{"id":"https://openalex.org/W4413018674","doi":"https://doi.org/10.1109/fg61629.2025.11099454","title":"Cross-modal Emotion-specific Attention model for Multimodal Emotion Recognition","display_name":"Cross-modal Emotion-specific Attention model for Multimodal Emotion Recognition","publication_year":2025,"publication_date":"2025-05-26","ids":{"openalex":"https://openalex.org/W4413018674","doi":"https://doi.org/10.1109/fg61629.2025.11099454"},"language":"en","primary_location":{"id":"doi:10.1109/fg61629.2025.11099454","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fg61629.2025.11099454","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 19th International Conference on Automatic Face and Gesture Recognition (FG)","raw_type":"proceedings-article"},"type":"article","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/A5100609080","display_name":"Jiayi Chen","orcid":"https://orcid.org/0000-0002-3541-8410"},"institutions":[{"id":"https://openalex.org/I4210126580","display_name":"RIKEN Center for Advanced Intelligence Project","ror":"https://ror.org/03ckxwf91","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652","https://openalex.org/I4210126580"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Jia-Yi Chen","raw_affiliation_strings":["RIKEN Guardian Robot Project, RIKEN,Kyoto,Japan"],"affiliations":[{"raw_affiliation_string":"RIKEN Guardian Robot Project, RIKEN,Kyoto,Japan","institution_ids":["https://openalex.org/I4210126580"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007962043","display_name":"Vijay John","orcid":"https://orcid.org/0000-0002-9553-0906"},"institutions":[{"id":"https://openalex.org/I4210126580","display_name":"RIKEN Center for Advanced Intelligence Project","ror":"https://ror.org/03ckxwf91","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652","https://openalex.org/I4210126580"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Vijay John","raw_affiliation_strings":["RIKEN Guardian Robot Project, RIKEN,Kyoto,Japan"],"affiliations":[{"raw_affiliation_string":"RIKEN Guardian Robot Project, RIKEN,Kyoto,Japan","institution_ids":["https://openalex.org/I4210126580"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027960360","display_name":"Yasutomo Kawanishi","orcid":"https://orcid.org/0000-0002-3799-4550"},"institutions":[{"id":"https://openalex.org/I4210126580","display_name":"RIKEN Center for Advanced Intelligence Project","ror":"https://ror.org/03ckxwf91","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652","https://openalex.org/I4210126580"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yasutomo Kawanishi","raw_affiliation_strings":["RIKEN Guardian Robot Project, RIKEN,Kyoto,Japan"],"affiliations":[{"raw_affiliation_string":"RIKEN Guardian Robot Project, RIKEN,Kyoto,Japan","institution_ids":["https://openalex.org/I4210126580"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100609080"],"corresponding_institution_ids":["https://openalex.org/I4210126580"],"apc_list":null,"apc_paid":null,"fwci":2.2291,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.89175779,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.8766000270843506,"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":0.8766000270843506,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.6928400993347168},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.632790207862854},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.621809184551239},{"id":"https://openalex.org/keywords/emotion-detection","display_name":"Emotion detection","score":0.5169231295585632},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3695601224899292},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3610501289367676},{"id":"https://openalex.org/keywords/cognitive-psychology","display_name":"Cognitive psychology","score":0.32848799228668213},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.26176947355270386}],"concepts":[{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.6928400993347168},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.632790207862854},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.621809184551239},{"id":"https://openalex.org/C2988148770","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion detection","level":3,"score":0.5169231295585632},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3695601224899292},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3610501289367676},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.32848799228668213},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.26176947355270386},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/fg61629.2025.11099454","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fg61629.2025.11099454","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 19th International Conference on Automatic Face and Gesture Recognition (FG)","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":22,"referenced_works":["https://openalex.org/W1834627138","https://openalex.org/W1979602797","https://openalex.org/W2030931454","https://openalex.org/W2510725918","https://openalex.org/W2593116425","https://openalex.org/W2745497104","https://openalex.org/W2796830519","https://openalex.org/W2990235563","https://openalex.org/W3008425820","https://openalex.org/W3010299549","https://openalex.org/W3196974791","https://openalex.org/W4206246784","https://openalex.org/W4283711157","https://openalex.org/W4312596733","https://openalex.org/W4313156423","https://openalex.org/W4385815506","https://openalex.org/W4402726986","https://openalex.org/W4402916290","https://openalex.org/W6757817989","https://openalex.org/W6779098134","https://openalex.org/W6795641562","https://openalex.org/W6840200333"],"related_works":["https://openalex.org/W3105646692","https://openalex.org/W4387914125","https://openalex.org/W3126677997","https://openalex.org/W1610857240","https://openalex.org/W4391307871","https://openalex.org/W4392502551","https://openalex.org/W2336827033","https://openalex.org/W1970739466","https://openalex.org/W2505228240","https://openalex.org/W4319430321"],"abstract_inverted_index":{"Emotion":[0],"recognition":[1,26,129,174],"plays":[2],"a":[3,63],"crucial":[4],"role":[5],"in":[6,171],"humanrobot":[7],"interaction,":[8],"where":[9],"accurately":[10],"interpreting":[11],"human":[12],"emotions":[13],"through":[14,145],"multiple":[15],"modalities":[16],"is":[17],"essential":[18],"for":[19,70],"heartfelt":[20],"communication.":[21],"Although":[22],"previous":[23],"multimodal":[24,71],"emotion":[25,72,111,173],"models":[27],"have":[28],"shown":[29],"reasonable":[30],"performance,":[31],"there":[32],"are":[33,52],"two":[34,78,115],"difficulties:":[35],"(1)":[36,86],"they":[37],"often":[38],"struggle":[39],"to":[40,81,121],"capture":[41,88,122],"the":[42,46,83,89,94,109,118,133,136,140,165],"fine-grained":[43,90],"interactions":[44],"between":[45],"modalities.":[47],"(2)":[48,99],"The":[49,74,154],"prominent":[50],"features":[51],"different":[53,55],"across":[54],"emotions.":[56],"To":[57,87,100],"address":[58,82],"these":[59,114],"difficulties,":[60],"we":[61,92,106],"propose":[62],"novel":[64],"Cross-modal":[65,159],"Emotion-specific":[66,160],"Attention":[67,161],"model":[68,76,162],"(CEA)":[69],"recognition.":[73],"proposed":[75,137],"has":[77],"key":[79],"components":[80,116],"difficulties":[84],"above:":[85],"interactions,":[91],"introduce":[93,108],"dense":[95],"interaction":[96],"matrix":[97],"representation.":[98],"focus":[101],"more":[102],"on":[103,139],"emotion-specific":[104],"features,":[105],"also":[107],"specific":[110],"tokens.":[112],"Combining":[113],"enhances":[117],"model\u2019s":[119],"ability":[120],"subtle":[123],"emotional":[124],"nuances":[125],"and":[126,149],"improves":[127],"overall":[128],"accuracy.":[130,175],"We":[131],"evaluate":[132],"performance":[134],"of":[135],"architecture":[138],"CREMA-D":[141],"public":[142],"audiovisual":[143],"datasets":[144],"comprehensive":[146],"ablation":[147],"studies":[148],"comparison":[150],"with":[151],"baseline":[152,166],"models.":[153],"results":[155],"demonstrate":[156],"that":[157],"our":[158],"significantly":[163],"outperforms":[164],"methods,":[167],"confirming":[168],"its":[169],"effectiveness":[170],"enhancing":[172]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}