{"id":"https://openalex.org/W4408354392","doi":"https://doi.org/10.1109/icassp49660.2025.10889829","title":"Enhancing Emotion Reasoning for Image Multi-Emotion Prediction","display_name":"Enhancing Emotion Reasoning for Image Multi-Emotion Prediction","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408354392","doi":"https://doi.org/10.1109/icassp49660.2025.10889829"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889829","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889829","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":"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/A5100760972","display_name":"Bingbing Wang","orcid":"https://orcid.org/0000-0001-9659-8892"},"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":"Bingbing Wang","raw_affiliation_strings":["Harbin Institute of Technology (Shenzhen),Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology (Shenzhen),Shenzhen,China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077104771","display_name":"Geng Tu","orcid":"https://orcid.org/0000-0002-3524-1408"},"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":"Geng Tu","raw_affiliation_strings":["Harbin Institute of Technology (Shenzhen),Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology (Shenzhen),Shenzhen,China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063075000","display_name":"Bin Liang","orcid":"https://orcid.org/0000-0001-7234-1347"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Bin Liang","raw_affiliation_strings":["The Chinese University of Hong Kong,Hong Kong,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,Hong Kong,China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113414261","display_name":"Zhixin Bai","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":"Zhixin Bai","raw_affiliation_strings":["Harbin Institute of Technology (Shenzhen),Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology (Shenzhen),Shenzhen,China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083369457","display_name":"Min Yang","orcid":"https://orcid.org/0000-0001-7345-5071"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Min Yang","raw_affiliation_strings":["Chinese Academy of Sciences,SIAT,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,SIAT,Shenzhen,China","institution_ids":["https://openalex.org/I4210145761","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071969642","display_name":"Xi Zeng","orcid":null},"institutions":[{"id":"https://openalex.org/I2800372957","display_name":"China Electronics Technology Group Corporation","ror":"https://ror.org/0098hst83","country_code":"CN","type":"company","lineage":["https://openalex.org/I2800372957"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xi Zeng","raw_affiliation_strings":["The 30th Research Institute of China Electronics Technology Group Corporation,Chengdu,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The 30th Research Institute of China Electronics Technology Group Corporation,Chengdu,China","institution_ids":["https://openalex.org/I2800372957"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100750589","display_name":"Liang Yao","orcid":"https://orcid.org/0000-0003-4068-3136"},"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":"Liang Yao","raw_affiliation_strings":["Harbin Institute of Technology (Shenzhen),Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology (Shenzhen),Shenzhen,China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018149714","display_name":"Ruifeng Xu","orcid":"https://orcid.org/0000-0001-9885-2364"},"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":"Ruifeng Xu","raw_affiliation_strings":["Harbin Institute of Technology (Shenzhen),Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology (Shenzhen),Shenzhen,China","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"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":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.7835000157356262,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10812","display_name":"Human Pose and Action Recognition","score":0.7835000157356262,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.7527999877929688,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10667","display_name":"Emotion and Mood Recognition","score":0.6973000168800354,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6626960635185242},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5299879908561707},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46704500913619995},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.462772011756897},{"id":"https://openalex.org/keywords/emotion-detection","display_name":"Emotion detection","score":0.4447272717952728},{"id":"https://openalex.org/keywords/emotion-classification","display_name":"Emotion classification","score":0.4266435205936432},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.34030449390411377}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6626960635185242},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5299879908561707},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46704500913619995},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.462772011756897},{"id":"https://openalex.org/C2988148770","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion detection","level":3,"score":0.4447272717952728},{"id":"https://openalex.org/C206310091","wikidata":"https://www.wikidata.org/wiki/Q750859","display_name":"Emotion classification","level":2,"score":0.4266435205936432},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.34030449390411377}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10889829","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889829","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/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":40,"referenced_works":["https://openalex.org/W1950412479","https://openalex.org/W2075456404","https://openalex.org/W2194775991","https://openalex.org/W2525450952","https://openalex.org/W2898769710","https://openalex.org/W2946410230","https://openalex.org/W2962820470","https://openalex.org/W2971765953","https://openalex.org/W2997168619","https://openalex.org/W3000577085","https://openalex.org/W3101924153","https://openalex.org/W3124728922","https://openalex.org/W3166683310","https://openalex.org/W3183221431","https://openalex.org/W4311700433","https://openalex.org/W4311770445","https://openalex.org/W4312986439","https://openalex.org/W4313392084","https://openalex.org/W4323865916","https://openalex.org/W4379619596","https://openalex.org/W4385586577","https://openalex.org/W4386076530","https://openalex.org/W4389028103","https://openalex.org/W4392001696","https://openalex.org/W4393149524","https://openalex.org/W4401718527","https://openalex.org/W4402670323","https://openalex.org/W4402716381","https://openalex.org/W4411119463","https://openalex.org/W6637373629","https://openalex.org/W6796581206","https://openalex.org/W6849177959","https://openalex.org/W6851592950","https://openalex.org/W6851950068","https://openalex.org/W6854992507","https://openalex.org/W6855350031","https://openalex.org/W6856570897","https://openalex.org/W6861592589","https://openalex.org/W6862746083","https://openalex.org/W6868892175"],"related_works":["https://openalex.org/W4391307871","https://openalex.org/W4392502551","https://openalex.org/W2336827033","https://openalex.org/W1970739466","https://openalex.org/W2505228240","https://openalex.org/W4319430321","https://openalex.org/W4389296211","https://openalex.org/W2922915988","https://openalex.org/W4391584532","https://openalex.org/W2787157782"],"abstract_inverted_index":{"Image":[0],"multi-emotion":[1,77,121],"prediction":[2,93],"aims":[3],"to":[4,22,40,45,101,124,137,170],"identify":[5],"the":[6,14,41,112,139,158,172],"emotions":[7],"evoked":[8],"by":[9],"images":[10],"in":[11,115],"humans.":[12],"In":[13],"real":[15],"world,":[16],"individual":[17],"cognitive":[18,118,160],"differences":[19],"can":[20],"lead":[21],"different":[23],"viewers":[24],"experiencing":[25],"varied":[26],"emotions.":[27,50],"Most":[28],"existing":[29],"researchers":[30],"primarily":[31],"focus":[32],"on":[33,63,148],"analyzing":[34],"image":[35,116],"features,":[36],"which":[37,69,156],"are":[38],"limited":[39],"perceptual":[42],"level,":[43],"leading":[44],"a":[46,64,82,98,106,130],"superficial":[47],"understanding":[48],"of":[49,127,162,178],"To":[51],"address":[52],"this":[53],"gap,":[54],"we":[55,80],"propose":[56],"an":[57],"Emotional":[58],"Reasoning":[59],"Chain":[60],"(EReC)":[61],"based":[62],"multimodal":[65],"large":[66,128,179],"language":[67],"model,":[68],"learns":[70],"both":[71],"perception":[72],"and":[73,92,120,164,175],"reasoning":[74],"abilities":[75],"for":[76,108],"prediction.":[78,122],"Specifically,":[79],"design":[81],"parameter-efficient":[83],"fine-tuning":[84],"paradigm":[85,96],"encompassing":[86],"three":[87],"task":[88],"instructions:":[89],"perception,":[90,117],"reasoning,":[91,119,174],"instruction.":[94],"This":[95],"involves":[97],"progressive":[99,168],"process":[100,161],"perform":[102],"targeted":[103],"instructions":[104],"within":[105],"domain":[107],"fine-tuning,":[109],"thereby":[110],"optimizing":[111],"model\u2019s":[113],"capabilities":[114,177],"Furthermore,":[123],"alleviate":[125],"hallucinations":[126],"models,":[129,180],"Reason-level":[131],"Alignment":[132],"Score":[133],"(RAS)":[134],"is":[135],"introduced":[136],"guide":[138],"model":[140],"toward":[141],"closer":[142],"alignment":[143],"with":[144],"human":[145,159],"cognition.":[146],"Experiments":[147],"four":[149],"datasets":[150],"demonstrate":[151],"that":[152],"our":[153],"EReC":[154],"method,":[155],"emulates":[157],"viewing":[163],"interpreting":[165],"images,":[166],"employs":[167],"tuning":[169],"integrate":[171],"perceptual,":[173],"predictive":[176],"achieving":[181],"superior":[182],"performance.":[183]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}