{"id":"https://openalex.org/W2981072818","doi":"https://doi.org/10.1145/3340555.3355713","title":"Exploring Emotion Features and Fusion Strategies for Audio-Video Emotion Recognition","display_name":"Exploring Emotion Features and Fusion Strategies for Audio-Video Emotion Recognition","publication_year":2019,"publication_date":"2019-10-14","ids":{"openalex":"https://openalex.org/W2981072818","doi":"https://doi.org/10.1145/3340555.3355713","mag":"2981072818"},"language":"en","primary_location":{"id":"doi:10.1145/3340555.3355713","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3340555.3355713","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":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2012.13912","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103235094","display_name":"Hengshun Zhou","orcid":"https://orcid.org/0000-0001-7878-6531"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Hengshun Zhou","raw_affiliation_strings":["National Engineering Laboratory for Speech and Language Information Processing (NEL-SLIP), University of Science and Technology of China, P.R.China"],"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Speech and Language Information Processing (NEL-SLIP), University of Science and Technology of China, P.R.China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073252742","display_name":"Debin Meng","orcid":null},"institutions":[{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Debin Meng","raw_affiliation_strings":["ShenZhen Key Lab of Computer Vision and Pattern Recognition, SIAT-SenseTime Joint Lab, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, China"],"affiliations":[{"raw_affiliation_string":"ShenZhen Key Lab of Computer Vision and Pattern Recognition, SIAT-SenseTime Joint Lab, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210145761"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100320637","display_name":"Yuanyuan Zhang","orcid":"https://orcid.org/0000-0002-0329-2518"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuanyuan Zhang","raw_affiliation_strings":["National Engineering Laboratory for Speech and Language Information Processing (NEL-SLIP), University of Science and Technology of China, P.R.China"],"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Speech and Language Information Processing (NEL-SLIP), University of Science and Technology of China, P.R.China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033413473","display_name":"Xiaojiang Peng","orcid":"https://orcid.org/0000-0002-5783-321X"},"institutions":[{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaojiang Peng","raw_affiliation_strings":["ShenZhen Key Lab of Computer Vision and Pattern Recognition, SIAT-SenseTime Joint Lab, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, China"],"affiliations":[{"raw_affiliation_string":"ShenZhen Key Lab of Computer Vision and Pattern Recognition, SIAT-SenseTime Joint Lab, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210145761"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066595711","display_name":"Jun Du","orcid":"https://orcid.org/0000-0002-2387-0389"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Du","raw_affiliation_strings":["National Engineering Laboratory for Speech and Language Information Processing (NEL-SLIP), University of Science and Technology of China, P.R.China"],"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Speech and Language Information Processing (NEL-SLIP), University of Science and Technology of China, P.R.China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100437036","display_name":"Kai Wang","orcid":"https://orcid.org/0000-0002-6170-4744"},"institutions":[{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kai Wang","raw_affiliation_strings":["ShenZhen Key Lab of Computer Vision and Pattern Recognition, SIAT-SenseTime Joint Lab, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, China"],"affiliations":[{"raw_affiliation_string":"ShenZhen Key Lab of Computer Vision and Pattern Recognition, SIAT-SenseTime Joint Lab, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210145761"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100748135","display_name":"Yu Qiao","orcid":"https://orcid.org/0000-0002-1889-2567"},"institutions":[{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Qiao","raw_affiliation_strings":["ShenZhen Key Lab of Computer Vision and Pattern Recognition, SIAT-SenseTime Joint Lab, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, China"],"affiliations":[{"raw_affiliation_string":"ShenZhen Key Lab of Computer Vision and Pattern Recognition, SIAT-SenseTime Joint Lab, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210145761"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5103235094"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":6.8623,"has_fulltext":false,"cited_by_count":74,"citation_normalized_percentile":{"value":0.97095141,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"562","last_page":"566"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9994999766349792,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9987999796867371,"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/spectrogram","display_name":"Spectrogram","score":0.7454490661621094},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7222254276275635},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.7009190320968628},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6348139643669128},{"id":"https://openalex.org/keywords/concatenation","display_name":"Concatenation (mathematics)","score":0.5972826480865479},{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.5884644389152527},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.5175334811210632},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5136534571647644},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5058107376098633},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.4999086856842041},{"id":"https://openalex.org/keywords/emotion-classification","display_name":"Emotion classification","score":0.4236252009868622},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4187985956668854},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.41049641370773315},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.1559165120124817}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.7454490661621094},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7222254276275635},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.7009190320968628},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6348139643669128},{"id":"https://openalex.org/C87619178","wikidata":"https://www.wikidata.org/wiki/Q126002","display_name":"Concatenation (mathematics)","level":2,"score":0.5972826480865479},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.5884644389152527},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.5175334811210632},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5136534571647644},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5058107376098633},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.4999086856842041},{"id":"https://openalex.org/C206310091","wikidata":"https://www.wikidata.org/wiki/Q750859","display_name":"Emotion classification","level":2,"score":0.4236252009868622},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4187985956668854},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.41049641370773315},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.1559165120124817},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3340555.3355713","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3340555.3355713","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"},{"id":"pmh:oai:arXiv.org:2012.13912","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2012.13912","pdf_url":"https://arxiv.org/pdf/2012.13912","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2012.13912","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2012.13912","pdf_url":"https://arxiv.org/pdf/2012.13912","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1981918162","https://openalex.org/W2079735306","https://openalex.org/W2116261113","https://openalex.org/W2134431612","https://openalex.org/W2159957987","https://openalex.org/W2194775991","https://openalex.org/W2325939864","https://openalex.org/W2470673105","https://openalex.org/W2481681431","https://openalex.org/W2518732252","https://openalex.org/W2520774990","https://openalex.org/W2546875627","https://openalex.org/W2548529926","https://openalex.org/W2548899748","https://openalex.org/W2626778328","https://openalex.org/W2745497104","https://openalex.org/W2752491485","https://openalex.org/W2767359575","https://openalex.org/W2767618761","https://openalex.org/W2784874046","https://openalex.org/W2806432949","https://openalex.org/W2885005742","https://openalex.org/W2889978276","https://openalex.org/W2894805842","https://openalex.org/W2894871570","https://openalex.org/W2895006884","https://openalex.org/W2895443688","https://openalex.org/W2895475421","https://openalex.org/W2910074218","https://openalex.org/W2944210297","https://openalex.org/W2962685937","https://openalex.org/W2963252191"],"related_works":["https://openalex.org/W2184242386","https://openalex.org/W2325729322","https://openalex.org/W1923358586","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/W4380370144"],"abstract_inverted_index":{"The":[0],"audio-video":[1],"based":[2],"emotion":[3,27,39,62,83],"recognition":[4],"aims":[5],"to":[6,80],"classify":[7],"a":[8],"given":[9],"video":[10],"into":[11],"basic":[12],"emotions.":[13],"In":[14],"this":[15],"paper,":[16],"we":[17,41,68,100],"describe":[18],"our":[19],"approaches":[20],"in":[21,117],"EmotiW":[22],"2019,":[23],"which":[24],"mainly":[25],"explores":[26],"features":[28,55],"and":[29,35,48,51,60,71,88,108,114],"feature":[30,44,86,95],"fusion":[31,66,73],"strategies":[32],"for":[33,93],"audio":[34,43],"visual":[36],"modality.":[37],"For":[38,65],"features,":[40],"explore":[42,69],"with":[45,56],"both":[46],"speech-spectrogram":[47],"Log":[49],"Mel-spectrogram":[50],"evaluate":[52],"several":[53],"facial":[54],"different":[57,61],"CNN":[58],"models":[59],"pretrained":[63],"strategies.":[64],"strategies,":[67],"intra-modal":[70],"cross-modal":[72,94],"methods,":[74],"such":[75],"as":[76],"designing":[77],"attention":[78],"mechanisms":[79],"highlights":[81],"important":[82],"feature,":[84],"exploring":[85],"concatenation":[87],"factorized":[89],"bilinear":[90],"pooling":[91],"(FBP)":[92],"fusion.":[96],"With":[97],"careful":[98],"evaluation,":[99],"obtain":[101],"65.5%":[102],"on":[103,110],"the":[104,111,118],"AFEW":[105],"validation":[106],"set":[107,113],"62.48%":[109],"test":[112],"rank":[115],"third":[116],"challenge.":[119]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":15},{"year":2023,"cited_by_count":19},{"year":2022,"cited_by_count":19},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":6}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2019-10-25T00:00:00"}