{"id":"https://openalex.org/W4408353706","doi":"https://doi.org/10.1109/icassp49660.2025.10889974","title":"Learning Class Prototypes for Visual Emotion Recognition","display_name":"Learning Class Prototypes for Visual Emotion Recognition","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408353706","doi":"https://doi.org/10.1109/icassp49660.2025.10889974"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889974","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889974","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5111265935","display_name":"Jiankun Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiankun Zhu","raw_affiliation_strings":["Harbin Institute of Technology,Faculty of Computing,Harbin,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,Faculty of Computing,Harbin,China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101748079","display_name":"Sicheng Zhao","orcid":"https://orcid.org/0000-0003-2869-2355"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sicheng Zhao","raw_affiliation_strings":["Tsinghua University,BNRist,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,BNRist,Beijing,China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110779522","display_name":"Jing Jiang","orcid":null},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Jiang","raw_affiliation_strings":["Harbin Institute of Technology,Faculty of Computing,Harbin,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,Faculty of Computing,Harbin,China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032718392","display_name":"Zhaopan Xu","orcid":"https://orcid.org/0009-0009-4985-0528"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhaopan Xu","raw_affiliation_strings":["Harbin Institute of Technology,Faculty of Computing,Harbin,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,Faculty of Computing,Harbin,China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041221751","display_name":"Wenbo Tang","orcid":"https://orcid.org/0000-0003-4361-6705"},"institutions":[{"id":"https://openalex.org/I4210150405","display_name":"Hongzhiwei Technology (China)","ror":"https://ror.org/04bapa014","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210150405"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenbo Tang","raw_affiliation_strings":["Siwei Zhilian Technology,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Siwei Zhilian Technology,Shanghai,China","institution_ids":["https://openalex.org/I4210150405"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036604288","display_name":"Hongxun Yao","orcid":null},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongxun Yao","raw_affiliation_strings":["Harbin Institute of Technology,Faculty of Computing,Harbin,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,Faculty of Computing,Harbin,China","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.3589,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.86551569,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13565","display_name":"Education and Learning Interventions","score":0.8159999847412109,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T13565","display_name":"Education and Learning Interventions","score":0.8159999847412109,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.6764489412307739},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.6734259724617004},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.5444189310073853},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4693986475467682},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3803158402442932},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.34017130732536316},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3367982804775238},{"id":"https://openalex.org/keywords/cognitive-psychology","display_name":"Cognitive psychology","score":0.3320106267929077},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.2404872477054596}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6764489412307739},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.6734259724617004},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.5444189310073853},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4693986475467682},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3803158402442932},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34017130732536316},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3367982804775238},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.3320106267929077},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.2404872477054596}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10889974","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889974","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320329860","display_name":"National Science and Technology Major Project","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1950412479","https://openalex.org/W2003856922","https://openalex.org/W2074356411","https://openalex.org/W2075456404","https://openalex.org/W2194775991","https://openalex.org/W2347880541","https://openalex.org/W2525668096","https://openalex.org/W2766251611","https://openalex.org/W2867696556","https://openalex.org/W2908347420","https://openalex.org/W2963992782","https://openalex.org/W2971765953","https://openalex.org/W3128968443","https://openalex.org/W3174134652","https://openalex.org/W3195946570","https://openalex.org/W3198377975","https://openalex.org/W3206577156","https://openalex.org/W4200169818","https://openalex.org/W4226109992","https://openalex.org/W4312986439","https://openalex.org/W4313042449","https://openalex.org/W4386766906","https://openalex.org/W4387902718","https://openalex.org/W4389610068","https://openalex.org/W4396672078","https://openalex.org/W4402753911","https://openalex.org/W4405284100","https://openalex.org/W4405969487","https://openalex.org/W4409346435","https://openalex.org/W6638212731","https://openalex.org/W6733814495","https://openalex.org/W6791353385"],"related_works":["https://openalex.org/W2368454205","https://openalex.org/W2536562190","https://openalex.org/W2370467235","https://openalex.org/W2989824750","https://openalex.org/W2347925354","https://openalex.org/W4238050384","https://openalex.org/W2359737466","https://openalex.org/W2183768935","https://openalex.org/W3126677997","https://openalex.org/W1610857240"],"abstract_inverted_index":{"Visual":[0],"emotion":[1,120],"recognition":[2],"(VER),":[3],"which":[4,187],"aims":[5],"at":[6],"understanding":[7],"humans\u2019":[8],"emotional":[9,53,68,81,98,106],"reactions":[10],"toward":[11],"different":[12],"visual":[13,49,109,135],"stimuli,":[14],"has":[15],"attracted":[16],"increasing":[17],"attention.":[18],"However,":[19],"because":[20],"of":[21,27,37,59,104,125,143,185],"the":[22,38,44,52,57,67,74,138,166,177,183,189],"subjectivity":[23],"and":[24,51,108,150,195],"complex":[25],"nature":[26],"emotion,":[28],"existing":[29],"VER":[30,91],"methods":[31],"suffer":[32],"from":[33,128],"one":[34],"or":[35],"more":[36,148],"following":[39],"problems:":[40],"1)":[41],"semantic":[42,132],"gap:":[43],"large":[45],"affective":[46],"gap":[47],"between":[48,76],"clues":[50],"expressions;":[54],"2)":[55],"overfitting:":[56],"lack":[58],"model":[60],"robustness":[61],"due":[62],"to":[63,159,164],"unclear":[64],"features":[65,117,142],"in":[66],"category":[69,121],"samples;":[70],"3)":[71],"label":[72,167,172],"ambiguity:":[73],"overlap":[75],"categories":[77],"caused":[78],"by":[79,100,122,191],"diverse":[80],"responses.":[82],"To":[83],"address":[84],"these":[85],"limitations,":[86],"we":[87,169],"present":[88],"a":[89,147,171],"novel":[90],"method":[92],"named":[93],"ProtoEmotion":[94],"(PoE),":[95],"exploring":[96],"discriminative":[97,151],"representations":[99],"jointly":[101],"learning":[102],"prototypes":[103,113,124,136],"textual":[105,116],"expressions":[107],"features.":[110],"Specifically,":[111],"text":[112],"build":[114],"explicit":[115],"for":[118],"each":[119,144],"extracting":[123],"learnable":[126],"prompts":[127],"multiple":[129],"aspects,":[130],"reducing":[131],"differences.":[133],"The":[134],"capture":[137],"most":[139],"defining":[140],"image":[141],"category,":[145],"providing":[146],"robust":[149],"feature":[152],"representation,":[153],"while":[154],"bringing":[155],"samples":[156],"closer":[157],"together":[158],"reduce":[160],"overfitting.":[161],"In":[162],"addition,":[163],"alleviate":[165],"ambiguity,":[168],"propose":[170],"smoothing":[173],"algorithm":[174],"based":[175],"on":[176,193,197],"prototype":[178],"distance.":[179],"Extensive":[180],"experiments":[181],"demonstrate":[182],"effectiveness":[184],"PoE,":[186],"outperforms":[188],"state-of-the-art":[190],"1.37%":[192],"FI":[194],"1.52%":[196],"EmotionROI":[198],"datasets.":[199]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}