{"id":"https://openalex.org/W4410639046","doi":"https://doi.org/10.1109/taffc.2025.3573180","title":"VISTANet: VIsual Spoken Textual Additive Net for Interpretable Multimodal Emotion Recognition","display_name":"VISTANet: VIsual Spoken Textual Additive Net for Interpretable Multimodal Emotion Recognition","publication_year":2025,"publication_date":"2025-05-23","ids":{"openalex":"https://openalex.org/W4410639046","doi":"https://doi.org/10.1109/taffc.2025.3573180"},"language":"en","primary_location":{"id":"doi:10.1109/taffc.2025.3573180","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taffc.2025.3573180","pdf_url":null,"source":{"id":"https://openalex.org/S104780363","display_name":"IEEE Transactions on Affective Computing","issn_l":"1949-3045","issn":["1949-3045","2371-9850"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Affective Computing","raw_type":"journal-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/A5044412028","display_name":"Puneet Kumar","orcid":"https://orcid.org/0000-0002-4318-1353"},"institutions":[{"id":"https://openalex.org/I98381234","display_name":"University of Oulu","ror":"https://ror.org/03yj89h83","country_code":"FI","type":"education","lineage":["https://openalex.org/I98381234"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Puneet Kumar","raw_affiliation_strings":["Center for Machine Vision and Signal Analysis, University of Oulu, Oulu, Finland","Center for Machine Vision and Signal Analysis, University of Oulu, Finland"],"raw_orcid":"https://orcid.org/0000-0002-4318-1353","affiliations":[{"raw_affiliation_string":"Center for Machine Vision and Signal Analysis, University of Oulu, Oulu, Finland","institution_ids":["https://openalex.org/I98381234"]},{"raw_affiliation_string":"Center for Machine Vision and Signal Analysis, University of Oulu, Finland","institution_ids":["https://openalex.org/I98381234"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085194462","display_name":"Sarthak Malik","orcid":"https://orcid.org/0000-0001-5224-1445"},"institutions":[{"id":"https://openalex.org/I154851008","display_name":"Indian Institute of Technology Roorkee","ror":"https://ror.org/00582g326","country_code":"IN","type":"education","lineage":["https://openalex.org/I154851008"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sarthak Malik","raw_affiliation_strings":["Indian Institute of Technology Roorkee, Roorkee, India","Indian Institute of Technology Roorkee, India"],"raw_orcid":"https://orcid.org/0000-0001-5224-1445","affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Roorkee, Roorkee, India","institution_ids":["https://openalex.org/I154851008"]},{"raw_affiliation_string":"Indian Institute of Technology Roorkee, India","institution_ids":["https://openalex.org/I154851008"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030765476","display_name":"Balasubramanian Raman","orcid":"https://orcid.org/0000-0001-6277-6267"},"institutions":[{"id":"https://openalex.org/I154851008","display_name":"Indian Institute of Technology Roorkee","ror":"https://ror.org/00582g326","country_code":"IN","type":"education","lineage":["https://openalex.org/I154851008"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Balasubramanian Raman","raw_affiliation_strings":["Indian Institute of Technology Roorkee, Roorkee, India","Indian Institute of Technology Roorkee, India"],"raw_orcid":"https://orcid.org/0000-0001-6277-6267","affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Roorkee, Roorkee, India","institution_ids":["https://openalex.org/I154851008"]},{"raw_affiliation_string":"Indian Institute of Technology Roorkee, India","institution_ids":["https://openalex.org/I154851008"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101691493","display_name":"Xiaobai Li","orcid":"https://orcid.org/0000-0003-4519-7823"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]},{"id":"https://openalex.org/I98381234","display_name":"University of Oulu","ror":"https://ror.org/03yj89h83","country_code":"FI","type":"education","lineage":["https://openalex.org/I98381234"]}],"countries":["CN","FI"],"is_corresponding":false,"raw_author_name":"Xiaobai Li","raw_affiliation_strings":["State Key Laboratory of Blockchain and Data Security, Zhejiang University, Hangzhou, China","Center for Machine Vision and Signal Analysis, University of Oulu, Finland"],"raw_orcid":"https://orcid.org/0000-0003-4519-7823","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Blockchain and Data Security, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]},{"raw_affiliation_string":"Center for Machine Vision and Signal Analysis, University of Oulu, Finland","institution_ids":["https://openalex.org/I98381234"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.4545,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.91846431,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"16","issue":"4","first_page":"2881","last_page":"2893"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.880299985408783,"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":0.880299985408783,"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.7570000290870667,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.5528789758682251},{"id":"https://openalex.org/keywords/net","display_name":"Net (polyhedron)","score":0.5363757610321045},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4865492880344391},{"id":"https://openalex.org/keywords/affective-computing","display_name":"Affective computing","score":0.4697318971157074},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46868234872817993},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.45869511365890503},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.4514651298522949},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4118933379650116},{"id":"https://openalex.org/keywords/cognitive-psychology","display_name":"Cognitive psychology","score":0.40978139638900757},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.33833223581314087},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1286085844039917}],"concepts":[{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.5528789758682251},{"id":"https://openalex.org/C14166107","wikidata":"https://www.wikidata.org/wiki/Q253829","display_name":"Net (polyhedron)","level":2,"score":0.5363757610321045},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4865492880344391},{"id":"https://openalex.org/C6438553","wikidata":"https://www.wikidata.org/wiki/Q1185804","display_name":"Affective computing","level":2,"score":0.4697318971157074},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46868234872817993},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.45869511365890503},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.4514651298522949},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4118933379650116},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.40978139638900757},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.33833223581314087},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1286085844039917},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taffc.2025.3573180","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taffc.2025.3573180","pdf_url":null,"source":{"id":"https://openalex.org/S104780363","display_name":"IEEE Transactions on Affective Computing","issn_l":"1949-3045","issn":["1949-3045","2371-9850"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Affective Computing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":69,"referenced_works":["https://openalex.org/W1133916940","https://openalex.org/W1993267429","https://openalex.org/W2012289576","https://openalex.org/W2073231946","https://openalex.org/W2075274068","https://openalex.org/W2086146798","https://openalex.org/W2087618018","https://openalex.org/W2091084672","https://openalex.org/W2135198734","https://openalex.org/W2146334809","https://openalex.org/W2149628368","https://openalex.org/W2282821441","https://openalex.org/W2345305417","https://openalex.org/W2347880541","https://openalex.org/W2610961739","https://openalex.org/W2619383789","https://openalex.org/W2770602608","https://openalex.org/W2784281622","https://openalex.org/W2798802604","https://openalex.org/W2883254424","https://openalex.org/W2919127404","https://openalex.org/W2936372954","https://openalex.org/W2961723205","https://openalex.org/W2962770129","https://openalex.org/W2962858109","https://openalex.org/W2963351448","https://openalex.org/W2963686995","https://openalex.org/W2964300796","https://openalex.org/W2967729586","https://openalex.org/W2979200397","https://openalex.org/W2985882473","https://openalex.org/W2986660805","https://openalex.org/W2988157455","https://openalex.org/W3007274205","https://openalex.org/W3096690837","https://openalex.org/W3107416342","https://openalex.org/W3127521573","https://openalex.org/W3156669407","https://openalex.org/W3176399185","https://openalex.org/W3195841930","https://openalex.org/W3198791972","https://openalex.org/W3201356490","https://openalex.org/W3208632377","https://openalex.org/W3215440557","https://openalex.org/W4200528506","https://openalex.org/W4221154966","https://openalex.org/W4254751698","https://openalex.org/W4285149123","https://openalex.org/W4296976275","https://openalex.org/W4309969826","https://openalex.org/W4312287430","https://openalex.org/W4312677365","https://openalex.org/W4312832890","https://openalex.org/W4321062741","https://openalex.org/W4360595168","https://openalex.org/W4360930863","https://openalex.org/W4367281761","https://openalex.org/W4377234444","https://openalex.org/W4379382378","https://openalex.org/W4380839097","https://openalex.org/W4385573848","https://openalex.org/W4385597818","https://openalex.org/W4385731851","https://openalex.org/W4385822805","https://openalex.org/W4386076442","https://openalex.org/W4386491989","https://openalex.org/W4387968043","https://openalex.org/W4389195633","https://openalex.org/W4391307921"],"related_works":["https://openalex.org/W3080495370","https://openalex.org/W3126677997","https://openalex.org/W1610857240","https://openalex.org/W4285597148","https://openalex.org/W2901531394","https://openalex.org/W1559262936","https://openalex.org/W2134707158","https://openalex.org/W4321599321","https://openalex.org/W4408503249","https://openalex.org/W2767348466"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"a":[3,50,65,100],"multimodal":[4,109],"emotion":[5,52,102,110,115,132,146],"recognition":[6,147],"system,":[7],"VIsual":[8],"Spoken":[9],"Textual":[10],"Additive":[11,33],"Net":[12],"(VISTANet),":[13],"to":[14,48],"classify":[15],"emotions":[16],"reflected":[17],"by":[18],"input":[19],"containing":[20],"image,":[21,59],"speech,":[22,60],"and":[23,44,61,69,95,129,131,137,159,169],"text":[24,62],"into":[25],"discrete":[26,114],"classes.":[27],"A":[28],"new":[29],"interpretability":[30],"technique,":[31],"K-Average":[32],"exPlanation":[34],"(KAAP),":[35],"has":[36,141],"been":[37],"developed":[38],"that":[39],"identifies":[40],"important":[41],"visual,":[42,157],"spoken,":[43,158],"textual":[45,160],"features":[46,97],"leading":[47],"predicting":[49,99],"particular":[51,101],"class.":[53,103],"The":[54,86,139,167],"VISTANet":[55,140],"fuses":[56],"information":[57],"from":[58],"modalities":[63],"using":[64,156],"hybrid":[66],"of":[67,77,92,108,125,149],"intermediate":[68,79],"late":[70],"fusion.":[71],"It":[72],"automatically":[73],"adjusts":[74],"the":[75,83,90,106,120,152],"weights":[76],"their":[78],"outputs":[80],"while":[81],"computing":[82],"weighted":[84],"average.":[85],"KAAP":[87],"technique":[88],"computes":[89],"contribution":[91],"each":[93],"modality":[94],"corresponding":[96,127],"toward":[98],"To":[104],"mitigate":[105],"insufficiency":[107],"datasets":[111],"labelled":[112],"with":[113],"classes,":[116],"we":[117],"have":[118],"constructed":[119],"IIT-R":[121,153],"MMEmoRec":[122,154],"dataset":[123,155],"consisting":[124],"images,":[126],"speech":[128],"text,":[130],"labels":[133],"(\u2018angry,\u2019":[134],"\u2018happy,\u2019":[135],"\u2018hate,\u2019":[136],"\u2018sad\u2019).":[138],"resulted":[142],"in":[143],"an":[144],"overall":[145],"accuracy":[148],"80.11%":[150],"on":[151],"modalities,":[161],"outperforming":[162],"single":[163],"or":[164],"dual-modality":[165],"configurations.":[166],"code":[168],"data":[170],"can":[171],"be":[172],"accessed":[173],"at":[174],"github.com/MIntelligence-Group/MMEmoRec.":[175]},"counts_by_year":[{"year":2026,"cited_by_count":3}],"updated_date":"2026-07-19T07:52:34.831488","created_date":"2025-10-10T00:00:00"}