{"id":"https://openalex.org/W3193484423","doi":"https://doi.org/10.3390/s21165452","title":"Multi-Modal Residual Perceptron Network for Audio\u2013Video Emotion Recognition","display_name":"Multi-Modal Residual Perceptron Network for Audio\u2013Video Emotion Recognition","publication_year":2021,"publication_date":"2021-08-12","ids":{"openalex":"https://openalex.org/W3193484423","doi":"https://doi.org/10.3390/s21165452","mag":"3193484423","pmid":"https://pubmed.ncbi.nlm.nih.gov/34450894"},"language":"en","primary_location":{"id":"doi:10.3390/s21165452","is_oa":true,"landing_page_url":"https://doi.org/10.3390/s21165452","pdf_url":"https://www.mdpi.com/1424-8220/21/16/5452/pdf?version=1629078133","source":{"id":"https://openalex.org/S101949793","display_name":"Sensors","issn_l":"1424-8220","issn":["1424-8220"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sensors","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/1424-8220/21/16/5452/pdf?version=1629078133","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103065488","display_name":"Xin Chang","orcid":"https://orcid.org/0000-0003-2402-1124"},"institutions":[{"id":"https://openalex.org/I108403487","display_name":"Warsaw University of Technology","ror":"https://ror.org/00y0xnp53","country_code":"PL","type":"education","lineage":["https://openalex.org/I108403487"]}],"countries":["PL"],"is_corresponding":true,"raw_author_name":"Xin Chang","raw_affiliation_strings":["Institute of Radioelectronics and Multimedia Technology, Warsaw University of Technology, 00-665 Warsaw, Poland"],"raw_orcid":"https://orcid.org/0000-0003-2402-1124","affiliations":[{"raw_affiliation_string":"Institute of Radioelectronics and Multimedia Technology, Warsaw University of Technology, 00-665 Warsaw, Poland","institution_ids":["https://openalex.org/I108403487"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090710349","display_name":"W\u0142adys\u0142aw Skarbek","orcid":"https://orcid.org/0000-0002-1917-9181"},"institutions":[{"id":"https://openalex.org/I108403487","display_name":"Warsaw University of Technology","ror":"https://ror.org/00y0xnp53","country_code":"PL","type":"education","lineage":["https://openalex.org/I108403487"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"W\u0142adys\u0142aw Skarbek","raw_affiliation_strings":["Institute of Radioelectronics and Multimedia Technology, Warsaw University of Technology, 00-665 Warsaw, Poland"],"raw_orcid":"https://orcid.org/0000-0002-1917-9181","affiliations":[{"raw_affiliation_string":"Institute of Radioelectronics and Multimedia Technology, Warsaw University of Technology, 00-665 Warsaw, Poland","institution_ids":["https://openalex.org/I108403487"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5103065488"],"corresponding_institution_ids":["https://openalex.org/I108403487"],"apc_list":{"value":2400,"currency":"CHF","value_usd":2598},"apc_paid":{"value":2400,"currency":"CHF","value_usd":2598},"fwci":2.6949,"has_fulltext":true,"cited_by_count":24,"citation_normalized_percentile":{"value":0.9091541,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"21","issue":"16","first_page":"5452","last_page":"5452"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T11309","display_name":"Music and Audio Processing","score":0.9991999864578247,"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":0.9965999722480774,"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/modal","display_name":"Modal","score":0.7663984894752502},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7120442986488342},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.6774781942367554},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.5693939328193665},{"id":"https://openalex.org/keywords/perceptron","display_name":"Perceptron","score":0.5646443367004395},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5591028928756714},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5159190893173218},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5067625641822815},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5008985996246338},{"id":"https://openalex.org/keywords/multilayer-perceptron","display_name":"Multilayer perceptron","score":0.4188229739665985},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4104645550251007},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38916832208633423},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3819854259490967},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.0874604880809784}],"concepts":[{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.7663984894752502},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7120442986488342},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.6774781942367554},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.5693939328193665},{"id":"https://openalex.org/C60908668","wikidata":"https://www.wikidata.org/wiki/Q690207","display_name":"Perceptron","level":3,"score":0.5646443367004395},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5591028928756714},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5159190893173218},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5067625641822815},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5008985996246338},{"id":"https://openalex.org/C179717631","wikidata":"https://www.wikidata.org/wiki/Q2991667","display_name":"Multilayer perceptron","level":3,"score":0.4188229739665985},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4104645550251007},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38916832208633423},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3819854259490967},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.0874604880809784},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[{"descriptor_ui":"D004644","descriptor_name":"Emotions","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D004644","descriptor_name":"Emotions","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D004644","descriptor_name":"Emotions","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009040","descriptor_name":"Motion Pictures","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009040","descriptor_name":"Motion Pictures","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009040","descriptor_name":"Motion Pictures","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013060","descriptor_name":"Speech","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013060","descriptor_name":"Speech","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013060","descriptor_name":"Speech","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":5,"locations":[{"id":"doi:10.3390/s21165452","is_oa":true,"landing_page_url":"https://doi.org/10.3390/s21165452","pdf_url":"https://www.mdpi.com/1424-8220/21/16/5452/pdf?version=1629078133","source":{"id":"https://openalex.org/S101949793","display_name":"Sensors","issn_l":"1424-8220","issn":["1424-8220"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sensors","raw_type":"journal-article"},{"id":"pmid:34450894","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/34450894","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sensors (Basel, Switzerland)","raw_type":null},{"id":"pmh:oai:doaj.org/article:22e4b089f12a482b8e09fb272949de70","is_oa":true,"landing_page_url":"https://doaj.org/article/22e4b089f12a482b8e09fb272949de70","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Sensors, Vol 21, Iss 16, p 5452 (2021)","raw_type":"article"},{"id":"pmh:oai:mdpi.com:/1424-8220/21/16/5452/","is_oa":true,"landing_page_url":"https://dx.doi.org/10.3390/s21165452","pdf_url":null,"source":{"id":"https://openalex.org/S4306400947","display_name":"MDPI (MDPI AG)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210097602","host_organization_name":"Multidisciplinary Digital Publishing Institute (Switzerland)","host_organization_lineage":["https://openalex.org/I4210097602"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Sensors; Volume 21; Issue 16; Pages: 5452","raw_type":"Text"},{"id":"pmh:oai:pubmedcentral.nih.gov:8399720","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/8399720","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Sensors (Basel)","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.3390/s21165452","is_oa":true,"landing_page_url":"https://doi.org/10.3390/s21165452","pdf_url":"https://www.mdpi.com/1424-8220/21/16/5452/pdf?version=1629078133","source":{"id":"https://openalex.org/S101949793","display_name":"Sensors","issn_l":"1424-8220","issn":["1424-8220"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sensors","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.4699999988079071,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3193484423.pdf","grobid_xml":"https://content.openalex.org/works/W3193484423.grobid-xml"},"referenced_works_count":44,"referenced_works":["https://openalex.org/W2030931454","https://openalex.org/W2064675550","https://openalex.org/W2112796928","https://openalex.org/W2115252128","https://openalex.org/W2121647436","https://openalex.org/W2146334809","https://openalex.org/W2194775991","https://openalex.org/W2253728219","https://openalex.org/W2507009361","https://openalex.org/W2624340939","https://openalex.org/W2626778328","https://openalex.org/W2703895418","https://openalex.org/W2726515241","https://openalex.org/W2744909235","https://openalex.org/W2780113219","https://openalex.org/W2787581402","https://openalex.org/W2803193013","https://openalex.org/W2888683367","https://openalex.org/W2899366898","https://openalex.org/W2913340405","https://openalex.org/W2918087949","https://openalex.org/W2949833607","https://openalex.org/W2950971447","https://openalex.org/W2952186347","https://openalex.org/W2963087613","https://openalex.org/W2963192057","https://openalex.org/W2963252191","https://openalex.org/W2963524571","https://openalex.org/W2977259558","https://openalex.org/W2977659243","https://openalex.org/W2990113535","https://openalex.org/W2990235563","https://openalex.org/W2995479270","https://openalex.org/W2997359900","https://openalex.org/W2997700007","https://openalex.org/W2999157588","https://openalex.org/W3022013598","https://openalex.org/W3035333188","https://openalex.org/W3093521632","https://openalex.org/W3094502228","https://openalex.org/W3104377639","https://openalex.org/W3167773216","https://openalex.org/W6677618333","https://openalex.org/W6771698606"],"related_works":["https://openalex.org/W627697492","https://openalex.org/W2076543106","https://openalex.org/W2019891950","https://openalex.org/W2085842814","https://openalex.org/W2523437662","https://openalex.org/W4387048144","https://openalex.org/W2492135063","https://openalex.org/W2362514456","https://openalex.org/W2766585573","https://openalex.org/W4387490624"],"abstract_inverted_index":{"Emotion":[0],"recognition":[1,12,147],"is":[2,13],"an":[3],"important":[4],"research":[5],"field":[6],"for":[7,61,140,153,167,185],"human-computer":[8],"interaction.":[9],"Audio-video":[10],"emotion":[11],"now":[14],"attacked":[15],"with":[16,189],"deep":[17],"neural":[18,81],"network":[19,82,94,114,121,134,180],"modeling":[20,80],"tools.":[21],"In":[22,55],"published":[23],"papers,":[24],"as":[25],"a":[26,110],"rule,":[27],"the":[28,34,67,76,79,87,103,129,136,144,154,168,176],"authors":[29],"show":[30],"only":[31,193],"cases":[32,46],"of":[33,47,64,78,100,158,194],"superiority":[35,48],"in":[36,49,75,86,105],"multi-modality":[37],"over":[38],"audio-only":[39],"or":[40],"video-only":[41],"modality.":[42],"However,":[43],"there":[44],"are":[45],"uni-modality":[50],"that":[51,60],"can":[52],"be":[53],"found.":[54],"our":[56],"research,":[57],"we":[58,108],"hypothesize":[59],"fuzzy":[62],"categories":[63],"emotional":[65],"events,":[66],"within-modal":[68],"and":[69,91,101,135,161,164,196],"inter-modal":[70],"noisy":[71],"information":[72],"represented":[73],"indirectly":[74],"parameters":[77],"impedes":[83],"better":[84,124],"performance":[85],"existing":[88],"late":[89],"fusion":[90],"end-to-end":[92,117],"multi-modal":[93,111,120,125,131,177,186],"training":[95],"strategies.":[96],"To":[97],"take":[98],"advantage":[99],"overcome":[102],"deficiencies":[104],"both":[106],"solutions,":[107],"define":[109],"residual":[112,132,178],"perceptron":[113,133,179],"which":[115],"performs":[116],"learning":[118],"from":[119],"branches,":[122],"generalizing":[123],"feature":[126],"representation.":[127],"For":[128],"proposed":[130],"novel":[137],"time":[138],"augmentation":[139],"streaming":[141],"digital":[142],"movies,":[143],"state-of-the-art":[145],"average":[146],"rate":[148],"was":[149],"improved":[150],"to":[151,165],"91.4%":[152],"Ryerson":[155],"Audio-Visual":[156],"Database":[157],"Emotional":[159,170],"Speech":[160],"Song":[162],"dataset":[163],"83.15%":[166],"Crowd-Sourced":[169],"Multi":[171],"Modal":[172],"Actors":[173],"dataset.":[174],"Moreover,":[175],"concept":[181],"shows":[182],"its":[183],"potential":[184],"applications":[187],"dealing":[188],"signal":[190],"sources":[191],"not":[192],"optical":[195],"acoustical":[197],"types.":[198]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}