{"id":"https://openalex.org/W7138463056","doi":"https://doi.org/10.1609/aaai.v40i32.39906","title":"Facial-R1: Aligning Reasoning and Recognition for Facial Emotion Analysis","display_name":"Facial-R1: Aligning Reasoning and Recognition for Facial Emotion Analysis","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138463056","doi":"https://doi.org/10.1609/aaai.v40i32.39906"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i32.39906","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i32.39906","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/39906/43867","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/39906/43867","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129724260","display_name":"Jiulong Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I3923682","display_name":"Soochow University","ror":"https://ror.org/05t8y2r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I3923682"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiulong Wu","raw_affiliation_strings":["School of Computer Science and Technology, Soochow University, Suzhou, China\nBaidu Inc., Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Soochow University, Suzhou, China\nBaidu Inc., Beijing, China","institution_ids":["https://openalex.org/I3923682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085330182","display_name":"Yi Shen","orcid":"https://orcid.org/0000-0001-6539-4918"},"institutions":[{"id":"https://openalex.org/I3923682","display_name":"Soochow University","ror":"https://ror.org/05t8y2r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I3923682"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yucheng Shen","raw_affiliation_strings":["School of Computer Science and Technology, Soochow University, Suzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Soochow University, Suzhou, China","institution_ids":["https://openalex.org/I3923682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050161084","display_name":"Lingyong Yan","orcid":"https://orcid.org/0000-0002-6547-1984"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lingyong Yan","raw_affiliation_strings":["Baidu Inc., Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Baidu Inc., Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101424227","display_name":"Haixin Sun","orcid":"https://orcid.org/0000-0002-6876-2939"},"institutions":[{"id":"https://openalex.org/I3923682","display_name":"Soochow University","ror":"https://ror.org/05t8y2r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I3923682"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haixin Sun","raw_affiliation_strings":["School of Computer Science and Technology, Soochow University, Suzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Soochow University, Suzhou, China","institution_ids":["https://openalex.org/I3923682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076144487","display_name":"Deguo Xia","orcid":"https://orcid.org/0000-0003-3366-2230"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Deguo Xia","raw_affiliation_strings":["Baidu Inc., Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Baidu Inc., Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005312000","display_name":"Jizhou Huang","orcid":"https://orcid.org/0000-0003-1022-0309"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jizhou Huang","raw_affiliation_strings":["Baidu Inc., Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Baidu Inc., Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129686395","display_name":"Min Cao","orcid":null},"institutions":[{"id":"https://openalex.org/I3923682","display_name":"Soochow University","ror":"https://ror.org/05t8y2r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I3923682"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Min Cao","raw_affiliation_strings":["School of Computer Science and Technology, Soochow University, Suzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Soochow University, Suzhou, China","institution_ids":["https://openalex.org/I3923682"]}]}],"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":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"32","first_page":"26939","last_page":"26947"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9800000190734863,"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":0.9800000190734863,"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.0031999999191612005,"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/T11094","display_name":"Face Recognition and Perception","score":0.0017999999690800905,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/hallucinating","display_name":"Hallucinating","score":0.7247999906539917},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5393000245094299},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.4828999936580658},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.47209998965263367},{"id":"https://openalex.org/keywords/facial-expression","display_name":"Facial expression","score":0.45410001277923584},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.4496000111103058},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.4449999928474426},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4440000057220459}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7484999895095825},{"id":"https://openalex.org/C2911011789","wikidata":"https://www.wikidata.org/wiki/Q130741","display_name":"Hallucinating","level":2,"score":0.7247999906539917},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6175000071525574},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5393000245094299},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.4828999936580658},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.47209998965263367},{"id":"https://openalex.org/C195704467","wikidata":"https://www.wikidata.org/wiki/Q327968","display_name":"Facial expression","level":2,"score":0.45410001277923584},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.4496000111103058},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.4449999928474426},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4440000057220459},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4424999952316284},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4352000057697296},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4146000146865845},{"id":"https://openalex.org/C31510193","wikidata":"https://www.wikidata.org/wiki/Q1192553","display_name":"Facial recognition system","level":3,"score":0.3912999927997589},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3846000134944916},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.38029998540878296},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.374099999666214},{"id":"https://openalex.org/C206310091","wikidata":"https://www.wikidata.org/wiki/Q750859","display_name":"Emotion classification","level":2,"score":0.35510000586509705},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.3296000063419342},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.3077999949455261},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.30550000071525574},{"id":"https://openalex.org/C108154423","wikidata":"https://www.wikidata.org/wiki/Q1469792","display_name":"Salience (neuroscience)","level":2,"score":0.26750001311302185},{"id":"https://openalex.org/C2776035091","wikidata":"https://www.wikidata.org/wiki/Q7928819","display_name":"Viewpoints","level":2,"score":0.2623000144958496},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.25679999589920044}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i32.39906","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i32.39906","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/39906/43867","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i32.39906","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i32.39906","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/39906/43867","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7138463056.pdf","grobid_xml":"https://content.openalex.org/works/W7138463056.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Facial":[0],"Emotion":[1],"Analysis":[2],"(FEA)":[3],"extends":[4],"traditional":[5],"facial":[6,20,78],"emotion":[7,27,68,119,180],"recognition":[8],"by":[9,73,118],"incorporating":[10],"explainable,":[11],"fine-grained":[12,179],"reasoning.":[13],"The":[14],"task":[15],"integrates":[16],"three":[17],"subtasks\u2014emotion":[18],"recognition,":[19,24,71],"Action":[21],"Unit":[22],"(AU)":[23],"and":[25,40,64,70,80,120,174,200],"AU-based":[26],"reasoning\u2014to":[28],"jointly":[29],"model":[30],"affective":[31],"states.":[32],"While":[33],"recent":[34],"approaches":[35],"leverage":[36],"Vision-Language":[37],"Models":[38],"(VLMs)":[39],"achieve":[41],"promising":[42],"results,":[43],"they":[44],"face":[45],"two":[46],"critical":[47],"limitations:":[48],"(1)":[49],"hallucinated":[50],"reasoning,":[51],"where":[52],"VLMs":[53],"generate":[54],"plausible":[55],"but":[56],"inaccurate":[57],"explanations":[58],"due":[59],"to":[60,103,150],"insufficient":[61],"emotion-specific":[62],"knowledge;":[63],"(2)":[65],"misalignment":[66],"between":[67,76],"reasoning":[69,107,131],"caused":[72],"fragmented":[74],"connections":[75],"observed":[77],"features":[79],"final":[81],"labels.":[82],"We":[83],"propose":[84],"Facial-R1,":[85],"a":[86,140,168],"three-stage":[87],"alignment":[88],"framework":[89],"that":[90,144,190],"effectively":[91],"addresses":[92],"both":[93],"challenges":[94],"with":[95,133,178,197],"minimal":[96],"supervision.":[97],"First,":[98],"we":[99,113,138,165],"employ":[100],"instruction":[101],"fine-tuning":[102],"establish":[104],"basic":[105],"emotional":[106],"capability":[108],"for":[109],"reducing":[110],"hallucinations.":[111],"Second,":[112],"introduce":[114,166],"reinforcement":[115],"training":[116,153,173],"guided":[117],"AU":[121],"labels":[122],"as":[123],"reward":[124],"signals,":[125],"which":[126],"explicitly":[127],"aligns":[128],"the":[129,134,147,152,159],"generated":[130],"process":[132],"predicted":[135],"emotion.":[136],"Third,":[137],"design":[139],"data":[141],"synthesis":[142],"pipeline":[143],"iteratively":[145],"leverages":[146],"prior":[148],"stages":[149],"expand":[151],"dataset,":[154],"enabling":[155],"scalable":[156],"self-improvement":[157],"of":[158],"model.":[160],"Built":[161],"upon":[162],"this":[163],"framework,":[164],"FEA-20K,":[167],"benchmark":[169],"dataset":[170],"comprising":[171],"17,737":[172],"1,688":[175],"test":[176],"samples":[177],"analysis":[181],"annotations.":[182],"Extensive":[183],"experiments":[184],"across":[185],"eight":[186],"standard":[187],"benchmarks":[188],"demonstrate":[189],"Facial-R1":[191],"achieves":[192],"state-of-the-art":[193],"performance":[194],"in":[195],"FEA,":[196],"strong":[198],"generalization":[199],"robust":[201],"interpretability.":[202]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-03-18T00:00:00"}