{"id":"https://openalex.org/W4415538058","doi":"https://doi.org/10.1145/3746027.3762011","title":"Agent-MER: A Cognitive Agent with Hierarchical Deliberation for Open-Vocabulary Multimodal Emotion Recognition","display_name":"Agent-MER: A Cognitive Agent with Hierarchical Deliberation for Open-Vocabulary Multimodal Emotion Recognition","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415538058","doi":"https://doi.org/10.1145/3746027.3762011"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3762011","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3762011","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","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/A5108941678","display_name":"Zengyuan Lai","orcid":"https://orcid.org/0009-0003-6144-5396"},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhengqin Lai","raw_affiliation_strings":["Harbin Institute of Technology, Shenzhen, China and Pengcheng Laboratory, Shenzhen, China"],"raw_orcid":"https://orcid.org/0009-0003-6144-5396","affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Shenzhen, China and Pengcheng Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101067579","display_name":"Zhilin Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhilin Zhu","raw_affiliation_strings":["Harbin Institute of Technology, Shenzhen, China and Pengcheng Laboratory, Shenzhen, China"],"raw_orcid":"https://orcid.org/0009-0002-8657-6408","affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Shenzhen, China and Pengcheng Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026880795","display_name":"Xiaopeng Hong","orcid":"https://orcid.org/0000-0002-0611-0636"},"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"]},{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaopeng Hong","raw_affiliation_strings":["Harbin Institute of Technology, Harbin, China and Pengcheng Laboratory, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-0611-0636","affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Harbin, China and Pengcheng Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I204983213","https://openalex.org/I4210136793"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073082132","display_name":"Yaowei Wang","orcid":"https://orcid.org/0000-0002-6110-4036"},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yaowei Wang","raw_affiliation_strings":["Harbin Institute of Technology, Shenzhen, China and Pengcheng Laboratory, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-6110-4036","affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Shenzhen, China and Pengcheng Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I4210136793"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.27926516,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"13864","last_page":"13871"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9979000091552734,"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":0.9979000091552734,"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":0.9922000169754028,"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/T10709","display_name":"Social Robot Interaction and HRI","score":0.9916999936103821,"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/deliberation","display_name":"Deliberation","score":0.7132999897003174},{"id":"https://openalex.org/keywords/cognition","display_name":"Cognition","score":0.5615000128746033},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.47130000591278076},{"id":"https://openalex.org/keywords/voting","display_name":"Voting","score":0.45649999380111694},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.448199987411499},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.4456000030040741},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.41359999775886536},{"id":"https://openalex.org/keywords/cognitive-architecture","display_name":"Cognitive architecture","score":0.3675000071525574}],"concepts":[{"id":"https://openalex.org/C2776946740","wikidata":"https://www.wikidata.org/wiki/Q358652","display_name":"Deliberation","level":3,"score":0.7132999897003174},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6564000248908997},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.5615000128746033},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.47130000591278076},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.460099995136261},{"id":"https://openalex.org/C520049643","wikidata":"https://www.wikidata.org/wiki/Q189760","display_name":"Voting","level":3,"score":0.45649999380111694},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.448199987411499},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.4456000030040741},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.41359999775886536},{"id":"https://openalex.org/C20854674","wikidata":"https://www.wikidata.org/wiki/Q4386060","display_name":"Cognitive architecture","level":3,"score":0.3675000071525574},{"id":"https://openalex.org/C161407221","wikidata":"https://www.wikidata.org/wiki/Q4382939","display_name":"Cognitive model","level":3,"score":0.3224000036716461},{"id":"https://openalex.org/C74072328","wikidata":"https://www.wikidata.org/wiki/Q1142726","display_name":"Intelligent agent","level":2,"score":0.31619998812675476},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.3158000111579895},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.310699999332428},{"id":"https://openalex.org/C6438553","wikidata":"https://www.wikidata.org/wiki/Q1185804","display_name":"Affective computing","level":2,"score":0.3043999969959259},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.2912999987602234},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.28529998660087585},{"id":"https://openalex.org/C115086926","wikidata":"https://www.wikidata.org/wiki/Q17004651","display_name":"Causal reasoning","level":3,"score":0.2816999852657318},{"id":"https://openalex.org/C143587482","wikidata":"https://www.wikidata.org/wiki/Q1543216","display_name":"Iterative and incremental development","level":2,"score":0.27459999918937683},{"id":"https://openalex.org/C4679612","wikidata":"https://www.wikidata.org/wiki/Q866298","display_name":"Aggregate (composite)","level":2,"score":0.274399995803833},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.2696000039577484},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.2662999927997589},{"id":"https://openalex.org/C105409693","wikidata":"https://www.wikidata.org/wiki/Q5937824","display_name":"Human intelligence","level":2,"score":0.2635999917984009},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2628999948501587},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.25949999690055847}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3762011","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3762011","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6863356025","display_name":null,"funder_award_id":"62076195, 62376070","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W3173859428","https://openalex.org/W4323642664","https://openalex.org/W4376455521","https://openalex.org/W4387835442","https://openalex.org/W4387968043","https://openalex.org/W4393065402","https://openalex.org/W4402754220","https://openalex.org/W4403713281","https://openalex.org/W4403713286","https://openalex.org/W4412889895"],"related_works":[],"abstract_inverted_index":{"This":[0,88,161],"paper":[1],"focuses":[2],"on":[3,78],"Open-Vocabulary":[4],"Multimodal":[5],"Emotion":[6,68],"Recognition":[7],"(OV-MER)":[8],"and":[9,22,109,156],"is":[10,119],"dedicated":[11],"to":[12,48,70,121],"solving":[13],"the":[14,42,56,73,92,104,123,130,133,139],"two":[15],"challenges":[16],"it":[17],"faces:":[18],"concept":[19],"semantic":[20],"misalignment":[21],"incomplete":[23],"coverage":[24],"of":[25,106,112,132,151],"fine-grained":[26],"emotion":[27],"categories.":[28],"To":[29],"address":[30],"this,":[31,79],"we":[32,80],"propose":[33],"a":[34,46,66,82,97,107,115,148],"novel":[35],"cognitive":[36,58],"agent":[37,53],"framework":[38],"(Agent-MER),":[39],"which":[40],"reframes":[41],"OV-MER":[43,170],"task":[44],"as":[45,72],"problem":[47],"be":[49],"solved":[50],"by":[51],"an":[52,166],"that":[54,143],"mimics":[55],"human":[57],"process":[59,89],"through":[60,96],"knowledge-guided":[61],"deliberation.":[62],"We":[63],"first":[64,154],"construct":[65],"hierarchical":[67],"Tree":[69],"serve":[71],"agent's":[74],"knowledge":[75],"base.":[76],"Building":[77],"design":[81],"Knowledge-Guided":[83],"Hierarchical":[84],"Deliberation":[85],"reasoning":[86,101,127],"process.":[87],"systematically":[90],"explores":[91],"entire":[93],"emotional":[94],"landscape":[95],"three-level,":[98],"coarse-to-fine":[99],"iterative":[100],"process,":[102],"enabling":[103],"identification":[105],"richer":[108],"deeper":[110],"range":[111],"emotions.":[113],"Finally,":[114],"Self-Consistent":[116],"Voting":[117],"mechanism":[118],"employed":[120],"aggregate":[122],"results":[124],"from":[125],"multiple":[126],"runs,":[128],"ensuring":[129],"robustness":[131],"final":[134],"output.":[135],"Experiments":[136],"conducted":[137],"in":[138],"MER2025":[140],"Challenge":[141],"demonstrate":[142],"our":[144],"proposed":[145],"method":[146],"achieved":[147],"top-ranking":[149],"score":[150],"61.04%,":[152],"securing":[153],"place":[155],"significantly":[157],"outperforming":[158],"existing":[159],"baselines.":[160],"work":[162],"not":[163],"only":[164],"provides":[165],"effective":[167],"solution":[168],"for":[169,177],"but":[171],"also":[172],"opens":[173],"up":[174],"new":[175],"avenues":[176],"developing":[178],"more":[179],"human-like":[180],"affective":[181],"intelligence":[182],"systems.":[183]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-25T00:00:00"}