{"id":"https://openalex.org/W7138252849","doi":"https://doi.org/10.1609/aaai.v40i3.37210","title":"Voices, Faces, and Feelings: Multi-modal Emotion-Cognition Captioning for Mental Health Understanding","display_name":"Voices, Faces, and Feelings: Multi-modal Emotion-Cognition Captioning for Mental Health Understanding","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138252849","doi":"https://doi.org/10.1609/aaai.v40i3.37210"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v40i3.37210","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i3.37210","pdf_url":null,"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://doi.org/10.1609/aaai.v40i3.37210","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129663544","display_name":"Zhiyuan Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiyuan Zhou","raw_affiliation_strings":["Hefei University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hefei University of Technology","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129746060","display_name":"Yanrong Guo","orcid":null},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanrong Guo","raw_affiliation_strings":["Hefei University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hefei University of Technology","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129649305","display_name":"Shijie Hao","orcid":null},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shijie Hao","raw_affiliation_strings":["Hefei University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hefei University of Technology","institution_ids":["https://openalex.org/I16365422"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I16365422"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"3","first_page":"2263","last_page":"2271"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12488","display_name":"Mental Health via Writing","score":0.6687999963760376,"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"}},"topics":[{"id":"https://openalex.org/T12488","display_name":"Mental Health via Writing","score":0.6687999963760376,"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"}},{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.07620000094175339,"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/T11519","display_name":"Digital Mental Health Interventions","score":0.06530000269412994,"subfield":{"id":"https://openalex.org/subfields/3202","display_name":"Applied 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/interpretability","display_name":"Interpretability","score":0.9459999799728394},{"id":"https://openalex.org/keywords/mental-health","display_name":"Mental health","score":0.6633999943733215},{"id":"https://openalex.org/keywords/cognition","display_name":"Cognition","score":0.5947999954223633},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5063999891281128},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.4472000002861023},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.3718999922275543},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.3481999933719635}],"concepts":[{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.9459999799728394},{"id":"https://openalex.org/C134362201","wikidata":"https://www.wikidata.org/wiki/Q317309","display_name":"Mental health","level":2,"score":0.6633999943733215},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.5947999954223633},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5063999891281128},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.49630001187324524},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.492900013923645},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.45739999413490295},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.4472000002861023},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3935000002384186},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.3718999922275543},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3528999984264374},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3481999933719635},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.29490000009536743},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.28189998865127563},{"id":"https://openalex.org/C511192102","wikidata":"https://www.wikidata.org/wiki/Q5156948","display_name":"Comprehension","level":2,"score":0.28189998865127563},{"id":"https://openalex.org/C96199812","wikidata":"https://www.wikidata.org/wiki/Q2145290","display_name":"Mental representation","level":3,"score":0.27959999442100525},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.2750000059604645},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2696000039577484},{"id":"https://openalex.org/C205778803","wikidata":"https://www.wikidata.org/wiki/Q38404","display_name":"Autism","level":2,"score":0.2653000056743622},{"id":"https://openalex.org/C75630572","wikidata":"https://www.wikidata.org/wiki/Q538904","display_name":"Applied psychology","level":1,"score":0.25870001316070557},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2556000053882599}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1609/aaai.v40i3.37210","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i3.37210","pdf_url":null,"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"},{"id":"pmh:oai:ojs.aaai.org:article/37210","is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/37210","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i3.37210","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i3.37210","pdf_url":null,"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":[{"display_name":"Quality Education","score":0.8329845666885376,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Emotional":[0],"and":[1,26,45,49,91,97,106,139,158,169,186],"cognitive":[2,50,92,140],"factors":[3],"are":[4,123],"essential":[5],"for":[6,24,35],"understanding":[7],"mental":[8,36,67,109,170,189],"health":[9,37,68,110,171,190],"disorders.":[10],"However,":[11],"existing":[12,166],"methods":[13],"often":[14],"treat":[15],"multi-modal":[16,53,95,167],"data":[17],"as":[18],"classification":[19],"tasks,":[20],"limiting":[21],"interpretability":[22,107,187],"especially":[23],"emotion":[25],"cognition.":[27],"Although":[28],"large":[29],"language":[30,87],"models":[31,172],"(LLMs)":[32],"offer":[33],"opportunities":[34],"analysis,":[38],"they":[39],"mainly":[40],"rely":[41],"on":[42,130],"textual":[43],"semantics":[44],"overlook":[46],"fine-grained":[47],"emotional":[48,59,90,138],"cues":[51],"in":[52,173,188],"inputs.":[54],"While":[55],"some":[56],"studies":[57],"incorporate":[58],"features":[60,148],"via":[61],"transfer":[62],"learning,":[63],"their":[64],"connection":[65],"to":[66,152],"conditions":[69],"remains":[70],"implicit.":[71],"To":[72],"address":[73],"these":[74,147],"issues,":[75],"we":[76],"propose":[77],"ECMC,":[78],"a":[79,126],"novel":[80],"task":[81],"that":[82,101],"aims":[83],"at":[84],"generating":[85,174],"natural":[86],"descriptions":[88],"of":[89,108,137],"states":[93],"from":[94],"data,":[96],"producing":[98],"emotion\u2013cognition":[99,175,180],"profiles":[100,181],"improve":[102,183],"both":[103],"the":[104,135,178],"accuracy":[105],"assessments.":[111],"We":[112],"adopt":[113],"an":[114],"encoder\u2013decoder":[115],"architecture,":[116],"where":[117],"modality-specific":[118],"encoders":[119],"extract":[120],"features,":[121],"which":[122],"fused":[124],"by":[125],"dual-stream":[127],"BridgeNet":[128],"based":[129],"Q-former.":[131],"Contrastive":[132],"learning":[133],"enhances":[134],"extraction":[136],"features.":[141],"A":[142],"LLaMA":[143],"decoder":[144],"then":[145],"aligns":[146],"with":[149],"annotated":[150],"captions":[151],"produce":[153],"detailed":[154],"descriptions.":[155],"Extensive":[156],"objective":[157],"subjective":[159],"evaluations":[160],"demonstrate":[161],"that:":[162],"1)":[163],"ECMC":[164],"outperforms":[165],"LLMs":[168],"captions;":[176],"2)":[177],"generated":[179],"significantly":[182],"assistive":[184],"diagnosis":[185],"analysis.":[191]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-03-18T00:00:00"}
