{"id":"https://openalex.org/W7124887652","doi":"https://doi.org/10.1109/cloudcom67567.2025.11331522","title":"Edge-Cloud Audio-Visual Emotion Recognition with Transformer Fusion and ELM Classification","display_name":"Edge-Cloud Audio-Visual Emotion Recognition with Transformer Fusion and ELM Classification","publication_year":2025,"publication_date":"2025-11-14","ids":{"openalex":"https://openalex.org/W7124887652","doi":"https://doi.org/10.1109/cloudcom67567.2025.11331522"},"language":null,"primary_location":{"id":"doi:10.1109/cloudcom67567.2025.11331522","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cloudcom67567.2025.11331522","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 lEEE International Conference on Cloud Computing Technology and Science (CloudCom)","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/A5123427820","display_name":"Yidan Ni","orcid":null},"institutions":[{"id":"https://openalex.org/I4388482657","display_name":"Shenzhen MSU-BIT University","ror":"https://ror.org/02q963474","country_code":null,"type":"education","lineage":["https://openalex.org/I4388482657"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yidan Ni","raw_affiliation_strings":["Shenzhen MSU-BIT University,Department of Engineering,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"Shenzhen MSU-BIT University,Department of Engineering,Shenzhen,China","institution_ids":["https://openalex.org/I4388482657"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123374895","display_name":"Zaixu Yuan","orcid":null},"institutions":[{"id":"https://openalex.org/I4388482657","display_name":"Shenzhen MSU-BIT University","ror":"https://ror.org/02q963474","country_code":null,"type":"education","lineage":["https://openalex.org/I4388482657"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zaixu Yuan","raw_affiliation_strings":["Shenzhen MSU-BIT University,Department of Engineering,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"Shenzhen MSU-BIT University,Department of Engineering,Shenzhen,China","institution_ids":["https://openalex.org/I4388482657"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123399562","display_name":"Hairui Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I4388482657","display_name":"Shenzhen MSU-BIT University","ror":"https://ror.org/02q963474","country_code":null,"type":"education","lineage":["https://openalex.org/I4388482657"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hairui Wang","raw_affiliation_strings":["Shenzhen MSU-BIT University,Department of Engineering,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"Shenzhen MSU-BIT University,Department of Engineering,Shenzhen,China","institution_ids":["https://openalex.org/I4388482657"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034363178","display_name":"Yuzhe Cheng","orcid":null},"institutions":[{"id":"https://openalex.org/I4388482657","display_name":"Shenzhen MSU-BIT University","ror":"https://ror.org/02q963474","country_code":null,"type":"education","lineage":["https://openalex.org/I4388482657"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuzhe Cheng","raw_affiliation_strings":["Shenzhen MSU-BIT University,Department of Engineering,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"Shenzhen MSU-BIT University,Department of Engineering,Shenzhen,China","institution_ids":["https://openalex.org/I4388482657"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123449380","display_name":"Jiran Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I4388482657","display_name":"Shenzhen MSU-BIT University","ror":"https://ror.org/02q963474","country_code":null,"type":"education","lineage":["https://openalex.org/I4388482657"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiran Wang","raw_affiliation_strings":["Shenzhen MSU-BIT University,Department of Engineering,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"Shenzhen MSU-BIT University,Department of Engineering,Shenzhen,China","institution_ids":["https://openalex.org/I4388482657"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088066872","display_name":"Jianbo Zheng","orcid":"https://orcid.org/0000-0002-8286-0383"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]},{"id":"https://openalex.org/I4388482657","display_name":"Shenzhen MSU-BIT University","ror":"https://ror.org/02q963474","country_code":null,"type":"education","lineage":["https://openalex.org/I4388482657"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianbo Zheng","raw_affiliation_strings":["Artifcial Intelligence Research Institute, Shenzhen MSU-BIT University,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"Artifcial Intelligence Research Institute, Shenzhen MSU-BIT University,Shenzhen,China","institution_ids":["https://openalex.org/I180726961","https://openalex.org/I4388482657"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5123427820"],"corresponding_institution_ids":["https://openalex.org/I4388482657"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.78548278,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"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/T10667","display_name":"Emotion and Mood Recognition","score":0.9781000018119812,"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":0.9781000018119812,"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/T12676","display_name":"Machine Learning and ELM","score":0.003599999938160181,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10057","display_name":"Face and Expression Recognition","score":0.003000000026077032,"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/emotion-recognition","display_name":"Emotion recognition","score":0.5914999842643738},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5304999947547913},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4641000032424927},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.42579999566078186},{"id":"https://openalex.org/keywords/facial-expression","display_name":"Facial expression","score":0.3824999928474426},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.36550000309944153},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.36039999127388}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7250999808311462},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5954999923706055},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.5914999842643738},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5304999947547913},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4788999855518341},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4641000032424927},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.42579999566078186},{"id":"https://openalex.org/C195704467","wikidata":"https://www.wikidata.org/wiki/Q327968","display_name":"Facial expression","level":2,"score":0.3824999928474426},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.36550000309944153},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36469998955726624},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.36039999127388},{"id":"https://openalex.org/C31510193","wikidata":"https://www.wikidata.org/wiki/Q1192553","display_name":"Facial recognition system","level":3,"score":0.3158000111579895},{"id":"https://openalex.org/C2780150128","wikidata":"https://www.wikidata.org/wiki/Q21948731","display_name":"Extreme learning machine","level":3,"score":0.3147999942302704},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3043000102043152},{"id":"https://openalex.org/C206310091","wikidata":"https://www.wikidata.org/wiki/Q750859","display_name":"Emotion classification","level":2,"score":0.29109999537467957},{"id":"https://openalex.org/C71901391","wikidata":"https://www.wikidata.org/wiki/Q7126699","display_name":"Upload","level":2,"score":0.28610000014305115},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.27880001068115234},{"id":"https://openalex.org/C121687571","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Activity recognition","level":2,"score":0.27570000290870667},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.2540999948978424}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cloudcom67567.2025.11331522","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cloudcom67567.2025.11331522","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 lEEE International Conference on Cloud Computing Technology and Science (CloudCom)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W2030931454","https://openalex.org/W2061319836","https://openalex.org/W2111072639","https://openalex.org/W2156503193","https://openalex.org/W2163352848","https://openalex.org/W2168692779","https://openalex.org/W2171801645","https://openalex.org/W2584561145","https://openalex.org/W2803098682","https://openalex.org/W2963125010","https://openalex.org/W2964051877","https://openalex.org/W2997399314","https://openalex.org/W4230277160","https://openalex.org/W4239510810","https://openalex.org/W4407559183","https://openalex.org/W4411787321"],"related_works":[],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"an":[3],"edge-cloud":[4],"audio-visual":[5],"emotion":[6,12],"recognition":[7,13,18],"framework":[8,83,102],"that":[9,100],"integrates":[10],"speech":[11],"(SER)":[14],"and":[15,25,30,61,89,96,110],"facial":[16],"expression":[17],"(FER).":[19],"On":[20],"the":[21,52,72,78,82,94,101],"edge":[22],"device,":[23],"audio":[24],"visual":[26],"features":[27,47],"are":[28,48],"extracted":[29],"preprocessed,":[31],"then":[32],"classified":[33],"by":[34],"a":[35,55,67,85],"lightweight":[36],"Extreme":[37],"Learning":[38],"Machine":[39],"(ELM)":[40],"to":[41,51,65],"ensure":[42],"low-latency":[43],"inference.":[44],"These":[45],"low-dimensional":[46],"also":[49],"uploaded":[50],"cloud,":[53],"where":[54],"multimodal":[56],"Transformer":[57],"captures":[58],"temporal":[59],"dependencies":[60],"cross-":[62],"modal":[63],"interactions":[64],"generate":[66],"unified":[68],"representation.":[69],"By":[70],"combining":[71],"cloud's":[73],"powerful":[74],"modeling":[75],"capacity":[76],"with":[77],"edge's":[79],"efficient":[80],"inference,":[81],"achieves":[84],"balance":[86],"between":[87],"accuracy":[88,109],"real-time":[90],"performance.":[91],"Experiments":[92],"on":[93],"Enterface05":[95],"CREMA-D":[97],"datasets":[98],"demonstrate":[99],"consistently":[103],"surpasses":[104],"traditional":[105],"baselines":[106],"in":[107],"both":[108],"efficiency,":[111],"highlighting":[112],"its":[113],"suitability":[114],"for":[115],"practical":[116],"human-computer":[117],"interaction":[118],"applications.":[119]},"counts_by_year":[],"updated_date":"2026-02-23T20:09:44.859080","created_date":"2026-01-21T00:00:00"}