{"id":"https://openalex.org/W3186351311","doi":"https://doi.org/10.1109/taslp.2021.3096037","title":"Information Fusion in Attention Networks Using Adaptive and Multi-Level Factorized Bilinear Pooling for Audio-Visual Emotion Recognition","display_name":"Information Fusion in Attention Networks Using Adaptive and Multi-Level Factorized Bilinear Pooling for Audio-Visual Emotion Recognition","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3186351311","doi":"https://doi.org/10.1109/taslp.2021.3096037","mag":"3186351311"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2021.3096037","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2021.3096037","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"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/ACM Transactions on Audio, Speech, and Language Processing","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/A5103235094","display_name":"Hengshun Zhou","orcid":"https://orcid.org/0000-0001-7878-6531"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Hengshun Zhou","raw_affiliation_strings":["National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066595711","display_name":"Jun Du","orcid":"https://orcid.org/0000-0002-2387-0389"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Du","raw_affiliation_strings":["National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100320637","display_name":"Yuanyuan Zhang","orcid":"https://orcid.org/0000-0002-0329-2518"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuanyuan Zhang","raw_affiliation_strings":["National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100434900","display_name":"Qing Wang","orcid":"https://orcid.org/0000-0003-3843-3920"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qing Wang","raw_affiliation_strings":["National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100349237","display_name":"Qingfeng Liu","orcid":"https://orcid.org/0000-0003-2492-8092"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qing-Feng Liu","raw_affiliation_strings":["National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066868860","display_name":"Chin\u2010Hui Lee","orcid":"https://orcid.org/0000-0002-1892-2551"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chin-Hui Lee","raw_affiliation_strings":["School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA, USA"],"affiliations":[{"raw_affiliation_string":"School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5103235094"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":9.8278,"has_fulltext":false,"cited_by_count":74,"citation_normalized_percentile":{"value":0.98655123,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":"29","issue":null,"first_page":"2617","last_page":"2629"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9997000098228455,"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":0.9997000098228455,"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/T11309","display_name":"Music and Audio Processing","score":0.9850000143051147,"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/T10860","display_name":"Speech and Audio Processing","score":0.9842000007629395,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7955599427223206},{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.6647430658340454},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.6022800207138062},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5835208892822266},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5516388416290283},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.45245158672332764},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.40018153190612793}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7955599427223206},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.6647430658340454},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6022800207138062},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5835208892822266},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5516388416290283},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.45245158672332764},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.40018153190612793},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2021.3096037","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2021.3096037","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"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/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7200000286102295,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":85,"referenced_works":["https://openalex.org/W1522734439","https://openalex.org/W1586176709","https://openalex.org/W1821462560","https://openalex.org/W1981070999","https://openalex.org/W1981918162","https://openalex.org/W2005445667","https://openalex.org/W2026243162","https://openalex.org/W2058127449","https://openalex.org/W2071249869","https://openalex.org/W2071954570","https://openalex.org/W2074657431","https://openalex.org/W2080289724","https://openalex.org/W2104657103","https://openalex.org/W2106390385","https://openalex.org/W2112555538","https://openalex.org/W2115252128","https://openalex.org/W2123260696","https://openalex.org/W2126552487","https://openalex.org/W2136155248","https://openalex.org/W2146334809","https://openalex.org/W2156387975","https://openalex.org/W2163026698","https://openalex.org/W2163605009","https://openalex.org/W2163685610","https://openalex.org/W2168692779","https://openalex.org/W2187089797","https://openalex.org/W2214134199","https://openalex.org/W2300860047","https://openalex.org/W2532034655","https://openalex.org/W2546875627","https://openalex.org/W2551829638","https://openalex.org/W2604290265","https://openalex.org/W2625297138","https://openalex.org/W2648194195","https://openalex.org/W2703895418","https://openalex.org/W2747664154","https://openalex.org/W2767618761","https://openalex.org/W2806051338","https://openalex.org/W2806432949","https://openalex.org/W2884739346","https://openalex.org/W2885005742","https://openalex.org/W2888683367","https://openalex.org/W2889065492","https://openalex.org/W2889374687","https://openalex.org/W2889462515","https://openalex.org/W2889717020","https://openalex.org/W2890915920","https://openalex.org/W2891182955","https://openalex.org/W2894458059","https://openalex.org/W2894805842","https://openalex.org/W2894871570","https://openalex.org/W2895006884","https://openalex.org/W2937624600","https://openalex.org/W2937977583","https://openalex.org/W2949197413","https://openalex.org/W2956824775","https://openalex.org/W2963066927","https://openalex.org/W2963150162","https://openalex.org/W2970710980","https://openalex.org/W2970868904","https://openalex.org/W2972463723","https://openalex.org/W2972495317","https://openalex.org/W2972640480","https://openalex.org/W2972688505","https://openalex.org/W2973037561","https://openalex.org/W2977809668","https://openalex.org/W2980393359","https://openalex.org/W2980495289","https://openalex.org/W2980730551","https://openalex.org/W2981072818","https://openalex.org/W2981101532","https://openalex.org/W2981171802","https://openalex.org/W2982395984","https://openalex.org/W3097488938","https://openalex.org/W3097969370","https://openalex.org/W3104696513","https://openalex.org/W3131553854","https://openalex.org/W3156237571","https://openalex.org/W6638523607","https://openalex.org/W6677618333","https://openalex.org/W6682889407","https://openalex.org/W6684070144","https://openalex.org/W6684191040","https://openalex.org/W6728881024","https://openalex.org/W6791050154"],"related_works":["https://openalex.org/W2953234277","https://openalex.org/W2626256601","https://openalex.org/W2900413183","https://openalex.org/W4390975304","https://openalex.org/W147410782","https://openalex.org/W1617617605","https://openalex.org/W2404514746","https://openalex.org/W1652783584","https://openalex.org/W2088733771","https://openalex.org/W2958404818"],"abstract_inverted_index":{"Multimodal":[0],"emotion":[1,8,61,95,158,188,222],"recognition":[2,62,189],"is":[3,12,43,91,103,137,165],"a":[4,53,77,98],"challenging":[5],"task":[6],"in":[7,24,174],"computing":[9],"as":[10],"it":[11],"quite":[13],"difficult":[14],"to":[15,19,35,105,128,153],"extract":[16],"discriminative":[17],"features":[18],"identify":[20],"the":[21,74,117,131,141,146,156,183,194,199,210,217,224,229,238],"subtle":[22],"differences":[23],"human":[25],"emotions":[26],"with":[27,83,116,190,202],"abstract":[28],"concept":[29],"and":[30,40,66,87,161,171,216,234],"multiple":[31],"expressions.":[32],"Moreover,":[33,207],"how":[34],"fully":[36,78,154],"utilize":[37,155],"both":[38,169],"audio":[39,75,119,192],"visual":[41],"information":[42,108],"still":[44],"an":[45,124,203],"open":[46],"problem.":[47],"In":[48],"this":[49],"paper,":[50],"we":[51],"propose":[52],"novel":[54],"multimodal":[55],"fusion":[56,109,132],"attention":[57,85,147],"network":[58,80],"for":[59,73,93,186,220],"audio-visual":[60,107,221],"based":[63,113,139],"on":[64,140,177,182,209,237],"adaptive":[65,125,160],"multi-level":[67,162],"factorized":[68],"bilinear":[69],"pooling":[70],"(FBP).":[71],"First,":[72],"stream,":[76,193],"convolutional":[79],"(FCN)":[81],"equipped":[82],"1-D":[84],"mechanism":[86,148],"local":[88,157],"response":[89],"normalization":[90],"designed":[92],"speech":[94,187],"recognition.":[96],"Next,":[97],"global":[99],"FBP":[100,163],"(G-FBP)":[101],"approach":[102,227],"presented":[104],"perform":[106],"by":[110,167],"integrating":[111],"self-attention":[112],"video":[114],"stream":[115],"proposed":[118,225],"stream.":[120],"To":[121],"improve":[122],"G-FBP,":[123],"strategy":[126],"(AG-FBP)":[127],"dynamically":[129],"calculate":[130],"weight":[133],"of":[134,149,179,205,213,232],"two":[135],"modalities":[136],"devised":[138],"emotion-related":[142],"representation":[143],"vectors":[144],"from":[145],"respective":[150],"modalities.":[151],"Finally,":[152],"information,":[159],"(AM-FBP)":[164],"introduced":[166],"combining":[168],"global-trunk":[170],"intra-trunk":[172],"data":[173],"one":[175],"recording":[176],"top":[178],"AG-FBP.":[180],"Tested":[181],"IEMOCAP":[184,218],"corpus":[185,219],"only":[191],"new":[195],"FCN":[196],"method":[197],"outperforms":[198],"state-of-the-art":[200],"results":[201],"accuracy":[204,231],"71.40%.":[206],"validated":[208],"AFEW":[211],"database":[212],"EmotiW2019":[214],"sub-challenge":[215],"recognition,":[223],"AM-FBP":[226],"achieves":[228],"best":[230],"63.09%":[233],"75.49%":[235],"respectively":[236],"test":[239],"set.":[240]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":16},{"year":2024,"cited_by_count":26},{"year":2023,"cited_by_count":17},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":4}],"updated_date":"2026-03-15T09:29:46.208133","created_date":"2025-10-10T00:00:00"}