{"id":"https://openalex.org/W4403534752","doi":"https://doi.org/10.1109/icarm62033.2024.10715789","title":"Context-aware Emotion Recognition Based on Vision-Language Pre-trained Model","display_name":"Context-aware Emotion Recognition Based on Vision-Language Pre-trained Model","publication_year":2024,"publication_date":"2024-07-08","ids":{"openalex":"https://openalex.org/W4403534752","doi":"https://doi.org/10.1109/icarm62033.2024.10715789"},"language":"en","primary_location":{"id":"doi:10.1109/icarm62033.2024.10715789","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icarm62033.2024.10715789","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Conference on Advanced Robotics and Mechatronics (ICARM)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5000910355","display_name":"Xinran Li","orcid":"https://orcid.org/0000-0001-5701-1876"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"XingLin Li","raw_affiliation_strings":["Southeast University,School of Automation,Nanjing,China,210008"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southeast University,School of Automation,Nanjing,China,210008","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010863275","display_name":"Xinde Li","orcid":"https://orcid.org/0000-0002-1529-4537"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinde Li","raw_affiliation_strings":["Southeast University,School of Automation,Nanjing,China,210008"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southeast University,School of Automation,Nanjing,China,210008","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047723747","display_name":"Chuanfei Hu","orcid":"https://orcid.org/0000-0003-1669-9429"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chuanfei Hu","raw_affiliation_strings":["Southeast University,School of Automation,Nanjing,China,210008"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southeast University,School of Automation,Nanjing,China,210008","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041101317","display_name":"Huaping Liu","orcid":"https://orcid.org/0000-0002-4042-6044"},"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":"Huaping Liu","raw_affiliation_strings":["Tsinghua University,Department of Computer Science and Technology,Beijing,China,100000"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Computer Science and Technology,Beijing,China,100000","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"37","issue":null,"first_page":"70","last_page":"75"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13731","display_name":"Advanced Computing and Algorithms","score":0.5593000054359436,"subfield":{"id":"https://openalex.org/subfields/3322","display_name":"Urban Studies"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T13731","display_name":"Advanced Computing and Algorithms","score":0.5593000054359436,"subfield":{"id":"https://openalex.org/subfields/3322","display_name":"Urban Studies"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8208149075508118},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5589576363563538},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5335963368415833},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5268898010253906},{"id":"https://openalex.org/keywords/context-model","display_name":"Context model","score":0.5253925919532776},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.46295222640037537},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4282679557800293},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.372062623500824},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.35480064153671265}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8208149075508118},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5589576363563538},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5335963368415833},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5268898010253906},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.5253925919532776},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.46295222640037537},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4282679557800293},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.372062623500824},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.35480064153671265},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icarm62033.2024.10715789","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icarm62033.2024.10715789","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Conference on Advanced Robotics and Mechatronics (ICARM)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.41999998688697815,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W2605648900","https://openalex.org/W2799041689","https://openalex.org/W2954818883","https://openalex.org/W2970408855","https://openalex.org/W2981101532","https://openalex.org/W3001529617","https://openalex.org/W3007690119","https://openalex.org/W3035565904","https://openalex.org/W3095320185","https://openalex.org/W3138516171","https://openalex.org/W3160306726","https://openalex.org/W3163086403","https://openalex.org/W3193402170","https://openalex.org/W3198377975","https://openalex.org/W3203711169","https://openalex.org/W3210908220","https://openalex.org/W3213351348","https://openalex.org/W4285175808","https://openalex.org/W4292947219","https://openalex.org/W4310633314","https://openalex.org/W4312849330","https://openalex.org/W4313158203","https://openalex.org/W4372341111","https://openalex.org/W4379089779","https://openalex.org/W4386065595","https://openalex.org/W4386075843","https://openalex.org/W4386228569","https://openalex.org/W4386287543","https://openalex.org/W4386790226","https://openalex.org/W4390189960","https://openalex.org/W4390874467","https://openalex.org/W4403242122","https://openalex.org/W6790019176","https://openalex.org/W6795641562","https://openalex.org/W6800139874","https://openalex.org/W6853336233","https://openalex.org/W6856455417"],"related_works":["https://openalex.org/W2169518243","https://openalex.org/W2252095989","https://openalex.org/W2106335228","https://openalex.org/W2105076537","https://openalex.org/W2028371633","https://openalex.org/W2071315630","https://openalex.org/W2096375461","https://openalex.org/W1863657797","https://openalex.org/W3096664139","https://openalex.org/W4385890381"],"abstract_inverted_index":{"Given":[0],"the":[1,37,56,65,72,92,111,118,123,126,135,139,146,150,163,169,176],"difficulty":[2],"of":[3,36,64,117,125,148,171],"recognizing":[4],"ambiguous":[5],"emotions":[6],"in":[7,52,175],"facial":[8,59],"expression":[9],"recognition":[10,101,183],"tasks,":[11],"we":[12,95],"propose":[13],"a":[14,81,172],"visual-language":[15],"model":[16,42,179],"named":[17],"CAER-CLIP":[18,25,53,133,164],"to":[19,46,70,109,114],"address":[20],"this":[21],"challenge.":[22],"The":[23,105,120,142],"proposed":[24,127],"standed":[26],"for":[27,85,99],"Context-Aware":[28],"Emotion":[29],"Recognition":[30],"(CAER),":[31],"and":[32,61,129,152,168],"were":[33,107],"incorporated":[34],"structure":[35,165],"Contrastive":[38],"Language\u2013Image":[39],"Pre-training":[40],"(CLIP)":[41],"as":[43,80,103],"promising":[44],"alternative":[45],"classifier.":[47],"There":[48],"are":[49,67,77],"two":[50],"parts":[51],"model.":[54,119],"In":[55,91],"visual":[57],"part,":[58,94],"expressions":[60],"contextual":[62],"information":[63],"image":[66],"simultaneously":[68],"extracted":[69],"obtain":[71],"final":[73],"feature":[74],"embeddings,":[75],"which":[76],"then":[78],"used":[79],"learnable":[82],"\u201cclass\u201d":[83],"token":[84],"text-image":[86],"pairing":[87],"with":[88,162],"desired":[89],"module.":[90],"textual":[93],"use":[96],"text":[97,173],"labels":[98],"emotion":[100],"classes":[102],"input.":[104],"outputs":[106],"merged":[108],"participate":[110],"comparative":[112],"study":[113],"generated":[115],"parameters":[116],"experiments":[121],"demonstrate":[122],"effectiveness":[124,147],"method":[128,161],"show":[130],"that":[131,159],"our":[132,160],"outperforms":[134],"state-of-the-art":[136],"results":[137],"on":[138],"CAER":[140],"benchmark.":[141],"ablation":[143],"experiment":[144],"verified":[145],"both":[149],"classifier-based":[151],"text-based":[153],"(ours":[154],"without":[155],"classifier)":[156],"models,":[157],"demonstrating":[158],"performed":[166],"better,":[167],"incorporation":[170],"encoder":[174],"deep":[177],"network":[178],"architecture":[180],"effectively":[181],"enhancing":[182],"accuracy.":[184]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}