{"id":"https://openalex.org/W2548128734","doi":"https://doi.org/10.1145/2993148.2997637","title":"Audio and face video emotion recognition in the wild using deep neural networks and small datasets","display_name":"Audio and face video emotion recognition in the wild using deep neural networks and small datasets","publication_year":2016,"publication_date":"2016-10-31","ids":{"openalex":"https://openalex.org/W2548128734","doi":"https://doi.org/10.1145/2993148.2997637","mag":"2548128734"},"language":"en","primary_location":{"id":"doi:10.1145/2993148.2997637","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2993148.2997637","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 18th ACM 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/A5100543848","display_name":"Wan Ding","orcid":null},"institutions":[{"id":"https://openalex.org/I40963666","display_name":"Central China Normal University","ror":"https://ror.org/03x1jna21","country_code":"CN","type":"education","lineage":["https://openalex.org/I40963666"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Wan Ding","raw_affiliation_strings":["Central China Normal University, China"],"affiliations":[{"raw_affiliation_string":"Central China Normal University, China","institution_ids":["https://openalex.org/I40963666"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102998516","display_name":"Mingyu Xu","orcid":"https://orcid.org/0009-0002-1168-2054"},"institutions":[{"id":"https://openalex.org/I141945490","display_name":"University of British Columbia","ror":"https://ror.org/03rmrcq20","country_code":"CA","type":"education","lineage":["https://openalex.org/I141945490"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Mingyu Xu","raw_affiliation_strings":["University of British Columbia, Canada"],"affiliations":[{"raw_affiliation_string":"University of British Columbia, Canada","institution_ids":["https://openalex.org/I141945490"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112133862","display_name":"Dongyan Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210161496","display_name":"A*STAR Graduate Academy","ror":"https://ror.org/059yjzn93","country_code":"SG","type":"education","lineage":["https://openalex.org/I115228651","https://openalex.org/I4210161496"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Dongyan Huang","raw_affiliation_strings":["A*STAR, Singapore"],"affiliations":[{"raw_affiliation_string":"A*STAR, Singapore","institution_ids":["https://openalex.org/I4210161496"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100403129","display_name":"Weisi Lin","orcid":"https://orcid.org/0000-0001-9866-1947"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Weisi Lin","raw_affiliation_strings":["Nanyang Technological University, Singapore"],"affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021872761","display_name":"Minghui Dong","orcid":"https://orcid.org/0000-0001-6543-2929"},"institutions":[{"id":"https://openalex.org/I4210161496","display_name":"A*STAR Graduate Academy","ror":"https://ror.org/059yjzn93","country_code":"SG","type":"education","lineage":["https://openalex.org/I115228651","https://openalex.org/I4210161496"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Minghui Dong","raw_affiliation_strings":["A*STAR, Singapore"],"affiliations":[{"raw_affiliation_string":"A*STAR, Singapore","institution_ids":["https://openalex.org/I4210161496"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043642303","display_name":"Xinguo Yu","orcid":"https://orcid.org/0000-0001-8379-6742"},"institutions":[{"id":"https://openalex.org/I40963666","display_name":"Central China Normal University","ror":"https://ror.org/03x1jna21","country_code":"CN","type":"education","lineage":["https://openalex.org/I40963666"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinguo Yu","raw_affiliation_strings":["Central China Normal University, China"],"affiliations":[{"raw_affiliation_string":"Central China Normal University, China","institution_ids":["https://openalex.org/I40963666"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032690182","display_name":"Haizhou Li","orcid":"https://orcid.org/0000-0001-9158-9401"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]},{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Haizhou Li","raw_affiliation_strings":["A*STAR, Singapore / National University of Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"A*STAR, Singapore / National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596","https://openalex.org/I115228651"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5100543848"],"corresponding_institution_ids":["https://openalex.org/I40963666"],"apc_list":null,"apc_paid":null,"fwci":5.4426,"has_fulltext":false,"cited_by_count":48,"citation_normalized_percentile":{"value":0.95468781,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"506","last_page":"513"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9961000084877014,"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":0.9944999814033508,"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":0.7755221128463745},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7110493183135986},{"id":"https://openalex.org/keywords/surprise","display_name":"Surprise","score":0.6032349467277527},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.5835593938827515},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5564800500869751},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.549911618232727},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5462427139282227},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5381131768226624},{"id":"https://openalex.org/keywords/disgust","display_name":"Disgust","score":0.5218664407730103},{"id":"https://openalex.org/keywords/facial-expression","display_name":"Facial expression","score":0.47569334506988525},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.4722418487071991},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4678889811038971},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.45887959003448486},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.45460835099220276},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.44190090894699097},{"id":"https://openalex.org/keywords/facial-recognition-system","display_name":"Facial recognition system","score":0.4377521574497223},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.4319216012954712},{"id":"https://openalex.org/keywords/emotion-classification","display_name":"Emotion classification","score":0.4235183298587799},{"id":"https://openalex.org/keywords/test-data","display_name":"Test data","score":0.41428595781326294},{"id":"https://openalex.org/keywords/anger","display_name":"Anger","score":0.06748461723327637}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7755221128463745},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7110493183135986},{"id":"https://openalex.org/C2780343955","wikidata":"https://www.wikidata.org/wiki/Q333173","display_name":"Surprise","level":2,"score":0.6032349467277527},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.5835593938827515},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5564800500869751},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.549911618232727},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5462427139282227},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5381131768226624},{"id":"https://openalex.org/C2777375102","wikidata":"https://www.wikidata.org/wiki/Q208351","display_name":"Disgust","level":3,"score":0.5218664407730103},{"id":"https://openalex.org/C195704467","wikidata":"https://www.wikidata.org/wiki/Q327968","display_name":"Facial expression","level":2,"score":0.47569334506988525},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.4722418487071991},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4678889811038971},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.45887959003448486},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.45460835099220276},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.44190090894699097},{"id":"https://openalex.org/C31510193","wikidata":"https://www.wikidata.org/wiki/Q1192553","display_name":"Facial recognition system","level":3,"score":0.4377521574497223},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.4319216012954712},{"id":"https://openalex.org/C206310091","wikidata":"https://www.wikidata.org/wiki/Q750859","display_name":"Emotion classification","level":2,"score":0.4235183298587799},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.41428595781326294},{"id":"https://openalex.org/C2779302386","wikidata":"https://www.wikidata.org/wiki/Q79871","display_name":"Anger","level":2,"score":0.06748461723327637},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0},{"id":"https://openalex.org/C118552586","wikidata":"https://www.wikidata.org/wiki/Q7867","display_name":"Psychiatry","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2993148.2997637","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2993148.2997637","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 18th ACM International Conference on Multimodal Interaction","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.46000000834465027,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G3955649278","display_name":null,"funder_award_id":"61272206","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W304834817","https://openalex.org/W1516748092","https://openalex.org/W1525636403","https://openalex.org/W1655469623","https://openalex.org/W1815076433","https://openalex.org/W1916406603","https://openalex.org/W1964920275","https://openalex.org/W1981918162","https://openalex.org/W1992227055","https://openalex.org/W2008887256","https://openalex.org/W2009119155","https://openalex.org/W2015645277","https://openalex.org/W2021913835","https://openalex.org/W2064675550","https://openalex.org/W2080576537","https://openalex.org/W2090777335","https://openalex.org/W2110242546","https://openalex.org/W2126017757","https://openalex.org/W2129106196","https://openalex.org/W2132438428","https://openalex.org/W2141830256","https://openalex.org/W2144093206","https://openalex.org/W2151103935","https://openalex.org/W2155893237","https://openalex.org/W2158198839","https://openalex.org/W2160304657","https://openalex.org/W2161969291","https://openalex.org/W2163605009","https://openalex.org/W2239141610","https://openalex.org/W2243226955","https://openalex.org/W2253728219","https://openalex.org/W2259317772","https://openalex.org/W2277498883","https://openalex.org/W2293078015","https://openalex.org/W2293804193","https://openalex.org/W2294427751","https://openalex.org/W2346454595","https://openalex.org/W2546649374","https://openalex.org/W2618530766","https://openalex.org/W2949833607"],"related_works":["https://openalex.org/W3199829813","https://openalex.org/W1550318927","https://openalex.org/W4305042383","https://openalex.org/W2546649374","https://openalex.org/W2773396412","https://openalex.org/W4380854332","https://openalex.org/W2184859701","https://openalex.org/W4386232293","https://openalex.org/W4380370144","https://openalex.org/W2009950829"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"the":[3,13,22,27,63,132,156,179,183,193],"techniques":[4],"used":[5],"in":[6,12],"our":[7],"contribution":[8],"to":[9,25,41,135],"Emotion":[10],"Recognition":[11],"Wild":[14],"2016\u2019s":[15],"video":[16],"based":[17,45],"sub-challenge.":[18],"The":[19,104,175],"purpose":[20],"of":[21,65,122,178,196],"sub-challenge":[23],"is":[24,62,95,128,152,187,190],"classify":[26],"six":[28],"basic":[29],"emotions":[30],"(angry,":[31],"sad,":[32],"happy,":[33],"surprise,":[34],"fear":[35],"&":[36],"disgust)":[37],"and":[38,69,111,166],"neutral.":[39],"Compared":[40],"earlier":[42],"years\u2019":[43],"movie":[44],"datasets,":[46],"this":[47],"year\u2019s":[48],"test":[49,185],"dataset":[50,186],"introduced":[51],"reality":[52],"TV":[53],"videos":[54],"containing":[55],"more":[56],"spontaneous":[57],"emotion.":[58],"Our":[59],"proposed":[60,180],"solution":[61],"fusion":[64,121],"facial":[66,78],"expression":[67],"recognition":[68,72],"audio":[70,140],"emotion":[71,79,141],"subsystems":[73,164],"at":[74,131],"score":[75,133],"level.":[76],"For":[77,139],"recognition,":[80,142],"starting":[81],"from":[82,125],"a":[83,90,143,168],"network":[84],"pre-trained":[85],"on":[86,97,182],"ImageNet":[87],"training":[88,99],"data,":[89],"deep":[91,144],"Convolutional":[92],"Neural":[93,149],"Network":[94,150],"fine-tuned":[96],"FER2013":[98],"data":[100],"for":[101,117],"feature":[102],"extraction.":[103],"classifiers,":[105],"i.e.,":[106],"kernel":[107],"SVM,":[108],"logistic":[109],"regression":[110],"partial":[112],"least":[113],"squares":[114],"are":[115],"studied":[116],"comparison.":[118],"An":[119],"optimal":[120],"classifiers":[123],"learned":[124],"different":[126],"kernels":[127],"carried":[129],"out":[130],"level":[134],"improve":[136],"system":[137],"performance.":[138,174],"Long":[145],"Short-Term":[146],"Memory":[147],"Recurrent":[148],"(LSTM-RNN)":[151],"trained":[153],"directly":[154],"using":[155],"challenge":[157,184,194],"dataset.":[158],"Experimental":[159],"results":[160],"show":[161],"that":[162],"both":[163],"individually":[165],"as":[167],"whole":[169],"can":[170],"achieve":[171],"state-of-the":[172],"art":[173],"overall":[176],"accuracy":[177],"approach":[181],"53.9%,":[188],"which":[189],"better":[191],"than":[192],"baseline":[195],"40.47%":[197],".":[198]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":12},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":5}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}