{"id":"https://openalex.org/W2980393359","doi":"https://doi.org/10.1145/3340555.3355719","title":"Bi-modality Fusion for Emotion Recognition in the Wild","display_name":"Bi-modality Fusion for Emotion Recognition in the Wild","publication_year":2019,"publication_date":"2019-10-14","ids":{"openalex":"https://openalex.org/W2980393359","doi":"https://doi.org/10.1145/3340555.3355719","mag":"2980393359"},"language":"en","primary_location":{"id":"doi:10.1145/3340555.3355719","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3340555.3355719","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 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":[],"countries":[],"is_corresponding":true,"raw_author_name":"Sunan Li","raw_affiliation_strings":["Southeast University"],"affiliations":[{"raw_affiliation_string":"Southeast University","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029771864","display_name":"Wenming Zheng","orcid":"https://orcid.org/0000-0002-7764-5179"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wenming Zheng","raw_affiliation_strings":["Southeast University"],"affiliations":[{"raw_affiliation_string":"Southeast University","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027316177","display_name":"Yuan Zong","orcid":"https://orcid.org/0000-0002-0839-8792"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuan Zong","raw_affiliation_strings":["Southeast University"],"affiliations":[{"raw_affiliation_string":"Southeast University","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054796879","display_name":"Cheng Lu","orcid":"https://orcid.org/0000-0002-1477-1020"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cheng Lu","raw_affiliation_strings":["Southeast University"],"affiliations":[{"raw_affiliation_string":"Southeast University","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038686056","display_name":"Chuangao Tang","orcid":"https://orcid.org/0000-0002-3653-136X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chuangao Tang","raw_affiliation_strings":["Southeast University"],"affiliations":[{"raw_affiliation_string":"Southeast University","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028139864","display_name":"Xingxun Jiang","orcid":"https://orcid.org/0000-0002-2139-8623"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xingxun Jiang","raw_affiliation_strings":["Southeast University"],"affiliations":[{"raw_affiliation_string":"Southeast University","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075297564","display_name":"Jiateng Liu","orcid":"https://orcid.org/0000-0002-2974-5802"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiateng Liu","raw_affiliation_strings":["Southeast University"],"affiliations":[{"raw_affiliation_string":"Southeast University","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018772221","display_name":"Wanchuang Xia","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wanchuang Xia","raw_affiliation_strings":["Southeast University"],"affiliations":[{"raw_affiliation_string":"Southeast University","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5114859532"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.7573,"has_fulltext":false,"cited_by_count":39,"citation_normalized_percentile":{"value":0.96321312,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"589","last_page":"594"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9998999834060669,"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":0.9998999834060669,"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/T10057","display_name":"Face and Expression Recognition","score":0.9936000108718872,"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/T11448","display_name":"Face recognition and analysis","score":0.9918000102043152,"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":0.7854760885238647},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.7296196222305298},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6805100440979004},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.6088613867759705},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.604602038860321},{"id":"https://openalex.org/keywords/facial-expression","display_name":"Facial expression","score":0.6000210642814636},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5753023624420166},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.5097126364707947},{"id":"https://openalex.org/keywords/expression","display_name":"Expression (computer science)","score":0.5008060932159424},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.4905034899711609},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.486786812543869},{"id":"https://openalex.org/keywords/long-short-term-memory","display_name":"Long short term memory","score":0.4660685360431671},{"id":"https://openalex.org/keywords/facial-recognition-system","display_name":"Facial recognition system","score":0.41918349266052246},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.35064589977264404},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.30822885036468506},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.25682762265205383}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7854760885238647},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.7296196222305298},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6805100440979004},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.6088613867759705},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.604602038860321},{"id":"https://openalex.org/C195704467","wikidata":"https://www.wikidata.org/wiki/Q327968","display_name":"Facial expression","level":2,"score":0.6000210642814636},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5753023624420166},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.5097126364707947},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.5008060932159424},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.4905034899711609},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.486786812543869},{"id":"https://openalex.org/C133488467","wikidata":"https://www.wikidata.org/wiki/Q6673524","display_name":"Long short term memory","level":4,"score":0.4660685360431671},{"id":"https://openalex.org/C31510193","wikidata":"https://www.wikidata.org/wiki/Q1192553","display_name":"Facial recognition system","level":3,"score":0.41918349266052246},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.35064589977264404},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.30822885036468506},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.25682762265205383},{"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},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3340555.3355719","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3340555.3355719","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 International Conference on Multimodal Interaction","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.46000000834465027,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W179875071","https://openalex.org/W1686810756","https://openalex.org/W1974932989","https://openalex.org/W1981918162","https://openalex.org/W2064675550","https://openalex.org/W2079735306","https://openalex.org/W2097117768","https://openalex.org/W2149933564","https://openalex.org/W2194775991","https://openalex.org/W2245421092","https://openalex.org/W2259209600","https://openalex.org/W2293804193","https://openalex.org/W2295579880","https://openalex.org/W2325939864","https://openalex.org/W2341528187","https://openalex.org/W2523915246","https://openalex.org/W2618530766","https://openalex.org/W2745497104","https://openalex.org/W2894805842","https://openalex.org/W2963446712","https://openalex.org/W2981103441","https://openalex.org/W2981234363","https://openalex.org/W3101998545","https://openalex.org/W3122081138","https://openalex.org/W4297683907"],"related_works":["https://openalex.org/W2530685530","https://openalex.org/W4375868962","https://openalex.org/W2088854863","https://openalex.org/W2011227383","https://openalex.org/W1976719989","https://openalex.org/W2184242386","https://openalex.org/W2325729322","https://openalex.org/W1923358586","https://openalex.org/W2584926856","https://openalex.org/W2014713986"],"abstract_inverted_index":{"The":[0,67,86,174],"emotion":[1,25,62,171],"recognition":[2,26,63,91,100,143,172],"in":[3,12,27,64],"the":[4,13,24,28,37,65,73,81,97,116,125,129,146,149,170,180,187,191,198,207],"wild":[5,29],"has":[6],"been":[7,22],"a":[8,55,139],"hot":[9],"research":[10],"topic":[11],"field":[14],"of":[15,39,72,115,124,183,190,201],"affective":[16],"computing.":[17],"Though":[18],"some":[19],"progresses":[20],"have":[21],"achieved,":[23],"is":[30,109,132,194],"still":[31],"an":[32],"unsolved":[33],"problem":[34],"due":[35],"to":[36,95,111,120,137,168],"challenge":[38,193],"head":[40],"movement,":[41],"face":[42],"deformation,":[43],"illumination":[44],"variation":[45],"etc.":[46],"To":[47],"deal":[48],"with":[49],"these":[50],"unconstrained":[51],"challenges,":[52],"we":[53],"propose":[54],"bi-modality":[56],"fusion":[57],"method":[58],"for":[59],"video":[60],"based":[61,89,151],"wild.":[66],"proposed":[68],"framework":[69],"takes":[70],"advantages":[71,123],"visual":[74],"information":[75,83,114],"from":[76,84],"facial":[77,98,126,141],"expression":[78,99,127,142],"sequences":[79],"and":[80,158,203],"speech":[82],"audio.":[85],"state-of-the-art":[87],"CNN":[88],"object":[90],"models":[92],"are":[93,165],"employed":[94,110],"facilitate":[96],"performance.":[101,173],"A":[102],"bi-direction":[103],"long":[104],"short":[105],"term":[106],"Memory":[107],"(Bi-LSTM)":[108],"capture":[112],"dynamic":[113],"learned":[117],"features.":[118],"Additionally,":[119],"take":[121],"full":[122],"information,":[128],"VGG16":[130],"network":[131],"trained":[133],"on":[134,186],"AffectNet":[135],"dataset":[136,189],"learn":[138],"specialized":[140],"model.":[144],"On":[145],"other":[147],"hand,":[148],"audio":[150],"features,":[152],"like":[153],"low":[154],"level":[155],"descriptor":[156],"(LLD)":[157],"deep":[159],"features":[160],"obtained":[161],"by":[162],"spectrogram":[163],"image,":[164],"also":[166],"developed":[167],"improve":[169],"best":[175,199],"experimental":[176],"result":[177,200],"shows":[178],"that":[179],"overall":[181],"accuracy":[182],"our":[184],"algorithm":[185],"Test":[188],"EmotiW":[192],"62.78,":[195],"which":[196],"outperforms":[197],"EmotiW2018":[202],"ranks":[204],"2nd":[205],"at":[206],"EmotiW2019":[208],"challenge.":[209]},"counts_by_year":[{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":12},{"year":2021,"cited_by_count":11},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}