":2022,"publication_date":"2022-09-13","ids":{"openalex":"https://openalex.org/W4296591846","doi":"https://doi.org/10.1145/3523227.3546774"},"language":"en","primary_location":{"id":"doi:10.1145/3523227.3546774","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3523227.3546774","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 16th ACM Conference on Recommender Systems","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://eprints.gla.ac.uk/view/author/55148.html>,","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102858602","display_name":"Yaxiong Wu","orcid":"https://orcid.org/0000-0002-1860-0122"},"institutions":[{"id":"https://openalex.org/I7882870","display_name":"University of Glasgow","ror":"https://ror.org/00vtgdb53","country_code":"GB","type":"education","lineage":["https://openalex.org/I7882870"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yaxiong Wu","raw_affiliation_strings":["School of Computing Science, University of Glasgow, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing Science, University of Glasgow, United Kingdom","institution_ids":["https://openalex.org/I7882870"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057643560","display_name":"Craig Macdonald","orcid":"https://orcid.org/0000-0003-3143-279X"},"institutions":[{"id":"https://openalex.org/I7882870","display_name":"University of Glasgow","ror":"https://ror.org/00vtgdb53","country_code":"GB","type":"education","lineage":["https://openalex.org/I7882870"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Craig Macdonald","raw_affiliation_strings":["School of Computing Science, University of Glasgow, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing Science, University of Glasgow, United Kingdom","institution_ids":["https://openalex.org/I7882870"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079046603","display_name":"Iadh Ounis","orcid":"https://orcid.org/0000-0003-4701-3223"},"institutions":[{"id":"https://openalex.org/I7882870","display_name":"University of Glasgow","ror":"https://ror.org/00vtgdb53","country_code":"GB","type":"education","lineage":["https://openalex.org/I7882870"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Iadh Ounis","raw_affiliation_strings":["School of Computing Science, University of Glasgow, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing Science, University of Glasgow, United Kingdom","institution_ids":["https://openalex.org/I7882870"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I7882870"],"apc_list":null,"apc_paid":null,"fwci":0.7357,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.80687598,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"124","last_page":"133"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"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":0.9998999834060669,"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/T10203","display_name":"Recommender Systems and Techniques","score":0.996999979019165,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9952999949455261,"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/computer-science","display_name":"Computer science","score":0.8365581035614014},{"id":"https://openalex.org/keywords/dialog-box","display_name":"Dialog box","score":0.6420873403549194},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.6395179629325867},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6279162168502808},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.6041446328163147},{"id":"https://openalex.org/keywords/visual-analytics","display_name":"Visual analytics","score":0.5536721348762512},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.5508718490600586},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.541419506072998},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4642670154571533},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4614945650100708},{"id":"https://openalex.org/keywords/recommender-system","display_name":"Recommender system","score":0.45063111186027527},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.41950559616088867},{"id":"https://openalex.org/keywords/dialog-system","display_name":"Dialog system","score":0.41112127900123596},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.34656572341918945},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.3300662040710449},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.2763349413871765},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.10447406768798828}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8365581035614014},{"id":"https://openalex.org/C173853756","wikidata":"https://www.wikidata.org/wiki/Q86915","display_name":"Dialog box","level":2,"score":0.6420873403549194},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.6395179629325867},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6279162168502808},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.6041446328163147},{"id":"https://openalex.org/C59732488","wikidata":"https://www.wikidata.org/wiki/Q2528440","display_name":"Visual analytics","level":3,"score":0.5536721348762512},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5508718490600586},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.541419506072998},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4642670154571533},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4614945650100708},{"id":"https://openalex.org/C557471498","wikidata":"https://www.wikidata.org/wiki/Q554950","display_name":"Recommender system","level":2,"score":0.45063111186027527},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41950559616088867},{"id":"https://openalex.org/C190954187","wikidata":"https://www.wikidata.org/wiki/Q5270587","display_name":"Dialog system","level":3,"score":0.41112127900123596},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.34656572341918945},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3300662040710449},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2763349413871765},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.10447406768798828},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3523227.3546774","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3523227.3546774","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 16th ACM Conference on Recommender Systems","raw_type":"proceedings-article"},{"id":"pmh:oai:eprints.gla.ac.uk:273808","is_oa":true,"landing_page_url":"https://eprints.gla.ac.uk/view/author/55148.html>,","pdf_url":null,"source":{"id":"https://openalex.org/S4210235606","display_name":"ENLIGHTEN (Jurnal Bimbingan dan Konseling Islam)","issn_l":"2622-8912","issn":["2622-8912","2622-8920"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"Conference Proceedings"}],"best_oa_location":{"id":"pmh:oai:eprints.gla.ac.uk:273808","is_oa":true,"landing_page_url":"https://eprints.gla.ac.uk/view/author/55148.html>,","pdf_url":null,"source":{"id":"https://openalex.org/S4210235606","display_name":"ENLIGHTEN (Jurnal Bimbingan dan Konseling Islam)","issn_l":"2622-8912","issn":["2622-8912","2622-8920"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"Conference Proceedings"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1989121949","display_name":null,"funder_award_id":"EP/R018634/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G5187265158","display_name":"Closed-Loop Data Science for Complex, Computationally- and Data-Intensive Analytics","funder_award_id":"EP/R018634/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G8352026019","display_name":null,"funder_award_id":"R018634/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1895577753","https://openalex.org/W1956340063","https://openalex.org/W2194775991","https://openalex.org/W2654637199","https://openalex.org/W2739805805","https://openalex.org/W2750004028","https://openalex.org/W2798749602","https://openalex.org/W2897182555","https://openalex.org/W2899366898","https://openalex.org/W2949395487","https://openalex.org/W2961593954","https://openalex.org/W2963641307","https://openalex.org/W2964112275","https://openalex.org/W2996960746","https://openalex.org/W2997662139","https://openalex.org/W3019166713","https://openalex.org/W3035734059","https://openalex.org/W3044084930","https://openalex.org/W3087647883","https://openalex.org/W3089177865","https://openalex.org/W3099865390","https://openalex.org/W3102862020","https://openalex.org/W3116062118","https://openalex.org/W3152929911","https://openalex.org/W3154189934","https://openalex.org/W3154257542","https://openalex.org/W3155833376","https://openalex.org/W3162337509","https://openalex.org/W3172514680","https://openalex.org/W3193171560","https://openalex.org/W3199755719","https://openalex.org/W3206565617","https://openalex.org/W4214587494","https://openalex.org/W4385794172","https://openalex.org/W4386845623"],"related_works":["https://openalex.org/W1532946172","https://openalex.org/W1872130062","https://openalex.org/W2377424484","https://openalex.org/W2278256305","https://openalex.org/W3008329436","https://openalex.org/W4200630887","https://openalex.org/W4226468312","https://openalex.org/W2047526010","https://openalex.org/W42454751","https://openalex.org/W4296591846"],"abstract_inverted_index":{"Multi-modal":[0],"interactive":[1,63],"recommendation":[2],"is":[3],"a":[4,104,137,143,177,230,236],"type":[5],"of":[6,26,36,62,76,83,86,124,154,165,224],"task":[7],"that":[8,245],"allows":[9],"users":[10],"to":[11,49,70,112,146,182,192,220],"receive":[12],"visual":[13,39,80,121,132,152,158],"recommendations":[14,40,81,159],"and":[15,41,79,129,151,157,191,215],"express":[16],"natural-language":[17,44,127,155],"feedback":[18,78,128,144,156],"about":[19],"the":[20,37,42,52,59,72,97,115,119,125,130,149,166,184,189,195,210,222],"recommended":[21],"items":[22],"across":[23,55],"multiple":[24,56],"iterations":[25],"interactions.":[27],"However,":[28],"such":[29],"multi-modal":[30,73,98,106,170],"dialog":[31,122],"sequences":[32,123],"(i.e.":[33,163],"turns":[34],"consisting":[35],"system\u2019s":[38,131],"user\u2019s":[43],"feedback)":[45],"make":[46],"it":[47],"challenging":[48],"correctly":[50],"incorporate":[51,114],"users\u2019":[53,116,126],"preferences":[54,117],"turns.":[57],"Indeed,":[58],"existing":[60,254],"formulations":[61],"recommender":[64],"systems":[65],"suffer":[66],"from":[67],"their":[68,84],"inability":[69],"capture":[71],"sequential":[74,99],"dependencies":[75],"textual":[77,150],"because":[82],"use":[85],"recurrent":[87,107,139],"neural":[88],"network-based":[89],"(i.e.,":[90],"RNN-based)":[91],"or":[92],"transformer-based":[93,232],"models.":[94,257],"To":[95],"alleviate":[96],"dependency":[100],"issue,":[101],"we":[102,135,175,205],"propose":[103],"novel":[105],"attention":[108,179],"network":[109,140,180],"(MMRAN)":[110],"model":[111,227,249],"effectively":[113],"over":[118],"long":[120],"recommendations.":[133],"Specifically,":[134],"leverage":[136],"gated":[138],"(GRN)":[141],"with":[142],"gate":[145],"separately":[147],"process":[148],"representations":[153,164],"into":[160],"hidden":[161,185],"states":[162,186],"past":[167],"interactions)":[168],"for":[169,238],"sequence":[171],"combination.":[172],"In":[173],"addition,":[174],"apply":[176],"multi-head":[178],"(MAN)":[181],"refine":[183],"generated":[187],"by":[188,228],"GRN":[190],"further":[193],"enhance":[194],"model\u2019s":[196],"ability":[197],"in":[198],"dynamic":[199],"state":[200],"tracking.":[201],"Following":[202],"previous":[203],"work,":[204],"conduct":[206],"extensive":[207],"experiments":[208],"on":[209],"Fashion":[211],"IQ":[212],"Dresses,":[213],"Shirts,":[214],"Tops":[216],"&":[217],"Tees":[218],"datasets":[219],"assess":[221],"effectiveness":[223],"our":[225,246],"proposed":[226,247],"using":[229],"vision-language":[231],"user":[233],"simulator":[234],"as":[235],"surrogate":[237],"real":[239],"human":[240],"users.":[241],"Our":[242],"results":[243],"show":[244],"MMRAN":[248],"can":[250],"significantly":[251],"outperform":[252],"several":[253],"state-of-the-art":[255],"baseline":[256]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2}],"updated_date":"2026-08-25T07:29:55.448023","created_date":"2025-10-10T00:00:00"}