{"id":"https://openalex.org/W2896323182","doi":"https://doi.org/10.1145/3264869.3264873","title":"Audio-Visual Attention Networks for Emotion Recognition","display_name":"Audio-Visual Attention Networks for Emotion Recognition","publication_year":2018,"publication_date":"2018-10-17","ids":{"openalex":"https://openalex.org/W2896323182","doi":"https://doi.org/10.1145/3264869.3264873","mag":"2896323182"},"language":"en","primary_location":{"id":"doi:10.1145/3264869.3264873","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3264869.3264873","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2018 Workshop on Audio-Visual Scene Understanding for Immersive Multimedia","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/A5100447461","display_name":"Jiyoung Lee","orcid":"https://orcid.org/0000-0003-0840-3317"},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Jiyoung Lee","raw_affiliation_strings":["Yonsei University, Seoul, Rebublic of Korea"],"affiliations":[{"raw_affiliation_string":"Yonsei University, Seoul, Rebublic of Korea","institution_ids":["https://openalex.org/I193775966"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002561350","display_name":"Sunok Kim","orcid":"https://orcid.org/0000-0002-9665-4214"},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sunok Kim","raw_affiliation_strings":["Yonsei University, Seoul, Rebublic of Korea"],"affiliations":[{"raw_affiliation_string":"Yonsei University, Seoul, Rebublic of Korea","institution_ids":["https://openalex.org/I193775966"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085363061","display_name":"Seungryong Kim","orcid":"https://orcid.org/0000-0003-2927-6273"},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Seungryong Kim","raw_affiliation_strings":["Yonsei University, Seoul, Rebublic of Korea"],"affiliations":[{"raw_affiliation_string":"Yonsei University, Seoul, Rebublic of Korea","institution_ids":["https://openalex.org/I193775966"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073320959","display_name":"Kwanghoon Sohn","orcid":"https://orcid.org/0000-0002-3715-0331"},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Kwanghoon Sohn","raw_affiliation_strings":["Yonsei University, Seoul, Rebublic of Korea"],"affiliations":[{"raw_affiliation_string":"Yonsei University, Seoul, Rebublic of Korea","institution_ids":["https://openalex.org/I193775966"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100447461"],"corresponding_institution_ids":["https://openalex.org/I193775966"],"apc_list":null,"apc_paid":null,"fwci":0.2049,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.61201603,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"1","issue":null,"first_page":"27","last_page":"32"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9991999864578247,"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":0.9991999864578247,"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":0.9987999796867371,"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/T10860","display_name":"Speech and Audio Processing","score":0.9952999949455261,"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":0.7966505289077759},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.6822409629821777},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.6266018152236938},{"id":"https://openalex.org/keywords/fuse","display_name":"Fuse (electrical)","score":0.6178867220878601},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6024124622344971},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5947273373603821},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.5287149548530579},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.49837279319763184},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4891844093799591},{"id":"https://openalex.org/keywords/facial-expression","display_name":"Facial expression","score":0.47915786504745483},{"id":"https://openalex.org/keywords/gesture","display_name":"Gesture","score":0.4612426161766052},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.41993412375450134},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4139927625656128}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7966505289077759},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.6822409629821777},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.6266018152236938},{"id":"https://openalex.org/C141353440","wikidata":"https://www.wikidata.org/wiki/Q182221","display_name":"Fuse (electrical)","level":2,"score":0.6178867220878601},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6024124622344971},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5947273373603821},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.5287149548530579},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.49837279319763184},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4891844093799591},{"id":"https://openalex.org/C195704467","wikidata":"https://www.wikidata.org/wiki/Q327968","display_name":"Facial expression","level":2,"score":0.47915786504745483},{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.4612426161766052},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.41993412375450134},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4139927625656128},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"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/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3264869.3264873","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3264869.3264873","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2018 Workshop on Audio-Visual Scene Understanding for Immersive Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.75,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1533861849","https://openalex.org/W1903399393","https://openalex.org/W1923034539","https://openalex.org/W2021913835","https://openalex.org/W2064675550","https://openalex.org/W2081835714","https://openalex.org/W2085662862","https://openalex.org/W2115252128","https://openalex.org/W2153822685","https://openalex.org/W2172806452","https://openalex.org/W2195207531","https://openalex.org/W2271840356","https://openalex.org/W2277498883","https://openalex.org/W2342662179","https://openalex.org/W2346454595","https://openalex.org/W2397302540","https://openalex.org/W2531466839","https://openalex.org/W2604292070","https://openalex.org/W2751214333","https://openalex.org/W2791271581","https://openalex.org/W2793286375","https://openalex.org/W2887068828","https://openalex.org/W2915606245","https://openalex.org/W2916322827","https://openalex.org/W2949408958","https://openalex.org/W2950178297","https://openalex.org/W2952430919","https://openalex.org/W2953118818","https://openalex.org/W6677618333"],"related_works":["https://openalex.org/W3013693939","https://openalex.org/W2159052453","https://openalex.org/W2566616303","https://openalex.org/W3131327266","https://openalex.org/W2734887215","https://openalex.org/W4297051394","https://openalex.org/W4206297952","https://openalex.org/W2584926856","https://openalex.org/W2075935902","https://openalex.org/W2014713986"],"abstract_inverted_index":{"We":[0],"present":[1],"a":[2],"spatiotemporal":[3,51,64,85],"attention":[4,24,39,52],"based":[5],"multimodal":[6,16,108],"deep":[7,42],"neu-":[8],"ral":[9],"networks":[10,44,91],"for":[11],"dimensional":[12,100,135],"emotion":[13,101,119,136],"recognition":[14,137],"in":[15,102,134],"audio-visual":[17],"video":[18,116],"sequence.":[19],"To":[20],"learn":[21,49],"the":[22,37,50,63,84,87,99,113,131,139],"temporal":[23,38],"that":[25,53,126],"discriminatively":[26],"focuses":[27,55],"on":[28,56,145],"emotional":[29,57],"sailient":[30,58],"parts":[31,59],"within":[32,60],"speech":[33],"audios,":[34],"we":[35,111],"formulate":[36],"network":[40,66],"using":[41,70],"neural":[43,90],"(DNNs).":[45],"In":[46],"addition,":[47],"to":[48,96,106,118],"selectively":[54],"facial":[61,103],"videos,":[62],"encoder-decoder":[65],"is":[67,93],"formu-":[68],"lated":[69],"Convolutional":[71],"LSTM":[72],"(ConvLSTM)":[73],"modules,":[74],"and":[75,115],"learned":[76],"implicitly":[77],"without":[78],"any":[79],"pixel-level":[80],"annotations.":[81],"By":[82],"leveraging":[83],"attention,":[86],"3D":[88],"convolutional":[89],"(3D-CNNs)":[92],"also":[94],"formulated":[95],"robustly":[97],"recognize":[98],"videos.":[104],"Furthermore,":[105],"exploit":[107],"infor-":[109],"mation,":[110],"fuse":[112],"audio":[114],"features":[117],"regression":[120],"model.":[121],"The":[122],"experimental":[123],"results":[124,133],"show":[125],"our":[127],"method":[128],"can":[129],"achieve":[130],"state-of-the-art":[132],"with":[138],"highest":[140],"concordance":[141],"correlation":[142],"coefficient":[143],"(CCC)":[144],"AV+EC":[146],"2017":[147],"dataset.":[148]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}