{"id":"https://openalex.org/W2977809668","doi":"https://doi.org/10.1109/ijcnn.2019.8851942","title":"Deep Fusion: An Attention Guided Factorized Bilinear Pooling for Audio-video Emotion Recognition","display_name":"Deep Fusion: An Attention Guided Factorized Bilinear Pooling for Audio-video Emotion Recognition","publication_year":2019,"publication_date":"2019-07-01","ids":{"openalex":"https://openalex.org/W2977809668","doi":"https://doi.org/10.1109/ijcnn.2019.8851942","mag":"2977809668"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn.2019.8851942","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2019.8851942","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 International Joint Conference on Neural Networks (IJCNN)","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/A5100320684","display_name":"Yuanyuan Zhang","orcid":"https://orcid.org/0000-0003-1714-9736"},"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":"Yuanyuan Zhang","raw_affiliation_strings":["National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100607794","display_name":"Zi-Rui Wang","orcid":"https://orcid.org/0000-0002-6600-8801"},"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":"Zi-Rui Wang","raw_affiliation_strings":["National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","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, University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100320684"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":3.483,"has_fulltext":false,"cited_by_count":31,"citation_normalized_percentile":{"value":0.93764576,"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":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998000264167786,"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/T10860","display_name":"Speech and Audio Processing","score":0.9994000196456909,"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/T10667","display_name":"Emotion and Mood Recognition","score":0.9993000030517578,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7972699403762817},{"id":"https://openalex.org/keywords/concatenation","display_name":"Concatenation (mathematics)","score":0.7382996082305908},{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.7057802677154541},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5868905186653137},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5197155475616455},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.5157849788665771},{"id":"https://openalex.org/keywords/bilinear-interpolation","display_name":"Bilinear interpolation","score":0.4918479919433594},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.48208242654800415},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4800897240638733},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.47100889682769775},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.46987348794937134},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.20133739709854126}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7972699403762817},{"id":"https://openalex.org/C87619178","wikidata":"https://www.wikidata.org/wiki/Q126002","display_name":"Concatenation (mathematics)","level":2,"score":0.7382996082305908},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.7057802677154541},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5868905186653137},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5197155475616455},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.5157849788665771},{"id":"https://openalex.org/C205203396","wikidata":"https://www.wikidata.org/wiki/Q612143","display_name":"Bilinear interpolation","level":2,"score":0.4918479919433594},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.48208242654800415},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4800897240638733},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.47100889682769775},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.46987348794937134},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.20133739709854126},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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/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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"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:10.1109/ijcnn.2019.8851942","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2019.8851942","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.4399999976158142}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1522734439","https://openalex.org/W1686810756","https://openalex.org/W1981918162","https://openalex.org/W2009375902","https://openalex.org/W2032254851","https://openalex.org/W2085662862","https://openalex.org/W2104657103","https://openalex.org/W2106390385","https://openalex.org/W2115252128","https://openalex.org/W2163605009","https://openalex.org/W2170653751","https://openalex.org/W2194775991","https://openalex.org/W2295739661","https://openalex.org/W2325939864","https://openalex.org/W2399733683","https://openalex.org/W2546875627","https://openalex.org/W2551829638","https://openalex.org/W2625297138","https://openalex.org/W2648194195","https://openalex.org/W2747664154","https://openalex.org/W2767618761","https://openalex.org/W2767915528","https://openalex.org/W2792191740","https://openalex.org/W2806051338","https://openalex.org/W2806432949","https://openalex.org/W2888683367","https://openalex.org/W2889445231","https://openalex.org/W2894805842","https://openalex.org/W2894871570","https://openalex.org/W2963150162","https://openalex.org/W2963252191","https://openalex.org/W3104696513","https://openalex.org/W4388315058","https://openalex.org/W6637373629","https://openalex.org/W6677618333","https://openalex.org/W6684191040","https://openalex.org/W6700903540"],"related_works":["https://openalex.org/W2950524887","https://openalex.org/W2883502031","https://openalex.org/W2261271299","https://openalex.org/W2963066927","https://openalex.org/W4280638452","https://openalex.org/W3111811104","https://openalex.org/W4380083739","https://openalex.org/W4285020665","https://openalex.org/W2984974891","https://openalex.org/W4322208588"],"abstract_inverted_index":{"Automatic":[0],"emotion":[1],"recognition":[2],"(AER)":[3],"is":[4,20],"a":[5,24,64,126],"challenging":[6],"task":[7],"due":[8],"to":[9,48,92,114],"the":[10,95,102,107,116,131,135,140,149],"abstract":[11],"concept":[12],"and":[13,35,52,71,81,99],"multiple":[14],"expressions":[15],"of":[16,97,134,146],"emotion.":[17],"Although":[18],"there":[19],"no":[21],"consensus":[22],"on":[23,130],"definition,":[25],"human":[26,44],"emotional":[27],"states":[28],"usually":[29],"can":[30,122],"be":[31,123],"apperceived":[32],"by":[33,39],"auditory":[34],"visual":[36,53],"systems.":[37],"Inspired":[38],"this":[40,84],"cognitive":[41],"process":[42],"in":[43,55,125,138],"beings,":[45],"it's":[46],"natural":[47],"simultaneously":[49],"utilize":[50],"audio":[51,80,98],"information":[54],"AER.":[56],"However,":[57],"most":[58],"traditional":[59],"fusion":[60],"approaches":[61],"only":[62],"build":[63],"linear":[65],"paradigm,":[66],"such":[67],"as":[68],"feature":[69],"concatenation":[70],"multi-system":[72],"fusion,":[73],"which":[74],"hardly":[75],"captures":[76],"complex":[77],"association":[78],"between":[79],"video.":[82,100],"In":[83],"paper,":[85],"we":[86],"introduce":[87],"factorized":[88],"bilinear":[89],"pooling":[90],"(FBP)":[91],"deeply":[93],"integrate":[94],"features":[96,103],"Specifically,":[101],"are":[104],"selected":[105],"through":[106],"embedded":[108],"attention":[109],"mechanism":[110],"from":[111],"respective":[112],"modalities":[113],"obtain":[115],"emotion-related":[117],"regions.":[118],"The":[119],"whole":[120],"pipeline":[121],"completed":[124],"neural":[127],"network.":[128],"Validated":[129],"AFEW":[132],"database":[133],"audio-video":[136],"sub-challenge":[137],"EmotiW2018,":[139],"proposed":[141],"approach":[142],"achieves":[143],"an":[144],"accuracy":[145],"62.48%,":[147],"outperforming":[148],"state-of-the-art":[150],"result.":[151]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":11},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}