{"id":"https://openalex.org/W4387421554","doi":"https://doi.org/10.1145/3577190.3616544","title":"Audio-Visual Group-based Emotion Recognition using Local and Global Feature Aggregation based Multi-Task Learning","display_name":"Audio-Visual Group-based Emotion Recognition using Local and Global Feature Aggregation based Multi-Task Learning","publication_year":2023,"publication_date":"2023-10-07","ids":{"openalex":"https://openalex.org/W4387421554","doi":"https://doi.org/10.1145/3577190.3616544"},"language":"en","primary_location":{"id":"doi:10.1145/3577190.3616544","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3577190.3616544","pdf_url":null,"source":{"id":"https://openalex.org/S4363608440","display_name":"INTERNATIONAL CONFERENCE ON MULTIMODAL INTERACTION","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERNATIONAL CONFERENCE ON MULTIMODAL INTERACTION","raw_type":"proceedings-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/A5114859532","display_name":"Sunan Li","orcid":"https://orcid.org/0000-0003-1494-4873"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sunan Li","raw_affiliation_strings":["School of Information Science and Engineering, Southeast University, China"],"raw_orcid":"https://orcid.org/0000-0003-1494-4873","affiliations":[{"raw_affiliation_string":"School of Information Science and Engineering, Southeast University, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091060125","display_name":"Hailun Lian","orcid":"https://orcid.org/0000-0002-1355-9503"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hailun Lian","raw_affiliation_strings":["School of Information Science and Engineering, Southeast University, China"],"raw_orcid":"https://orcid.org/0000-0002-1355-9503","affiliations":[{"raw_affiliation_string":"School of Information Science and Engineering, Southeast University, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054796879","display_name":"Cheng Lu","orcid":"https://orcid.org/0000-0002-1477-1020"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cheng Lu","raw_affiliation_strings":["School of Biological Science and Medical Engineering, Southeast University, China"],"raw_orcid":"https://orcid.org/0000-0002-1477-1020","affiliations":[{"raw_affiliation_string":"School of Biological Science and Medical Engineering, Southeast University, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100727732","display_name":"Yan Zhao","orcid":"https://orcid.org/0000-0003-4577-7078"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yan Zhao","raw_affiliation_strings":["School of Information Science and Engineering, Southeast University, China"],"raw_orcid":"https://orcid.org/0000-0003-4577-7078","affiliations":[{"raw_affiliation_string":"School of Information Science and Engineering, Southeast University, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038686056","display_name":"Chuangao Tang","orcid":"https://orcid.org/0000-0002-3653-136X"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chuangao Tang","raw_affiliation_strings":["School of Biological Science and Medical Engineering, Southeast University, China"],"raw_orcid":"https://orcid.org/0000-0002-3653-136X","affiliations":[{"raw_affiliation_string":"School of Biological Science and Medical Engineering, Southeast University, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027316177","display_name":"Yuan Zong","orcid":"https://orcid.org/0000-0002-0839-8792"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuan Zong","raw_affiliation_strings":["School of Biological Science and Medical Engineering, Southeast University, China"],"raw_orcid":"https://orcid.org/0000-0002-0839-8792","affiliations":[{"raw_affiliation_string":"School of Biological Science and Medical Engineering, Southeast University, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029771864","display_name":"Wenming Zheng","orcid":"https://orcid.org/0000-0002-7764-5179"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenming Zheng","raw_affiliation_strings":["Key Laboratory of Child Development and Learning Science of Ministry of Education, Southeast University, China"],"raw_orcid":"https://orcid.org/0000-0002-7764-5179","affiliations":[{"raw_affiliation_string":"Key Laboratory of Child Development and Learning Science of Ministry of Education, Southeast University, China","institution_ids":["https://openalex.org/I76569877"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I76569877"],"apc_list":null,"apc_paid":null,"fwci":0.1161,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.33473154,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"741","last_page":"745"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.998199999332428,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.998199999332428,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.9979000091552734,"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/T10860","display_name":"Speech and Audio Processing","score":0.9958999752998352,"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":0.7999668717384338},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6123203039169312},{"id":"https://openalex.org/keywords/fuse","display_name":"Fuse (electrical)","score":0.5842992067337036},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5625602602958679},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5565692782402039},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.5309431552886963},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5105975270271301},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.4853004813194275},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4759126305580139},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.45850497484207153},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4027506113052368},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3874143958091736},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3500763177871704}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7999668717384338},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6123203039169312},{"id":"https://openalex.org/C141353440","wikidata":"https://www.wikidata.org/wiki/Q182221","display_name":"Fuse (electrical)","level":2,"score":0.5842992067337036},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5625602602958679},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5565692782402039},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.5309431552886963},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5105975270271301},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.4853004813194275},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4759126305580139},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.45850497484207153},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4027506113052368},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3874143958091736},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3500763177871704},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"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/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3577190.3616544","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3577190.3616544","pdf_url":null,"source":{"id":"https://openalex.org/S4363608440","display_name":"INTERNATIONAL CONFERENCE ON MULTIMODAL INTERACTION","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERNATIONAL CONFERENCE ON MULTIMODAL INTERACTION","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W2041616772","https://openalex.org/W2194775991","https://openalex.org/W2245421092","https://openalex.org/W2259209600","https://openalex.org/W2293804193","https://openalex.org/W2295579880","https://openalex.org/W3084809844","https://openalex.org/W3093581966","https://openalex.org/W3094309768","https://openalex.org/W3094378983","https://openalex.org/W3209059054","https://openalex.org/W4312857458","https://openalex.org/W4387423997"],"related_works":["https://openalex.org/W3000097931","https://openalex.org/W2354322770","https://openalex.org/W4237547500","https://openalex.org/W1570848052","https://openalex.org/W2373192430","https://openalex.org/W4239268388","https://openalex.org/W4243305035","https://openalex.org/W1537496349","https://openalex.org/W2379407973","https://openalex.org/W4309346246"],"abstract_inverted_index":{"Audio-video":[0],"group":[1],"emotion":[2],"recognition":[3],"is":[4],"a":[5,38,108,143],"challenging":[6],"task":[7],"and":[8,49,69,162],"has":[9],"attracted":[10],"more":[11],"attention":[12,103],"in":[13,24,62,97],"recent":[14],"decades.":[15],"Recently,":[16],"deep":[17],"learning":[18],"models":[19],"have":[20],"shown":[21],"tremendous":[22],"advances":[23],"analyzing":[25],"human":[26],"emotion.":[27],"However,":[28],"due":[29],"to":[30,36,44,51,78,117,141,152],"its":[31,129],"difficulties":[32],"such":[33],"as":[34,107],"hard":[35,50],"gather":[37],"broad":[39],"range":[40],"of":[41,88,147,174],"potential":[42],"information":[43],"obtain":[45],"meaningful":[46],"emotional":[47],"representations":[48],"associate":[52],"implicit":[53],"contextual":[54],"knowledge":[55],"like":[56],"humans.":[57],"To":[58],"tackle":[59,79],"these":[60],"problems,":[61],"this":[63],"paper,":[64],"we":[65,127],"proposed":[66],"the":[67,80,124,132,148,153,156,166,172],"Local":[68],"Global":[70],"Feature":[71],"Aggregation":[72],"based":[73],"Multi-Task":[74],"Learning":[75],"(LGFAM)":[76],"method":[77],"Group":[81],"Emotion":[82,136],"Recognition":[83,137],"problem.":[84],"The":[85],"framework":[86],"consists":[87],"three":[89,149],"parallel":[90],"feature":[91],"extraction":[92],"networks":[93],"that":[94],"were":[95],"verified":[96],"previous":[98],"work.":[99],"After":[100],"that,":[101],"an":[102],"network":[104],"using":[105],"MLP":[106],"backbone":[109],"with":[110],"specially":[111],"designed":[112],"loss":[113],"functions":[114],"was":[115],"used":[116],"fuse":[118],"features":[119],"from":[120],"different":[121],"modalities.":[122],"In":[123],"experiment":[125],"section,":[126],"present":[128],"performance":[130],"on":[131,165],"EmotiW2023":[133],"Audio-Visual":[134],"Group-based":[135],"subchallenge":[138],"which":[139],"aims":[140],"classify":[142],"video":[144],"into":[145],"one":[146],"emotions.":[150],"According":[151],"feedback":[154],"results,":[155],"best":[157],"result":[158],"achieved":[159],"70.63":[160],"WAR":[161],"70.38":[163],"UAR":[164],"test":[167],"set.":[168],"Such":[169],"improvement":[170],"proves":[171],"effectiveness":[173],"our":[175],"method.":[176]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}