{"id":"https://openalex.org/W4312832890","doi":"https://doi.org/10.1109/tbc.2022.3215245","title":"FV2ES: A Fully End2End Multimodal System for Fast Yet Effective Video Emotion Recognition Inference","display_name":"FV2ES: A Fully End2End Multimodal System for Fast Yet Effective Video Emotion Recognition Inference","publication_year":2022,"publication_date":"2022-11-09","ids":{"openalex":"https://openalex.org/W4312832890","doi":"https://doi.org/10.1109/tbc.2022.3215245"},"language":"en","primary_location":{"id":"doi:10.1109/tbc.2022.3215245","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tbc.2022.3215245","pdf_url":null,"source":{"id":"https://openalex.org/S100142436","display_name":"IEEE Transactions on Broadcasting","issn_l":"0018-9316","issn":["0018-9316","1557-9611"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Broadcasting","raw_type":"journal-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/A5055082886","display_name":"Qinglan Wei","orcid":"https://orcid.org/0000-0002-2710-0410"},"institutions":[{"id":"https://openalex.org/I75689368","display_name":"Communication University of China","ror":"https://ror.org/04facbs33","country_code":"CN","type":"education","lineage":["https://openalex.org/I75689368"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Qinglan Wei","raw_affiliation_strings":["Communication University of China, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-2710-0410","affiliations":[{"raw_affiliation_string":"Communication University of China, Beijing, China","institution_ids":["https://openalex.org/I75689368"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065536223","display_name":"Xuling Huang","orcid":"https://orcid.org/0000-0003-1169-4944"},"institutions":[{"id":"https://openalex.org/I75689368","display_name":"Communication University of China","ror":"https://ror.org/04facbs33","country_code":"CN","type":"education","lineage":["https://openalex.org/I75689368"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuling Huang","raw_affiliation_strings":["Communication University of China, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-1169-4944","affiliations":[{"raw_affiliation_string":"Communication University of China, Beijing, China","institution_ids":["https://openalex.org/I75689368"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067423633","display_name":"Yuan Zhang","orcid":"https://orcid.org/0000-0003-3783-7974"},"institutions":[{"id":"https://openalex.org/I75689368","display_name":"Communication University of China","ror":"https://ror.org/04facbs33","country_code":"CN","type":"education","lineage":["https://openalex.org/I75689368"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuan Zhang","raw_affiliation_strings":["Communication University of China, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-3783-7974","affiliations":[{"raw_affiliation_string":"Communication University of China, Beijing, China","institution_ids":["https://openalex.org/I75689368"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5055082886"],"corresponding_institution_ids":["https://openalex.org/I75689368"],"apc_list":null,"apc_paid":null,"fwci":4.803,"has_fulltext":false,"cited_by_count":30,"citation_normalized_percentile":{"value":0.95554573,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"69","issue":"1","first_page":"10","last_page":"20"},"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":0.9879999756813049,"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.9857000112533569,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7849705815315247},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.7228003144264221},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5995494723320007},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.539125382900238},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5146840214729309},{"id":"https://openalex.org/keywords/gesture","display_name":"Gesture","score":0.5122613310813904},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4860999584197998},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.48341476917266846},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3546774983406067}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7849705815315247},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.7228003144264221},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5995494723320007},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.539125382900238},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5146840214729309},{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.5122613310813904},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4860999584197998},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.48341476917266846},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3546774983406067},{"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tbc.2022.3215245","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tbc.2022.3215245","pdf_url":null,"source":{"id":"https://openalex.org/S100142436","display_name":"IEEE Transactions on Broadcasting","issn_l":"0018-9316","issn":["0018-9316","1557-9611"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Broadcasting","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7099999785423279}],"awards":[{"id":"https://openalex.org/G1110555499","display_name":null,"funder_award_id":"CUC220F003","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G5261554428","display_name":null,"funder_award_id":"CUC21GZ012","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G6938695607","display_name":null,"funder_award_id":"62271455","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7758632813","display_name":null,"funder_award_id":"ZW21099","funder_id":"https://openalex.org/F4320321543","funder_display_name":"China Postdoctoral Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321543","display_name":"China Postdoctoral Science Foundation","ror":"https://ror.org/0426zh255"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1815942593","https://openalex.org/W1930223417","https://openalex.org/W2061116763","https://openalex.org/W2106564373","https://openalex.org/W2122563357","https://openalex.org/W2406223855","https://openalex.org/W2465534249","https://openalex.org/W2474425654","https://openalex.org/W2583643061","https://openalex.org/W2612041314","https://openalex.org/W2964010806","https://openalex.org/W2964051877","https://openalex.org/W2964260444","https://openalex.org/W2982645239","https://openalex.org/W2990670609","https://openalex.org/W2993371911","https://openalex.org/W2996428491","https://openalex.org/W2999565548","https://openalex.org/W3011170675","https://openalex.org/W3016010032","https://openalex.org/W3027790991","https://openalex.org/W3037572520","https://openalex.org/W3048093647","https://openalex.org/W3087434251","https://openalex.org/W3153807302","https://openalex.org/W3164540605","https://openalex.org/W3167976421","https://openalex.org/W3168391820","https://openalex.org/W3174977508","https://openalex.org/W3195949276","https://openalex.org/W3209634803","https://openalex.org/W3211666705","https://openalex.org/W4200556038","https://openalex.org/W4207085209","https://openalex.org/W4221139382","https://openalex.org/W4287644981","https://openalex.org/W4294967921","https://openalex.org/W6631190155","https://openalex.org/W6638667902","https://openalex.org/W6682889407","https://openalex.org/W6718683173","https://openalex.org/W6719667659","https://openalex.org/W6739901393","https://openalex.org/W6768021236","https://openalex.org/W6780226713","https://openalex.org/W6783497617","https://openalex.org/W6784444198","https://openalex.org/W6795467770","https://openalex.org/W6845759482"],"related_works":["https://openalex.org/W73545470","https://openalex.org/W4224266612","https://openalex.org/W2383394264","https://openalex.org/W4320153225","https://openalex.org/W4293261942","https://openalex.org/W3125968744","https://openalex.org/W2167701463","https://openalex.org/W2110287964","https://openalex.org/W4307407935","https://openalex.org/W649759291"],"abstract_inverted_index":{"In":[0,144],"the":[1,52,55,82,85,89,108,130,170,175,180,184,189,200,203,219,223,227,234,240],"latest":[2],"social":[3],"networks,":[4],"more":[5,7,78],"and":[6,19,39,46,69,126,187,196,217,246],"people":[8],"prefer":[9],"to":[10,67,76,80,124],"express":[11],"their":[12],"emotions":[13],"in":[14,41,44,51,61,117],"videos":[15],"through":[16,179],"text,":[17],"speech,":[18],"rich":[20],"facial":[21],"expressions.":[22],"Multimodal":[23],"video":[24,137],"emotion":[25,92,138],"analysis":[26],"techniques":[27],"can":[28,99],"help":[29],"understand":[30],"users\u2019":[31],"inner":[32],"world":[33],"automatically":[34],"based":[35],"on":[36,193],"human":[37],"expressions":[38],"gestures":[40],"images,":[42],"tones":[43],"voices,":[45],"recognized":[47],"natural":[48],"language.":[49],"However,":[50],"existing":[53,190],"research,":[54],"acoustic":[56,86,185],"modality":[57,87],"has":[58],"long":[59],"been":[60],"a":[62,133,149],"marginal":[63],"position":[64],"as":[65],"compared":[66],"visual":[68,208],"textual":[70],"modalities.":[71],"That":[72],"is,":[73],"it":[74],"tends":[75],"be":[77,100],"difficult":[79],"improve":[81],"contribution":[83,182],"of":[84,111,132,169,183,202,205,230,243],"for":[88,156,207,212],"whole":[90],"multimodal":[91,136,151,236],"recognition":[93,139,160],"task.":[94],"Besides,":[95],"although":[96],"better":[97],"performance":[98,192],"obtained":[101],"by":[102],"introducing":[103],"common":[104],"deep":[105],"learning":[106,237],"methods,":[107],"complex":[109],"structures":[110],"these":[112],"training":[113],"models":[114],"always":[115],"result":[116],"low":[118],"inference":[119,213],"efficiency,":[120],"especially":[121],"when":[122],"exposed":[123],"high-resolution":[125],"long-length":[127],"videos.":[128],"Moreover,":[129],"lack":[131],"fully":[134,150],"end-to-end":[135],"system":[140,153],"hinders":[141],"its":[142],"application.":[143],"this":[145],"paper,":[146],"we":[147],"designed":[148],"video-to-emotion":[152],"(named":[154],"FV2ES)":[155],"fast":[157],"yet":[158],"effective":[159],"inference,":[161],"whose":[162],"benefits":[163],"are":[164],"threefold:":[165],"(1)":[166],"The":[167],"adoption":[168],"hierarchical":[171],"attention":[172],"method":[173],"upon":[174],"sound":[176],"spectra":[177],"breaks":[178],"limited":[181],"modality,":[186],"outperforms":[188],"models\u2019":[191],"both":[194],"IEMOCAP":[195],"CMU-MOSEI":[197],"datasets;":[198],"(2)":[199],"introduction":[201],"idea":[204],"multi-scale":[206],"extraction":[209],"while":[210],"single-branch":[211],"brings":[214],"higher":[215],"efficiency":[216],"maintains":[218],"prediction":[220],"accuracy":[221],"at":[222],"same":[224],"time;":[225],"(3)":[226],"further":[228],"integration":[229],"data":[231],"pre-processing":[232],"into":[233],"aligned":[235],"model":[238],"allows":[239],"significant":[241],"reduction":[242],"computational":[244],"costs":[245],"storage":[247],"space.":[248]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":6}],"updated_date":"2026-05-02T08:42:23.175194","created_date":"2025-10-10T00:00:00"}