{"id":"https://openalex.org/W7138321224","doi":"https://doi.org/10.1609/aaai.v40i28.39565","title":"Who Should I Trust? Explicit Confidence-Focused Multimodal Intent Recognition","display_name":"Who Should I Trust? Explicit Confidence-Focused Multimodal Intent Recognition","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138321224","doi":"https://doi.org/10.1609/aaai.v40i28.39565"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i28.39565","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i28.39565","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/39565/43526","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/39565/43526","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129735829","display_name":"Yi Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yi Liu","raw_affiliation_strings":["Xinjiang University"],"affiliations":[{"raw_affiliation_string":"Xinjiang University","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007922382","display_name":"Qimeng Yang","orcid":"https://orcid.org/0000-0002-5007-8805"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qimeng Yang","raw_affiliation_strings":["Xinjiang University"],"affiliations":[{"raw_affiliation_string":"Xinjiang University","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5123259168","display_name":"Lanlan Lu","orcid":null},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lanlan Lu","raw_affiliation_strings":["Xinjiang University"],"affiliations":[{"raw_affiliation_string":"Xinjiang University","institution_ids":["https://openalex.org/I96908189"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5129735829"],"corresponding_institution_ids":["https://openalex.org/I96908189"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.525,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"28","first_page":"23891","last_page":"23898"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.2500999867916107,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.2500999867916107,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.1274999976158142,"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/T10709","display_name":"Social Robot Interaction and HRI","score":0.07850000262260437,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.5817999839782715},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.529699981212616},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5253000259399414},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.4936000108718872},{"id":"https://openalex.org/keywords/dialog-box","display_name":"Dialog box","score":0.4375},{"id":"https://openalex.org/keywords/core","display_name":"Core (optical fiber)","score":0.3634999990463257},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.3546999990940094}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7519999742507935},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6154000163078308},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.5817999839782715},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.529699981212616},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5253000259399414},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.4936000108718872},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.460999995470047},{"id":"https://openalex.org/C173853756","wikidata":"https://www.wikidata.org/wiki/Q86915","display_name":"Dialog box","level":2,"score":0.4375},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3725999891757965},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.3634999990463257},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3546999990940094},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.34470000863075256},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.32339999079704285},{"id":"https://openalex.org/C121687571","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Activity recognition","level":2,"score":0.30239999294281006},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2994999885559082},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.26899999380111694},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.26109999418258667},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.2540000081062317}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i28.39565","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i28.39565","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/39565/43526","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i28.39565","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i28.39565","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/39565/43526","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/8","score":0.40547075867652893,"display_name":"Decent work and economic growth"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7138321224.pdf","grobid_xml":"https://content.openalex.org/works/W7138321224.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Multimodal":[0],"intent":[1,94,154],"recognition":[2,95,155],"is":[3,103],"aimed":[4],"at":[5],"understanding":[6],"user":[7],"intentions":[8],"by":[9,55],"integrating":[10],"information":[11],"from":[12],"multiple":[13],"modalities.":[14],"It":[15],"has":[16],"attracted":[17],"increasing":[18],"attention":[19],"in":[20,124],"recently":[21],"developed":[22],"dialog":[23],"systems.":[24],"The":[25,97],"existing":[26],"studies":[27],"have":[28],"focused":[29],"mainly":[30],"on":[31,150],"modeling":[32],"semantic":[33],"interactions":[34],"within":[35],"and":[36,77,108,136,175],"across":[37],"modalities,":[38],"but":[39],"they":[40],"often":[41],"overlook":[42],"the":[43,69,121,132,138,158],"reliability":[44],"of":[45,100,134,140,160],"each":[46,106,109],"modality.":[47],"In":[48],"real-world":[49],"scenarios,":[50],"inputs":[51],"may":[52],"be":[53],"corrupted":[54],"noisy":[56],"audio,":[57],"blurred":[58],"or":[59,62],"occluded":[60],"videos,":[61],"ambiguous":[63],"text,":[64],"making":[65],"it":[66],"difficult":[67],"for":[68,172],"employed":[70],"model":[71],"to":[72,75,80,104],"determine":[73],"who":[74],"trust":[76],"how":[78],"much":[79],"trust.":[81],"To":[82],"address":[83],"this":[84,101],"challenge,":[85],"we":[86],"propose":[87],"a":[88,113,125],"method":[89],"called":[90],"explicit":[91],"confidence-focused":[92],"multimodal":[93,153],"(ECFMIR).":[96],"core":[98],"idea":[99],"approach":[102],"assign":[105],"modality":[107],"cross-modal":[110],"associations":[111],"feature":[112],"dedicated":[114],"confidence":[115,122],"lens":[116],"(CLens)":[117],"that":[118,167],"explicitly":[119],"estimates":[120],"level":[123],"hypothetical":[126],"manner.":[127],"This":[128],"design":[129],"helps":[130],"reduce":[131],"degree":[133],"uncertainty":[135],"mitigate":[137],"risk":[139],"incorrect":[141],"predictions":[142],"when":[143],"addressing":[144],"conflicting":[145],"inputs.":[146],"Comprehensive":[147],"experiments":[148],"conducted":[149],"two":[151],"benchmark":[152],"datasets":[156],"demonstrate":[157],"effectiveness":[159],"our":[161],"method.":[162],"A":[163],"further":[164],"analysis":[165],"reveals":[166],"ECFMIR":[168],"achieves":[169],"significant":[170],"advantages":[171],"high-conflict":[173],"categories":[174],"under":[176],"low-resource":[177],"conditions.":[178]},"counts_by_year":[],"updated_date":"2026-03-20T20:47:17.329874","created_date":"2026-03-18T00:00:00"}