{"id":"https://openalex.org/W4313639160","doi":"https://doi.org/10.1109/taffc.2023.3234777","title":"Audio-Visual Emotion Recognition With Preference Learning Based on Intended and Multi-Modal Perceived Labels","display_name":"Audio-Visual Emotion Recognition With Preference Learning Based on Intended and Multi-Modal Perceived Labels","publication_year":2023,"publication_date":"2023-01-06","ids":{"openalex":"https://openalex.org/W4313639160","doi":"https://doi.org/10.1109/taffc.2023.3234777"},"language":"en","primary_location":{"id":"doi:10.1109/taffc.2023.3234777","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taffc.2023.3234777","pdf_url":null,"source":{"id":"https://openalex.org/S104780363","display_name":"IEEE Transactions on Affective Computing","issn_l":"1949-3045","issn":["1949-3045","2371-9850"],"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 Affective Computing","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/A5057935275","display_name":"Yuanyuan Lei","orcid":"https://orcid.org/0000-0002-9753-8071"},"institutions":[{"id":"https://openalex.org/I91045830","display_name":"Texas A&M University","ror":"https://ror.org/01f5ytq51","country_code":"US","type":"education","lineage":["https://openalex.org/I91045830"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuanyuan Lei","raw_affiliation_strings":["Department of Computer Science, Texas A&M University, TX, USA"],"raw_orcid":"https://orcid.org/0000-0002-9753-8071","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Texas A&M University, TX, USA","institution_ids":["https://openalex.org/I91045830"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102992790","display_name":"Houwei Cao","orcid":"https://orcid.org/0000-0002-2310-7682"},"institutions":[{"id":"https://openalex.org/I4210104314","display_name":"New York Institute of Technology","ror":"https://ror.org/01bghzb51","country_code":"US","type":"education","lineage":["https://openalex.org/I4210104314"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Houwei Cao","raw_affiliation_strings":["Department of Computer Science, New York Institute of Technology, New York, NY, USA"],"raw_orcid":"https://orcid.org/0000-0002-2310-7682","affiliations":[{"raw_affiliation_string":"Department of Computer Science, New York Institute of Technology, New York, NY, USA","institution_ids":["https://openalex.org/I4210104314"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":2345,"currency":"USD","value_usd":2345},"apc_paid":null,"fwci":9.0033,"has_fulltext":false,"cited_by_count":45,"citation_normalized_percentile":{"value":0.98484195,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"14","issue":"4","first_page":"2954","last_page":"2969"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9957000017166138,"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/T12496","display_name":"Color perception and design","score":0.994700014591217,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social 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/emotion-recognition","display_name":"Emotion recognition","score":0.7181766629219055},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.6962963938713074},{"id":"https://openalex.org/keywords/preference","display_name":"Preference","score":0.6181424260139465},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.5760501623153687},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.5477676391601562},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5028428435325623},{"id":"https://openalex.org/keywords/cognitive-psychology","display_name":"Cognitive psychology","score":0.49607834219932556},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.47146397829055786},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3661752939224243},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35982492566108704},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.2706103026866913},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09365138411521912}],"concepts":[{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.7181766629219055},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.6962963938713074},{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.6181424260139465},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.5760501623153687},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.5477676391601562},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5028428435325623},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.49607834219932556},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.47146397829055786},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3661752939224243},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35982492566108704},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.2706103026866913},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09365138411521912},{"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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taffc.2023.3234777","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taffc.2023.3234777","pdf_url":null,"source":{"id":"https://openalex.org/S104780363","display_name":"IEEE Transactions on Affective Computing","issn_l":"1949-3045","issn":["1949-3045","2371-9850"],"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 Affective Computing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.6700000166893005}],"awards":[{"id":"https://openalex.org/G546698723","display_name":null,"funder_award_id":"IIS-2034791","funder_id":"https://openalex.org/F4320335353","funder_display_name":"National Science Foundation of Sri Lanka"}],"funders":[{"id":"https://openalex.org/F4320335353","display_name":"National Science Foundation of Sri Lanka","ror":"https://ror.org/010xaa060"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W1527117961","https://openalex.org/W1628791547","https://openalex.org/W1964744287","https://openalex.org/W1966797434","https://openalex.org/W1969386661","https://openalex.org/W1971737742","https://openalex.org/W1980299015","https://openalex.org/W1983703866","https://openalex.org/W1993008008","https://openalex.org/W2015212590","https://openalex.org/W2026984028","https://openalex.org/W2030931454","https://openalex.org/W2032139348","https://openalex.org/W2032254851","https://openalex.org/W2035720976","https://openalex.org/W2041347087","https://openalex.org/W2047221353","https://openalex.org/W2086655908","https://openalex.org/W2090777335","https://openalex.org/W2092206588","https://openalex.org/W2097726431","https://openalex.org/W2115584760","https://openalex.org/W2120675333","https://openalex.org/W2128877075","https://openalex.org/W2133180260","https://openalex.org/W2137639365","https://openalex.org/W2143331230","https://openalex.org/W2143350951","https://openalex.org/W2156503193","https://openalex.org/W2158061940","https://openalex.org/W2163293471","https://openalex.org/W2166835339","https://openalex.org/W2178285610","https://openalex.org/W2345305417","https://openalex.org/W2400120934","https://openalex.org/W2404446881","https://openalex.org/W2508783453","https://openalex.org/W2787552263","https://openalex.org/W2799041689","https://openalex.org/W2803098682","https://openalex.org/W2807126412","https://openalex.org/W2889113107","https://openalex.org/W2973220962","https://openalex.org/W3124054989","https://openalex.org/W4210993929","https://openalex.org/W6677385034","https://openalex.org/W6712588427","https://openalex.org/W6745609711"],"related_works":["https://openalex.org/W2271369634","https://openalex.org/W3147472394","https://openalex.org/W2047100085","https://openalex.org/W2350550760","https://openalex.org/W578794879","https://openalex.org/W2625296515","https://openalex.org/W3105646692","https://openalex.org/W4387914125","https://openalex.org/W3126677997","https://openalex.org/W1610857240"],"abstract_inverted_index":{"This":[0],"article":[1],"introduces":[2],"a":[3],"novel":[4],"preference":[5,72,107,133],"learning":[6,108,134],"framework":[7],"that":[8,104,167,247],"simultaneously":[9],"considers":[10],"both":[11],"the":[12,15,20,27,32,35,49,52,112,117,126,132,137,154,161,183,191,202,214,219,225,239,244],"intended":[13,33,171],"and":[14,29,34,44,93,116,172,189,207,237],"perceived":[16,36,173,251],"labels":[17,37,174,252],"while":[18],"addressing":[19],"mismatches":[21],"between":[22,31],"them.":[23],"Based":[24],"on":[25,197,234,243],"analyzing":[26],"discrepancies":[28],"agreements":[30],"in":[38,175],"different":[39,144,186],"modalities":[40],"of":[41,55,62,139,146,185,195],"audio-only,":[42],"visual-only,":[43],"audio-visual,":[45],"as":[46,48],"well":[47],"consistency":[50],"among":[51],"perceptual":[53],"ratings":[54],"all":[56,105],"raters,":[57],"we":[58,168,223],"propose":[59],"three":[60,106],"sets":[61],"pair-wise":[63],"ranking":[64,82,157,187,205],"rules":[65],"to":[66,78],"generate":[67],"multi-scale":[68],"relevant":[69],"scores":[70],"for":[71],"learning,":[73],"scaling":[74],"from":[75,131,153],"sketchy":[76],"manner":[77],"detailed":[79,155],"manner.":[80],"Three":[81],"models":[83,109,135],"with":[84,120,160],"support":[85],"vector":[86],"machine":[87],"(SVM),":[88],"deep":[89],"neural":[90],"networks":[91],"(DNN),":[92],"gradient":[94,121],"boosting":[95,122],"decision":[96,123],"trees":[97,124],"(GBDT)":[98],"are":[99],"developed.":[100],"Our":[101],"results":[102],"demonstrate":[103],"significantly":[110,211],"outperform":[111],"conventional":[113],"classifiers":[114],"baselines,":[115],"LambdaMART":[118,163],"model":[119],"achieves":[125],"best":[127,162,192,204],"performance.":[128],"The":[129],"improvement":[130,152],"confirm":[136],"benefits":[138],"complementary":[140,184],"information":[141],"provided":[142],"by":[143,218,230],"types":[145],"labels.":[147],"We":[148,180],"also":[149],"observe":[150],"additional":[151],"\u2018complex":[156],"rules\u2019,":[158],"particular":[159],"model,":[164],"which":[165,209],"suggests":[166],"should":[169],"treat":[170],"single-model":[176],"&":[177],"multi-modal":[178],"differently.":[179],"further":[181],"discuss":[182],"models,":[188],"obtain":[190],"overall":[193],"accuracy":[194,216],"85.06%":[196],"CREMA-D":[198,235],"dataset":[199,236,246],"when":[200],"combining":[201],"two":[203],"models\u2013LambdaMART":[206],"RankNet\u2013together,":[208],"is":[210],"better":[212],"than":[213],"76.19%":[215],"attained":[217],"baseline":[220],"models.":[221],"Finally,":[222],"perform":[224],"cross-corpus":[226],"emotion":[227,232,241],"recognition":[228],"experiments":[229],"training":[231],"rankers":[233],"tested":[238],"ranking-based":[240],"classifier":[242],"SAVEE":[245],"do":[248],"not":[249],"have":[250],"annotated.":[253]},"counts_by_year":[{"year":2026,"cited_by_count":8},{"year":2025,"cited_by_count":17},{"year":2024,"cited_by_count":12},{"year":2023,"cited_by_count":8}],"updated_date":"2026-08-28T12:50:07.497085","created_date":"2025-10-10T00:00:00"}