{"id":"https://openalex.org/W4412567269","doi":"https://doi.org/10.1109/taffc.2025.3591567","title":"ATTSF-Net: Attention-Based Similarity Fusion Network for Audio-Visual Emotion Recognition","display_name":"ATTSF-Net: Attention-Based Similarity Fusion Network for Audio-Visual Emotion Recognition","publication_year":2025,"publication_date":"2025-07-22","ids":{"openalex":"https://openalex.org/W4412567269","doi":"https://doi.org/10.1109/taffc.2025.3591567"},"language":"en","primary_location":{"id":"doi:10.1109/taffc.2025.3591567","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taffc.2025.3591567","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/A5016982554","display_name":"Jiaming Zhang","orcid":"https://orcid.org/0009-0001-5707-7290"},"institutions":[{"id":"https://openalex.org/I157507598","display_name":"Shenyang University of Technology","ror":"https://ror.org/00d7f8730","country_code":"CN","type":"education","lineage":["https://openalex.org/I157507598"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jiaming Zhang","raw_affiliation_strings":["School of Artificial Intelligence, Shenyang University of Technology, Shenyang, China","School of Artificial Intelligence, Shenyang University of Technology, China"],"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Shenyang University of Technology, Shenyang, China","institution_ids":["https://openalex.org/I157507598"]},{"raw_affiliation_string":"School of Artificial Intelligence, Shenyang University of Technology, China","institution_ids":["https://openalex.org/I157507598"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031945999","display_name":"Zhijia Zhang","orcid":"https://orcid.org/0000-0001-7217-2678"},"institutions":[{"id":"https://openalex.org/I157507598","display_name":"Shenyang University of Technology","ror":"https://ror.org/00d7f8730","country_code":"CN","type":"education","lineage":["https://openalex.org/I157507598"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhijia Zhang","raw_affiliation_strings":["School of Artificial Intelligence, Shenyang University of Technology, Shenyang, China","School of Artificial Intelligence, Shenyang University of Technology, China"],"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Shenyang University of Technology, Shenyang, China","institution_ids":["https://openalex.org/I157507598"]},{"raw_affiliation_string":"School of Artificial Intelligence, Shenyang University of Technology, China","institution_ids":["https://openalex.org/I157507598"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056287221","display_name":"Zhaojie Ju","orcid":"https://orcid.org/0000-0002-9524-7609"},"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhaojie Ju","raw_affiliation_strings":["College of Biomedical Engineering and Instrument Science, Zhejiang University, Zhejiang, China","College of Biomedical Engineering and Instrument Science, Zhejiang University, China"],"affiliations":[{"raw_affiliation_string":"College of Biomedical Engineering and Instrument Science, Zhejiang University, Zhejiang, China","institution_ids":["https://openalex.org/I76130692"]},{"raw_affiliation_string":"College of Biomedical Engineering and Instrument Science, Zhejiang University, China","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5016982554"],"corresponding_institution_ids":["https://openalex.org/I157507598"],"apc_list":null,"apc_paid":null,"fwci":1.5804,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.84394689,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"16","issue":"4","first_page":"3291","last_page":"3303"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9836999773979187,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9836999773979187,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11309","display_name":"Music and Audio Processing","score":0.97079998254776,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10667","display_name":"Emotion and Mood Recognition","score":0.9495999813079834,"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/audio-visual","display_name":"Audio visual","score":0.7243252396583557},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.6280274391174316},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6067246794700623},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.5569413900375366},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5362389087677002},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.4843941330909729},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47611838579177856},{"id":"https://openalex.org/keywords/net","display_name":"Net (polyhedron)","score":0.44322526454925537},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.3772892653942108},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3620583415031433},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.16772615909576416},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.09568694233894348},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08296555280685425}],"concepts":[{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.7243252396583557},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6280274391174316},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6067246794700623},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.5569413900375366},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5362389087677002},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.4843941330909729},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47611838579177856},{"id":"https://openalex.org/C14166107","wikidata":"https://www.wikidata.org/wiki/Q253829","display_name":"Net (polyhedron)","level":2,"score":0.44322526454925537},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3772892653942108},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3620583415031433},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.16772615909576416},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.09568694233894348},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08296555280685425},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taffc.2025.3591567","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taffc.2025.3591567","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":48,"referenced_works":["https://openalex.org/W2146334809","https://openalex.org/W2790404832","https://openalex.org/W2809734421","https://openalex.org/W2972424567","https://openalex.org/W2972463723","https://openalex.org/W2977259558","https://openalex.org/W3016092640","https://openalex.org/W3016138882","https://openalex.org/W3035570025","https://openalex.org/W3081192838","https://openalex.org/W3083650259","https://openalex.org/W3090471441","https://openalex.org/W3172353912","https://openalex.org/W3172448037","https://openalex.org/W3174977508","https://openalex.org/W3186351311","https://openalex.org/W3196974791","https://openalex.org/W3198791972","https://openalex.org/W3199258042","https://openalex.org/W3203115521","https://openalex.org/W3213879871","https://openalex.org/W4205633160","https://openalex.org/W4220829848","https://openalex.org/W4225959162","https://openalex.org/W4283016277","https://openalex.org/W4286436501","https://openalex.org/W4312292725","https://openalex.org/W4312976151","https://openalex.org/W4313349512","https://openalex.org/W4327852215","https://openalex.org/W4372260527","https://openalex.org/W4384341518","https://openalex.org/W4385245566","https://openalex.org/W4386824973","https://openalex.org/W4387757537","https://openalex.org/W4387967914","https://openalex.org/W4387969816","https://openalex.org/W4389733467","https://openalex.org/W4390331593","https://openalex.org/W4392903856","https://openalex.org/W4400276083","https://openalex.org/W4401044014","https://openalex.org/W4401871933","https://openalex.org/W4402858546","https://openalex.org/W4403063401","https://openalex.org/W4403987189","https://openalex.org/W4406657586","https://openalex.org/W4407559183"],"related_works":["https://openalex.org/W2271369634","https://openalex.org/W3147472394","https://openalex.org/W2047100085","https://openalex.org/W2350550760","https://openalex.org/W578794879","https://openalex.org/W2625296515","https://openalex.org/W3137890128","https://openalex.org/W1984634519","https://openalex.org/W4245955731","https://openalex.org/W2393726419"],"abstract_inverted_index":{"Emotional":[0],"factors":[1,21],"play":[2],"a":[3,123,205],"pivotal":[4],"role":[5],"in":[6,24,37],"fields":[7],"such":[8],"as":[9],"autonomous":[10],"driving":[11],"and":[12,67,80,105,116,127,197,204,216],"intelligent":[13],"emotional":[14,20,39,151,179],"robotics.":[15],"The":[16,98,181],"accurate":[17],"extraction":[18,72,156],"of":[19,35,61,73,157,175,187,202,209,225,234],"is":[22,100,136,169],"instrumental":[23],"reducing":[25],"error":[26],"rates":[27],"within":[28,64],"these":[29],"domains.":[30],"With":[31],"the":[32,38,56,82,107,154,173,176,190,212,232,235],"continuous":[33],"deepening":[34],"exploration":[36],"domain,":[40],"rich":[41],"multimodal":[42,51,78,103],"data":[43,104],"has":[44],"progressively":[45],"supplanted":[46],"unimodal":[47],"data.":[48],"Nevertheless,":[49],"current":[50],"approaches":[52],"still":[53],"grapple":[54],"with":[55],"following":[57],"challenges:":[58],"1.Partial":[59],"loss":[60,162],"information":[62],"both":[63],"individual":[65],"modalities":[66],"across":[68],"different":[69],"modalities.":[70,134],"2.Incorrect":[71],"modality-invariant":[74,140],"features.":[75,141],"To":[76],"facilitate":[77,131],"interaction":[79],"address":[81],"aforementioned":[83],"issues,":[84],"this":[85],"paper":[86],"proposes":[87],"an":[88,185,198],"Attention-based":[89],"Similarity":[90,112],"Fusion":[91],"Network":[92],"(ATTSF-Net)":[93],"for":[94],"audio-visual":[95,145,178],"emotion":[96],"recognition.":[97],"network":[99],"based":[101,164],"on":[102,165,189,211],"comprises":[106],"proposed":[108,182,236],"Cross-Multimodal":[109],"Block":[110,114],"(CMB),":[111],"Adjustment":[113],"(SAB),":[115],"Audio-Visual":[117],"Auxiliary":[118],"Modules":[119],"(AVAM).":[120],"CMB":[121],"employs":[122],"cross-modal":[124],"attention":[125],"mechanism":[126],"model-level":[128],"fusion":[129],"to":[130,138,148,171,230],"interactions":[132],"between":[133],"SAB":[135],"designed":[137,170],"learn":[139],"AVAM":[142],"utilizes":[143],"additional":[144],"auxiliary":[146],"networks":[147],"provide":[149],"supplementary":[150],"information,":[152],"enabling":[153],"full":[155],"intra-modal":[158],"information.":[159,180],"A":[160,223],"similarity":[161],"function":[163],"Kullback-Leibler":[166],"(KL)":[167],"divergence":[168],"ensure":[172],"consistency":[174],"learned":[177],"model":[183],"achieves":[184],"accuracy":[186,200,207],"88.67%":[188],"RAVDESS":[191],"dataset":[192,214],"(8.67%":[193],"higher":[194,218],"than":[195,219],"human)":[196],"unweighted":[199],"(UA)":[201],"81.93%":[203],"weighted":[206],"(WA)":[208],"79.77%":[210],"IEMOCAP":[213],"(4.01%":[215],"5.86%":[217],"transfer":[220],"learning,":[221],"respectively).":[222],"series":[224],"visualization":[226],"experiments":[227],"are":[228],"conducted":[229],"demonstrate":[231],"effectiveness":[233],"model.":[237]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-03-17T09:09:15.849793","created_date":"2025-10-10T00:00:00"}