{"id":"https://openalex.org/W3100219394","doi":"https://doi.org/10.1109/tmm.2020.3037496","title":"Transformer Encoder With Multi-Modal Multi-Head Attention for Continuous Affect Recognition","display_name":"Transformer Encoder With Multi-Modal Multi-Head Attention for Continuous Affect Recognition","publication_year":2020,"publication_date":"2020-11-12","ids":{"openalex":"https://openalex.org/W3100219394","doi":"https://doi.org/10.1109/tmm.2020.3037496","mag":"3100219394"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2020.3037496","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2020.3037496","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Multimedia","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/A5100456775","display_name":"Haifeng Chen","orcid":"https://orcid.org/0000-0001-7164-5840"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]},{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haifeng Chen","raw_affiliation_strings":["NPU-VUB Joint AVSP Research Laboratory, Shaanxi Key Laboratory on Speech and Image Information Processing, School of Computer Science, Northwestern Polytechnical University (NPU), National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology, Xi\u2019an, China","Peng Cheng Laboratory, Shenzhen, China","NPU-VUB Joint AVSP Research Laboratory, Shaanxi Key Laboratory on Speech and Image Information Processing, School of Computer Science, Northwestern Polytechnical University (NPU), National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology, Xi'an, China"],"raw_orcid":"https://orcid.org/0000-0001-7164-5840","affiliations":[{"raw_affiliation_string":"NPU-VUB Joint AVSP Research Laboratory, Shaanxi Key Laboratory on Speech and Image Information Processing, School of Computer Science, Northwestern Polytechnical University (NPU), National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology, Xi\u2019an, China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"Peng Cheng Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I4210136793"]},{"raw_affiliation_string":"NPU-VUB Joint AVSP Research Laboratory, Shaanxi Key Laboratory on Speech and Image Information Processing, School of Computer Science, Northwestern Polytechnical University (NPU), National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102021514","display_name":"Dongmei Jiang","orcid":"https://orcid.org/0000-0002-6238-8499"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]},{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dongmei Jiang","raw_affiliation_strings":["NPU-VUB Joint AVSP Research Laboratory, Shaanxi Key Laboratory on Speech and Image Information Processing, School of Computer Science, Northwestern Polytechnical University (NPU), National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology, Xi\u2019an, China","Peng Cheng Laboratory, Shenzhen, China","NPU-VUB Joint AVSP Research Laboratory, Shaanxi Key Laboratory on Speech and Image Information Processing, School of Computer Science, Northwestern Polytechnical University (NPU), National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology, Xi'an, China"],"raw_orcid":"https://orcid.org/0000-0002-6238-8499","affiliations":[{"raw_affiliation_string":"NPU-VUB Joint AVSP Research Laboratory, Shaanxi Key Laboratory on Speech and Image Information Processing, School of Computer Science, Northwestern Polytechnical University (NPU), National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology, Xi\u2019an, China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"Peng Cheng Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I4210136793"]},{"raw_affiliation_string":"NPU-VUB Joint AVSP Research Laboratory, Shaanxi Key Laboratory on Speech and Image Information Processing, School of Computer Science, Northwestern Polytechnical University (NPU), National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073820422","display_name":"Hichem Sahli","orcid":"https://orcid.org/0000-0002-1774-2970"},"institutions":[{"id":"https://openalex.org/I13469542","display_name":"Vrije Universiteit Brussel","ror":"https://ror.org/006e5kg04","country_code":"BE","type":"education","lineage":["https://openalex.org/I13469542"]},{"id":"https://openalex.org/I4210114974","display_name":"IMEC","ror":"https://ror.org/02kcbn207","country_code":"BE","type":"nonprofit","lineage":["https://openalex.org/I4210114974"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Hichem Sahli","raw_affiliation_strings":["Interuniversity Microelectronics Centre, Heverlee, Belgium","VUB-NPU joint AVSP Research Laboratory, Department of Electronics and Informatics, Vrije Universiteit Brussel, Brussels, Belgium"],"raw_orcid":"https://orcid.org/0000-0002-1774-2970","affiliations":[{"raw_affiliation_string":"Interuniversity Microelectronics Centre, Heverlee, Belgium","institution_ids":["https://openalex.org/I4210114974"]},{"raw_affiliation_string":"VUB-NPU joint AVSP Research Laboratory, Department of Electronics and Informatics, Vrije Universiteit Brussel, Brussels, Belgium","institution_ids":["https://openalex.org/I13469542"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":8.0896,"has_fulltext":false,"cited_by_count":133,"citation_normalized_percentile":{"value":0.97980519,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"23","issue":null,"first_page":"4171","last_page":"4183"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9837999939918518,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9812999963760376,"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":0.7989858388900757},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6351035237312317},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5987058877944946},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.5452213883399963},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5100334286689758},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.4484291076660156},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4250313639640808},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.39121466875076294},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3341901898384094},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.08953991532325745}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7989858388900757},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6351035237312317},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5987058877944946},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5452213883399963},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5100334286689758},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.4484291076660156},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4250313639640808},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.39121466875076294},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3341901898384094},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.08953991532325745},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/tmm.2020.3037496","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2020.3037496","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Multimedia","raw_type":"journal-article"},{"id":"pmh:oai:vubissmart:VUBISSMART:2000:155217","is_oa":false,"landing_page_url":"https://biblio.vub.ac.be/vubir/transformer-encoder-with-multimodal-multihead-attention-for-continuous-affect-recognition(e32a5783-11c1-423e-ae80-52f22ee86a2b).html","pdf_url":null,"source":{"id":"https://openalex.org/S4306402573","display_name":"VUBIR (Vrije Universiteit Brussel)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I13469542","host_organization_name":"Vrije Universiteit Brussel","host_organization_lineage":["https://openalex.org/I13469542"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},{"id":"pmh:oai:vubissmart:VUBISSMART:2000:155217","is_oa":false,"landing_page_url":"https://doi.org/10.1109/TMM.2020.3037496","pdf_url":null,"source":{"id":"https://openalex.org/S4306402573","display_name":"VUBIR (Vrije Universiteit Brussel)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I13469542","host_organization_name":"Vrije Universiteit Brussel","host_organization_lineage":["https://openalex.org/I13469542"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},{"id":"pmh:oai:vubissmart:VUBISSMART:2000:184356","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306402573","display_name":"VUBIR (Vrije Universiteit Brussel)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I13469542","host_organization_name":"Vrije Universiteit Brussel","host_organization_lineage":["https://openalex.org/I13469542"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G331486752","display_name":null,"funder_award_id":"B16039","funder_id":"https://openalex.org/F4320327912","funder_display_name":"Higher Education Discipline Innovation Project"}],"funders":[{"id":"https://openalex.org/F4320327336","display_name":"Vlaamse regering","ror":null},{"id":"https://openalex.org/F4320327912","display_name":"Higher Education Discipline Innovation Project","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":85,"referenced_works":["https://openalex.org/W1533861849","https://openalex.org/W1595126664","https://openalex.org/W1789721553","https://openalex.org/W1899504021","https://openalex.org/W1902237438","https://openalex.org/W1964757081","https://openalex.org/W1976066595","https://openalex.org/W1976235033","https://openalex.org/W1986740180","https://openalex.org/W1987030537","https://openalex.org/W2021913835","https://openalex.org/W2026243162","https://openalex.org/W2037441721","https://openalex.org/W2045528981","https://openalex.org/W2064675550","https://openalex.org/W2129013408","https://openalex.org/W2130942839","https://openalex.org/W2131774270","https://openalex.org/W2132555391","https://openalex.org/W2149628368","https://openalex.org/W2152627593","https://openalex.org/W2156503193","https://openalex.org/W2162753443","https://openalex.org/W2164186291","https://openalex.org/W2164699598","https://openalex.org/W2171939880","https://openalex.org/W2194775991","https://openalex.org/W2346454595","https://openalex.org/W2526050071","https://openalex.org/W2531648894","https://openalex.org/W2560025328","https://openalex.org/W2584561145","https://openalex.org/W2610961739","https://openalex.org/W2625297138","https://openalex.org/W2734377693","https://openalex.org/W2747227176","https://openalex.org/W2751214333","https://openalex.org/W2765291577","https://openalex.org/W2766122029","https://openalex.org/W2766925079","https://openalex.org/W2787581402","https://openalex.org/W2792764867","https://openalex.org/W2891187402","https://openalex.org/W2892550322","https://openalex.org/W2895907940","https://openalex.org/W2896457183","https://openalex.org/W2896480997","https://openalex.org/W2897337310","https://openalex.org/W2897444637","https://openalex.org/W2910165986","https://openalex.org/W2913453026","https://openalex.org/W2936644098","https://openalex.org/W2937977583","https://openalex.org/W2952728748","https://openalex.org/W2962718314","https://openalex.org/W2963196848","https://openalex.org/W2963341956","https://openalex.org/W2963403868","https://openalex.org/W2964010806","https://openalex.org/W2964051877","https://openalex.org/W2972660800","https://openalex.org/W2981648259","https://openalex.org/W2981677410","https://openalex.org/W2981810796","https://openalex.org/W2981938460","https://openalex.org/W2990629080","https://openalex.org/W3005680577","https://openalex.org/W3016138882","https://openalex.org/W3099388488","https://openalex.org/W3103512193","https://openalex.org/W3182920176","https://openalex.org/W4290610135","https://openalex.org/W4385245566","https://openalex.org/W6631943919","https://openalex.org/W6638035981","https://openalex.org/W6639569935","https://openalex.org/W6679436768","https://openalex.org/W6687483927","https://openalex.org/W6739901393","https://openalex.org/W6740756965","https://openalex.org/W6749825310","https://openalex.org/W6755207826","https://openalex.org/W6770782798","https://openalex.org/W6774314701","https://openalex.org/W6780226713"],"related_works":["https://openalex.org/W4293226380","https://openalex.org/W4390516098","https://openalex.org/W2181948922","https://openalex.org/W2384362569","https://openalex.org/W2142795561","https://openalex.org/W4205302943","https://openalex.org/W2561132942","https://openalex.org/W4321487865","https://openalex.org/W3155418658","https://openalex.org/W4243199227"],"abstract_inverted_index":{"Continuous":[0],"affect":[1,87,112],"recognition":[2],"is":[3,150],"becoming":[4],"an":[5,135],"increasingly":[6],"attractive":[7],"research":[8],"topic":[9],"in":[10,152,179],"affective":[11,34,145],"computing.":[12],"Previous":[13],"works":[14],"mainly":[15],"focused":[16],"on":[17,159,174,194],"modelling":[18],"the":[19,42,50,64,81,93,121,144,160,195],"temporal":[20,82,126],"dependency":[21,83],"within":[22],"a":[23,67,72,102,153],"sensor":[24],"modality,":[25],"or":[26,29],"adopting":[27],"early":[28,38],"late":[30,47],"fusion":[31,39,48],"for":[32,84,110,188,192],"multi-modal":[33,111,130],"state":[35],"recognition.":[36,88,113],"However,":[37],"suffers":[40],"from":[41],"curse":[43],"of":[44,181],"dimensionality,":[45],"and":[46,52,70,95,118,124,155,162,177,190],"ignores":[49],"complementarity":[51,94],"redundancy":[53,96],"between":[54,97],"multiple":[55,98],"modal":[56,86],"streams.":[57],"In":[58],"this":[59],"paper,":[60],"we":[61,100],"first":[62],"introduce":[63],"transformer-encoder":[65],"with":[66,105,138],"self-attention":[68],"mechanism":[69],"propose":[71,101],"Convolutional":[73],"Neural":[74],"Network-Transformer":[75],"Encoder":[76,104],"(CNN-TE)":[77],"framework":[78,149],"to":[79,90,116,134,142,166],"model":[80],"single":[85],"Further,":[89],"effectively":[91],"consider":[92],"streams":[99],"Transformer":[103],"Multi-modal":[106],"Multi-head":[107],"Attention":[108],"(TEMMA)":[109],"TEMMA":[114],"allows":[115],"progressively":[117],"simultaneously":[119],"refine":[120],"inter-modality":[122],"interactions":[123],"intra-modality":[125],"dependency.":[127],"The":[128,147],"learned":[129],"representations":[131],"are":[132],"fed":[133],"Inference":[136],"Sub-network":[137],"fully":[139],"connected":[140],"layers":[141],"estimate":[143],"state.":[146],"proposed":[148],"trained":[151],"nutshell":[154],"demonstrates":[156],"its":[157],"effectiveness":[158],"AVEC2016":[161],"AVEC2019":[163,196],"datasets.":[164],"Compared":[165],"state-of-the-art":[167],"models,":[168],"our":[169],"approach":[170],"obtains":[171],"remarkable":[172],"improvements":[173],"both":[175],"arousal":[176,189],"valence":[178,193],"terms":[180],"concordance":[182],"correlation":[183],"coefficient":[184],"(CCC)":[185],"reaching":[186],"0.583":[187],"0.564":[191],"test":[197],"set.":[198]},"counts_by_year":[{"year":2026,"cited_by_count":13},{"year":2025,"cited_by_count":42},{"year":2024,"cited_by_count":31},{"year":2023,"cited_by_count":27},{"year":2022,"cited_by_count":13},{"year":2021,"cited_by_count":7}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}