{"id":"https://openalex.org/W4415821696","doi":"https://doi.org/10.1109/ro-man63969.2025.11217904","title":"Fusion in Context: A Multimodal Approach to Affective State Recognition","display_name":"Fusion in Context: A Multimodal Approach to Affective State Recognition","publication_year":2025,"publication_date":"2025-08-25","ids":{"openalex":"https://openalex.org/W4415821696","doi":"https://doi.org/10.1109/ro-man63969.2025.11217904"},"language":null,"primary_location":{"id":"doi:10.1109/ro-man63969.2025.11217904","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ro-man63969.2025.11217904","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 34th IEEE International Conference on Robot and Human Interactive Communication (RO-MAN)","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/A5049066753","display_name":"Youssef Mohamed","orcid":"https://orcid.org/0000-0001-5660-5330"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Youssef Mohamed","raw_affiliation_strings":["KTH: The Royal Institute of Technology,Stockholm,Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KTH: The Royal Institute of Technology,Stockholm,Sweden","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074580437","display_name":"S\u00e9verin Lemaignan","orcid":"https://orcid.org/0000-0002-3391-8876"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"S\u00e9verin Lemaignan","raw_affiliation_strings":["PAL Robotics,Barcelona,Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"PAL Robotics,Barcelona,Spain","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089148668","display_name":"Arzu G\u00fcneysu \u00d6zg\u00fcr","orcid":"https://orcid.org/0000-0003-2282-9939"},"institutions":[{"id":"https://openalex.org/I90267481","display_name":"Ume\u00e5 University","ror":"https://ror.org/05kb8h459","country_code":"SE","type":"education","lineage":["https://openalex.org/I90267481"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Arzu G\u00fcneysu","raw_affiliation_strings":["Ume&#x00E5; University,Ume&#x00E5;,Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ume&#x00E5; University,Ume&#x00E5;,Sweden","institution_ids":["https://openalex.org/I90267481"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028082686","display_name":"Patric Jensfelt","orcid":"https://orcid.org/0000-0002-1170-7162"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Patric Jensfelt","raw_affiliation_strings":["KTH: The Royal Institute of Technology,Stockholm,Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KTH: The Royal Institute of Technology,Stockholm,Sweden","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060213000","display_name":"Christian Smith","orcid":"https://orcid.org/0000-0003-2078-8854"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Christian Smith","raw_affiliation_strings":["KTH: The Royal Institute of Technology,Stockholm,Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KTH: The Royal Institute of Technology,Stockholm,Sweden","institution_ids":["https://openalex.org/I86987016"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1049","last_page":"1055"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9923999905586243,"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":0.9923999905586243,"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/T10709","display_name":"Social Robot Interaction and HRI","score":0.0017999999690800905,"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"}},{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.0005000000237487257,"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/modalities","display_name":"Modalities","score":0.7343000173568726},{"id":"https://openalex.org/keywords/facial-expression","display_name":"Facial expression","score":0.6743999719619751},{"id":"https://openalex.org/keywords/affective-computing","display_name":"Affective computing","score":0.6080999970436096},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6014000177383423},{"id":"https://openalex.org/keywords/action-recognition","display_name":"Action recognition","score":0.600600004196167},{"id":"https://openalex.org/keywords/multimodal-learning","display_name":"Multimodal learning","score":0.5947999954223633},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5054000020027161},{"id":"https://openalex.org/keywords/multimodality","display_name":"Multimodality","score":0.49239999055862427},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.48669999837875366}],"concepts":[{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.7343000173568726},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6819999814033508},{"id":"https://openalex.org/C195704467","wikidata":"https://www.wikidata.org/wiki/Q327968","display_name":"Facial expression","level":2,"score":0.6743999719619751},{"id":"https://openalex.org/C6438553","wikidata":"https://www.wikidata.org/wiki/Q1185804","display_name":"Affective computing","level":2,"score":0.6080999970436096},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6014000177383423},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.600600004196167},{"id":"https://openalex.org/C2780660688","wikidata":"https://www.wikidata.org/wiki/Q25052564","display_name":"Multimodal learning","level":2,"score":0.5947999954223633},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5054000020027161},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.49239999055862427},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.48669999837875366},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48240000009536743},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.4505999982357025},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.42590001225471497},{"id":"https://openalex.org/C2776035688","wikidata":"https://www.wikidata.org/wiki/Q1606558","display_name":"Affect (linguistics)","level":2,"score":0.4239000082015991},{"id":"https://openalex.org/C4441509","wikidata":"https://www.wikidata.org/wiki/Q6418787","display_name":"Multimodal therapy","level":2,"score":0.3781999945640564},{"id":"https://openalex.org/C121687571","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Activity recognition","level":2,"score":0.3635999858379364},{"id":"https://openalex.org/C31510193","wikidata":"https://www.wikidata.org/wiki/Q1192553","display_name":"Facial recognition system","level":3,"score":0.34700000286102295},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.3440000116825104},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.33649998903274536},{"id":"https://openalex.org/C135641252","wikidata":"https://www.wikidata.org/wiki/Q738567","display_name":"Multimodal interaction","level":2,"score":0.3255999982357025},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.30469998717308044},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.289000004529953},{"id":"https://openalex.org/C71611378","wikidata":"https://www.wikidata.org/wiki/Q5165191","display_name":"Contextual design","level":3,"score":0.2879999876022339},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.2827000021934509},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.27059999108314514},{"id":"https://openalex.org/C2982962833","wikidata":"https://www.wikidata.org/wiki/Q17092450","display_name":"Information fusion","level":2,"score":0.26339998841285706},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.26019999384880066},{"id":"https://openalex.org/C130064352","wikidata":"https://www.wikidata.org/wiki/Q853725","display_name":"Social relation","level":2,"score":0.2574999928474426},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.2563999891281128},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.251800000667572}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ro-man63969.2025.11217904","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ro-man63969.2025.11217904","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 34th IEEE International Conference on Robot and Human Interactive Communication (RO-MAN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1588539311","https://openalex.org/W1595126664","https://openalex.org/W2068124150","https://openalex.org/W2143350951","https://openalex.org/W2584561145","https://openalex.org/W2604778133","https://openalex.org/W2619383789","https://openalex.org/W2811286022","https://openalex.org/W2896766043","https://openalex.org/W2912483755","https://openalex.org/W2997258743","https://openalex.org/W3001529617","https://openalex.org/W3137284029","https://openalex.org/W3176899168","https://openalex.org/W3209798173","https://openalex.org/W4221147459","https://openalex.org/W4252830706","https://openalex.org/W4313123356","https://openalex.org/W4385245566","https://openalex.org/W4385573848","https://openalex.org/W4386065863","https://openalex.org/W4388071773","https://openalex.org/W4392903163","https://openalex.org/W4394606408","https://openalex.org/W4394719501","https://openalex.org/W4402917209","https://openalex.org/W4405680594"],"related_works":[],"abstract_inverted_index":{"Accurate":[0],"recognition":[1],"of":[2],"human":[3],"emotions":[4],"is":[5,43,116],"a":[6,19,67,103,119,126],"crucial":[7],"challenge":[8],"in":[9,22,60,125],"affective":[10,135],"computing":[11],"and":[12,26,54,80,100,111,145,163],"human-robot":[13],"interaction":[14],"(HRI).":[15],"Emotional":[16],"states":[17],"play":[18],"vital":[20],"role":[21],"shaping":[23],"behaviors,":[24],"decisions,":[25],"social":[27],"interactions.":[28,112],"However,":[29],"emotional":[30],"expressions":[31],"can":[32],"be":[33],"influenced":[34],"by":[35,102],"contextual":[36,143],"factors,":[37],"leading":[38],"to":[39,92,107,132,157],"misinterpretations":[40],"if":[41],"context":[42,82],"not":[44],"considered.":[45],"Multimodal":[46],"fusion,":[47,147],"combining":[48],"modalities":[49],"like":[50],"facial":[51,74,77],"expressions,":[52],"speech,":[53],"physiological":[55],"signals,":[56],"has":[57],"shown":[58],"promise":[59],"improving":[61],"affect":[62],"recognition.":[63,87],"This":[64],"paper":[65],"proposes":[66],"transformer-based":[68],"multimodal":[69,146],"fusion":[70],"approach":[71],"that":[72],"leverages":[73],"thermal":[75,166],"data,":[76],"action":[78,160],"units,":[79],"textual":[81],"information":[83,144],"for":[84,159,165],"context-aware":[85],"emotion":[86],"We":[88],"explore":[89],"modality-specific":[90],"encoders":[91],"learn":[93],"tailored":[94],"representations,":[95],"which":[96],"are":[97],"then":[98],"fused":[99],"processed":[101],"shared":[104],"transformer":[105],"encoder":[106],"capture":[108],"temporal":[109],"dependencies":[110],"The":[113],"proposed":[114],"method":[115],"evaluated":[117],"on":[118],"dataset":[120],"collected":[121],"from":[122,141],"participants":[123],"engaged":[124],"tangible":[127],"tabletop":[128],"Pacman":[129],"game":[130],"designed":[131],"induce":[133],"various":[134],"states.":[136],"Our":[137],"results":[138],"demonstrate":[139],"improvements":[140],"incorporating":[142],"achieving":[148],"89%":[149],"F1":[150],"score":[151],"with":[152],"our":[153],"full":[154],"model":[155],"compared":[156],"65%":[158],"units":[161],"alone":[162],"30%":[164],"data":[167],"alone.":[168]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
