{"id":"https://openalex.org/W4404048966","doi":"https://doi.org/10.1007/s11042-024-20409-2","title":"Constructing multi-modal emotion recognition model based on convolutional neural network","display_name":"Constructing multi-modal emotion recognition model based on convolutional neural network","publication_year":2024,"publication_date":"2024-11-04","ids":{"openalex":"https://openalex.org/W4404048966","doi":"https://doi.org/10.1007/s11042-024-20409-2"},"language":"en","primary_location":{"id":"doi:10.1007/s11042-024-20409-2","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11042-024-20409-2","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11042-024-20409-2.pdf","source":{"id":"https://openalex.org/S110206669","display_name":"Multimedia Tools and Applications","issn_l":"1380-7501","issn":["1380-7501","1573-7721"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Multimedia Tools and Applications","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s11042-024-20409-2.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5021782845","display_name":"Jong-Yih Kuo","orcid":"https://orcid.org/0000-0001-5723-2222"},"institutions":[{"id":"https://openalex.org/I118292597","display_name":"National Taipei University of Technology","ror":"https://ror.org/00cn92c09","country_code":"TW","type":"education","lineage":["https://openalex.org/I118292597"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Jong-Yih Kuo","raw_affiliation_strings":["Department of Computer Science and Information Engineering, National Taipei University of Technology, Taipei, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Information Engineering, National Taipei University of Technology, Taipei, Taiwan","institution_ids":["https://openalex.org/I118292597"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Ti-Feng Hsieh","orcid":"https://orcid.org/0009-0003-8488-261X"},"institutions":[{"id":"https://openalex.org/I118292597","display_name":"National Taipei University of Technology","ror":"https://ror.org/00cn92c09","country_code":"TW","type":"education","lineage":["https://openalex.org/I118292597"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Ti-Feng Hsieh","raw_affiliation_strings":["Department of Computer Science and Information Engineering, National Taipei University of Technology, Taipei, Taiwan"],"raw_orcid":"https://orcid.org/0009-0003-8488-261X","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Information Engineering, National Taipei University of Technology, Taipei, Taiwan","institution_ids":["https://openalex.org/I118292597"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044734253","display_name":"Tzu\u2010Yu Lin","orcid":"https://orcid.org/0000-0002-7915-4373"},"institutions":[{"id":"https://openalex.org/I118292597","display_name":"National Taipei University of Technology","ror":"https://ror.org/00cn92c09","country_code":"TW","type":"education","lineage":["https://openalex.org/I118292597"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Ta-Yu Lin","raw_affiliation_strings":["Department of Computer Science and Information Engineering, National Taipei University of Technology, Taipei, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Information Engineering, National Taipei University of Technology, Taipei, Taiwan","institution_ids":["https://openalex.org/I118292597"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I118292597"],"apc_list":null,"apc_paid":null,"fwci":2.1685,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.8819796,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":"84","issue":"26","first_page":"31093","last_page":"31118"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9994999766349792,"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":0.9994999766349792,"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9962999820709229,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9890000224113464,"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":0.8504570722579956},{"id":"https://openalex.org/keywords/facial-expression","display_name":"Facial expression","score":0.645632803440094},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6153736710548401},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5928159952163696},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5388370156288147},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5332030653953552},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.43070146441459656},{"id":"https://openalex.org/keywords/emotion-classification","display_name":"Emotion classification","score":0.42235153913497925},{"id":"https://openalex.org/keywords/expression","display_name":"Expression (computer science)","score":0.41825270652770996},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4164454936981201}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8504570722579956},{"id":"https://openalex.org/C195704467","wikidata":"https://www.wikidata.org/wiki/Q327968","display_name":"Facial expression","level":2,"score":0.645632803440094},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6153736710548401},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5928159952163696},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5388370156288147},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5332030653953552},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.43070146441459656},{"id":"https://openalex.org/C206310091","wikidata":"https://www.wikidata.org/wiki/Q750859","display_name":"Emotion classification","level":2,"score":0.42235153913497925},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.41825270652770996},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4164454936981201},{"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s11042-024-20409-2","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11042-024-20409-2","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11042-024-20409-2.pdf","source":{"id":"https://openalex.org/S110206669","display_name":"Multimedia Tools and Applications","issn_l":"1380-7501","issn":["1380-7501","1573-7721"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Multimedia Tools and Applications","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s11042-024-20409-2","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11042-024-20409-2","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11042-024-20409-2.pdf","source":{"id":"https://openalex.org/S110206669","display_name":"Multimedia Tools and Applications","issn_l":"1380-7501","issn":["1380-7501","1573-7721"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Multimedia Tools and Applications","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.46000000834465027,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320324051","display_name":"National Taipei University of Technology","ror":"https://ror.org/00cn92c09"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4404048966.pdf","grobid_xml":"https://content.openalex.org/works/W4404048966.grobid-xml"},"referenced_works_count":15,"referenced_works":["https://openalex.org/W1522734439","https://openalex.org/W1583837637","https://openalex.org/W1983364832","https://openalex.org/W2112796928","https://openalex.org/W2168692779","https://openalex.org/W2394998899","https://openalex.org/W2595840341","https://openalex.org/W2889466822","https://openalex.org/W2963163009","https://openalex.org/W2995255435","https://openalex.org/W2996906606","https://openalex.org/W3034552680","https://openalex.org/W3202835744","https://openalex.org/W4213102761","https://openalex.org/W4308906267"],"related_works":["https://openalex.org/W2642127892","https://openalex.org/W2945121592","https://openalex.org/W2584926856","https://openalex.org/W2075935902","https://openalex.org/W3000867607","https://openalex.org/W2798351401","https://openalex.org/W2729544402","https://openalex.org/W2913821117","https://openalex.org/W2519456985","https://openalex.org/W1992768889"],"abstract_inverted_index":{"As":[0],"society":[1],"advances,":[2],"an":[3],"increasing":[4],"number":[5],"of":[6,42,61,71,170,191],"individuals":[7],"spend":[8],"significant":[9],"time":[10,238],"interacting":[11],"with":[12,55],"computers":[13],"daily.":[14],"To":[15],"enhance":[16,86],"the":[17,27,76,80,110,196,206,216,236,240,244],"human-computer":[18],"interaction":[19],"experience,":[20],"it":[21],"has":[22],"become":[23,40],"crucial":[24],"to":[25,44,78,188],"augment":[26],"computer\u2019s":[28],"ability":[29,77],"for":[30,128],"emotion":[31,95,107,115,130,142,158,245],"recognition.":[32,131],"This":[33,122,213],"capability":[34],"holds":[35],"excellent":[36],"importance":[37],"as":[38,162,174],"machines":[39],"capable":[41,169],"responding":[43],"us":[45],"in":[46,94,223],"a":[47,125,165,184],"more":[48],"natural":[49],"and":[50,66,102,117,119,134,144,198,201,219,232],"contextually":[51],"relevant":[52],"manner,":[53],"aligned":[54],"our":[56],"current":[57],"emotional":[58],"states.":[59],"Examples":[60],"such":[62],"applications":[63],"include":[64,97],"caregiving":[65],"social":[67],"robots.":[68],"Accurate":[69],"recognition":[70,96,108],"human":[72],"emotions,":[73],"followed":[74],"by":[75],"determine":[79],"most":[81,90],"appropriate":[82],"responses,":[83],"can":[84,239],"significantly":[85],"user":[87],"experiences.":[88],"The":[89,105,132,140,156,177,226],"commonly":[91],"employed":[92],"methods":[93],"observing":[98],"facial":[99,178,192,233],"expressions,":[100],"audio,":[101],"conversational":[103],"content.":[104],"multi-modal":[106],"lacks":[109],"explicit":[111],"mapping":[112],"relation":[113],"between":[114],"state":[116],"audio":[118,133,141,157,231],"image":[120],"features.":[121],"study":[123],"proposes":[124],"fusion":[126],"method":[127],"audio-visual":[129],"video":[135],"data":[136],"are":[137,247],"preprocessed":[138],"separately.":[139],"features":[143,147,200,234],"visual":[145,197],"expression":[146,179,193],"were":[148],"then":[149],"extracted":[150],"using":[151,205],"two":[152],"distinct":[153],"feature":[154,159,180,203],"extractors.":[155],"extractor,":[160,181],"denoted":[161],"audio-net,":[163],"employs":[164],"2D":[166],"CNN":[167,186],"architecture":[168,187],"processing":[171],"image-based":[172],"Mel-spectrograms":[173],"input":[175],"data.":[176],"visual-net,":[182],"uses":[183,215],"3D":[185],"process":[189],"sequences":[190],"images.":[194],"Fusing":[195],"auditory":[199],"enhancing":[202],"correlation":[204,209],"deep":[207],"canonical":[208],"analysis":[210],"(DCCA)":[211],"method.":[212],"research":[214],"eNTERFACE05":[217],"dataset":[218],"reaches":[220],"89.13%":[221],"accuracy":[222],"classifying":[224],"emotions.":[225],"result":[227],"shows":[228],"that":[229],"considering":[230],"at":[235],"same":[237],"model":[241],"better":[242],"recognize":[243],"people":[246],"having.":[248]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":2}],"updated_date":"2026-06-13T06:13:01.061226","created_date":"2025-10-10T00:00:00"}