{"id":"https://openalex.org/W3160215661","doi":"https://doi.org/10.1109/mmul.2021.3080305","title":"End-to-End Learning for Multimodal Emotion Recognition in Video With Adaptive Loss","display_name":"End-to-End Learning for Multimodal Emotion Recognition in Video With Adaptive Loss","publication_year":2021,"publication_date":"2021-04-01","ids":{"openalex":"https://openalex.org/W3160215661","doi":"https://doi.org/10.1109/mmul.2021.3080305","mag":"3160215661"},"language":"en","primary_location":{"id":"doi:10.1109/mmul.2021.3080305","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mmul.2021.3080305","pdf_url":null,"source":{"id":"https://openalex.org/S72873717","display_name":"IEEE Multimedia","issn_l":"1070-986X","issn":["1070-986X","1941-0166"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 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/A5012883484","display_name":"Van Thong Huynh","orcid":"https://orcid.org/0000-0002-6240-2959"},"institutions":[{"id":"https://openalex.org/I111277659","display_name":"Chonnam National University","ror":"https://ror.org/05kzjxq56","country_code":"KR","type":"education","lineage":["https://openalex.org/I111277659"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Van Thong Huynh","raw_affiliation_strings":["Chonnam National University, Gwangju, South Korea"],"affiliations":[{"raw_affiliation_string":"Chonnam National University, Gwangju, South Korea","institution_ids":["https://openalex.org/I111277659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087619194","display_name":"Hyung-Jeong Yang","orcid":"https://orcid.org/0000-0003-3024-5060"},"institutions":[{"id":"https://openalex.org/I111277659","display_name":"Chonnam National University","ror":"https://ror.org/05kzjxq56","country_code":"KR","type":"education","lineage":["https://openalex.org/I111277659"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hyung-Jeong Yang","raw_affiliation_strings":["Chonnam National University, Gwangju, South Korea"],"affiliations":[{"raw_affiliation_string":"Chonnam National University, Gwangju, South Korea","institution_ids":["https://openalex.org/I111277659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070936425","display_name":"Guee-Sang Lee","orcid":"https://orcid.org/0000-0002-8756-1382"},"institutions":[{"id":"https://openalex.org/I111277659","display_name":"Chonnam National University","ror":"https://ror.org/05kzjxq56","country_code":"KR","type":"education","lineage":["https://openalex.org/I111277659"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Guee-Sang Lee","raw_affiliation_strings":["Chonnam National University, Gwangju, South Korea"],"affiliations":[{"raw_affiliation_string":"Chonnam National University, Gwangju, South Korea","institution_ids":["https://openalex.org/I111277659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100605822","display_name":"Soo-Hyung Kim","orcid":"https://orcid.org/0000-0003-3575-5035"},"institutions":[{"id":"https://openalex.org/I111277659","display_name":"Chonnam National University","ror":"https://ror.org/05kzjxq56","country_code":"KR","type":"education","lineage":["https://openalex.org/I111277659"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Soo-Hyung Kim","raw_affiliation_strings":["Chonnam National University, Gwangju, South Korea"],"affiliations":[{"raw_affiliation_string":"Chonnam National University, Gwangju, South Korea","institution_ids":["https://openalex.org/I111277659"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5012883484"],"corresponding_institution_ids":["https://openalex.org/I111277659"],"apc_list":null,"apc_paid":null,"fwci":0.8765,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.74014735,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"28","issue":"2","first_page":"59","last_page":"66"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9998000264167786,"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":0.9998000264167786,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.996399998664856,"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9962000250816345,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8832839727401733},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5648531913757324},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.523827850818634},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5094149708747864},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.45716843008995056},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.4343975782394409},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4303121566772461},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.4275946617126465},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.42561644315719604},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4185760021209717},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3530251383781433},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3227502405643463}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8832839727401733},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5648531913757324},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.523827850818634},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5094149708747864},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.45716843008995056},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.4343975782394409},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4303121566772461},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.4275946617126465},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.42561644315719604},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4185760021209717},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3530251383781433},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3227502405643463},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","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:10.1109/mmul.2021.3080305","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mmul.2021.3080305","pdf_url":null,"source":{"id":"https://openalex.org/S72873717","display_name":"IEEE Multimedia","issn_l":"1070-986X","issn":["1070-986X","1941-0166"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 MultiMedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6700000166893005}],"awards":[{"id":"https://openalex.org/G3915194844","display_name":null,"funder_award_id":"NRF-2020R1A4A1019191","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"},{"id":"https://openalex.org/G8530313645","display_name":null,"funder_award_id":"NRF-2018R1D1A3A03000947","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"}],"funders":[{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W2119217515","https://openalex.org/W2177696193","https://openalex.org/W2617750261","https://openalex.org/W2624340939","https://openalex.org/W2787581402","https://openalex.org/W2883409523","https://openalex.org/W2892071465","https://openalex.org/W2905628412","https://openalex.org/W2949391930","https://openalex.org/W2963163009","https://openalex.org/W2963452792","https://openalex.org/W2963677766","https://openalex.org/W2964010806","https://openalex.org/W2964051877","https://openalex.org/W2972602947","https://openalex.org/W2980175391","https://openalex.org/W2995479270","https://openalex.org/W2997258743","https://openalex.org/W3094524767","https://openalex.org/W3099153556","https://openalex.org/W6748551036"],"related_works":["https://openalex.org/W73545470","https://openalex.org/W4224266612","https://openalex.org/W2383394264","https://openalex.org/W4320153225","https://openalex.org/W4293261942","https://openalex.org/W3125968744","https://openalex.org/W2167701463","https://openalex.org/W2110287964","https://openalex.org/W4307407935","https://openalex.org/W649759291"],"abstract_inverted_index":{"This":[0],"work":[1],"presents":[2],"an":[3,20],"approach":[4],"for":[5,50,56,149],"emotion":[6,61,150],"recognition":[7,62,151],"in":[8,19,59,66],"video":[9],"through":[10],"the":[11,51,60,69,86,90,102,109,119,125,138,155],"interaction":[12,123],"of":[13,72,81,92,104,114,157],"visual,":[14],"audio,":[15],"and":[16,35,88,112,164],"language":[17],"information":[18],"end-to-end":[21],"learning":[22,113],"manner":[23],"with":[24,45,76,132],"three":[25],"key":[26],"points:":[27],"1)":[28],"lightweight":[29,42],"feature":[30,57],"extractor,":[31],"2)":[32],"attention":[33,96,162],"strategy,":[34],"3)":[36],"adaptive":[37,133,165],"loss.":[38],"We":[39],"proposed":[40],"a":[41,146],"deep":[43],"architecture":[44,83],"approximately":[46],"1":[47],"MB,":[48],"which":[49,136],"most":[52],"crucial":[53],"part,":[54],"accounts":[55],"extraction,":[58],"systems.":[63],"The":[64,95,122,141],"relationship":[65],"regard":[67],"to":[68,84,100,118],"time":[70,110],"dimension":[71,111],"features":[73],"is":[74,98,127],"explored":[75],"temporal":[77,105],"convolutional":[78],"network":[79],"instead":[80],"RNNs-based":[82],"leverage":[85],"parallelism":[87],"avoid":[89],"challenge":[91],"vanishing":[93],"gradient.":[94,140],"strategy":[97],"employed":[99],"adjust":[101],"knowledge":[103],"networks":[106],"based":[107],"on":[108,145,152],"each":[115],"modality's":[116],"contribution":[117],"final":[120],"results.":[121],"between":[124],"modalities":[126],"also":[128],"investigated":[129],"when":[130,160],"training":[131],"objective":[134],"function,":[135],"adjusts":[137],"network's":[139],"experimental":[142],"results":[143],"obtained":[144],"large-scale":[147],"dataset":[148],"Koreans":[153],"demonstrate":[154],"superiority":[156],"our":[158],"method":[159],"employing":[161],"mechanism":[163],"loss":[166],"during":[167],"training.":[168]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}