{"id":"https://openalex.org/W3007193627","doi":"https://doi.org/10.1109/icassp40776.2020.9052916","title":"Multitask Learning and Multistage Fusion for Dimensional Audiovisual Emotion Recognition","display_name":"Multitask Learning and Multistage Fusion for Dimensional Audiovisual Emotion Recognition","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3007193627","doi":"https://doi.org/10.1109/icassp40776.2020.9052916","mag":"3007193627"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9052916","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9052916","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2002.11312","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5065879041","display_name":"Bagus Tris Atmaja","orcid":"https://orcid.org/0000-0003-1560-2824"},"institutions":[{"id":"https://openalex.org/I177738480","display_name":"Japan Advanced Institute of Science and Technology","ror":"https://ror.org/03frj4r98","country_code":"JP","type":"education","lineage":["https://openalex.org/I177738480"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Bagus Tris Atmaja","raw_affiliation_strings":["School of Information Science, Japan Advanced Institute of Science and Technology, Japan","Japan Adv. Inst. of Science and Tech"],"affiliations":[{"raw_affiliation_string":"School of Information Science, Japan Advanced Institute of Science and Technology, Japan","institution_ids":["https://openalex.org/I177738480"]},{"raw_affiliation_string":"Japan Adv. Inst. of Science and Tech","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055059119","display_name":"Masato Akagi","orcid":"https://orcid.org/0000-0003-2450-6754"},"institutions":[{"id":"https://openalex.org/I177738480","display_name":"Japan Advanced Institute of Science and Technology","ror":"https://ror.org/03frj4r98","country_code":"JP","type":"education","lineage":["https://openalex.org/I177738480"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masato Akagi","raw_affiliation_strings":["School of Information Science, Japan Advanced Institute of Science and Technology, Japan","Japan Adv. Inst. of Science and Tech"],"affiliations":[{"raw_affiliation_string":"School of Information Science, Japan Advanced Institute of Science and Technology, Japan","institution_ids":["https://openalex.org/I177738480"]},{"raw_affiliation_string":"Japan Adv. Inst. of Science and Tech","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5065879041"],"corresponding_institution_ids":["https://openalex.org/I177738480"],"apc_list":null,"apc_paid":null,"fwci":0.5342,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.69043522,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"4482","last_page":"4486"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9950000047683716,"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":0.9950000047683716,"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":0.9911999702453613,"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":0.9896000027656555,"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/multi-task-learning","display_name":"Multi-task learning","score":0.6944938898086548},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6494516134262085},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.5961720943450928},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5839737057685852},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.5835197567939758},{"id":"https://openalex.org/keywords/arousal","display_name":"Arousal","score":0.5792783498764038},{"id":"https://openalex.org/keywords/valence","display_name":"Valence (chemistry)","score":0.5787053108215332},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.544503390789032},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.4894057810306549},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4843767583370209},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.47074541449546814},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4275890588760376},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.33842530846595764},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.1356794834136963},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07881015539169312}],"concepts":[{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.6944938898086548},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6494516134262085},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.5961720943450928},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5839737057685852},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.5835197567939758},{"id":"https://openalex.org/C36951298","wikidata":"https://www.wikidata.org/wiki/Q379784","display_name":"Arousal","level":2,"score":0.5792783498764038},{"id":"https://openalex.org/C168900304","wikidata":"https://www.wikidata.org/wiki/Q171407","display_name":"Valence (chemistry)","level":2,"score":0.5787053108215332},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.544503390789032},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.4894057810306549},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4843767583370209},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.47074541449546814},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4275890588760376},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33842530846595764},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.1356794834136963},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07881015539169312},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.1109/icassp40776.2020.9052916","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9052916","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2002.11312","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2002.11312","pdf_url":"https://arxiv.org/pdf/2002.11312","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},{"id":"pmh:oai:dspace.jaist.ac.jp:10119/16248","is_oa":false,"landing_page_url":"http://hdl.handle.net/10119/16248","pdf_url":null,"source":{"id":"https://openalex.org/S4406922663","display_name":"JAIST Repository","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""},{"id":"doi:10.48550/arxiv.2002.11312","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2002.11312","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"},{"id":"doi:10.17023/kqaq-qh76","is_oa":true,"landing_page_url":"https://doi.org/10.17023/kqaq-qh76","pdf_url":null,"source":{"id":"https://openalex.org/S7407051697","display_name":"IEEE RESOURCE CENTERS","issn_l":null,"issn":[],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"},{"id":"mag:3007193627","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2002.11312","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2002.11312","pdf_url":"https://arxiv.org/pdf/2002.11312","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1686810756","https://openalex.org/W2078833921","https://openalex.org/W2090777335","https://openalex.org/W2101234009","https://openalex.org/W2146334809","https://openalex.org/W2156848952","https://openalex.org/W2194775991","https://openalex.org/W2239141610","https://openalex.org/W2313339984","https://openalex.org/W2342475039","https://openalex.org/W2746419079","https://openalex.org/W2747172199","https://openalex.org/W2765291577","https://openalex.org/W2807126412","https://openalex.org/W2807805698","https://openalex.org/W2910165986","https://openalex.org/W2963614358","https://openalex.org/W2963702064","https://openalex.org/W2964010806","https://openalex.org/W2981677410","https://openalex.org/W3011985699","https://openalex.org/W6637373629","https://openalex.org/W6675354045","https://openalex.org/W6713639923","https://openalex.org/W6755423162"],"related_works":["https://openalex.org/W3016092640","https://openalex.org/W3165067022","https://openalex.org/W2005418748","https://openalex.org/W3127502324","https://openalex.org/W3013789346","https://openalex.org/W2991485489","https://openalex.org/W3185542152","https://openalex.org/W2016430603","https://openalex.org/W3117814038","https://openalex.org/W2765291577","https://openalex.org/W3088631780","https://openalex.org/W2951470742","https://openalex.org/W2531466839","https://openalex.org/W2794384003","https://openalex.org/W1995794789","https://openalex.org/W2020035762","https://openalex.org/W2066200210","https://openalex.org/W2997949149","https://openalex.org/W2343758848","https://openalex.org/W2889976648"],"abstract_inverted_index":{"Due":[0],"to":[1,4,27,56,67,100,131],"its":[2],"ability":[3],"accurately":[5],"predict":[6,28],"emotional":[7,29],"state":[8],"using":[9,36],"multimodal":[10],"features,":[11],"audiovisual":[12],"emotion":[13],"recognition":[14,59],"has":[15],"recently":[16],"gained":[17],"more":[18],"interest":[19],"from":[20,31,70],"researchers.":[21],"This":[22],"paper":[23],"proposes":[24],"two":[25],"methods":[26],"attributes":[30],"audio":[32],"and":[33,40,83,118,138],"visual":[34],"data":[35,126],"a":[37,41,62],"multitask":[38,45,78],"learning":[39,46,91],"fusion":[42,64,85,109],"strategy.":[43],"First,":[44],"is":[47,65],"employed":[48,80,105],"by":[49],"adjusting":[50],"three":[51],"parameters":[52],"for":[53,135],"each":[54],"attribute":[55],"improve":[57],"the":[58,107,113,122],"rate.":[60],"Second,":[61],"multistage":[63,103],"proposed":[66],"combine":[68],"results":[69],"various":[71],"modalities'":[72],"final":[73],"prediction.":[74],"Our":[75],"approach":[76],"used":[77],"learning,":[79],"at":[81,106],"unimodal":[82],"early":[84],"methods,":[86],"shows":[87],"improvement":[88],"over":[89],"single-task":[90],"with":[92],"an":[93],"average":[94],"CCC":[95],"score":[96,115],"of":[97,125],"0.431":[98],"compared":[99],"0.297.":[101],"A":[102],"method,":[104],"late":[108],"approach,":[110],"significantly":[111],"improved":[112],"agreement":[114],"between":[116],"true":[117],"predicted":[119],"values":[120],"on":[121],"development":[123],"set":[124],"(from":[127],"[0.537,":[128],"0.565,":[129],"0.083]":[130],"[0.68,":[132],"0.656,":[133],"0.443])":[134],"arousal,":[136],"valence,":[137],"liking.":[139]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}